Recent advances in bioinformatics analyses have led to the development of novel tools enabling the capture and trajectory mapping of single-cell RNA sequencing (scRNAseq) data. However, there is a lack of methods to assess the contributions of biological pathways and transcription factors to an overall developmental trajectory mapped from scRNAseq data. In this manuscript, we present a simplified approach for trajectory inference of pathway significance (TIPS) that leverages existing knowledgebases of functional pathways and other gene lists to provide further mechanistic insights into a biological process. TIPS identifies key pathways which contribute to a process of interest, as well as the individual genes that best reflect these changes. TIPS also provides insight into the relative timing of pathway changes, as well as a suite of visualizations to enable simplified data interpretation of scRNAseq libraries generated using a wide range of techniques. The TIPS package can be run through either a web server or downloaded as a user-friendly GUI run in R, and may serve as a useful tool to help biologists perform deeper functional analyses and visualization of their single-cell data.

Coronavirus disease 2019 has developed into a dramatic pandemic with tremendous global impact. The receptor-binding motif (RBM) region of the causative virus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), binds to host angiotensin-converting enzyme 2 (ACE2) receptors for infection. As ACE2 receptors are highly conserved within vertebrate species, SARS-CoV-2 can infect significant animal species as well as human populations. An analysis of SARS-CoV-2 genotypes isolated from human and significant animal species was conducted to compare and identify mutation and adaptation patterns across different animal species. The phylogenetic data revealed seven distinct phylogenetic clades with no significant relationship between the clades and geographical locations. A high rate of variation within SARS-CoV-2 mink isolates implies that mink populations were infected before human populations. Positions of most single-nucleotide polymorphisms (SNPs) within the spike (S) protein of SARS-CoV-2 genotypes from the different hosts are mostly accumulated in the RBM region and highlight the pronounced accumulation of variants with mutations in the RBM region in comparison with other variants. These SNPs play a crucial role in viral transmission and pathogenicity and are keys in identifying other animal species as potential intermediate hosts of SARS-CoV-2. The possible roles in the emergence of new viral strains and the possible implications of these changes, in compromising vaccine effectiveness, deserve urgent considerations.

The design of therapeutic antibodies has attracted a large amount of attention over the years. Antibodies are widely used to treat many diseases due to their high efficiency and low risk of adverse events. However, the experimental methods of antibody design are time-consuming and expensive. Although computational antibody design techniques have had significant advances in the past years, there are still some challenges that need to be solved, such as the flexibility of antigen structure, the lack of antibody structural data and the absence of standard antibody design protocol. In the present work, we elaborated on an in silico antibody design protocol for users to easily perform computer-aided antibody design. First, the Rosetta web server will be applied to generate the 3D structure of query antibodies if there is no structural information available. Then, two-step docking will be used to identify the binding pose of an antibody-antigen complex when the binding information is unknown. ClusPro is the first method to be used to conduct the global docking, and SnugDock is applied for the local docking. Sequentially, based on the predicted binding poses, in silico alanine scanning will be used to predict the potential hotspots (or key residues). Finally, computational affinity maturation protocol will be used to modify the structure of antibodies to theoretically increase their affinity and stability, which will be further validated by the bioassays in the future. As a proof of concept, we redesigned antibody D44.1 and compared it with previously reported data in order to validate IsAb protocol. To further illustrate our proposed protocol, we used cemiplimab antibody, a PD-1 checkpoint inhibitor, as an example to showcase a step-by-step tutorial.

Gene expression profiling has played a significant role in the identification and classification of tumor molecules. In gene expression data, only a few feature genes are closely related to tumors. It is a challenging task to select highly discriminative feature genes, and existing methods fail to deal with this problem efficiently. This article proposes a novel metaheuristic approach for gene feature extraction, called variable neighborhood learning Harris Hawks optimizer (VNLHHO). First, the F-score is used for a primary selection of the genes in gene expression data to narrow down the selection range of the feature genes. Subsequently, a variable neighborhood learning strategy is constructed to balance the global exploration and local exploitation of the Harris Hawks optimization. Finally, mutation operations are employed to increase the diversity of the population, so as to prevent the algorithm from falling into a local optimum. In addition, a novel activation function is used to convert the continuous solution of the VNLHHO into binary values, and a naive Bayesian classifier is utilized as a fitness function to select feature genes that can help classify biological tissues of binary and multi-class cancers. An experiment is conducted on gene expression profile data of eight types of tumors. The results show that the classification accuracy of the VNLHHO is greater than 96.128% for tumors in the colon, nervous system and lungs and 100% for the rest. We compare seven other algorithms and demonstrate the superiority of the VNLHHO in terms of the classification accuracy, fitness value and AUC value in feature selection for gene expression data.

Intrinsically disordered regions/proteins (IDRs) are abundant across all the domains of life, where they perform important regulatory roles and supplement the biological functions of structured proteins/regions (SRs). Despite the multifunctionality features of IDRs, several interrogations on the evolution of viral genomic regions encoding IDRs in diverse viral proteins remain unreciprocated. To fill this gap, we benchmarked the findings of two most widely used and reliable intrinsic disorder prediction algorithms (IUPred2A and ESpritz) to a dataset of 6108 reference viral proteomes to unravel the multifaceted evolutionary forces that shape the codon usage in the viral genomic regions encoding for IDRs and SRs. We found persuasive evidence that the natural selection predominantly governs the evolution of codon usage in regions encoding IDRs by most of the viruses. In addition, we confirm not only that codon usage in regions encoding IDRs is less optimized for the protein synthesis machinery (transfer RNAs pool) of their host than for those encoding SRs, but also that the selective constraints imposed by codon bias sustain this reduced optimization in IDRs. Our analysis also establishes that IDRs in viruses are likely to tolerate more translational errors than SRs. All these findings hold true, irrespective of the disorder prediction algorithms used to classify IDRs. In conclusion, our study offers a novel perspective on the evolution of viral IDRs and the evolutionary adaptability to multiple taxonomically divergent hosts.

Comment on Brief Bioinform. 2021 Jul 20;22(4):

Comment in Brief Bioinform. 2022 Mar 10;23(2):

Drug-target interaction (DTI) prediction has drawn increasing interest due to its substantial position in the drug discovery process. Many studies have introduced computational models to treat DTI prediction as a regression task, which directly predict the binding affinity of drug-target pairs. However, existing studies (i) ignore the essential correlations between atoms when encoding drug compounds and (ii) model the interaction of drug-target pairs simply by concatenation. Based on those observations, in this study, we propose an end-to-end model with multiple attention blocks to predict the binding affinity scores of drug-target pairs. Our proposed model offers the abilities to (i) encode the correlations between atoms by a relation-aware self-attention block and (ii) model the interaction of drug representations and target representations by the multi-head attention block. Experimental results of DTI prediction on two benchmark datasets show our approach outperforms existing methods, which are benefit from the correlation information encoded by the relation-aware self-attention block and the interaction information extracted by the multi-head attention block. Moreover, we conduct the experiments on the effects of max relative position length and find out the best max relative position length value $k \in \{3, 5\}$. Furthermore, we apply our model to predict the binding affinity of Corona Virus Disease 2019 (COVID-19)-related genome sequences and $3137$ FDA-approved drugs.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), better known as COVID-19, has become a current threat to humanity. The second wave of the SARS-CoV-2 virus has hit many countries, and the confirmed COVID-19 cases are quickly spreading. Therefore, the epidemic is still passing the terrible stage. Having idiopathic pulmonary fibrosis (IPF) and chronic obstructive pulmonary disease (COPD) are the risk factors of the COVID-19, but the molecular mechanisms that underlie IPF, COPD, and CVOID-19 are not well understood. Therefore, we implemented transcriptomic analysis to detect common pathways and molecular biomarkers in IPF, COPD, and COVID-19 that help understand the linkage of SARS-CoV-2 to the IPF and COPD patients. Here, three RNA-seq datasets (GSE147507, GSE52463, and GSE57148) from Gene Expression Omnibus (GEO) is employed to detect mutual differentially expressed genes (DEGs) for IPF, and COPD patients with the COVID-19 infection for finding shared pathways and candidate drugs. A total of 65 common DEGs among these three datasets were identified. Various combinatorial statistical methods and bioinformatics tools were used to build the protein-protein interaction (PPI) and then identified Hub genes and essential modules from this PPI network. Moreover, we performed functional analysis under ontologies terms and pathway analysis and found that IPF and COPD have some shared links to the progression of COVID-19 infection. Transcription factors-genes interaction, protein-drug interactions, and DEGs-miRNAs coregulatory network with common DEGs also identified on the datasets. We think that the candidate drugs obtained by this study might be helpful for effective therapeutic in COVID-19.

MOTIVATION: Identifying the proteins that interact with drugs can reduce the cost and time of drug development. Existing computerized methods focus on integrating drug-related and protein-related data from multiple sources to predict candidate drug-target interactions (DTIs). However, multi-scale neighboring node sequences and various kinds of drug and protein similarities are neither fully explored nor considered in decision making. RESULTS: We propose a drug-target interaction prediction method, DTIP, to encode and integrate multi-scale neighbouring topologies, multiple kinds of similarities, associations, interactions related to drugs and proteins. We firstly construct a three-layer heterogeneous network to represent interactions and associations across drug, protein, and disease nodes. Then a learning framework based on fully-connected autoencoder is proposed to learn the nodes' low-dimensional feature representations within the heterogeneous network. Secondly, multi-scale neighbouring sequences of drug and protein nodes are formulated by random walks. A module based on bidirectional gated recurrent unit is designed to learn the neighbouring sequential information and integrate the low-dimensional features of nodes. Finally, we propose attention mechanisms at feature level, neighbouring topological level and similarity level to learn more informative features, topologies and similarities. The prediction results are obtained by integrating neighbouring topologies, similarities and feature attributes using a multiple layer CNN. Comprehensive experimental results over public dataset demonstrated the effectiveness of our innovative features and modules. Comparison with other state-of-the-art methods and case studies of five drugs further validated DTIP's ability in discovering the potential candidate drug-related proteins.

Traditional Chinese medicine (TCM) has been practiced for thousands of years for treating human diseases. In comparison to modern medicine, one of the advantages of TCM is the principle of herb compatibility, known as TCM formulae. A TCM formula usually consists of multiple herbs to achieve the maximum treatment effects, where their interactions are believed to elicit the therapeutic effects. Despite being a fundamental component of TCM, the rationale of combining specific herb combinations remains unclear. In this study, we proposed a network-based method to quantify the interactions in herb pairs. We constructed a protein-protein interaction network for a given herb pair by retrieving the associated ingredients and protein targets, and determined multiple network-based distances including the closest, shortest, center, kernel, and separation, both at the ingredient and at the target levels. We found that the frequently used herb pairs tend to have shorter distances compared to random herb pairs, suggesting that a therapeutic herb pair is more likely to affect neighboring proteins in the human interactome. Furthermore, we found that the center distance determined at the ingredient level improves the discrimination of top-frequent herb pairs from random herb pairs, suggesting the rationale of considering the topologically important ingredients for inferring the mechanisms of action of TCM. Taken together, we have provided a network pharmacology framework to quantify the degree of herb interactions, which shall help explore the space of herb combinations more effectively to identify the synergistic compound interactions based on network topology.

MOTIVATION: The high accuracy of recent haplotype phasing tools is enabling the integration of haplotype (or phase) information more widely in genetic investigations. One such possibility is phase-aware expression quantitative trait loci (eQTL) analysis, where haplotype-based analysis has the potential to detect associations that may otherwise be missed by standard SNP-based approaches. RESULTS: We present eQTLHap, a novel method to investigate associations between gene expression and genetic variants, considering their haplotypic and genotypic effect. Using multiple simulations based on real data, we demonstrate that phase-aware eQTL analysis significantly outperforms typical SNP-based methods when the causal genetic architecture involves multiple SNPs. We show that phase-aware eQTL analysis is robust to phasing errors, showing only a minor impact ($<4\%$) on sensitivity. Applying eQTLHap to real GEUVADIS and GTEx datasets detects numerous novel eQTLs undetected by a single-SNP approach, with 22 eQTLs replicating across studies or tissue types, highlighting the utility of phase-aware eQTL analysis. AVAILABILITY AND IMPLEMENTATION: https://github.com/ziadbkh/eQTLHap. CONTACT: ziad.albkhetan@gmail.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Briefings in Bioinformatics online.

A major task in the analysis of microbiome data is to identify microbes associated with differing biological conditions. Before conducting analysis, raw data must first be adjusted so that counts from different samples are comparable. A typical approach is to estimate normalization factors by which all counts in a sample are multiplied or divided. However, the inherent variation associated with estimation of normalization factors are often not accounted for in subsequent analysis, leading to a loss of precision. Rank normalization is a nonparametric alternative to the estimation of normalization factors in which each count for a microbial feature is replaced by its intrasample rank. Although rank normalization has been successfully applied to microarray analysis in the past, it has yet to be explored for microbiome data, which is characterized by high frequencies of 0s, strongly correlated features and compositionality. We propose to use rank normalization as an alternative to the estimation of normalization factors and examine its performance when paired with a two-sample t-test. On a rigorous 3rd-party benchmarking simulation, it is shown to offer strong control over the false discovery rate, and at sample sizes greater than 50 per treatment group, to offer an improvement in performance over commonly used normalization factors paired with t-tests, Wilcoxon rank-sum tests and methodologies implemented by R packages. On two real datasets, it yielded valid and reproducible results that were strongly in agreement with the original findings and the existing literature, further demonstrating its robustness and future potential. Availability: The data underlying this article are available online along with R code and supplementary materials at https://github.com/matthewlouisdavisBioStat/Rank-Normalization-Empowers-a-T-Test.

Recent pharmacogenomic studies that generate sequencing data coupled with pharmacological characteristics for patient-derived cancer cell lines led to large amounts of multi-omics data for precision cancer medicine. Among various obstacles hindering clinical translation, lacking effective methods for multimodal and multisource data integration is becoming a bottleneck. Here we proposed DeepDRK, a machine learning framework for deciphering drug response through kernel-based data integration. To transfer information among different drugs and cancer types, we trained deep neural networks on more than 20 000 pan-cancer cell line-anticancer drug pairs. These pairs were characterized by kernel-based similarity matrices integrating multisource and multi-omics data including genomics, transcriptomics, epigenomics, chemical properties of compounds and known drug-target interactions. Applied to benchmark cancer cell line datasets, our model surpassed previous approaches with higher accuracy and better robustness. Then we applied our model on newly established patient-derived cancer cell lines and achieved satisfactory performance with AUC of 0.84 and AUPRC of 0.77. Moreover, DeepDRK was used to predict clinical response of cancer patients. Notably, the prediction of DeepDRK correlated well with clinical outcome of patients and revealed multiple drug repurposing candidates. In sum, DeepDRK provided a computational method to predict drug response of cancer cells from integrating pharmacogenomic datasets, offering an alternative way to prioritize repurposing drugs in precision cancer treatment. The DeepDRK is freely available via https://github.com/wangyc82/DeepDRK.

MOTIVATION: Geometry-based properties and characteristics of drug molecules play an important role in drug development for virtual screening in computational chemistry. The 3D characteristics of molecules largely determine the properties of the drug and the binding characteristics of the target. However, most of the previous studies focused on 1D or 2D molecular descriptors while ignoring the 3D topological structure, thereby degrading the performance of molecule-related prediction. Because it is very time-consuming to use dynamics to simulate molecular 3D conformer, we aim to use machine learning to represent 3D molecules by using the generated 3D molecular coordinates from the 2D structure. RESULTS: We proposed Drug3D-Net, a novel deep neural network architecture based on the spatial geometric structure of molecules for predicting molecular properties. It is grid-based 3D convolutional neural network with spatial-temporal gated attention module, which can extract the geometric features for molecular prediction tasks in the process of convolution. The effectiveness of Drug3D-Net is verified on the public molecular datasets. Compared with other deep learning methods, Drug3D-Net shows superior performance in predicting molecular properties and biochemical activities. AVAILABILITY AND IMPLEMENTATION: https://github.com/anny0316/Drug3D-Net. SUPPLEMENTARY DATA: Supplementary data are available online at https://academic.oup.com/bib.

In network and systems medicine, active module identification methods (AMIMs) are widely used for discovering candidate molecular disease mechanisms. To this end, AMIMs combine network analysis algorithms with molecular profiling data, most commonly, by projecting gene expression data onto generic protein-protein interaction (PPI) networks. Although active module identification has led to various novel insights into complex diseases, there is increasing awareness in the field that the combination of gene expression data and PPI network is problematic because up-to-date PPI networks have a very small diameter and are subject to both technical and literature bias. In this paper, we report the results of an extensive study where we analyzed for the first time whether widely used AMIMs really benefit from using PPI networks. Our results clearly show that, except for the recently proposed AMIM DOMINO, the tested AMIMs do not produce biologically more meaningful candidate disease modules on widely used PPI networks than on random networks with the same node degrees. AMIMs hence mainly learn from the node degrees and mostly fail to exploit the biological knowledge encoded in the edges of the PPI networks. This has far-reaching consequences for the field of active module identification. In particular, we suggest that novel algorithms are needed which overcome the degree bias of most existing AMIMs and/or work with customized, context-specific networks instead of generic PPI networks.

MOTIVATION: Volcano plots are used to select the most interesting discoveries when too many discoveries remain after application of Benjamini-Hochberg's procedure (BH). The volcano plot suggests a double filtering procedure that selects features with both small adjusted $P$-value and large estimated effect size. Despite its popularity, this type of selection overlooks the fact that BH does not guarantee error control over filtered subsets of discoveries. Therefore the selected subset of features may include an inflated number of false discoveries. RESULTS: In this paper, we illustrate the substantially inflated type I error rate of volcano plot selection with simulation experiments and RNA-seq data. In particular, we show that the feature with the largest estimated effect is a very likely false positive result. Next, we investigate two alternative approaches for multiple testing with double filtering that do not inflate the false discovery rate. Our procedure is implemented in an interactive web application and is publicly available.

The development and progression of cardiovascular disease (CVD) can mainly be attributed to the narrowing of blood vessels caused by atherosclerosis and thrombosis, which induces organ damage that will result in end-organ dysfunction characterized by events such as myocardial infarction or stroke. It is also essential to consider other contributory factors to CVD, including cardiac remodelling caused by cardiomyopathies and co-morbidities with other diseases such as chronic kidney disease. Besides, there is a growing amount of evidence linking the gut microbiota to CVD through several metabolic pathways. Hence, it is of utmost importance to decipher the underlying molecular mechanisms associated with these disease states to elucidate the development and progression of CVD. A wide array of systems biology approaches incorporating multi-omics data have emerged as an invaluable tool in establishing alterations in specific cell types and identifying modifications in signalling events that promote disease development. Here, we review recent studies that apply multi-omics approaches to further understand the underlying causes of CVD and provide possible treatment strategies by identifying novel drug targets and biomarkers. We also discuss very recent advances in gut microbiota research with an emphasis on how diet and microbial composition can impact the development of CVD. Finally, we present various biological network analyses and other independent studies that have been employed for providing mechanistic explanation and developing treatment strategies for end-stage CVD, namely myocardial infarction and stroke.

Network-based gene prioritization algorithms are designed to prioritize disease-associated genes based on known ones using biological networks of protein interactions, gene-disease associations (GDAs) and other relationships between biological entities. Various algorithms have been developed based on different mechanisms, but it is not obvious which algorithm is optimal for a specific disease. To address this issue, we benchmarked multiple algorithms for their application in cerebral small vessel disease (cSVD). We curated protein-gene interactions (PGIs) and GDAs from databases and assembled PGI networks and disease-gene heterogeneous networks. A screening of algorithms resulted in seven representative algorithms to be benchmarked. Performance of algorithms was assessed using both leave-one-out cross-validation (LOOCV) and external validation with MEGASTROKE genome-wide association study (GWAS). We found that random walk with restart on the heterogeneous network (RWRH) showed best LOOCV performance, with median LOOCV rediscovery rank of 185.5 (out of 19 463 genes). The GenePanda algorithm had most GWAS-confirmable genes in top 200 predictions, while RWRH had best ranks for small vessel stroke-associated genes confirmed in GWAS. In conclusion, RWRH has overall better performance for application in cSVD despite its susceptibility to bias caused by degree centrality. Choice of algorithms should be determined before applying to specific disease. Current pure network-based gene prioritization algorithms are unlikely to find novel disease-associated genes that are not associated with known ones. The tools for implementing and benchmarking algorithms have been made available and can be generalized for other diseases.

In the field of genome assembly, scaffolding methods make it possible to obtain a more complete and contiguous reference genome, which is the cornerstone of genomic research. Scaffolding methods typically utilize the alignments between contigs and sequencing data (reads) to determine the orientation and order among contigs and to produce longer scaffolds, which are helpful for genomic downstream analysis. With the rapid development of high-throughput sequencing technologies, diverse types of reads have emerged over the past decade, especially in long-range sequencing, which have greatly enhanced the assembly quality of scaffolding methods. As the number of scaffolding methods increases, biology and bioinformatics researchers need to perform in-depth analyses of state-of-the-art scaffolding methods. In this article, we focus on the difficulties in scaffolding, the differences in characteristics among various kinds of reads, the methods by which current scaffolding methods address these difficulties, and future research opportunities. We hope this work will benefit the design of new scaffolding methods and the selection of appropriate scaffolding methods for specific biological studies.

Contigs assembled from the third-generation sequencing long reads are usually more complete than the second-generation short reads. However, the current algorithms still have difficulty in assembling the long reads into the ideal complete and accurate genome, or the theoretical best result [1]. To improve the long read contigs and with more and more fully sequenced genomes available, it could still be possible to use the similar genome-assisted reassembly method [2], which was initially proposed for the short reads making use of a closely related genome (similar genome) to the sequencing genome (target genome). The method aligns the contigs and reads to the similar genome, and then extends and refines the aligned contigs with the aligned reads. Here, we introduce AlignGraph2, a similar genome-assisted reassembly pipeline for the PacBio long reads. The AlignGraph2 pipeline is the second version of AlignGraph algorithm proposed by us but completely redesigned, can be inputted with either error-prone or HiFi long reads, and contains four novel algorithms: similarity-aware alignment algorithm and alignment filtration algorithm for alignment of the long reads and preassembled contigs to the similar genome, and reassembly algorithm and weight-adjusted consensus algorithm for extension and refinement of the preassembled contigs. In our performance tests on both error-prone and HiFi long reads, AlignGraph2 can align 5.7-27.2% more long reads and 7.3-56.0% more bases than some current alignment algorithm and is more efficient or comparable to the others. For contigs assembled with various de novo algorithms and aligned to similar genomes (aligned contigs), AlignGraph2 can extend 8.7-94.7% of them (extendable contigs), and obtain contigs of 7.0-249.6% larger N50 value and 5.2-87.7% smaller number of indels per 100 kbp (extended contigs). With genomes of decreased similarities, AlignGraph2 also has relatively stable performance. The AlignGraph2 software can be downloaded for free from this site: https://github.com/huangs001/AlignGraph2.

Transcriptional enhanced associate domain (TEAD) is a family of transcription factors that plays a significant role during embryonic developmental processes, and its dysregulation is responsible for tumour progression. TEAD is considered as druggable targets in various diseases, namely cancer, cardiovascular diseases and neurodegenerative disorders. Previous structural studies revealed the importance of the central hydrophobic pocket of TEAD as a potential target for small-molecule inhibitors and demonstrated flufenamic acid (FLU) (a COX-2 enzyme inhibitor) to bind and inhibit TEAD2 functions. However, to date, no drug candidates that bind specifically to TEAD2 with high selectivity and efficacy have been developed or proposed. Within this framework, we present here a case study where we have identified potential TEAD2 inhibitor candidates by integrating multiple computational approaches. Among the candidates, the top two ranked compounds ZINC95969481 (LG1) which is a fused pyrazole derivative and ZINC05203789 (LG2), a fluorene derivative resulted in much favourable binding energy scores than the reference ligand, FLU. The drug likeliness of the best compounds was also evaluated in silico to ensure the bioavailability of these compounds particularly LG1 as compared to FLU thus providing a strong rationale for their development as leads against TEAD. Molecular dynamics simulations results highlighted the role of key residues contributing to favourable interactions in TEAD2-LG1 complex with much favourable interaction and binding free energy values with respect to the reference compound. Altogether, this study provides a starting platform to be more exploited by future experimental research towards the development of inhibitors against TEAD, a persuasive strategy for therapeutic intervention in cancer treatment.

In this paper, we show that the combination of NMR theoretical and experimental results can help to solve the molecular structure of peptides, here it is used as an example the residue Leucine-67 in Desulfovibrio vulgaris flavodoxin. We apply a computational protocol based on the leucine amino acid dipeptide, which, using calculated and experimental spin-spin coupling constants, allows us to obtain the conformation of the amino acid side chain. Calculated results show that the best agreement is obtained when three conformers around the lateral chain angle $\chi _1$ are considered or when the dynamic effect in the torsional angles is included. The population of each structure is estimated and analyzed according to the correlation between those two approaches. Independently of the approach, the estimated $\chi _1$ angle in solution is close to the staggered value of -60$^\circ $ and deviates significantly from the average x-ray angle of -90$^\circ $.

Gene regulatory network (GRN) is the important mechanism of maintaining life process, controlling biochemical reaction and regulating compound level, which plays an important role in various organisms and systems. Reconstructing GRN can help us to understand the molecular mechanism of organisms and to reveal the essential rules of a large number of biological processes and reactions in organisms. Various outstanding network reconstruction algorithms use specific assumptions that affect prediction accuracy, in order to deal with the uncertainty of processing. In order to study why a certain method is more suitable for specific research problem or experimental data, we conduct research from model-based, information-based and machine learning-based method classifications. There are obviously different types of computational tools that can be generated to distinguish GRNs. Furthermore, we discuss several classical, representative and latest methods in each category to analyze core ideas, general steps, characteristics, etc. We compare the performance of state-of-the-art GRN reconstruction technologies on simulated networks and real networks under different scaling conditions. Through standardized performance metrics and common benchmarks, we quantitatively evaluate the stability of various methods and the sensitivity of the same algorithm applying to different scaling networks. The aim of this study is to explore the most appropriate method for a specific GRN, which helps biologists and medical scientists in discovering potential drug targets and identifying cancer biomarkers.

Anticancer peptides constitute one of the most promising therapeutic agents for combating common human cancers. Using wet experiments to verify whether a peptide displays anticancer characteristics is time-consuming and costly. Hence, in this study, we proposed a computational method named identify anticancer peptides via deep representation learning features (iACP-DRLF) using light gradient boosting machine algorithm and deep representation learning features. Two kinds of sequence embedding technologies were used, namely soft symmetric alignment embedding and unified representation (UniRep) embedding, both of which involved deep neural network models based on long short-term memory networks and their derived networks. The results showed that the use of deep representation learning features greatly improved the capability of the models to discriminate anticancer peptides from other peptides. Also, UMAP (uniform manifold approximation and projection for dimension reduction) and SHAP (shapley additive explanations) analysis proved that UniRep have an advantage over other features for anticancer peptide identification. The python script and pretrained models could be downloaded from https://github.com/zhibinlv/iACP-DRLF or from http://public.aibiochem.net/iACP-DRLF/.

Accurately identifying potential drug-target interactions (DTIs) is a key step in drug discovery. Although many related experimental studies have been carried out for identifying DTIs in the past few decades, the biological experiment-based DTI identification is still timeconsuming and expensive. Therefore, it is of great significance to develop effective computational methods for identifying DTIs. In this paper, we develop a novel 'end-to-end' learning-based framework based on heterogeneous 'graph' convolutional networks for 'DTI' prediction called end-to-end graph (EEG)-DTI. Given a heterogeneous network containing multiple types of biological entities (i.e. drug, protein, disease, side-effect), EEG-DTI learns the low-dimensional feature representation of drugs and targets using a graph convolutional networks-based model and predicts DTIs based on the learned features. During the training process, EEG-DTI learns the feature representation of nodes in an end-to-end mode. The evaluation test shows that EEG-DTI performs better than existing state-of-art methods. The data and source code are available at: https://github.com/MedicineBiology-AI/EEG-DTI.

MOTIVATION: Gene set enrichment analysis (GSEA) has been widely used to identify gene sets with statistically significant difference between cases and controls against a large gene set. GSEA needs both phenotype labels and expression of genes. However, gene expression are assessed more often for model organisms than minor species. Also, importantly gene expression are not measured well under specific conditions for human, due to high risk of direct experiments, such as non-approved treatment or gene knockout, and then often substituted by mouse. Thus, predicting enrichment significance (on a phenotype) of a given gene set of a species (target, say human), by using gene expression measured under the same phenotype of the other species (source, say mouse) is a vital and challenging problem, which we call CROSS-species gene set enrichment problem (XGSEP). RESULTS: For XGSEP, we propose the CROSS-species gene set enrichment analysis (XGSEA), with three steps of: (1) running GSEA for a source species to obtain enrichment scores and $p$-values of source gene sets; (2) representing the relation between source and target gene sets by domain adaptation; and (3) using regression to predict $p$-values of target gene sets, based on the representation in (2). We extensively validated the XGSEA by using five regression and one classification measurements on four real data sets under various settings, proving that the XGSEA significantly outperformed three baseline methods in most cases. A case study of identifying important human pathways for T -cell dysfunction and reprogramming from mouse ATAC-Seq data further confirmed the reliability of the XGSEA. AVAILABILITY: Source code of the XGSEA is available through https://github.com/LiminLi-xjtu/XGSEA.

Exon skipping (ES), the most common alternative splicing event, has been reported to contribute to diverse human diseases due to the loss of functional domains/sites or frameshifting of the open reading frame (ORF) and noticed as therapeutic targets. Accumulating transcriptomic studies of aging brains show the splicing disruption is a widespread hallmark of neurodegenerative diseases such as Alzheimer's disease (AD). Here, we built ExonSkipAD, the ES annotation database aiming to provide a resource/reference for functional annotation of ES events in AD and identify therapeutic targets in exon units. We identified 16 414 genes that have ~156 K, ~ 69 K, ~ 231 K ES events from the three representative AD cohorts of ROSMAP, MSBB and Mayo, respectively. For these ES events, we performed multiple functional annotations relating to ES mechanisms or downstream. Specifically, through the functional feature retention studies followed by the open reading frames (ORFs), we identified 275 important cellular regulators that might lose their cellular regulator roles due to exon skipping in AD. ExonSkipAD provides twelve categories of annotations: gene summary, gene structures and expression levels, exon skipping events with PSIs, ORF annotation, exon skipping events in the canonical protein sequence, 3'-UTR located exon skipping events lost miRNA-binding sites, SNversus in the skipped exons with a depth of coverage, AD stage-associated exon skipping events, splicing quantitative trait loci (sQTLs) in the skipped exons, correlation with RNA-binding proteins, and related drugs & diseases. ExonSkipAD will be a unique resource of transcriptomic diversity research for understanding the mechanisms of neurodegenerative disease development and identifying potential therapeutic targets in AD. Significance AS the first comprehensive resource of the functional genomics of the alternative splicing events in AD, ExonSkipAD will be useful for many researchers in the fields of pathology, AD genomics and precision medicine, and pharmaceutical and therapeutic researches.

Over the past decades, learning to rank (LTR) algorithms have been gradually applied to bioinformatics. Such methods have shown significant advantages in multiple research tasks in this field. Therefore, it is necessary to summarize and discuss the application of these algorithms so that these algorithms are convenient and contribute to bioinformatics. In this paper, the characteristics of LTR algorithms and their strengths over other types of algorithms are analyzed based on the application of multiple perspectives in bioinformatics. Finally, the paper further discusses the shortcomings of the LTR algorithms, the methods and means to better use the algorithms and some open problems that currently exist.

With the rapid progress of sequencing technologies, various types of sequencing reads and assembly algorithms have been designed to construct genome assemblies. Although recent studies have attempted to evaluate the appropriate type of sequencing reads and algorithms for assembling high-quality genomes, it is still a challenge to set the correct combination for constructing animal genomes. Here, we present a comparative performance assessment of 14 assembly combinations-9 software programs with different short and long reads of Duroc pig. Based on the results of the optimization process for genome construction, we designed an integrated hybrid de novo assembly pipeline, HSCG, and constructed a draft genome for Duroc pig. Comparison between the new genome and Sus scrofa 11.1 revealed important breakpoints in two S. scrofa 11.1 genes. Our findings may provide new insights into the pan-genome analysis studies of agricultural animals, and the integrated assembly pipeline may serve as a guide for the assembly of other animal genomes.

Biological pathways reflect the key cellular mechanisms that dictate disease states, drug response and altered cellular function. The local areas of pathways are defined as subpathways (SPs), whose dysfunction has been reported to be associated with the occurrence and development of cancer. With the development of high-throughput sequencing technology, identifying dysfunctional SPs by using multi-omics data has become possible. Moreover, the SPs are not isolated in the biological system but interact with each other. Here, we propose a network-based calculated method, CNA2Subpathway, to identify dysfunctional SPs is driven by somatic copy number alterations (CNAs) in cancer through integrating pathway topology information, multi-omics data and SP crosstalk. This provides a novel way of SP analysis by using the SP interactions in the system biological level. Using data sets from breast cancer and head and neck cancer, we validate the effectiveness of CNA2Subpathway in identifying cancer-relevant SPs driven by the somatic CNAs, which are also shown to be associated with cancer immune and prognosis of patients. We further compare our results with five pathway or SP analysis methods based on CNA and gene expression data without considering SP crosstalk. With these analyses, we show that CNA2Subpathway could help to uncover dysfunctional SPs underlying cancer via the use of SP crosstalk. CNA2Subpathway is developed as an R-based tool, which is freely available on GitHub (https://github.com/hanjunwei-lab/CNA2Subpathway).

Machine-learning (ML)-based scoring functions (MLSFs) have gradually emerged as a promising alternative for protein-ligand binding affinity prediction and structure-based virtual screening. However, clouds of doubts have still been raised against the benefits of this novel type of scoring functions (SFs). In this study, to benchmark the performance of target-specific MLSFs on a relatively unbiased dataset, the MLSFs trained from three representative protein-ligand interaction representations were assessed on the LIT-PCBA dataset, and the classical Glide SP SF and three types of ligand-based quantitative structure-activity relationship (QSAR) models were also utilized for comparison. Two major aspects in virtual screening campaigns, including prediction accuracy and hit novelty, were systematically explored. The calculation results illustrate that the tested target-specific MLSFs yielded generally superior performance over the classical Glide SP SF, but they could hardly outperform the 2D fingerprint-based QSAR models. Although substantial improvements could be achieved by integrating multiple types of protein-ligand interaction features, the MLSFs were still not sufficient to exceed MACCS-based QSAR models. In terms of the correlations between the hit ranks or the structures of the top-ranked hits, the MLSFs developed by different featurization strategies would have the ability to identify quite different hits. Nevertheless, it seems that target-specific MLSFs do not have the intrinsic attributes of a traditional SF and may not be a substitute for classical SFs. In contrast, MLSFs can be regarded as a new derivative of ligand-based QSAR models. It is expected that our study may provide valuable guidance for the assessment and further development of target-specific MLSFs.

Studies have demonstrated that both mortality and severe illness rates exist significant difference in different gender COVID-19 patients, but the reasons are still very mysterious to date. Here, we firstly find that the survival outcome of female patients is better to male patients through analyzing the 3044 COVID-19 cases. Secondly, we identify many important master regulators [e.g. STAT1/STAT2 and zinc finger (ZNF) proteins], in particular female patients can express more ZNF proteins and stronger transcriptional activities than male patients in response to SARS-CoV-2 infection. Thirdly, we discover that ZNF protein activity is significantly negative correlation with the SARS-CoV-2 load of COVID-19 patients, and ZNF proteins as transcription factors can also activate their target genes to participate in anti-SARS-CoV-2 infection. Fourthly, we demonstrate that ZNF protein activity is positive correlation with the abundance of multiple immune cells of COVID-19 patients, implying that the highly ZNF protein activity might promote the abundance and the antiviral activity of multiple immune cells to effectively suppress SARS-CoV-2 infection. Taken together, our study proposes an underlying anti-SARS-COV-2 role of ZNF proteins, and differences in the amount and activity of ZNF proteins might be responsible for the distinct prognosis of different gender COVID-19 patients.

Current cancer genomics databases have accumulated millions of somatic mutations that remain to be further explored. Due to the over-excess mutations unrelated to cancer, the great challenge is to identify somatic mutations that are cancer-driven. Under the notion that carcinogenesis is a form of somatic-cell evolution, we developed a two-component mixture model: while the ground component corresponds to passenger mutations, the rapidly evolving component corresponds to driver mutations. Then, we implemented an empirical Bayesian procedure to calculate the posterior probability of a site being cancer-driven. Based on these, we developed a software CanDriS (Cancer Driver Sites) to profile the potential cancer-driving sites for thousands of tumor samples from the Cancer Genome Atlas and International Cancer Genome Consortium across tumor types and pan-cancer level. As a result, we identified that approximately 1% of the sites have posterior probabilities larger than 0.90 and listed potential cancer-wide and cancer-specific driver mutations. By comprehensively profiling all potential cancer-driving sites, CanDriS greatly enhances our ability to refine our knowledge of the genetic basis of cancer and might guide clinical medication in the upcoming era of precision medicine. The results were displayed in a database CandrisDB (http://biopharm.zju.edu.cn/candrisdb/).

Targeting tumor microenvironment (TME), such as immune checkpoint blockade (ICB), has achieved increased overall response rates in many advanced cancers, such as non-small cell lung cancer (NSCLC), however, only in a fraction of patients. To improve the overall and durable response rates, combining other therapeutics, such as natural products, with ICB therapy is under investigation. Unfortunately, due to the lack of systematic methods to characterize the relationship between TME and ICB, development of rational immune-combination therapy is a critical challenge. Here, we proposed a systems pharmacology strategy to identify resistance regulators of PD-1/PD-L1 blockade and develop its combinatorial drug by integrating multidimensional omics and pharmacological methods. First, a high-resolution TME cell atlas was inferred from bulk sequencing data by referring to a high-resolution single-cell data and was used to predict potential resistance regulators of PD-1/PD-L1 blockade through TME stratification analysis. Second, to explore the drug targeting the resistance regulator, we carried out the large-scale target fishing and the network analysis between multi-target drug and the resistance regulator. Finally, we predicted and verified that oxymatrine significantly enhances the infiltration of CD8+ T cells into TME and is a powerful combination agent to enhance the therapeutic effect of anti-PD-L1 in a mouse model of lung adenocarcinoma. Overall, the systems pharmacology strategy offers a paradigm to identify combinatorial drugs for ICB therapy with a systems biology perspective of drug-target-pathway-TME phenotype-ICB combination.

Erratum in Brief Bioinform. 2021 Jun 15;:

Topologically associated domains (TADs) are one of the important higher order chromatin structures with various sizes in the eukaryotic genomes. TAD boundaries, as the flanking regions between adjacent domains, can restrict the interactions of regulatory elements, including enhancers and promoters, and are generally dynamic and variable in different cells. However, the influence of sequence and epigenetic profile-based features in the identification of TAD boundaries is largely unknown. In this work, we proposed a method called pTADS (prediction of TAD boundary and strength), to predict TAD boundaries and boundary strength across multiple cell lines with DNA sequence and epigenetic profile information. The performance was assessed in seven cell lines and three TAD calling methods. The results demonstrate that the TAD boundary can be well predicted by the selected shared features across multiple cell lines. Especially, the model can be transferable to predict the TAD boundary from one cell line to other cell lines. The boundary strength can be characterized by boundary score with good performance. The predicted TAD boundary and TAD boundary strength are further confirmed by three Hi-C contact matrix-based methods across multiple cell lines. The codes and datasets are available at https://github.com/chrom3DEpi/pTADS.

The prediction of genes related to diseases is important to the study of the diseases due to high cost and time consumption of biological experiments. Network propagation is a popular strategy for disease-gene prediction. However, existing methods focus on the stable solution of dynamics while ignoring the useful information hidden in the dynamical process, and it is still a challenge to make use of multiple types of physical/functional relationships between proteins/genes to effectively predict disease-related genes. Therefore, we proposed a framework of network impulsive dynamics on multiplex biological network (NIDM) to predict disease-related genes, along with four variants of NIDM models and four kinds of impulsive dynamical signatures (IDSs). NIDM is to identify disease-related genes by mining the dynamical responses of nodes to impulsive signals being exerted at specific nodes. By a series of experimental evaluations in various types of biological networks, we confirmed the advantage of multiplex network and the important roles of functional associations in disease-gene prediction, demonstrated superior performance of NIDM compared with four types of network-based algorithms and then gave the effective recommendations of NIDM models and IDS signatures. To facilitate the prioritization and analysis of (candidate) genes associated to specific diseases, we developed a user-friendly web server, which provides three kinds of filtering patterns for genes, network visualization, enrichment analysis and a wealth of external links (http://bioinformatics.csu.edu.cn/DGP/NID.jsp). NIDM is a protocol for disease-gene prediction integrating different types of biological networks, which may become a very useful computational tool for the study of disease-related genes.

Signalling transduction pathways (STPs) are commonly hijacked by many cancers for their growth and malignancy, but demystifying their underlying mechanisms is difficult. Here, we developed methodologies with a fully Bayesian approach in discovering novel driver bio-markers in aberrant STPs given high-throughput gene expression (GE) data. This project, namely 'PathTurbEr' (Pathway Perturbation Driver) uses the GE dataset derived from the lapatinib (an EGFR/HER dual inhibitor) sensitive and resistant samples from breast cancer cell lines (SKBR3). Differential expression analysis revealed 512 differentially expressed genes (DEGs) and their pathway enrichment revealed 13 highly perturbed singalling pathways in lapatinib resistance, including PI3K-AKT, Chemokine, Hippo and TGF-$\beta $ singalling pathways. Next, the aberration in TGF-$\beta $ STP was modelled as a causal Bayesian network (BN) using three MCMC sampling methods, i.e. Neighbourhood sampler (NS) and Hit-and-Run (HAR) sampler that potentially yield robust inference with lower chances of getting stuck at local optima and faster convergence compared to other state-of-art methods. Next, we examined the structural features of the optimal BN as a statistical process that generates the global structure using $p_1$-model, a special class of Exponential Random Graph Models (ERGMs), and MCMC methods for their hyper-parameter sampling. This step enabled key drivers identification that drive the aberration within the perturbed BN structure of STP, and yielded 34, 34 and 23 perturbation driver genes out of 80 constituent genes of three perturbed STP models of TGF-$\beta $ signalling inferred by NS, HAR and MH sampling methods, respectively. Functional-relevance and disease-relevance analyses suggested their significant associations with breast cancer progression/resistance.

Gene-expression profiling can define the cell state and gene-expression pattern of cells at the genetic level in a high-throughput manner. With the development of transcriptome techniques, processing high-dimensional genetic data has become a major challenge in expression profiling. Thanks to the recent widespread use of matrix decomposition methods in bioinformatics, a computational framework based on compressed sensing was adopted to reduce dimensionality. However, compressed sensing requires an optimization strategy to learn the modular dictionaries and activity levels from the low-dimensional random composite measurements to reconstruct the high-dimensional gene-expression data. Considering this, here we introduce and compare four compressed sensing frameworks coming from nature-inspired optimization algorithms (CSCS, ABCCS, BACS and FACS) to improve the quality of the decompression process. Several experiments establish that the three proposed methods outperform benchmark methods on nine different datasets, especially the FACS method. We illustrate therefore, the robustness and convergence of FACS in various aspects; notably, time complexity and parameter analyses highlight properties of our proposed FACS. Furthermore, differential gene-expression analysis, cell-type clustering, gene ontology enrichment and pathology analysis are conducted, which bring novel insights into cell-type identification and characterization mechanisms from different perspectives. All algorithms are written in Python and available at https://github.com/Philyzh8/Nature-inspired-CS.

MicroRNA (miRNA) is not a single sequence, but a series of multiple variants (also termed isomiRs) with sequence and expression heterogeneity. Whether and how these isoforms contribute to functional variation and complexity at the systems and network levels remain largely unknown. To explore this question systematically, we comprehensively analyzed the expression of small RNAs and their target sites to interrogate functional variations between novel isomiRs and their canonical miRNA sequences. Our analyses of the pan-cancer landscape of miRNA expression indicate that multiple isomiRs generated from the same miRNA locus often exhibit remarkable variation in their sequence, expression and function. We interrogated abundant and differentially expressed 5' isomiRs with novel seed sequences via seed shifting and identified many potential novel targets of these 5' isomiRs that would expand interaction capabilities between small RNAs and mRNAs, rewiring regulatory networks and increasing signaling circuit complexity. Further analyses revealed that some miRNA loci might generate diverse dominant isomiRs that often involved isomiRs with varied seeds and arm-switching, suggesting a selective advantage of multiple isomiRs in regulating gene expression. Finally, experimental validation indicated that isomiRs with shifted seed sequences could regulate novel target mRNAs and therefore contribute to regulatory network rewiring. Our analysis uncovers a widespread expansion of isomiR and mRNA interaction networks compared with those seen in canonical small RNA analysis; this expansion suggests global gene regulation network perturbations by alternative small RNA variants or isoforms. Taken together, the variations in isomiRs that occur during miRNA processing and maturation are likely to play a far more complex and plastic role in gene regulation than previously anticipated.

Erratum in Brief Bioinform. 2021 Sep 15;:

Glioblastoma (GBM) is the most malignant and lethal intracranial tumor, with extremely limited treatment options. Immunotherapy has been widely studied in GBM, but none can significantly prolong the overall survival (OS) of patients without selection. Considering that GBM cancer stem cells (CSCs) play a non-negligible role in tumorigenesis and chemoradiotherapy resistance, we proposed a novel stemness-based classification of GBM and screened out certain population more responsive to immunotherapy. The one-class logistic regression algorithm was used to calculate the stemness index (mRNAsi) of 518 GBM patients from The Cancer Genome Atlas (TCGA) database based on transcriptomics of GBM and pluripotent stem cells. Based on their stemness signature, GBM patients were divided into two subtypes via consensus clustering, and patients in Stemness Subtype I presented significantly better OS but poorer progression-free survival than Stemness Subtype II. Genomic variations revealed patients in Stemness Subtype I had higher somatic mutation loads and copy number alteration burdens. Additionally, two stemness subtypes had distinct tumor immune microenvironment patterns. Tumor Immune Dysfunction and Exclusion and subclass mapping analysis further demonstrated patients in Stemness Subtype I were more likely to respond to immunotherapy, especially anti-PD1 treatment. The pRRophetic algorithm also indicated patients in Stemness Subtype I were more resistant to temozolomide therapy. Finally, multiple machine learning algorithms were used to develop a 7-gene Stemness Subtype Predictor, which were further validated in two external independent GBM cohorts. This novel stemness-based classification could provide a promising prognostic predictor for GBM and may guide physicians in selecting potential responders for preferential use of immunotherapy.

Molecular descriptors are essential to not only quantitative structure activity/property relationship (QSAR/QSPR) models, but also machine learning based chemical and biological data analysis. In this paper, we propose persistent spectral hypergraph (PSH) based molecular descriptors or fingerprints for the first time. Our PSH-based molecular descriptors are used in the characterization of molecular structures and interactions, and further combined with machine learning models, in particular gradient boosting tree (GBT), for protein-ligand binding affinity prediction. Different from traditional molecular descriptors, which are usually based on molecular graph models, a hypergraph-based topological representation is proposed for protein-ligand interaction characterization. Moreover, a filtration process is introduced to generate a series of nested hypergraphs in different scales. For each of these hypergraphs, its eigen spectrum information can be obtained from the corresponding (Hodge) Laplacain matrix. PSH studies the persistence and variation of the eigen spectrum of the nested hypergraphs during the filtration process. Molecular descriptors or fingerprints can be generated from persistent attributes, which are statistical or combinatorial functions of PSH, and combined with machine learning models, in particular, GBT. We test our PSH-GBT model on three most commonly used datasets, including PDBbind-2007, PDBbind-2013 and PDBbind-2016. Our results, for all these databases, are better than all existing machine learning models with traditional molecular descriptors, as far as we know.

The low capture rate of expressed RNAs from single-cell sequencing technology is one of the major obstacles to downstream functional genomics analyses. Recently, a number of imputation methods have emerged for single-cell transcriptome data, however, recovering missing values in very sparse expression matrices remains a substantial challenge. Here, we propose a new algorithm, WEDGE (WEighted Decomposition of Gene Expression), to impute gene expression matrices by using a biased low-rank matrix decomposition method. WEDGE successfully recovered expression matrices, reproduced the cell-wise and gene-wise correlations and improved the clustering of cells, performing impressively for applications with sparse datasets. Overall, this study shows a potent approach for imputing sparse expression matrix data, and our WEDGE algorithm should help many researchers to more profitably explore the biological meanings embedded in their single-cell RNA sequencing datasets. The source code of WEDGE has been released at https://github.com/QuKunLab/WEDGE.

The effectiveness of deep learning methods can be largely attributed to the automated extraction of relevant features from raw data. In the field of functional genomics, this generally concerns the automatic selection of relevant nucleotide motifs from DNA sequences. To benefit from automated learning methods, new strategies are required that unveil the decision-making process of trained models. In this paper, we present a new approach that has been successful in gathering insights on the transcription process in Escherichia coli. This work builds upon a transformer-based neural network framework designed for prokaryotic genome annotation purposes. We find that the majority of subunits (attention heads) of the model are specialized towards identifying transcription factors and are able to successfully characterize both their binding sites and consensus sequences, uncovering both well-known and potentially novel elements involved in the initiation of the transcription process. With the specialization of the attention heads occurring automatically, we believe transformer models to be of high interest towards the creation of explainable neural networks in this field.

A hierarchical random regression model (Hi-RRM) was extended into a genome-wide association analysis for longitudinal data, which significantly reduced the dimensionality of repeated measurements. The Hi-RRM first modeled the phenotypic trajectory of each individual using a RRM and then associated phenotypic regressions with genetic markers using a multivariate mixed model (mvLMM). By spectral decomposition of genomic relationship and regression covariance matrices, the mvLMM was transformed into a multiple linear regression, which improved computing efficiency while implementing mvLMM associations in efficient mixed-model association expedited (EMMAX). Compared with the existing RRM-based association analyses, the statistical utility of Hi-RRM was demonstrated by simulation experiments. The method proposed here was also applied to find the quantitative trait nucleotides controlling the growth pattern of egg weights in poultry data.

Minichromosome maintenance complex component 7 (MCM7) belongs to the minichromosome maintenance family that is important for the initiation of eukaryotic DNA replication. Overexpression of the MCM7 protein is relative to cellular proliferation and responsible for aggressive malignancy in various cancers. Mechanistically, inhibition of MCM7 significantly reduces the cellular proliferation associated with cancer. To date, no effective small molecular candidate has been identified that can block the progression of cancer induced by the MCM7 protein. Therefore, the study has been designed to identify small molecular-like natural drug candidates against aggressive malignancy associated with various cancers by targeting MCM7 protein. To identify potential compounds against the targeted protein a comprehensive in silico drug design including molecular docking, ADME (Absorption, Distribution, Metabolism and Excretion), toxicity, and molecular dynamics (MD) simulation approaches has been applied. Seventy phytochemicals isolated from the neem tree (Azadiractha indica) were retrieved and screened against MCM7 protein by using the molecular docking simulation method, where the top four compounds have been chosen for further evaluation based on their binding affinities. Analysis of ADME and toxicity properties reveals the efficacy and safety of the selected four compounds. To validate the stability of the protein-ligand complex structure MD simulations approach has also been performed to the protein-ligand complex structure, which confirmed the stability of the selected three compounds including CAS ID:105377-74-0, CID:12308716 and CID:10505484 to the binding site of the protein. In the study, a comprehensive data screening process has performed based on the docking, ADMET properties, and MD simulation approaches, which found a good value of the selected four compounds against the targeted MCM7 protein and indicates as a promising and effective human anticancer agent.

Metagenomics data provide rich information for the detection of foodborne pathogens from food and environmental samples that are mixed with complex background bacteria strains. While pathogen detection from metagenomic sequencing data has become an activity of increasing interest, shotgun sequencing of uncultured food samples typically produces data that contain reads from many different organisms, making accurate strain typing a challenging task. Particularly, as many pathogens may contain a common set of genes that are highly similar to those from normal bacteria in food samples, traditional strain-level abundance profiling approaches do not perform well at detecting pathogens of very low abundance levels. To overcome this limitation, we propose an abundance correction method based on species-specific genomic regions to achieve high sensitivity and high specificity in target pathogen detection at low abundance.

Next-generation sequencing studies are dependent on a high-quality reference genome for single nucleotide variant (SNV) calling. Although the two most recent builds of the human genome are widely used, position information is typically not directly comparable between them. Re-alignment gives the most accurate position information, but this procedure is often computationally expensive, and therefore, tools such as liftOver and CrossMap are used to convert data from one build to another. However, the positions of converted SNVs do not always match SNVs derived from aligned data, and in some instances, SNVs are known to change chromosome when converted. This is a significant problem when compiling sequencing resources or comparing results across studies. Here, we describe a novel algorithm to identify positions that are unstable when converting between human genome reference builds. These positions are detected independent of the conversion tools and are determined by the chain files, which provide a mapping of contiguous positions from one build to another. We also provide the list of unstable positions for converting between the two most commonly used builds GRCh37 and GRCh38. Pre-excluding SNVs at these positions, prior to conversion, results in SNVs that are stable to conversion. This simple procedure gives the same final list of stable SNVs as applying the algorithm and subsequently removing variants at unstable positions. This work highlights the care that must be taken when converting SNVs between genome builds and provides a simple method for ensuring higher confidence converted data. Unstable positions and algorithm code, available at https://github.com/cathaloruaidh/genomeBuildConversion.

Noncoding RNAs (ncRNAs) play crucial roles in many biological processes. Experimental methods for identifying ncRNA-protein interactions (NPIs) are always costly and time-consuming. Many computational approaches have been developed as alternative ways. In this work, we collected five benchmarking datasets for predicting NPIs. Based on these datasets, we evaluated and compared the prediction performances of existing machine-learning based methods. Graph neural network (GNN) is a recently developed deep learning algorithm for link predictions on complex networks, which has never been applied in predicting NPIs. We constructed a GNN-based method, which is called Noncoding RNA-Protein Interaction prediction using Graph Neural Networks (NPI-GNN), to predict NPIs. The NPI-GNN method achieved comparable performance with state-of-the-art methods in a 5-fold cross-validation. In addition, it is capable of predicting novel interactions based on network information and sequence information. We also found that insufficient sequence information does not affect the NPI-GNN prediction performance much, which makes NPI-GNN more robust than other methods. As far as we can tell, NPI-GNN is the first end-to-end GNN predictor for predicting NPIs. All benchmarking datasets in this work and all source codes of the NPI-GNN method have been deposited with documents in a GitHub repo (https://github.com/AshuiRUA/NPI-GNN).

With diverse types of omics data widely available, many computational methods have been recently developed to integrate these heterogeneous data, providing a comprehensive understanding of diseases and biological mechanisms. But most of them hardly take noise effects into account. Data-specific patterns unique to data types also make it challenging to uncover the consistent patterns and learn a compact representation of multi-omics data. Here we present a multi-omics integration method considering these issues. We explicitly model the error term in data reconstruction and simultaneously consider noise effects and data-specific patterns. We utilize a denoised network regularization in which we build a fused network using a denoising procedure to suppress noise effects and data-specific patterns. The error term collaborates with the denoised network regularization to capture data-specific patterns. We solve the optimization problem via an inexact alternating minimization algorithm. A comparative simulation study shows the method's superiority at discovering common patterns among data types at three noise levels. Transcriptomics-and-epigenomics integration, in seven cancer cohorts from The Cancer Genome Atlas, demonstrates that the learned integrative representation extracted in an unsupervised manner can depict survival information. Specially in liver hepatocellular carcinoma, the learned integrative representation attains average Harrell's C-index of 0.78 in 10 times 3-fold cross-validation for survival prediction, which far exceeds competing methods, and we discover an aggressive subtype in liver hepatocellular carcinoma with this latent representation, which is validated by an external dataset GSE14520. We also show that DeFusion is applicable to the integration of other omics types.

Single-cell RNA sequencing (scRNA-seq) has enabled us to study biological questions at the single-cell level. Currently, many analysis tools are available to better utilize these relatively noisy data. In this review, we summarize the most widely used methods for critical downstream analysis steps (i.e. clustering, trajectory inference, cell-type annotation and integrating datasets). The advantages and limitations are comprehensively discussed, and we provide suggestions for choosing proper methods in different situations. We hope this paper will be useful for scRNA-seq data analysts and bioinformatics tool developers.

With the increasing volume of high-throughput sequencing data from a variety of omics techniques in the field of plant-pathogen interactions, sorting, retrieving, processing and visualizing biological information have become a great challenge. Within the explosion of data, machine learning offers powerful tools to process these complex omics data by various algorithms, such as Bayesian reasoning, support vector machine and random forest. Here, we introduce the basic frameworks of machine learning in dissecting plant-pathogen interactions and discuss the applications and advances of machine learning in plant-pathogen interactions from molecular to network biology, including the prediction of pathogen effectors, plant disease resistance protein monitoring and the discovery of protein-protein networks. The aim of this review is to provide a summary of advances in plant defense and pathogen infection and to indicate the important developments of machine learning in phytopathology.

Emerging research shows that circular RNA (circRNA) plays a crucial role in the diagnosis, occurrence and prognosis of complex human diseases. Compared with traditional biological experiments, the computational method of fusing multi-source biological data to identify the association between circRNA and disease can effectively reduce cost and save time. Considering the limitations of existing computational models, we propose a semi-supervised generative adversarial network (GAN) model SGANRDA for predicting circRNA-disease association. This model first fused the natural language features of the circRNA sequence and the features of disease semantics, circRNA and disease Gaussian interaction profile kernel, and then used all circRNA-disease pairs to pre-train the GAN network, and fine-tune the network parameters through labeled samples. Finally, the extreme learning machine classifier is employed to obtain the prediction result. Compared with the previous supervision model, SGANRDA innovatively introduced circRNA sequences and utilized all the information of circRNA-disease pairs during the pre-training process. This step can increase the information content of the feature to some extent and reduce the impact of too few known associations on the model performance. SGANRDA obtained AUC scores of 0.9411 and 0.9223 in leave-one-out cross-validation and 5-fold cross-validation, respectively. Prediction results on the benchmark dataset show that SGANRDA outperforms other existing models. In addition, 25 of the top 30 circRNA-disease pairs with the highest scores of SGANRDA in case studies were verified by recent literature. These experimental results demonstrate that SGANRDA is a useful model to predict the circRNA-disease association and can provide reliable candidates for biological experiments.

BACKGROUND: Substructure screening is widely applied to evaluate the molecular potency and ADMET properties of compounds in drug discovery pipelines, and it can also be used to interpret QSAR models for the design of new compounds with desirable physicochemical and biological properties. With the continuous accumulation of more experimental data, data-driven computational systems which can derive representative substructures from large chemical libraries attract more attention. Therefore, the development of an integrated and convenient tool to generate and implement representative substructures is urgently needed. RESULTS: In this study, PySmash, a user-friendly and powerful tool to generate different types of representative substructures, was developed. The current version of PySmash provides both a Python package and an individual executable program, which achieves ease of operation and pipeline integration. Three types of substructure generation algorithms, including circular, path-based and functional group-based algorithms, are provided. Users can conveniently customize their own requirements for substructure size, accuracy and coverage, statistical significance and parallel computation during execution. Besides, PySmash provides the function for external data screening. CONCLUSION: PySmash, a user-friendly and integrated tool for the automatic generation and implementation of representative substructures, is presented. Three screening examples, including toxicophore derivation, privileged motif detection and the integration of substructures with machine learning (ML) models, are provided to illustrate the utility of PySmash in safety profile evaluation, therapeutic activity exploration and molecular optimization, respectively. Its executable program and Python package are available at https://github.com/kotori-y/pySmash.

Discovering drug-target (protein) interactions (DTIs) is of great significance for researching and developing novel drugs, having a tremendous advantage to pharmaceutical industries and patients. However, the prediction of DTIs using wet-lab experimental methods is generally expensive and time-consuming. Therefore, different machine learning-based methods have been developed for this purpose, but there are still substantial unknown interactions needed to discover. Furthermore, data imbalance and feature dimensionality problems are a critical challenge in drug-target datasets, which can decrease the classifier performances that have not been significantly addressed yet. This paper proposed a novel drug-target interaction prediction method called PreDTIs. First, the feature vectors of the protein sequence are extracted by the pseudo-position-specific scoring matrix (PsePSSM), dipeptide composition (DC) and pseudo amino acid composition (PseAAC); and the drug is encoded with MACCS substructure fingerings. Besides, we propose a FastUS algorithm to handle the class imbalance problem and also develop a MoIFS algorithm to remove the irrelevant and redundant features for getting the best optimal features. Finally, balanced and optimal features are provided to the LightGBM Classifier to identify DTIs, and the 5-fold CV validation test method was applied to evaluate the prediction ability of the proposed method. Prediction results indicate that the proposed model PreDTIs is significantly superior to other existing methods in predicting DTIs, and our model could be used to discover new drugs for unknown disorders or infections, such as for the coronavirus disease 2019 using existing drugs compounds and severe acute respiratory syndrome coronavirus 2 protein sequences.

Mendelian randomization (MR) is a powerful instrumental variable (IV) method for estimating the causal effect of an exposure on an outcome of interest even in the presence of unmeasured confounding by using genetic variants as IVs. However, the correlated and idiosyncratic pleiotropy phenomena in the human genome will lead to biased estimation of causal effects if they are not properly accounted for. In this article, we develop a novel MR approach named MRCIP to account for correlated and idiosyncratic pleiotropy simultaneously. We first propose a random-effect model to explicitly model the correlated pleiotropy and then propose a novel weighting scheme to handle the presence of idiosyncratic pleiotropy. The model parameters are estimated by maximizing a weighted likelihood function with our proposed PRW-EM algorithm. Moreover, we can also estimate the degree of the correlated pleiotropy and perform a likelihood ratio test for its presence. Extensive simulation studies show that the proposed MRCIP has improved performance over competing methods. We also illustrate the usefulness of MRCIP on two real datasets. The R package for MRCIP is publicly available at https://github.com/siqixu/MRCIP.

The protein-protein interactions (PPIs) between human and viruses mediate viral infection and host immunity processes. Therefore, the study of human-virus PPIs can help us understand the principles of human-virus relationships and can thus guide the development of highly effective drugs to break the transmission of viral infectious diseases. Recent years have witnessed the rapid accumulation of experimentally identified human-virus PPI data, which provides an unprecedented opportunity for bioinformatics studies revolving around human-virus PPIs. In this article, we provide a comprehensive overview of computational studies on human-virus PPIs, especially focusing on the method development for human-virus PPI predictions. We briefly introduce the experimental detection methods and existing database resources of human-virus PPIs, and then discuss the research progress in the development of computational prediction methods. In particular, we elaborate the machine learning-based prediction methods and highlight the need to embrace state-of-the-art deep-learning algorithms and new feature engineering techniques (e.g. the protein embedding technique derived from natural language processing). To further advance the understanding in this research topic, we also outline the practical applications of the human-virus interactome in fundamental biological discovery and new antiviral therapy development.

Single-cell RNA sequencing (scRNA-Seq) is an emerging strategy for characterizing immune cell populations. Compared to flow or mass cytometry, scRNA-Seq could potentially identify cell types and activation states that lack precise cell surface markers. However, scRNA-Seq is currently limited due to the need to manually classify each immune cell from its transcriptional profile. While recently developed algorithms accurately annotate coarse cell types (e.g. T cells versus macrophages), making fine distinctions (e.g. CD8+ effector memory T cells) remains a difficult challenge. To address this, we developed a machine learning classifier called ImmClassifier that leverages a hierarchical ontology of cell type. We demonstrate that its predictions are highly concordant with flow-based markers from CITE-seq and outperforms other tools (+15% recall, +14% precision) in distinguishing fine-grained cell types with comparable performance on coarse ones. Thus, ImmClassifier can be used to explore more deeply the heterogeneity of the immune system in scRNA-Seq experiments.

Three-dimensional (3D) architecture of the chromosomes is of crucial importance for transcription regulation and DNA replication. Various high-throughput chromosome conformation capture-based methods have revealed that CTCF-mediated chromatin loops are a major component of 3D architecture. However, CTCF-mediated chromatin loops are cell type specific, and most chromatin interaction capture techniques are time-consuming and labor-intensive, which restricts their usage on a very large number of cell types. Genomic sequence-based computational models are sophisticated enough to capture important features of chromatin architecture and help to identify chromatin loops. In this work, we develop Deep-loop, a convolutional neural network model, to integrate k-tuple nucleotide frequency component, nucleotide pair spectrum encoding, position conservation, position scoring function and natural vector features for the prediction of chromatin loops. By a series of examination based on cross-validation, Deep-loop shows excellent performance in the identification of the chromatin loops from different cell types. The source code of Deep-loop is freely available at the repository https://github.com/linDing-group/Deep-loop.

Erratum in Brief Bioinform. 2021 Sep 2;22(5):

As an essential task in protein structure and function prediction, protein fold recognition has attracted increasing attention. The majority of the existing machine learning-based protein fold recognition approaches strongly rely on handcrafted features, which depict the characteristics of different protein folds; however, effective feature extraction methods still represent the bottleneck for further performance improvement of protein fold recognition. As a powerful feature extractor, deep convolutional neural network (DCNN) can automatically extract discriminative features for fold recognition without human intervention, which has demonstrated an impressive performance on protein fold recognition. Despite the encouraging progress, DCNN often acts as a black box, and as such, it is challenging for users to understand what really happens in DCNN and why it works well for protein fold recognition. In this study, we explore the intrinsic mechanism of DCNN and explain why it works for protein fold recognition using a visual explanation technique. More specifically, we first trained a VGGNet-based DCNN model, termed VGGNet-FE, which can extract fold-specific features from the predicted protein residue-residue contact map for protein fold recognition. Subsequently, based on the trained VGGNet-FE, we implemented a new contact-assisted predictor, termed VGGfold, for protein fold recognition; we then visualized what features were extracted by each of the convolutional layers in VGGNet-FE using a deconvolution technique. Furthermore, we visualized the high-level semantic information, termed fold-discriminative region, of a predicted contact map from the localization map obtained from the last convolutional layer of VGGNet-FE. It is visually confirmed that VGGNet-FE could effectively extract distinct fold-discriminative regions for different types of protein folds, thereby accounting for the improved performance of VGGfold for protein fold recognition. In summary, this study is of great significance for both understanding the working principle of DCNNs in protein fold recognition and exploring the relationship between the predicted protein contact map and protein tertiary structure. This proposed visualization method is flexible and applicable to address other DCNN-based bioinformatics and computational biology questions. The online web server of VGGfold is freely available at http://csbio.njust.edu.cn/bioinf/vggfold/.

Multi-label proteins can participate in carrier transportation, enzyme catalysis, hormone regulation and other life activities. Meanwhile, they play a key role in the fields of biopharmaceuticals, gene and cell therapy. This article proposes a prediction method called Mps-mvRBRL to predict the subcellular localization (SCL) of multi-label protein. Firstly, pseudo position-specific scoring matrix, dipeptide composition, position specific scoring matrix-transition probability composition, gene ontology and pseudo amino acid composition algorithms are used to obtain numerical information from different views. Based on the contribution of five individual feature extraction methods, differential evolution is used for the first time to learn the weight of single feature, and then these original features use a weighted combination method to fuse multi-view information. Secondly, the fused high-dimensional features use a weighted linear discriminant analysis framework based on binary weight form to eliminate irrelevant information. Finally, the best feature vector is input into the joint ranking support vector machine and binary relevance with robust low-rank learning classifier to predict the SCL. After applying leave-one-out cross-validation, the overall actual accuracy (OAA) and overall location accuracy (OLA) of Mps-mvRBRL on the training set of Gram-positive bacteria are both 99.81%. The OAA on the test sets of plant, virus and Gram-negative bacteria datasets are 97.24%, 98.55% and 98.20%, respectively, and the OLA are 97.16%, 97.62% and 98.28%, respectively. The results show that the model achieves good prediction performance for predicting the SCL of multi-label protein.

One of the most intriguing fields emerging in current molecular biology is the study of membraneless organelles formed via liquid-liquid phase separation (LLPS). These organelles perform crucial functions in cell regulation and signalling, and recent years have also brought about the understanding of the molecular mechanism of their formation. The LLPS field is continuously developing and optimizing dedicated in vitro and in vivo methods to identify and characterize these non-stoichiometric molecular condensates and the proteins able to drive or contribute to LLPS. Building on these observations, several computational tools and resources have emerged in parallel to serve as platforms for the collection, annotation and prediction of membraneless organelle-linked proteins. In this survey, we showcase recent advancements in LLPS bioinformatics, focusing on (i) available databases and ontologies that are necessary to describe the studied phenomena and the experimental results in an unambiguous way and (ii) prediction methods to assess the potential LLPS involvement of proteins. Through hands-on application of these resources on example proteins and representative datasets, we give a practical guide to show how they can be used in conjunction to provide in silico information on LLPS.

The compositionality of the microbiome data is well-known but often neglected. The compositional transformation pertains to the supervised learning of microbiome data and is a critical step that decides the performance and reliability of the disease classifiers. We value the excellent performance of the distal discriminative balance analysis (DBA) method, which selects distal balances of pairs and trios of bacteria, in addressing the classification of high-dimensional microbiome data. By applying this method to the species-level abundances of all the disease phenotypes in the GMrepo database, we build a balance-based model repository for the classification of human gut microbiome-related diseases. The model repository supports the prediction of disease risks for new sample(s). More importantly, we highlight the concept of balance-disease associations rather than the conventional microbe-disease associations and develop the human Gut Balance-Disease Association Database (GBDAD). Each predictable balance for each disease model indicates a potential biomarker-disease relationship and can be interpreted as a bacteria ratio positively or negatively correlated with the disease. Furthermore, by linking the balance-disease associations to the evidenced microbe-disease associations in MicroPhenoDB, we surprisingly found that most species-disease associations inferred from the shotgun metagenomic datasets can be validated by external evidence beyond MicroPhenoDB. The balance-based species-disease association inference will accelerate the generation of new microbe-disease association hypotheses in gastrointestinal microecology research and clinical trials. The model repository and the GBDAD database are deployed on the GutBalance server, which supports interactive visualization and systematic interrogation of the disease models, disease-related balances and disease-related species of interest.

Fertility refers to the ability of animals to maintain reproductive function and give birth to offspring, which is an important indicator to measure the productivity of animals. Fertility is affected by many factors, among which environmental factors may also play key roles. During the past years, substantial research studies have been conducted to detect the factors related to fecundity, including genetic factors and environmental factors. However, the identified genes associated with fertility from countless previous studies are randomly dispersed in the literature, whereas some other novel fertility-related genes are needed to detect from omics-based datasets. Here, we constructed a fertility index factor database FifBase based on manually curated published literature and RNA-Seq datasets. During the construction of the literature group, we obtained 3301 articles related to fecundity for 13 species from PubMed, involving 2823 genes, which are related to 75 fecundity indicators or 47 environmental factors. Eventually, 1558 genes associated with fertility were filtered in 10 species, of which 1088 and 470 were from RNA-Seq datasets and text mining data, respectively, involving 2910 fertility-gene pairs and 58 fertility-environmental factors. All these data were cataloged into FifBase (http://www.nwsuaflmz.com/FifBase/), where the fertility-related factor information, including gene annotation and environmental factors, can be browsed, retrieved and downloaded with the user-friendly interface.

Shelterin, a protective complex at telomeres, plays essential roles in cancer. In addition to maintain telomere integrity, shelterin functions in various survival pathways. However, the detailed mechanisms of shelterin regulation in cancer remain elusive. Here, we perform a comprehensive analysis of shelterin in 9125 tumor samples across 33 cancer types using multi-omic data from The Cancer Genome Atlas, and validate some findings in Chinese Glioma Genome Atlas and cancer cell lines from Cancer Cell Line Encyclopedia. In the genomic landscape, we identify the amplification of TRF1 and POT1, co-amplification/deletion of TRF2-RAP1-TPP1 as the dominant alteration events. Clustering analysis based on shelterin expression reveals three cancer clusters with different degree of genome instability. To measure overall shelterin activity in cancer, we derive a shelterin score based on shelterin expression. Pathway analysis shows shelterin is positively correlated with E2F targets, while is negatively correlated with p53 pathway. Importantly, shelterin links to tumor immunity and predicts response to PD-1 blockade immune therapy. In-depth miRNA analysis reveals a miRNA-shelterin interaction network, with p53 regulated miRNAs targeting multiple shelterin components. We also identify a significant amount of lncRNAs regulating shelterin expression. In addition, we find shelterin expression could be used to predict patient survival in 24 cancer types. Finally, by mining the connective map database, we discover a number of potential drugs that might target shelterin. In summary, this study provides broad molecular signatures for further functional and therapeutic studies of shelterin, and also represents a systemic approach to characterize key protein complex in cancer.

Extended turnaround times and large economic costs hinder the usage of currently applied screening methods for bacterial pathogen identification (ID) and antimicrobial susceptibility testing. This review provides an overview of current detection methods and their usage in a clinical setting. Issues of timeliness and cost could soon be circumvented, however, with the emergence of detection methods involving single molecule sequencing technology. In the context of bringing diagnostics closer to the point of care, we examine the current state of Oxford Nanopore Technologies (ONT) products and their interaction with third-party software/databases to assess their capabilities for ID and antimicrobial resistance (AMR) prediction. We outline and discuss a potential diagnostic workflow, enumerating (1) rapid sample prep kits, (2) ONT hardware/software and (3) third-party software and databases to improve the cost, accuracy and turnaround times for ID and AMR. Multiple studies across a range of infection types support that the speed and accuracy of ONT sequencing is now such that established ID and AMR prediction tools can be used on its outputs, and so it can be harnessed for near real time, close to the point-of-care diagnostics in common clinical circumstances.

Artificial intelligence (AI) based drug design has demonstrated great potential to fundamentally change the pharmaceutical industries. Currently, a key issue in AI-based drug design is efficient transferable molecular descriptors or fingerprints. Here, we present hypergraph-based molecular topological representation, hypergraph-based (weighted) persistent cohomology (HPC/HWPC) and HPC/HWPC-based molecular fingerprints for machine learning models in drug design. Molecular structures and their atomic interactions are highly complicated and pose great challenges for efficient mathematical representations. We develop the first hypergraph-based topological framework to characterize detailed molecular structures and interactions at atomic level. Inspired by the elegant path complex model, hypergraph-based embedded homology and persistent homology have been proposed recently. Based on them, we construct HPC/HWPC, and use them to generate molecular descriptors for learning models in protein-ligand binding affinity prediction, one of the key step in drug design. Our models are tested on three most commonly-used databases, including PDBbind-v2007, PDBbind-v2013 and PDBbind-v2016, and outperform all existing machine learning models with traditional molecular descriptors. Our HPC/HWPC models have demonstrated great potential in AI-based drug design.

The evolution of protein-coding genes is usually driven by selective processes, which favor some evolutionary trajectories over others, optimizing the subsequent protein stability and activity. The analysis of selection in this type of genetic data is broadly performed with the metric nonsynonymous/synonymous substitution rate ratio (dN/dS). However, most of the well-established methodologies to estimate this metric make crucial assumptions, such as lack of recombination or invariable codon frequencies along genes, which can bias the estimation. Here, we review the most relevant biases in the dN/dS estimation and provide a detailed guide to estimate this metric using state-of-the-art procedures that account for such biases, along with illustrative practical examples and recommendations. We also discuss the traditional interpretation of the estimated dN/dS emphasizing the importance of considering complementary biological information such as the role of the observed substitutions on the stability and function of proteins. This review is oriented to help evolutionary biologists that aim to accurately estimate selection in protein-coding sequences.

Translation elongation is a crucial phase during protein biosynthesis. In this study, we develop a novel deep reinforcement learning-based framework, named Riboexp, to model the determinants of the uneven distribution of ribosomes on mRNA transcripts during translation elongation. In particular, our model employs a policy network to perform a context-dependent feature selection in the setting of ribosome density prediction. Our extensive tests demonstrated that Riboexp can significantly outperform the state-of-the-art methods in predicting ribosome density by up to 5.9% in terms of per-gene Pearson correlation coefficient on the datasets from three species. In addition, Riboexp can indicate more informative sequence features for the prediction task than other commonly used attribution methods in deep learning. In-depth analyses also revealed the meaningful biological insights generated by the Riboexp framework. Moreover, the application of Riboexp in codon optimization resulted in an increase of protein production by around 31% over the previous state-of-the-art method that models ribosome density. These results have established Riboexp as a powerful and useful computational tool in the studies of translation dynamics and protein synthesis. Availability: The data and code of this study are available on GitHub: https://github.com/Liuxg16/Riboexp. Contact:zengjy321@tsinghua.edu.cn; songsen@tsinghua.edu.cn.

MOTIVATION: Microsatellite instability (MSI) is a promising biomarker for cancer prognosis and chemosensitivity. Techniques are rapidly evolving for the detection of MSI from tumor-normal paired or tumor-only sequencing data. However, tumor tissues are often insufficient, unavailable, or otherwise difficult to procure. Increasing clinical evidence indicates the enormous potential of plasma circulating cell-free DNA (cfNDA) technology as a noninvasive MSI detection approach. RESULTS: We developed MSIsensor-ct, a bioinformatics tool based on a machine learning protocol, dedicated to detecting MSI status using cfDNA sequencing data with a potential stable MSIscore threshold of 20%. Evaluation of MSIsensor-ct on independent testing datasets with various levels of circulating tumor DNA (ctDNA) and sequencing depth showed 100% accuracy within the limit of detection (LOD) of 0.05% ctDNA content. MSIsensor-ct requires only BAM files as input, rendering it user-friendly and readily integrated into next generation sequencing (NGS) analysis pipelines. AVAILABILITY: MSIsensor-ct is freely available at https://github.com/niu-lab/MSIsensor-ct. SUPPLEMENTARY INFORMATION: Supplementary data are available at Briefings in Bioinformatics online.

The exploration of three-dimensional chromatin interaction and organization provides insight into mechanisms underlying gene regulation, cell differentiation and disease development. Advances in chromosome conformation capture technologies, such as high-throughput chromosome conformation capture (Hi-C) and chromatin interaction analysis by paired-end tag (ChIA-PET), have enabled the exploration of chromatin interaction and organization. However, high-resolution Hi-C and ChIA-PET data are only available for a limited number of cell lines, and their acquisition is costly, time consuming, laborious and affected by theoretical limitations. Increasing evidence shows that DNA sequence and epigenomic features are informative predictors of regulatory interaction and chromatin architecture. Based on these features, numerous computational methods have been developed for the prediction of chromatin interaction and organization, whereas they are not extensively applied in biomedical study. A systematical study to summarize and evaluate such methods is still needed to facilitate their application. Here, we summarize 48 computational methods for the prediction of chromatin interaction and organization using sequence and epigenomic profiles, categorize them and compare their performance. Besides, we provide a comprehensive guideline for the selection of suitable methods to predict chromatin interaction and organization based on available data and biological question of interest.

Dynamic modeling of biological systems is essential for understanding all properties of a given organism as it allows us to look not only at the static picture of an organism but also at its behavior under various conditions. With the increasing amount of experimental data, the number of tools that enable dynamic analysis also grows. However, various tools are based on different approaches, use different types of data and offer different functions for analyses; so it can be difficult to choose the most suitable tool for a selected type of model. Here, we bring a brief overview containing descriptions of 50 tools for the reconstruction of biological models, their time-course simulation and dynamic analysis. We examined each tool using test data and divided them based on the qualitative and quantitative nature of the mathematical apparatus they use.

Matched molecular pairs analysis (MMPA) has become a powerful tool for automatically and systematically identifying medicinal chemistry transformations from compound/property datasets. However, accurate determination of matched molecular pair (MMP) transformations largely depend on the size and quality of existing experimental data. Lack of high-quality experimental data heavily hampers the extraction of more effective medicinal chemistry knowledge. Here, we developed a new strategy called quantitative structure-activity relationship (QSAR)-assisted-MMPA to expand the number of chemical transformations and took the logD7.4 property endpoint as an example to demonstrate the reliability of the new method. A reliable logD7.4 consensus prediction model was firstly established, and its applicability domain was strictly assessed. By applying the reliable logD7.4 prediction model to screen two chemical databases, we obtained more high-quality logD7.4 data by defining a strict applicability domain threshold. Then, MMPA was performed on the predicted data and experimental data to derive more chemical rules. To validate the reliability of the chemical rules, we compared the magnitude and directionality of the property changes of the predicted rules with those of the measured rules. Then, we compared the novel chemical rules generated by our proposed approach with the published chemical rules, and found that the magnitude and directionality of the property changes were consistent, indicating that the proposed QSAR-assisted-MMPA approach has the potential to enrich the collection of rule types or even identify completely novel rules. Finally, we found that the number of the MMP rules derived from the experimental data could be amplified by the predicted data, which is helpful for us to analyze the medicinal chemical rules in local chemical environment. In summary, the proposed QSAR-assisted-MMPA approach could be regarded as a very promising strategy to expand the chemical transformation space for lead optimization, especially when no enough experimental data can support MMPA.

Predicting disease-related long non-coding RNAs (lncRNAs) is beneficial to finding of new biomarkers for prevention, diagnosis and treatment of complex human diseases. In this paper, we proposed a machine learning techniques-based classification approach to identify disease-related lncRNAs by graph auto-encoder (GAE) and random forest (RF) (GAERF). First, we combined the relationship of lncRNA, miRNA and disease into a heterogeneous network. Then, low-dimensional representation vectors of nodes were learned from the network by GAE, which reduce the dimension and heterogeneity of biological data. Taking these feature vectors as input, we trained a RF classifier to predict new lncRNA-disease associations (LDAs). Related experiment results show that the proposed method for the representation of lncRNA-disease characterizes them accurately. GAERF achieves superior performance owing to the ensemble learning method, outperforming other methods significantly. Moreover, case studies further demonstrated that GAERF is an effective method to predict LDAs.

A-to-I RNA editing, contributing to nearly 90% of all editing events in human, has been reported to involve in the pathogenesis of Alzheimer's disease (AD) due to its roles in brain development and immune regulation, such as the deficient editing of GluA2 Q/R related to cell death and memory loss. Currently, there are urgent needs for the systematic annotations of A-to-I RNA editing events in AD. Here, we built ADeditome, the annotation database of A-to-I RNA editing in AD available at https://ccsm.uth.edu/ADeditome, aiming to provide a resource and reference for functional annotation of A-to-I RNA editing in AD to identify therapeutically targetable genes in an individual. We detected 1676 363 editing sites in 1524 samples across nine brain regions from ROSMAP, MayoRNAseq and MSBB. For these editing events, we performed multiple functional annotations including identification of specific and disease stage associated editing events and the influence of editing events on gene expression, protein recoding, alternative splicing and miRNA regulation for all the genes, especially for AD-related genes in order to explore the pathology of AD. Combing all the analysis results, we found 108 010 and 26 168 editing events which may promote or inhibit AD progression, respectively. We also found 5582 brain region-specific editing events with potentially dual roles in AD across different brain regions. ADeditome will be a unique resource for AD and drug research communities to identify therapeutically targetable editing events. Significance: ADeditome is the first comprehensive resource of the functional genomics of individual A-to-I RNA editing events in AD, which will be useful for many researchers in the fields of AD pathology, precision medicine, and therapeutic researches.

Tissue immune cells have long been recognized as important regulators for the maintenance of balance in the body system. Quantification of the abundance of different immune cells will provide enhanced understanding of the correlation between immune cells and normal or abnormal situations. Currently, computational methods to predict tissue immune cell compositions from bulk transcriptomes have been largely developed. Therefore, summarizing the advantages and disadvantages is appropriate. In addition, an examination of the challenges and possible solutions for these computational models will assist the development of this field. The common hypothesis of these models is that the expression of signature genes for immune cell types might represent the proportion of immune cells that contribute to the tissue transcriptome. In general, we grouped all reported tools into three groups, including reference-free, reference-based scoring and reference-based deconvolution methods. In this review, a summary of all the currently reported computational immune cell quantification tools and their applications, limitations, and perspectives are presented. Furthermore, some critical problems are found that have limited the performance and application of these models, including inadequate immune cell type, the collinearity problem, the impact of the tissue environment on the immune cell expression level, and the deficiency of standard datasets for model validation. To address these issues, tissue specific training datasets that include all known immune cells, a hierarchical computational framework, and benchmark datasets including both tissue expression profiles and the abundances of all the immune cells are proposed to further promote the development of this field.

The 2019 novel coronavirus (SARS-CoV-2) has spread rapidly worldwide and was declared a pandemic by the WHO in March 2020. The evolution of SARS-CoV-2, either in its natural reservoir or in the human population, is still unclear, but this knowledge is essential for effective prevention and control. We propose a new framework to systematically identify recombination events, excluding those due to noise and convergent evolution. We found that several recombination events occurred for SARS-CoV-2 before its transfer to humans, including a more recent recombination event in the receptor-binding domain. We also constructed a probabilistic mutation network to explore the diversity and evolution of SARS-CoV-2 after human infection. Clustering results show that the novel coronavirus has diverged into several clusters that cocirculate over time in various regions and that several mutations across the genome are fixed during transmission throughout the human population, including D614G in the S gene and two accompanied mutations in ORF1ab. Together, these findings suggest that SARS-CoV-2 experienced a complicated evolution process in the natural environment and point to its continuous adaptation to humans. The new framework proposed in this study can help our understanding of and response to other emerging pathogens.

Time-course gene-expression data have been widely used to infer regulatory and signaling relationships between genes. Most of the widely used methods for such analysis were developed for bulk expression data. Single cell RNA-Seq (scRNA-Seq) data offer several advantages including the large number of expression profiles available and the ability to focus on individual cells rather than averages. However, the data also raise new computational challenges. Using a novel encoding for scRNA-Seq expression data, we develop deep learning methods for interaction prediction from time-course data. Our methods use a supervised framework which represents the data as 3D tensor and train convolutional and recurrent neural networks for predicting interactions. We tested our time-course deep learning (TDL) models on five different time-series scRNA-Seq datasets. As we show, TDL can accurately identify causal and regulatory gene-gene interactions and can also be used to assign new function to genes. TDL improves on prior methods for the above tasks and can be generally applied to new time-series scRNA-Seq data.

MOTIVATION: Next-generation sequencing has become exceedingly common and has transformed our ability to explore nonmodel systems. In particular, transcriptomics has facilitated the study of venom and evolution of toxins in venomous lineages; however, many challenges remain. Primarily, annotation of toxins in the transcriptome is a laborious and time-consuming task. Current annotation software often fails to predict the correct coding sequence and overestimates the number of toxins present in the transcriptome. Here, we present ToxCodAn, a python script designed to perform precise annotation of snake venom gland transcriptomes. We test ToxCodAn with a set of previously curated transcriptomes and compare the results to other annotators. In addition, we provide a guide for venom gland transcriptomics to facilitate future research and use Bothrops alternatus as a case study for ToxCodAn and our guide. RESULTS: Our analysis reveals that ToxCodAn provides precise annotation of toxins present in the transcriptome of venom glands of snakes. Comparison with other annotators demonstrates that ToxCodAn has better performance with regard to run time ($>20x$ faster), coding sequence prediction ($>3x$ more accurate) and the number of toxins predicted (generating $>4x$ less false positives). In this sense, ToxCodAn is a valuable resource for toxin annotation. The ToxCodAn framework can be expanded in the future to work with other venomous lineages and detect novel toxins.

Accurate predictions of druggability and bioactivities of compounds are desirable to reduce the high cost and time of drug discovery. After more than five decades of continuing developments, quantitative structure-activity relationship (QSAR) methods have been established as indispensable tools that facilitate fast, reliable and affordable assessments of physicochemical and biological properties of compounds in drug-discovery programs. Currently, there are mainly two types of QSAR methods, descriptor-based methods and graph-based methods. The former is developed based on predefined molecular descriptors, whereas the latter is developed based on simple atomic and bond information. In this study, we presented a simple but highly efficient modeling method by combining molecular graphs and molecular descriptors as the input of a modified graph neural network, called hyperbolic relational graph convolution network plus (HRGCN+). The evaluation results show that HRGCN+ achieves state-of-the-art performance on 11 drug-discovery-related datasets. We also explored the impact of the addition of traditional molecular descriptors on the predictions of graph-based methods, and found that the addition of molecular descriptors can indeed boost the predictive power of graph-based methods. The results also highlight the strong anti-noise capability of our method. In addition, our method provides a way to interpret models at both the atom and descriptor levels, which can help medicinal chemists extract hidden information from complex datasets. We also offer an HRGCN+'s online prediction service at https://quantum.tencent.com/hrgcn/.

Consensus molecular subtypes (CMSs) are emerging as critical factor for prognosis and treatment of colorectal cancer. Gene regulators, including chromatin regulator, RNA-binding protein and transcriptional factor, are critical modulators of cancer hallmark, yet little is known regarding the underlying functional mechanism in CMSs. Herein, we identified a core set of 235 functional gene regulators (FGRs) by integrating genome, epigenome, transcriptome and interactome of CMSs. FGRs exhibited significant multi-omics alterations and impacts on cell lines growth, as well as significantly enriched cancer driver genes and pathways. Moreover, common FGRs played different roles in the context of CMSs. In accordance with the immune characteristics of CMSs, we found that the anti-tumor immune pathways were mainly activated by FGRs (e.g. STAT1 and CREBBP) in CMS1, while inhibited by FGRs in CMS2-4. FGRs mediated aberrant expression of ligands, which bind to receptor on immune cells, and modulated tumor immune microenvironment of subtypes. Intriguingly, systematic exploration of datasets using genomic and transcriptome co-similarity reveals the coordinated manner in FGRs act in CMSs to orchestrate their pathways and patients' prognosis. Expression signatures of the FGRs revealed an optimized CMS classifier, which demonstrated 88% concordance with the gold-standard classifier, but avoiding the influence of sample composition. Overall, our integrative analysis identified FGRs to regulate core tumorigenic processes/pathways across CMSs.

Current coronavirus disease-2019 (COVID-19) pandemic has caused massive loss of lives. Clinical trials of vaccines and drugs are currently being conducted around the world; however, till now no effective drug is available for COVID-19. Identification of key genes and perturbed pathways in COVID-19 may uncover potential drug targets and biomarkers. We aimed to identify key gene modules and hub targets involved in COVID-19. We have analyzed SARS-CoV-2 infected peripheral blood mononuclear cell (PBMC) transcriptomic data through gene coexpression analysis. We identified 1520 and 1733 differentially expressed genes (DEGs) from the GSE152418 and CRA002390 PBMC datasets, respectively (FDR < 0.05). We found four key gene modules and hub gene signature based on module membership (MMhub) statistics and protein-protein interaction (PPI) networks (PPIhub). Functional annotation by enrichment analysis of the genes of these modules demonstrated immune and inflammatory response biological processes enriched by the DEGs. The pathway analysis revealed the hub genes were enriched with the IL-17 signaling pathway, cytokine-cytokine receptor interaction pathways. Then, we demonstrated the classification performance of hub genes (PLK1, AURKB, AURKA, CDK1, CDC20, KIF11, CCNB1, KIF2C, DTL and CDC6) with accuracy >0.90 suggesting the biomarker potential of the hub genes. The regulatory network analysis showed transcription factors and microRNAs that target these hub genes. Finally, drug-gene interactions analysis suggests amsacrine, BRD-K68548958, naproxol, palbociclib and teniposide as the top-scored repurposed drugs. The identified biomarkers and pathways might be therapeutic targets to the COVID-19.

Small molecule modulators of protein-protein interactions (PPIs) are being pursued as novel anticancer, antiviral and antimicrobial drug candidates. We have utilized a large data set of experimentally validated PPI modulators and developed machine learning classifiers for prediction of new small molecule modulators of PPI. Our analysis reveals that using random forest (RF) classifier, general PPI Modulators independent of PPI family can be predicted with ROC-AUC higher than 0.9, when training and test sets are generated by random split. The performance of the classifier on data sets very different from those used in training has also been estimated by using different state of the art protocols for removing various types of bias in division of data into training and test sets. The family-specific PPIM predictors developed in this work for 11 clinically important PPI families also have prediction accuracies of above 90% in majority of the cases. All these ML-based predictors have been implemented in a freely available software named SMMPPI for prediction of small molecule modulators for clinically relevant PPIs like RBD:hACE2, Bromodomain_Histone, BCL2-Like_BAX/BAK, LEDGF_IN, LFA_ICAM, MDM2-Like_P53, RAS_SOS1, XIAP_Smac, WDR5_MLL1, KEAP1_NRF2 and CD4_gp120. We have identified novel chemical scaffolds as inhibitors for RBD_hACE PPI involved in host cell entry of SARS-CoV-2. Docking studies for some of the compounds reveal that they can inhibit RBD_hACE2 interaction by high affinity binding to interaction hotspots on RBD. Some of these new scaffolds have also been found in SARS-CoV-2 viral growth inhibitors reported recently; however, it is not known if these molecules inhibit the entry phase.

In a recently published paper, we have found that SARS-CoV-2 hot-spot mutations are significantly associated with inverted repeat loci and CG dinucleotides. However, fast-spreading strains with new mutations (so-called mink farm mutations, England mutations and Japan mutations) have been recently described. We used the new datasets to check the positioning of mutation sites in genomes of the new SARS-CoV-2 strains. Using an open-access Palindrome analyzer tool, we found mutations in these new strains to be significantly enriched in inverted repeat loci.

Reverse engineering mechanistic gene regulatory network (GRN) models with a specific dynamic spatial behavior is an inverse problem without analytical solutions in general. Instead, heuristic machine learning algorithms have been proposed to infer the structure and parameters of a system of equations able to recapitulate a given gene expression pattern. However, these algorithms are computationally intensive as they need to simulate millions of candidate models, which limits their applicability and requires high computational resources. Graphics processing unit (GPU) computing is an affordable alternative for accelerating large-scale scientific computation, yet no method is currently available to exploit GPU technology for the reverse engineering of mechanistic GRNs from spatial phenotypes. Here we present an efficient methodology to parallelize evolutionary algorithms using GPU computing for the inference of mechanistic GRNs that can develop a given gene expression pattern in a multicellular tissue area or cell culture. The proposed approach is based on multi-CPU threads running the lightweight crossover, mutation and selection operators and launching GPU kernels asynchronously. Kernels can run in parallel in a single or multiple GPUs and each kernel simulates and scores the error of a model using the thread parallelism of the GPU. We tested this methodology for the inference of spatiotemporal mechanistic gene regulatory networks (GRNs)-including topology and parameters-that can develop a given 2D gene expression pattern. The results show a 700-fold speedup with respect to a single CPU implementation. This approach can streamline the extraction of knowledge from biological and medical datasets and accelerate the automatic design of GRNs for synthetic biology applications.

The current standard practice for assembling individual genomes involves mapping millions of short DNA sequences (also known as DNA 'reads') against a pre-constructed reference genome. Mapping vast amounts of short reads in a timely manner is a computationally challenging task that inevitably produces artefacts, including biases against alleles not found in the reference genome. This reference bias and other mapping artefacts are expected to be exacerbated in ancient DNA (aDNA) studies, which rely on the analysis of low quantities of damaged and very short DNA fragments (~30-80 bp). Nevertheless, the current gold-standard mapping strategies for aDNA studies have effectively remained unchanged for nearly a decade, during which time new software has emerged. In this study, we used simulated aDNA reads from three different human populations to benchmark the performance of 30 distinct mapping strategies implemented across four different read mapping software-BWA-aln, BWA-mem, NovoAlign and Bowtie2-and quantified the impact of reference bias in downstream population genetic analyses. We show that specific NovoAlign, BWA-aln and BWA-mem parameterizations achieve high mapping precision with low levels of reference bias, particularly after filtering out reads with low mapping qualities. However, unbiased NovoAlign results required the use of an IUPAC reference genome. While relevant only to aDNA projects where reference population data are available, the benefit of using an IUPAC reference demonstrates the value of incorporating population genetic information into the aDNA mapping process, echoing recent results based on graph genome representations.

Microorganisms in deep-sea hydrothermal vents provide valuable insights into life under extreme conditions. Mass spectrometry-based proteomics has been widely used to identify protein expression and function. However, the metaproteomic studies in deep-sea microbiota have been constrained largely by the low identification rates of protein or peptide. To improve the efficiency of metaproteomics for hydrothermal vent microbiota, we firstly constructed a microbial gene database (HVentDB) based on 117 public metagenomic samples from hydrothermal vents and proposed a metaproteomic analysis strategy, which takes the advantages of not only the sample-matched metagenome, but also the metagenomic information released publicly in the community of hydrothermal vents. A two-stage false discovery rate method was followed up to control the risk of false positive. By applying our community-supported strategy to a hydrothermal vent sediment sample, about twice as many peptides were identified when compared with the ways against the sample-matched metagenome or the public reference database. In addition, more enriched and explainable taxonomic and functional profiles were detected by the HVentDB-based approach exclusively, as well as many important proteins involved in methane, amino acid, sugar, glycan metabolism and DNA repair, etc. The new metaproteomic analysis strategy will enhance our understanding of microbiota, including their lifestyles and metabolic capabilities in extreme environments. The database HVentDB is freely accessible from http://lilab.life.sjtu.edu.cn:8080/HventDB/main.html.

How best to utilize the microbial taxonomic abundances in regard to the prediction and explanation of human diseases remains appealing and challenging, and the relative nature of microbiome data necessitates a proper feature selection method to resolve the compositional problem. In this study, we developed an all-in-one platform to address a series of issues in microbiome-based human disease prediction and taxonomic biomarkers discovery. We prioritize the interpretation, runtime and classification accuracy of the distal discriminative balances analysis (DBA-distal) method in selecting a set of distal discriminative balances, and develop DisBalance, a comprehensive platform, to integrate and streamline the workflows of disease model building, disease risk prediction and disease-related biomarker discovery for microbiome-based binary classifications. DisBalance allows the de novo model-building and disease risk prediction in a very fast and convenient way. To facilitate the model-driven and knowledge-driven discoveries, DisBalance dedicates multiple strategies for the mining of microbial biomarkers. The independent validation of the models constructed by the DisBalance pipeline is performed on seven microbiome datasets from the original article of DBA-distal. The implementation of the DisBalance platform is demonstrated by a complete analysis of a shotgun metagenomic dataset of Ulcerative Colitis (UC). As a free and open-source, DisBlance can be accessed at http://lab.malab.cn/soft/DisBalance. The source code and demo data for Disbalance are available at https://github.com/yangfenglong/DisBalance.

Erratum in Brief Bioinform. 2023 Jan 19;24(1):

The rapid increase of genome data brought by gene sequencing technologies poses a massive challenge to data processing. To solve the problems caused by enormous data and complex computing requirements, researchers have proposed many methods and tools which can be divided into three types: big data storage, efficient algorithm design and parallel computing. The purpose of this review is to investigate popular parallel programming technologies for genome sequence processing. Three common parallel computing models are introduced according to their hardware architectures, and each of which is classified into two or three types and is further analyzed with their features. Then, the parallel computing for genome sequence processing is discussed with four common applications: genome sequence alignment, single nucleotide polymorphism calling, genome sequence preprocessing, and pattern detection and searching. For each kind of application, its background is firstly introduced, and then a list of tools or algorithms are summarized in the aspects of principle, hardware platform and computing efficiency. The programming model of each hardware and application provides a reference for researchers to choose high-performance computing tools. Finally, we discuss the limitations and future trends of parallel computing technologies.

BACKGROUND: Coronavirus Disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has become a global pandemic following its initial emergence in China. SARS-CoV-2 has a positive-sense single-stranded RNA virus genome of around 30Kb. Using next-generation sequencing technologies, a large number of SARS-CoV-2 genomes are being sequenced at an unprecedented rate and being deposited in public repositories. For the de novo assembly of the SARS-CoV-2 genomes, a myriad of assemblers is being used, although their impact on the assembly quality has not been characterized for this virus. In this study, we aim to understand the variabilities on assembly qualities due to the choice of the assemblers. RESULTS: We performed 6648 de novo assemblies of 416 SARS-CoV-2 samples using eight different assemblers with different k-mer lengths. We used Illumina paired-end sequencing reads and compared the assembly quality of those assemblers. We showed that the choice of assembler plays a significant role in reconstructing the SARS-CoV-2 genome. Two metagenomic assemblers, e.g. MEGAHIT and metaSPAdes, performed better compared with others in most of the assembly quality metrics including, recovery of a larger fraction of the genome, constructing larger contigs and higher N50, NA50 values, etc. We showed that at least 09% (259/2873) of the variants present in the assemblies between MEGAHIT and metaSPAdes are unique to one of the assembly methods. CONCLUSION: Our analyses indicate the critical role of assembly methods for assembling SARS-CoV-2 genome using short reads and their impact on variant characterization. This study could help guide future studies to determine the best-suited assembler for the de novo assembly of virus genomes.

In recent years, single-cell RNA sequencing (scRNA-seq) technologies have been widely adopted to interrogate gene expression of individual cells; it brings opportunities to understand the underlying processes in a high-throughput manner. Deep embedded clustering (DEC) was demonstrated successful in high-dimensional sparse scRNA-seq data by joint feature learning and cluster assignment for identifying cell types simultaneously. However, the deep network architecture for embedding clustering is not trivial to optimize. Therefore, we propose an evolutionary multiobjective DEC by synergizing the multiobjective evolutionary optimization to simultaneously evolve the hyperparameters and architectures of DEC in an automatic manner. Firstly, a denoising autoencoder is integrated into the DEC to project the high-dimensional sparse scRNA-seq data into a low-dimensional space. After that, to guide the evolution, three objective functions are formulated to balance the model's generality and clustering performance for robustness. Meanwhile, migration and mutation operators are proposed to optimize the objective functions to select the suitable hyperparameters and architectures of DEC in the multiobjective framework. Multiple comparison analyses are conducted on twenty synthetic data and eight real data from different representative single-cell sequencing platforms to validate the effectiveness. The experimental results reveal that the proposed algorithm outperforms other state-of-the-art clustering methods under different metrics. Meanwhile, marker genes identification, gene ontology enrichment and pathology analysis are conducted to reveal novel insights into the cell type identification and characterization mechanisms.

MOTIVATION: Peptides have recently emerged as promising therapeutic agents against various diseases. For both research and safety regulation purposes, it is of high importance to develop computational methods to accurately predict the potential toxicity of peptides within the vast number of candidate peptides. RESULTS: In this study, we proposed ATSE, a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural networks and attention mechanism. More specifically, it consists of four modules: (i) a sequence processing module for converting peptide sequences to molecular graphs and evolutionary profiles, (ii) a feature extraction module designed to learn discriminative features from graph structural information and evolutionary information, (iii) an attention module employed to optimize the features and (iv) an output module determining a peptide as toxic or non-toxic, using optimized features from the attention module. CONCLUSION: Comparative studies demonstrate that the proposed ATSE significantly outperforms all other competing methods. We found that structural information is complementary to the evolutionary information, effectively improving the predictive performance. Importantly, the data-driven features learned by ATSE can be interpreted and visualized, providing additional information for further analysis. Moreover, we present a user-friendly online computational platform that implements the proposed ATSE, which is now available at http://server.malab.cn/ATSE. We expect that it can be a powerful and useful tool for researchers of interest.

Irregular splicing was associated with tumor formation and progression in renal cell carcinoma (RCC) and many other cancers. By using splicing data in the TCGA SpliceSeq database, RCC subtype classification was performed and splicing features and their correlations with clinical course, genetic variants, splicing factors, pathways activation and immune heterogeneity were systemically analyzed. In this research, alternative splicing was found useful for classifying RCC subtypes. Splicing inefficiency with upregulated intron retention and cassette exon was associated with advanced conditions and unfavorable overall survival of patients with RCC. Splicing characteristics like splice site strength, guanine and cytosine content and exon length may be important factors disrupting splicing balance in RCC. Other than cis-acting and trans-acting regulation, alternative splicing also differed in races and tissue types and is also affected by mutation conditions, pathway settings and the response to environmental changes. Severe irregular splicing in tumor not only indicated terrible intra-cellular homeostasis, but also changed the activity of cancer-associated pathways by different splicing effects including isoforms switching and expression regulation. Moreover, irregular splicing and splicing-associated antigens were involved in immune reprograming and formation of immunosuppressive tumor microenvironment. Overall, we have described several clinical and molecular features in RCC splicing subtypes, which may be important for patient management and targeting treatment.

In order to understand the mechanisms underlying the onset and the drug responses in multiple myeloma (MM), the second most frequent hematological cancer, the use of appropriate bioinformatic tools for integrative analysis of publicly available genomic data is required. We present MMRFBiolinks, a new R package for integrating and analyzing datasets from the Multiple Myeloma Research Foundation (MMRF) CoMMpass (Clinical Outcomes in MM to Personal Assessment of Genetic Profile) study, available at MMRF Researcher Gateway (MMRF-RG), and from the National Cancer Institute Genomic Data Commons (NCI-GDC) Data Portal. The package provides several methods for integrative analysis (array-array intensity correlation, Kaplan-Meier survival analysis) and visualization (response to treatments plot) of MMRF data, for performing an easily comprehensible analysis workflow. MMRFBiolinks extends the TCGABiolinks package by providing 13 new functions to analyze MMRF-CoMMpass data: six dealing with MMRF-RG data and seven with NCI-GDC data. As validation of the tool, we present two cases studies for searching, downloading and analyzing MMRF data. The former presents a workflow for identifying genes involved in survival depending on treatment. The latter presents an analysis workflow for analyzing the Best Overall (BO) response through correlation plots between the BO Response with respect to treatments, time, duration of treatment and annotated variants, as well as through Kaplan-Meier survival curves. The case studies demonstrate how MMRFBiolinks is able of overcoming the limitations of the analysis tools available at NCI-GDC and MMRF-RG, facilitating and making more comprehensive the retrieval, downloading and analysis of MMRF data.

Tuberculosis is a chronic inflammatory disease caused by Mycobacterium tuberculosis. When tuberculosis invades the human body, innate immunity is the first line of defense. However, how the innate immune microenvironment responds remains unclear. In this research, we studied the function of each type of cell and explained the principle of an immune microenvironment. Based on the differences in the innate immune microenvironment, we modularized the analysis of the response of five immune cells and two structural cells. The results showed that in the innate immune stress response, the genes CXCL3, PTGS2 and TNFAIP6 regulated by the nuclear factor kappa B(NK-KB) pathway played a crucial role in fighting against tuberculosis. Based on the active pathway algorithm, each immune cell showed metabolic heterogeneity. Besides, after tuberculosis infection, structural cells showed a chemotactic immunity effect based on the co-expression immunoregulatory module.

The overuse of antibiotics has led to emergence of antimicrobial resistance, and as a result, antibacterial peptides (ABPs) are receiving significant attention as an alternative. Identification of effective ABPs in lab from natural sources is a cost-intensive and time-consuming process. Therefore, there is a need for the development of in silico models, which can identify novel ABPs in protein sequences for chemical synthesis and testing. In this study, we propose a deep learning classifier named Deep-ABPpred that can identify ABPs in protein sequences. We developed Deep-ABPpred using bidirectional long short-term memory algorithm with amino acid level features from word2vec. The results show that Deep-ABPpred outperforms other state-of-the-art ABP classifiers on both test and independent datasets. Our proposed model achieved the precision of approximately 97 and 94% on test dataset and independent dataset, respectively. The high precision suggests applicability of Deep-ABPpred in proposing novel ABPs for synthesis and experimentation. By utilizing Deep-ABPpred, we identified ABPs in the tail protein sequences of Streptococcus bacteriophages, chemically synthesized identified peptides in lab and tested their activity in vitro. These ABPs showed potent antibacterial activity against selected Gram-positive and Gram-negative bacteria, which confirms the capability of Deep-ABPpred in identifying novel ABPs in protein sequences. Based on the proposed approach, an online prediction server is also developed, which is freely accessible at https://abppred.anvil.app/. This web server takes the protein sequence as input and provides ABPs with high probability (>0.95) as output.

Tumor suppressor genes (TSGs) exhibit distinct evolutionary features. We speculated that TSG promoters could have evolved specific features that facilitate their tumor-suppressing functions. We found that the promoter CpG dinucleotide frequencies of TSGs are significantly higher than that of non-cancer genes across vertebrate genomes, and positively correlated with gene expression across tissue types. The promoter CpG dinucleotide frequencies of all genes gradually increase with gene age, for which young TSGs have been subject to a stronger evolutionary pressure. Transcription-related features, namely chromatin accessibility, methylation and ZNF263-, SP1-, E2F4- and SP2-binding elements, are associated with gene expression. Moreover, higher promoter CpG dinucleotide frequencies and chromatin accessibility are positively associated with the ability of TSGs to resist downregulation during tumorigenesis. These results were successfully validated with independent datasets. In conclusion, TSGs evolved specific promoter features that optimized cancer resistance through achieving high expression in normal tissues and resistance to downregulation during tumorigenesis.

Multi-omics allows the systematic understanding of the information flow across different omics layers, while single omics can mainly reflect one aspect of the biological system. The advancement of bulk and single-cell sequencing technologies and related computational methods for multi-omics largely facilitated the development of system biology and precision medicine. Single-cell approaches have the advantage of dissecting cellular dynamics and heterogeneity, whereas traditional bulk technologies are limited to individual/population-level investigation. In this review, we first summarize the technologies for producing bulk and single-cell multi-omics data. Then, we survey the computational approaches for integrative analysis of bulk and single-cell multimodal data, respectively. Moreover, the databases and data storage for multi-omics, as well as the tools for visualizing multimodal data are summarized. We also outline the integration between bulk and single-cell data, and discuss the applications of multi-omics in precision medicine. Finally, we present the challenges and perspectives for multi-omics development.

Metabolomics, the comprehensive study of the metabolome, and lipidomics-the large-scale study of pathways and networks of cellular lipids-are major driving forces in enabling personalized medicine. Complicated and error-prone data analysis still remains a bottleneck, however, especially for identifying novel metabolites. Comparing experimental mass spectra to curated databases containing reference spectra has been the gold standard for identification of compounds, but constructing such databases is a costly and time-demanding task. Many software applications try to circumvent this process by utilizing cutting-edge advances in computational methods-including quantum chemistry and machine learning-and simulate mass spectra by performing theoretical, so called in silico fragmentations of compounds. Other solutions concentrate directly on experimental spectra and try to identify structural properties by investigating reoccurring patterns and the relationships between them. The considerable progress made in the field allows recent approaches to provide valuable clues to expedite annotation of experimental mass spectra. This review sheds light on individual strengths and weaknesses of these tools, and attempts to evaluate them-especially in view of lipidomics, when considering complex mixtures found in biological samples as well as mass spectrometer inter-instrument variability.

Structure-based virtual screenings (SBVSs) play an important role in drug discovery projects. However, it is still a challenge to accurately predict the binding affinity of an arbitrary molecule binds to a drug target and prioritize top ligands from an SBVS. In this study, we developed a novel method, using ligand-residue interaction profiles (IPs) to construct machine learning (ML)-based prediction models, to significantly improve the screening performance in SBVSs. Such a kind of the prediction model is called an IP scoring function (IP-SF). We systematically investigated how to improve the performance of IP-SFs from many perspectives, including the sampling methods before interaction energy calculation and different ML algorithms. Using six drug targets with each having hundreds of known ligands, we conducted a critical evaluation on the developed IP-SFs. The IP-SFs employing a gradient boosting decision tree (GBDT) algorithm in conjunction with the MIN + GB simulation protocol achieved the best overall performance. Its scoring power, ranking power and screening power significantly outperformed the Glide SF. First, compared with Glide, the average values of mean absolute error and root mean square error of GBDT/MIN + GB decreased about 38 and 36%, respectively. Second, the mean values of squared correlation coefficient and predictive index increased about 225 and 73%, respectively. Third, more encouragingly, the average value of the areas under the curve of receiver operating characteristic for six targets by GBDT, 0.87, is significantly better than that by Glide, which is only 0.71. Thus, we expected IP-SFs to have broad and promising applications in SBVSs.

RNA-sequencing (RNA-seq) is a widely used approach for accessing the transcriptome in biomedical research. Studies frequently include multiple samples taken from the same individual at various time points or under different conditions, correct assignment of those samples to each particular participant is evidently of great importance. Here, we propose taking advantage of typing the highly polymorphic genes from the human leukocyte antigen (HLA) complex in order to verify the correct allocation of RNA-seq samples to individuals. We introduce RNA2HLA, a novel quality control (QC) tool for performing study-wide HLA-typing for RNA-seq data and thereby identifying the samples from the common source. RNA2HLA allows precise allocation and grouping of RNA samples based on their HLA types. Strikingly, RNA2HLA revealed wrongly assigned samples from publicly available datasets and thereby demonstrated the importance of this tool for the quality control of RNA-seq studies. In addition, our tool successfully extracts HLA alleles in four-digital resolution and can be used to perform massive HLA-typing from RNA-seq based studies, which will serve multiple research purposes beyond sample QC.

Protein-protein interactions play a fundamental role in all cellular processes. Therefore, determining the structure of protein-protein complexes is crucial to understand their molecular mechanisms and develop drugs targeting the protein-protein interactions. Recently, deep learning has led to a breakthrough in intra-protein contact prediction, achieving an unusual high accuracy in recent Critical Assessment of protein Structure Prediction (CASP) structure prediction challenges. However, due to the limited number of known homologous protein-protein interactions and the challenge to generate joint multiple sequence alignments of two interacting proteins, the advances in inter-protein contact prediction remain limited. Here, we have proposed a deep learning model to predict inter-protein residue-residue contacts across homo-oligomeric protein interfaces, named as DeepHomo. Unlike previous deep learning approaches, we integrated intra-protein distance map and inter-protein docking pattern, in addition to evolutionary coupling, sequence conservation, and physico-chemical information of monomers. DeepHomo was extensively tested on both experimentally determined structures and realistic CASP-Critical Assessment of Predicted Interaction (CAPRI) targets. It was shown that DeepHomo achieved a high precision of >60% for the top predicted contact and outperformed state-of-the-art direct-coupling analysis and machine learning-based approaches. Integrating predicted inter-chain contacts into protein-protein docking significantly improved the docking accuracy on the benchmark dataset of realistic homo-dimeric targets from CASP-CAPRI experiments. DeepHomo is available at http://huanglab.phys.hust.edu.cn/DeepHomo/.

With the development of next-generation sequencing technology, a large number of transcripts need to be analyzed, and it has been a challenge to distinguish non-coding ribonucleic acid (RNAs) (ncRNAs) from coding RNAs. And for non-model organisms, due to the lack of transcriptional data, many existing methods cannot identify them. Therefore, in addition to using deoxyribonucleic acid-based and RNA-based features, we also proposed a hybrid framework based on the stacking strategy to identify ncRNAs, and we innovatively added eight features based on predicted peptides. The proposed framework was based on stacking two-layer classifier which combined random forest (RF), LightGBM, XGBoost and logistic regression (LR) models. We used this framework to build two types of models. For cross-species ncRNAs identification model, we tested it on six different species: human, mouse, zebrafish, fruit fly, worm and Arabidopsis. Compared with other tools, our model was the best in datasets of Arabidopsis, worm and zebrafish with the accuracy of 98.36%, 99.65% and 94.12%. For performance metrics analysis, the datasets of the six species were considered as a whole set, and the sensitivity, accuracy, precision and F1 values of our model were the best. For the plant-specific ncRNAs identification model, the average values of the six metrics of the two experiments were all greater than 95%, which demonstrated it can be used to identify ncRNAs in plants. The above indicates that the hybrid framework we designed is universal between animals and plants and has significant advantages in the identification of cross-species ncRNAs.

As consequence of the various genomic sequencing projects, an increasing volume of biological sequence data is being produced. Although machine learning algorithms have been successfully applied to a large number of genomic sequence-related problems, the results are largely affected by the type and number of features extracted. This effect has motivated new algorithms and pipeline proposals, mainly involving feature extraction problems, in which extracting significant discriminatory information from a biological set is challenging. Considering this, our work proposes a new study of feature extraction approaches based on mathematical features (numerical mapping with Fourier, entropy and complex networks). As a case study, we analyze long non-coding RNA sequences. Moreover, we separated this work into three studies. First, we assessed our proposal with the most addressed problem in our review, e.g. lncRNA and mRNA; second, we also validate the mathematical features in different classification problems, to predict the class of lncRNA, e.g. circular RNAs sequences; third, we analyze its robustness in scenarios with imbalanced data. The experimental results demonstrated three main contributions: first, an in-depth study of several mathematical features; second, a new feature extraction pipeline; and third, its high performance and robustness for distinct RNA sequence classification. Availability:https://github.com/Bonidia/FeatureExtraction_BiologicalSequences.

Interactions between proteins and small molecule metabolites play vital roles in regulating protein functions and controlling various cellular processes. The activities of metabolic enzymes, transcription factors, transporters and membrane receptors can all be mediated through protein-metabolite interactions (PMIs). Compared with the rich knowledge of protein-protein interactions, little is known about PMIs. To the best of our knowledge, no existing database has been developed for collecting PMIs. The recent rapid development of large-scale mass spectrometry analysis of biomolecules has led to the discovery of large amounts of PMIs. Therefore, we developed the PMI-DB to provide a comprehensive and accurate resource of PMIs. A total of 49 785 entries were manually collected in the PMI-DB, corresponding to 23 small molecule metabolites, 9631 proteins and 4 species. Unlike other databases that only provide positive samples, the PMI-DB provides non-interaction between proteins and metabolites, which not only reduces the experimental cost for biological experimenters but also facilitates the construction of more accurate algorithms for researchers using machine learning. To show the convenience of the PMI-DB, we developed a deep learning-based method to predict PMIs in the PMI-DB and compared it with several methods. The experimental results show that the area under the curve and area under the precision-recall curve of our method are 0.88 and 0.95, respectively. Overall, the PMI-DB provides a user-friendly interface for browsing the biological functions of metabolites/proteins of interest, and experimental techniques for identifying PMIs in different species, which provides important support for furthering the understanding of cellular processes. The PMI-DB is freely accessible at http://easybioai.com/PMIDB.

Transcription factors (TFs) act as key regulators in biological processes through controlling gene expression. Here, we conducted a systematic study for all human TFs on the expression, regulation, interaction, mutation, phenotype and cancer survival. We revealed that the average expression levels of TFs in normal tissues were lower than 50% expression of non-TFs, whereas TF expression was increased in cancers. TFs that are specifically expressed in an individual tissue or cancer may be potential marker genes. For instance, TGIF2LX/Y were preferentially expressed in testis and NEUROG1, PRDM14, SRY, ZNF705A and ZNF716 were specifically highly expressed in germ cell tumors. We found different distributions of target genes and TF co-regulations in different TF families. Some small TF families have huge protein interaction pairs, suggesting their central roles in transcriptional regulation. The bZIP family is a small family involving many signaling pathways. Survival analysis indicated that most TFs significantly affect survival of one or more cancers. Some survival-related TFs were also specifically highly expressed in the corresponding cancer types, which may be potential targets for cancer therapy. Finally, we identified 43 TFs whose mutations were closely correlated to survival, suggesting their cancer-driven roles. The systematic analysis of TFs provides useful clues for further investigation of TF regulatory mechanisms and the role of TFs in diseases.

The prognostic role of adjacent nontumor tissue in hepatocellular carcinoma (HCC) patients is still not clear. The activity changes of immunologic and hallmark gene sets in adjacent nontumor tissues may substantially impact on prognosis by affecting proliferation of liver cells and colonization of circulating tumor cells after HCC treatment measures such as hepatectomy. We aimed to identify HCC subtypes and prognostic gene sets based on the activity changes of gene sets in tumor and nontumor tissues, to improve patient outcomes. We comprehensively revealed the activity changes of immunologic and hallmark gene sets in HCC and nontumor samples by gene set variation analysis (GSVA), and identified three clinically relevant subtypes of HCC by nonnegative matrix factorization method (NMF). Patients with subtype 1 had good overall survival, whereas those with subtype 2 and subtype 3 had poor prognosis. Patients with subtype 1 in the validation group also tended to live longer. We also identified three prognostic gene sets in tumor and four prognostic gene sets in nontumor by least absolute shrinkage and selection operator method (LASSO). Interestingly, functional enrichment analysis revealed that in nontumor tissues, genes from four gene sets correlated with immune reaction, cell adhesion, whereas in tumor tissue, genes from three gene sets closely correlated with cell cycle. Our results offer new insights on accurately evaluating prognosis-the important role of gene sets in both tumor and adjacent nontumor tissues, suggesting that when selecting for HCC treatment modality, changes in tumor and nontumor tissues should also be considered, especially after hepatectomy.

Transcription factors (TFs) play an important role in regulating gene expression, thus identification of the regions bound by them has become a fundamental step for molecular and cellular biology. In recent years, an increasing number of deep learning (DL) based methods have been proposed for predicting TF binding sites (TFBSs) and achieved impressive prediction performance. However, these methods mainly focus on predicting the sequence specificity of TF-DNA binding, which is equivalent to a sequence-level binary classification task, and fail to identify motifs and TFBSs accurately. In this paper, we developed a fully convolutional network coupled with global average pooling (FCNA), which by contrast is equivalent to a nucleotide-level binary classification task, to roughly locate TFBSs and accurately identify motifs. Experimental results on human ChIP-seq datasets show that FCNA outperforms other competing methods significantly. Besides, we find that the regions located by FCNA can be used by motif discovery tools to further refine the prediction performance. Furthermore, we observe that FCNA can accurately identify TF-DNA binding motifs across different cell lines and infer indirect TF-DNA bindings.

Genetic correlation is the correlation of phenotypic effects by genetic variants across the genome on two phenotypes. It is an informative metric to quantify the overall genetic similarity between complex traits, which provides insights into their polygenic genetic architecture. Several methods have been proposed to estimate genetic correlation based on data collected from genome-wide association studies (GWAS). Due to the easy access of GWAS summary statistics and computational efficiency, methods only requiring GWAS summary statistics as input have become more popular than methods utilizing individual-level genotype data. Here, we present a benchmark study for different summary-statistics-based genetic correlation estimation methods through simulation and real data applications. We focus on two major technical challenges in estimating genetic correlation: marker dependency caused by linkage disequilibrium (LD) and sample overlap between different studies. To assess the performance of different methods in the presence of these two challenges, we first conducted comprehensive simulations with diverse LD patterns and sample overlaps. Then we applied these methods to real GWAS summary statistics for a wide spectrum of complex traits. Based on these experiments, we conclude that methods relying on accurate LD estimation are less robust in real data applications due to the imprecision of LD obtained from reference panels. Our findings offer guidance on how to choose appropriate methods for genetic correlation estimation in post-GWAS analysis.

Recent development of spatial transcriptomics (ST) is capable of associating spatial information at different spots in the tissue section with RNA abundance of cells within each spot, which is particularly important to understand tissue cytoarchitectures and functions. However, for such ST data, since a spot is usually larger than an individual cell, gene expressions measured at each spot are from a mixture of cells with heterogenous cell types. Therefore, ST data at each spot needs to be disentangled so as to reveal the cell compositions at that spatial spot. In this study, we propose a novel method, named deconvoluting spatial transcriptomics data through graph-based convolutional networks (DSTG), to accurately deconvolute the observed gene expressions at each spot and recover its cell constitutions, thus achieving high-level segmentation and revealing spatial architecture of cellular heterogeneity within tissues. DSTG not only demonstrates superior performance on synthetic spatial data generated from different protocols, but also effectively identifies spatial compositions of cells in mouse cortex layer, hippocampus slice and pancreatic tumor tissues. In conclusion, DSTG accurately uncovers the cell states and subpopulations based on spatial localization. DSTG is available as a ready-to-use open source software (https://github.com/Su-informatics-lab/DSTG) for precise interrogation of spatial organizations and functions in tissues.

The interactions between proteins and nucleic acid sequences play many important roles in gene expression and some cellular activities. Accurate prediction of the nucleic acid binding residues in proteins will facilitate the research of the protein functions, gene expression, drug design, etc. In this regard, several computational methods have been proposed to predict the nucleic acid binding residues in proteins. However, these methods cannot satisfactorily measure the global interactions among the residues along protein. Furthermore, these methods are suffering cross-prediction problem, new strategies should be explored to solve this problem. In this study, a new computational method called NCBRPred was proposed to predict the nucleic acid binding residues based on the multilabel sequence labeling model. NCBRPred used the bidirectional Gated Recurrent Units (BiGRUs) to capture the global interactions among the residues, and treats this task as a multilabel learning task. Experimental results on three widely used benchmark datasets and an independent dataset showed that NCBRPred achieved higher predictive results with lower cross-prediction, outperforming 10 existing state-of-the-art predictors. The web-server and a stand-alone package of NCBRPred are freely available at http://bliulab.net/NCBRPred. It is anticipated that NCBRPred will become a very useful tool for identifying nucleic acid binding residues.

Copy number variations (CNVs) are an important class of variations contributing to the pathogenesis of many disease phenotypes. Detecting CNVs from genomic data remains difficult, and the most currently applied methods suffer from an unacceptably high false positive rate. A common practice is to have human experts manually review original CNV calls for filtering false positives before further downstream analysis or experimental validation. Here, we propose DeepCNV, a deep learning-based tool, intended to replace human experts when validating CNV calls, focusing on the calls made by one of the most accurate CNV callers, PennCNV. The sophistication of the deep neural network algorithm is enriched with over 10 000 expert-scored samples that are split into training and testing sets. Variant confidence, especially for CNVs, is a main roadblock impeding the progress of linking CNVs with the disease. We show that DeepCNV adds to the confidence of the CNV calls with an optimal area under the receiver operating characteristic curve of 0.909, exceeding other machine learning methods. The superiority of DeepCNV was also benchmarked and confirmed using an experimental wet-lab validation dataset. We conclude that the improvement obtained by DeepCNV results in significantly fewer false positive results and failures to replicate the CNV association results.

CRISPR/Cas9 multigene editing is an active and widely studied topic in the fields of biomedicine and biology. It involves a simultaneous participation of multiple single-guide RNAs (sgRNAs) to edit multiple target genes in a way that each gene is edited by one of these sgRNAs. There are possibly numerous sgRNA candidates capable of on-target editing on each of these genes with various efficiencies. Meanwhile, each of these sgRNA candidates may cause unwanted off-target editing at many other genes. Therefore, selection optimization of these multiple sgRNAs is demanded so as to minimize the number of sgRNAs and thus reduce the collective negative effects caused by the off-target editing. This survey reviews wet-laboratory approaches to the implementation of multigene editing and their needs of computational tools for better design. We found that though off-target editing is unavoidable during the gene editing, those disfavored cuttings by some target genes' sgRNAs can potentially become on-target editing sites for some other genes of interests. This off-to-on role conversion is beneficial to optimize the sgRNA selection in multigene editing. We present a preference cutting score to assess those beneficial off-target cutting sites, which have a few mismatches with their host genes' on-target editing sites. These potential sgRNAs can be prioritized for recommendation via ranking their on-target average cutting efficiency, the total off-target site number and their average preference cutting score. We also present case studies on cancer-associated genes to demonstrate tremendous usefulness of the new method.

Triple-negative breast cancer (TNBC) has been a challenging breast cancer subtype for oncological therapy. Normally, it can be classified into different molecular subtypes. Accurate and stable classification of the six subtypes is essential for personalized treatment of TNBC. In this study, we proposed a new framework to distinguish the six subtypes of TNBC, and this is one of the handful studies that completed the classification based on mRNA and long noncoding RNA expression data. Particularly, we developed a gene selection approach named DGGA, which takes correlation information between genes into account in the process of measuring gene importance and then effectively removes redundant genes. A gene scoring approach that combined GeneRank scores with gene importance generated by deep neural network (DNN), taking inter-subtype discrimination and inner-gene correlations into account, was came up to improve gene selection performance. More importantly, we embedded a gene connectivity matrix in the DNN for sparse learning, which takes additional consideration with weight changes during training when obtaining the measurement of the relative importance of each gene. Finally, Genetic Algorithm was used to simulate the natural evolutionary process to search for the optimal subset of TNBC subtype classification. We validated the proposed method through cross-validation, and the results demonstrate that it can use fewer genes to obtain more accurate classification results. The implementation for the proposed method is available at https://github.com/RanSuLab/TNBC.

Glioblastoma (GBM) is a common malignant brain tumor which often presents as a comorbidity with central nervous system (CNS) disorders. Both CNS disorders and GBM cells release glutamate and show an abnormality, but differ in cellular behavior. So, their etiology is not well understood, nor is it clear how CNS disorders influence GBM behavior or growth. This led us to employ a quantitative analytical framework to unravel shared differentially expressed genes (DEGs) and cell signaling pathways that could link CNS disorders and GBM using datasets acquired from the Gene Expression Omnibus database (GEO) and The Cancer Genome Atlas (TCGA) datasets where normal tissue and disease-affected tissue were examined. After identifying DEGs, we identified disease-gene association networks and signaling pathways and performed gene ontology (GO) analyses as well as hub protein identifications to predict the roles of these DEGs. We expanded our study to determine the significant genes that may play a role in GBM progression and the survival of the GBM patients by exploiting clinical and genetic factors using the Cox Proportional Hazard Model and the Kaplan-Meier estimator. In this study, 177 DEGs with 129 upregulated and 48 downregulated genes were identified. Our findings indicate new ways that CNS disorders may influence the incidence of GBM progression, growth or establishment and may also function as biomarkers for GBM prognosis and potential targets for therapies. Our comparison with gold standard databases also provides further proof to support the connection of our identified biomarkers in the pathology underlying the GBM progression.

Protein-nucleic acid interactions play essential roles in many biological processes, such as transcription, replication and translation. In protein-nucleic acid interfaces, hotspot residues contribute the majority of binding affinity toward molecular recognition. Hotspot residues are commonly regarded as potential binding sites for compound molecules in drug design projects. The dynamic property is a considerable factor that affects the binding of ligands. Computational approaches have been developed to expedite the prediction of hotspot residues on protein-nucleic acid interfaces. However, existing approaches overlook hotspot dynamics, despite their essential role in protein function. Here, we report a web server named Hotspots In silico Scanning on Nucleic Acid and Protein Interface (HISNAPI) to analyze hotspot residue dynamics by integrating molecular dynamics simulation and one-step free energy perturbation. HISNAPI is capable of not only predicting the hotspot residues in protein-nucleic acid interfaces but also providing insights into their intensity and correlation of dynamic motion. Protein dynamics have been recognized as a vital factor that has an effect on the interaction specificity and affinity of the binding partners. We applied HISNAPI to the case of SARS-CoV-2 RNA-dependent RNA polymerase, a vital target of the antiviral drug for the treatment of coronavirus disease 2019. We identified the hotspot residues and characterized their dynamic behaviors, which might provide insight into the target site for antiviral drug design. The web server is freely available via a user-friendly web interface at http://chemyang.ccnu.edu.cn/ccb/server/HISNAPI/ and http://agroda.gzu.edu.cn:9999/ccb/server/HISNAPI/.

Individual variations in drug efficacy, side effects and adverse drug reactions are still challenging that cannot be ignored in drug research and development. The aim of pharmacometabonomics is to better understand the pharmacokinetic properties of drugs and monitor the drug effects on specific metabolic pathways. Here, we systematically reviewed the recent technological advances in pharmacometabonomics for better understanding the pathophysiological mechanisms of diseases as well as the metabolic effects of drugs on bodies. First, the advantages and disadvantages of all mainstream analytical techniques were compared. Second, many data processing strategies including filtering, missing value imputation, quality control-based correction, transformation, normalization together with the methods implemented in each step were discussed. Third, various feature selection and feature extraction algorithms commonly applied in pharmacometabonomics were described. Finally, the databases that facilitate current pharmacometabonomics were collected and discussed. All in all, this review provided guidance for researchers engaged in pharmacometabonomics and metabolomics, and it would promote the wide application of metabolomics in drug research and personalized medicine.

Internal tandem duplication (ITD) of FMS-like tyrosine kinase 3 (FLT3-ITD) constitutes an independent indicator of poor prognosis in acute myeloid leukaemia (AML). AML with FLT3-ITD usually presents with poor treatment outcomes, high recurrence rate and short overall survival. Currently, polymerase chain reaction and capillary electrophoresis are widely adopted for the clinical detection of FLT3-ITD, whereas the length and mutation frequency of ITD are evaluated using fragment analysis. With the development of sequencing technology and the high incidence of FLT3-ITD mutations, a multitude of bioinformatics tools and pipelines have been developed to detect FLT3-ITD using next-generation sequencing data. However, systematic comparison and evaluation of the methods or software have not been performed. In this study, we provided a comprehensive review of the principles, functionality and limitations of the existing methods for detecting FLT3-ITD. We further compared the qualitative and quantitative detection capabilities of six representative tools using simulated and biological data. Our results will provide practical guidance for researchers and clinicians to select the appropriate FLT3-ITD detection tools and highlight the direction of future developments in this field. Availability: A Docker image with several programs pre-installed is available at https://github.com/niu-lab/docker-flt3-itd to facilitate the application of FLT3-ITD detection tools.

Bridging heterogeneous mutation data fills in the gap between various data categories and propels discovery of disease-related genes. It is known that genome-wide association study (GWAS) infers significant mutation associations that link genotype and phenotype. However, due to the differences of size and quality between GWAS studies, not all de facto vital variations are able to pass the multiple testing. In the meantime, mutation events widely reported in literature unveil typical functional biological process, including mutation types like gain of function and loss of function. To bring together the heterogeneous mutation data, we propose a 'Gene-Disease Association prediction by Mutation Data Bridging (GDAMDB)' pipeline with a statistic generative model. The model learns the distribution parameters of mutation associations and mutation types and recovers false-negative GWAS mutations that fail to pass significant test but represent supportive evidences of functional biological process in literature. Eventually, we applied GDAMDB in Alzheimer's disease (AD) and predicted 79 AD-associated genes. Besides, 12 of them from the original GWAS, 60 of them are supported to be AD-related by other GWAS or literature report, and rest of them are newly predicted genes. Our model is capable of enhancing the GWAS-based gene association discovery by well combining text mining results. The positive result indicates that bridging the heterogeneous mutation data is contributory for the novel disease-related gene discovery.

Batch effect correction is an essential step in the integrative analysis of multiple single-cell RNA-sequencing (scRNA-seq) data. One state-of-the-art strategy for batch effect correction is via unsupervised or supervised detection of mutual nearest neighbors (MNNs). However, both types of methods only detect MNNs across batches of uncorrected data, where the large batch effects may affect the MNN search. To address this issue, we presented a batch effect correction approach via iterative supervised MNN (iSMNN) refinement across data after correction. Our benchmarking on both simulation and real datasets showed the advantages of the iterative refinement of MNNs on the performance of correction. Compared to popular alternative methods, our iSMNN is able to better mix the cells of the same cell type across batches. In addition, iSMNN can also facilitate the identification of differentially expressed genes (DEGs) that are relevant to the biological function of certain cell types. These results indicated that iSMNN will be a valuable method for integrating multiple scRNA-seq datasets that can facilitate biological and medical studies at single-cell level.

Venn diagrams are widely used tools for graphical depiction of the unions, intersections and distinctions among multiple datasets, and a large number of programs have been developed to generate Venn diagrams for applications in various research areas. However, a comprehensive review comparing these tools has not been previously performed. In this review, we collect Venn diagram generators (i.e. tools for visualizing the relationships of input lists within a Venn diagram) and Venn diagram application tools (i.e. tools for analyzing the relationships between biological data and visualizing them in a Venn diagram) to compare their functional capacity as follows: ability to generate high-quality diagrams; maximum datasets handled by each program; input data formats; output diagram styles and image output formats. We also evaluate the picture beautification parameters of the Venn diagram generators in terms of the graphical layout and briefly describe the functional characteristics of the most popular Venn diagram application tools. Finally, we discuss the challenges in improving Venn diagram application tools and provide a perspective on Venn diagram applications in bioinformatics. Our aim is to assist users in selecting suitable tools for analyzing and visualizing user-defined datasets.

Knowledge of the specificity of DNA-protein binding is crucial for understanding the mechanisms of gene expression, regulation and gene therapy. In recent years, deep-learning-based methods for predicting DNA-protein binding from sequence data have achieved significant success. Nevertheless, the current state-of-the-art computational methods have some drawbacks associated with the use of limited datasets with insufficient experimental data. To address this, we propose a novel transfer learning-based method, termed SAResNet, which combines the self-attention mechanism and residual network structure. More specifically, the attention-driven module captures the position information of the sequence, while the residual network structure guarantees that the high-level features of the binding site can be extracted. Meanwhile, the pre-training strategy used by SAResNet improves the learning ability of the network and accelerates the convergence speed of the network during transfer learning. The performance of SAResNet is extensively tested on 690 datasets from the ChIP-seq experiments with an average AUC of 92.0%, which is 4.4% higher than that of the best state-of-the-art method currently available. When tested on smaller datasets, the predictive performance is more clearly improved. Overall, we demonstrate that the superior performance of DNA-protein binding prediction on DNA sequences can be achieved by combining the attention mechanism and residual structure, and a novel pipeline is accordingly developed. The proposed methodology is generally applicable and can be used to address any other sequence classification problems.

Post-translational modifications (PTMs) play significant roles in regulating protein structure, activity and function, and they are closely involved in various pathologies. Therefore, the identification of associated PTMs is the foundation of in-depth research on related biological mechanisms, disease treatments and drug design. Due to the high cost and time consumption of high-throughput sequencing techniques, developing machine learning-based predictors has been considered an effective approach to rapidly recognize potential modified sites. However, the imbalanced distribution of true and false PTM sites, namely, the data imbalance problem, largely effects the reliability and application of prediction tools. In this article, we conduct a systematic survey of the research progress in the imbalanced PTMs classification. First, we describe the modeling process in detail and outline useful data imbalance solutions. Then, we summarize the recently proposed bioinformatics tools based on imbalanced PTM data and simultaneously build a convenient website, ImClassi_PTMs (available at lab.malab.cn/∼dlj/ImbClassi_PTMs/), to facilitate the researchers to view. Moreover, we analyze the challenges of current computational predictors and propose some suggestions to improve the efficiency of imbalance learning. We hope that this work will provide comprehensive knowledge of imbalanced PTM recognition and contribute to advanced predictors in the future.

Transcriptional regulation is associated with complicated mechanisms including multiple molecular interactions and collaborative drive. Long noncoding RNAs (lncRNAs) have highly structured characteristics and play vital roles in the regulation of transcription in organisms. However, the specific contributions of conformation feature and underlying molecular mechanisms are still unclear. In the present paper, a hypothesis regarding molecular structure effect is presented, which proposes that lncRNAs fold into a complex spatial architecture and act as a skeleton to recruit transcription factors (TF) targeted binding, and which is involved in cooperative regulation. A candidate set of TF-lncRNA coregulation was constructed, and it was found that structural accessibility affected molecular binding force. In addition, transcription factor binding site (TFBS) regions of myopia-related lncRNA transcripts were disturbed, and it was discovered that base mutations affected the occurrence of significant molecular allosteric changes in important elements and variable splicing regions, mediating the onset and development of myopia. The results originated from structureomics and interactionomics and created conditions for systematic research on the mechanisms of structure-mediated TF-lncRNA coregulation in transcriptional regulation. Finally, these findings will help further the understanding of key regulatory roles of molecular allostery in cell physiological and pathological processes.

Biomolecular recognition between ligand and protein plays an essential role in drug discovery and development. However, it is extremely time and resource consuming to determine the protein-ligand binding affinity by experiments. At present, many computational methods have been proposed to predict binding affinity, most of which usually require protein 3D structures that are not often available. Therefore, new methods that can fully take advantage of sequence-level features are greatly needed to predict protein-ligand binding affinity and accelerate the drug discovery process. We developed a novel deep learning approach, named DeepDTAF, to predict the protein-ligand binding affinity. DeepDTAF was constructed by integrating local and global contextual features. More specifically, the protein-binding pocket, which possesses some special properties for directly binding the ligand, was firstly used as the local input feature for protein-ligand binding affinity prediction. Furthermore, dilated convolution was used to capture multiscale long-range interactions. We compared DeepDTAF with the recent state-of-art methods and analyzed the effectiveness of different parts of our model, the significant accuracy improvement showed that DeepDTAF was a reliable tool for affinity prediction. The resource codes and data are available at https: //github.com/KailiWang1/DeepDTAF.

Detailed maps of the molecular basis of the disease are powerful tools for interpreting data and building predictive models. Modularity and composability are considered necessary network features for large-scale collaborative efforts to build comprehensive molecular descriptions of disease mechanisms. An effective way to create and manage large systems is to compose multiple subsystems. Composable network components could effectively harness the contributions of many individuals and enable teams to seamlessly assemble many individual components into comprehensive maps. We examine manually built versions of the RAS-RAF-MEK-ERK cascade from the Atlas of Cancer Signalling Network, PANTHER and Reactome databases and review them in terms of their reusability and composability for assembling new disease models. We identify design principles for managing complex systems that could make it easier for investigators to share and reuse network components. We demonstrate the main challenges including incompatible levels of detail and ambiguous representation of complexes and highlight the need to address these challenges.

Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis (Mtb) and it has been one of the top 10 causes of death globally. Drug-resistant tuberculosis (XDR-TB), extensively resistant to the commonly used first-line drugs, has emerged as a major challenge to TB treatment. Hence, it is quite necessary to discover novel drug candidates for TB treatment. In this study, based on different types of molecular representations, four machine learning (ML) algorithms, including support vector machine, random forest (RF), extreme gradient boosting (XGBoost) and deep neural networks (DNN), were used to develop classification models to distinguish Mtb inhibitors from noninhibitors. The results demonstrate that the XGBoost model exhibits the best prediction performance. Then, two consensus strategies were employed to integrate the predictions from multiple models. The evaluation results illustrate that the consensus model by stacking the RF, XGBoost and DNN predictions offers the best predictions with area under the receiver operating characteristic curve of 0.842 and 0.942 for the 10-fold cross-validated training set and external test set, respectively. Besides, the association between the important descriptors and the bioactivities of molecules was interpreted by using the Shapley additive explanations method. Finally, an online webserver called ChemTB (http://cadd.zju.edu.cn/chemtb/) was developed, and it offers a freely available computational tool to detect potential Mtb inhibitors.

Next-generation sequencing (NGS) enables massively parallel acquisition of large-scale omics data; however, objective data quality filtering parameters are lacking. Although a useful metric, evidence reveals that platform-generated Phred values overestimate per-base quality scores. We have developed novel and empirically based algorithms that streamline NGS data quality filtering. The pipeline leverages known sequence motifs to enable empirical estimation of error rates, detection of erroneous base calls and removal of contaminating adapter sequence. The performance of motif-based error detection and quality filtering were further validated with read compression rates as an unbiased metric. Elevated error rates at read ends, where known motifs lie, tracked with propagation of erroneous base calls. Barcode swapping, an inherent problem with pooled libraries, was also effectively mitigated. The ngsComposer pipeline is suitable for various NGS protocols and platforms due to the universal concepts on which the algorithms are based.

MOTIVATION: Rare variant-based analyses are beginning to identify risk genes for neuropsychiatric disorders and other diseases. However, the identified genes only account for a fraction of predicted causal genes. Recent studies have shown that rare damaging variants are significantly enriched in specific gene-sets. Methods which are able to jointly model rare variants and gene-sets to identify enriched gene-sets and use these enriched gene-sets to prioritize additional risk genes could improve understanding of the genetic architecture of diseases. RESULTS: We propose DECO (Integrated analysis of de novo mutations, rare case/control variants and omics information via gene-sets), an integrated method for rare-variant and gene-set analysis. The method can (i) test the enrichment of gene-sets directly within the statistical model, and (ii) use enriched gene-sets to rank existing genes and prioritize additional risk genes for tested disorders. In simulations, DECO performs better than a homologous method that uses only variant data. To demonstrate the application of the proposed protocol, we have applied this approach to rare-variant datasets of schizophrenia. Compared with a method which only uses variant information, DECO is able to prioritize additional risk genes. AVAILABILITY: DECO can be used to analyze rare-variants and biological pathways or cell types for any disease. The package is available on Github https://github.com/hoangtn/DECO.

MOTIVATION: There is growing evidence showing that the dysregulations of miRNAs cause diseases through various kinds of the underlying mechanism. Thus, predicting the multiple-category associations between microRNAs (miRNAs) and diseases plays an important role in investigating the roles of miRNAs in diseases. Moreover, in contrast with traditional biological experiments which are time-consuming and expensive, computational approaches for the prediction of multicategory miRNA-disease associations are time-saving and cost-effective that are highly desired for us. RESULTS: We present a novel data-driven end-to-end learning-based method of neural multiple-category miRNA-disease association prediction (NMCMDA) for predicting multiple-category miRNA-disease associations. The NMCMDA has two main components: (i) encoder operates directly on the miRNA-disease heterogeneous network and leverages Graph Neural Network to learn miRNA and disease latent representations, respectively. (ii) Decoder yields miRNA-disease association scores with the learned latent representations as input. Various kinds of encoders and decoders are proposed for NMCMDA. Finally, the NMCMDA with the encoder of Relational Graph Convolutional Network and the neural multirelational decoder (NMR-RGCN) achieves the best prediction performance. We compared the NMCMDA with other baselines on three experimental datasets. The experimental results show that the NMR-RGCN is significantly superior to the state-of-the-art method TDRC in terms of Top-1 precision, Top-1 Recall, and Top-1 F1. Additionally, case studies are provided for two high-risk human diseases (namely, breast cancer and lung cancer) and we also provide the prediction and validation of top-10 miRNA-disease-category associations based on all known data of HMDD v3.2, which further validate the effectiveness and feasibility of the proposed method.

Antimicrobial peptides (AMPs) are a unique and diverse group of molecules that play a crucial role in a myriad of biological processes and cellular functions. AMP-related studies have become increasingly popular in recent years due to antimicrobial resistance, which is becoming an emerging global concern. Systematic experimental identification of AMPs faces many difficulties due to the limitations of current methods. Given its significance, more than 30 computational methods have been developed for accurate prediction of AMPs. These approaches show high diversity in their data set size, data quality, core algorithms, feature extraction, feature selection techniques and evaluation strategies. Here, we provide a comprehensive survey on a variety of current approaches for AMP identification and point at the differences between these methods. In addition, we evaluate the predictive performance of the surveyed tools based on an independent test data set containing 1536 AMPs and 1536 non-AMPs. Furthermore, we construct six validation data sets based on six different common AMP databases and compare different computational methods based on these data sets. The results indicate that amPEPpy achieves the best predictive performance and outperforms the other compared methods. As the predictive performances are affected by the different data sets used by different methods, we additionally perform the 5-fold cross-validation test to benchmark different traditional machine learning methods on the same data set. These cross-validation results indicate that random forest, support vector machine and eXtreme Gradient Boosting achieve comparatively better performances than other machine learning methods and are often the algorithms of choice of multiple AMP prediction tools.

A comprehensible representation of a molecular network is key to communicating and understanding scientific results in systems biology. The Systems Biology Graphical Notation (SBGN) has emerged as the main standard to represent such networks graphically. It has been implemented by different software tools, and is now largely used to communicate maps in scientific publications. However, learning the standard, and using it to build large maps, can be tedious. Moreover, SBGN maps are not grounded on a formal semantic layer and therefore do not enable formal analysis. Here, we introduce a new set of patterns representing recurring concepts encountered in molecular networks, called SBGN bricks. The bricks are structured in a new ontology, the Bricks Ontology (BKO), to define clear semantics for each of the biological concepts they represent. We show the usefulness of the bricks and BKO for both the template-based construction and the semantic annotation of molecular networks. The SBGN bricks and BKO can be freely explored and downloaded at sbgnbricks.org.

Recent advances in high-throughput sequencing technologies and computational methods have added a new dimension to metagenomic data analysis i.e. genome-resolved metagenomics. In general terms, it refers to the recovery of draft or high-quality microbial genomes and their taxonomic classification and functional annotation. In recent years, several studies have utilized the genome-resolved metagenome analysis approach and identified previously unknown microbial species from human and environmental metagenomes. In this review, we describe genome-resolved metagenome analysis as a series of four necessary steps: (i) preprocessing of the sequencing reads, (ii) de novo metagenome assembly, (iii) genome binning and (iv) taxonomic and functional analysis of the recovered genomes. For each of these four steps, we discuss the most commonly used tools and the currently available pipelines to guide the scientific community in the recovery and subsequent analyses of genomes from any metagenome sample. Furthermore, we also discuss the tools required for validation of assembly quality as well as for improving quality of the recovered genomes. We also highlight the currently available pipelines that can be used to automate the whole analysis without having advanced bioinformatics knowledge. Finally, we will highlight the most widely adapted and actively maintained tools and pipelines that can be helpful to the scientific community in decision making before they commence the analysis.

Last two decades, the studies on microRNAs (miRNAs) and the numbers of annotated miRNAs in plants and animals have surged. Herein, we reviewed the current progress and challenges of miRNA annotation in plants. Via the comparison of plant and animal miRNAs, we pinpointed out the difficulties on plant miRNA annotation and proposed potential solutions. In terms of recalling the history of methods and criteria in plant miRNA annotation, we detailed how the major progresses made and evolved. By collecting and categorizing bioinformatics tools for plant miRNA annotation, we surveyed their advantages and disadvantages, especially for ones with the principle of mimicking the miRNA biogenesis pathway by parsing deeply sequenced small RNA (sRNA) libraries. In addition, we summarized all available databases hosting plant miRNAs, and posted the potential optimization solutions such as how to increase the signal-to-noise ratio (SNR) in these databases. Finally, we discussed the challenges and perspectives of plant miRNA annotations, and indicated the possibilities offered by an all-in-one tool and platform according to the integration of artificial intelligence.

DNase I hypersensitive site (DHS) refers to the hypersensitive region of chromatin for the DNase I enzyme. It is an important part of the noncoding region and contains a variety of regulatory elements, such as promoter, enhancer, and transcription factor-binding site, etc. Moreover, the related locus of disease (or trait) are usually enriched in the DHS regions. Therefore, the detection of DHS region is of great significance. In this study, we develop a deep learning-based algorithm to identify whether an unknown sequence region would be potential DHS. The proposed method showed high prediction performance on both training datasets and independent datasets in different cell types and developmental stages, demonstrating that the method has excellent superiority in the identification of DHSs. Furthermore, for the convenience of related wet-experimental researchers, the user-friendly web-server iDHS-Deep was established at http://lin-group.cn/server/iDHS-Deep/, by which users can easily distinguish DHS and non-DHS and obtain the corresponding developmental stage ofDHS.

Proteins interact with each other to play critical roles in many biological processes in cells. Although promising, laboratory experiments usually suffer from the disadvantages of being time-consuming and labor-intensive. The results obtained are often not robust and considerably uncertain. Due recently to advances in high-throughput technologies, a large amount of proteomics data has been collected and this presents a significant opportunity and also a challenge to develop computational models to predict protein-protein interactions (PPIs) based on these data. In this paper, we present a comprehensive survey of the recent efforts that have been made towards the development of effective computational models for PPI prediction. The survey introduces the algorithms that can be used to learn computational models for predicting PPIs, and it classifies these models into different categories. To understand their relative merits, the paper discusses different validation schemes and metrics to evaluate the prediction performance. Biological databases that are commonly used in different experiments for performance comparison are also described and their use in a series of extensive experiments to compare different prediction models are discussed. Finally, we present some open issues in PPI prediction for future work. We explain how the performance of PPI prediction can be improved if these issues are effectively tackled.

Cell clustering is one of the most important and commonly performed tasks in single-cell RNA sequencing (scRNA-seq) data analysis. An important step in cell clustering is to select a subset of genes (referred to as 'features'), whose expression patterns will then be used for downstream clustering. A good set of features should include the ones that distinguish different cell types, and the quality of such set could have a significant impact on the clustering accuracy. All existing scRNA-seq clustering tools include a feature selection step relying on some simple unsupervised feature selection methods, mostly based on the statistical moments of gene-wise expression distributions. In this work, we carefully evaluate the impact of feature selection on cell clustering accuracy. In addition, we develop a feature selection algorithm named FEAture SelecTion (FEAST), which provides more representative features. We apply the method on 12 public scRNA-seq datasets and demonstrate that using features selected by FEAST with existing clustering tools significantly improve the clustering accuracy.

Erratum in Brief Bioinform. 2021 May 29;:

m6A RNA methylation is an emerging epigenetic modification, and its potential role in immunity and stemness remains unknown. Based on 17 widely recognized m6A regulators, the m6A modification patterns and corresponding characteristics of immune infiltration and stemness of 1152 low-grade glioma samples were comprehensively analyzed. Machine-learning strategies for constructing m6AScores were trained to quantify the m6A modification patterns of individual samples. Here, we reveal a significant correlation between the multi-omics data of regulators and clinicopathological parameters. We identified two distinct m6A modification patterns (an immune-activated differentiation pattern and an immune-desert dedifferentiation pattern) and four regulatory patterns of m6A methylation on immunity and stemness. We show that the m6AScores can predict the molecular subtype of low-grade glioma, the abundance of immune infiltration, the enrichment of signaling pathways, gene variation and prognosis. The concentration of high immunogenicity and clinical benefits in the low-m6AScore group confirmed the sensitive response to radio-chemotherapy and immunotherapy in patients with high-m6AScore. The results of the pan-cancer analyses illustrate the significant correlation between m6AScore and clinical outcome, the burden of neoepitope, immune infiltration and stemness. The assessment of individual tumor m6A modification patterns will guide us in improving treatment strategies and developing objective diagnostic tools.

This article describes some use case studies and self-assessments of FAIR status of de.NBI services to illustrate the challenges and requirements for the definition of the needs of adhering to the FAIR (findable, accessible, interoperable and reusable) data principles in a large distributed bioinformatics infrastructure. We address the challenge of heterogeneity of wet lab technologies, data, metadata, software, computational workflows and the levels of implementation and monitoring of FAIR principles within the different bioinformatics sub-disciplines joint in de.NBI. On the one hand, this broad service landscape and the excellent network of experts are a strong basis for the development of useful research data management plans. On the other hand, the large number of tools and techniques maintained by distributed teams renders FAIR compliance challenging.

Recently, language representation models have drawn a lot of attention in the natural language processing field due to their remarkable results. Among them, bidirectional encoder representations from transformers (BERT) has proven to be a simple, yet powerful language model that achieved novel state-of-the-art performance. BERT adopted the concept of contextualized word embedding to capture the semantics and context of the words in which they appeared. In this study, we present a novel technique by incorporating BERT-based multilingual model in bioinformatics to represent the information of DNA sequences. We treated DNA sequences as natural sentences and then used BERT models to transform them into fixed-length numerical matrices. As a case study, we applied our method to DNA enhancer prediction, which is a well-known and challenging problem in this field. We then observed that our BERT-based features improved more than 5-10% in terms of sensitivity, specificity, accuracy and Matthews correlation coefficient compared to the current state-of-the-art features in bioinformatics. Moreover, advanced experiments show that deep learning (as represented by 2D convolutional neural networks; CNN) holds potential in learning BERT features better than other traditional machine learning techniques. In conclusion, we suggest that BERT and 2D CNNs could open a new avenue in biological modeling using sequence information.

Alkaptonuria (AKU, OMIM: 203500) is an autosomal recessive disorder caused by mutations in the Homogentisate 1,2-dioxygenase (HGD) gene. A lack of standardized data, information and methodologies to assess disease severity and progression represents a common complication in ultra-rare disorders like AKU. This is the reason why we developed a comprehensive tool, called ApreciseKUre, able to collect AKU patients deriving data, to analyse the complex network among genotypic and phenotypic information and to get new insight in such multi-systemic disease. By taking advantage of the dataset, containing the highest number of AKU patient ever considered, it is possible to apply more sophisticated computational methods (such as machine learning) to achieve a first AKU patient stratification based on phenotypic and genotypic data in a typical precision medicine perspective. Thanks to our sufficiently populated and organized dataset, it is possible, for the first time, to extensively explore the phenotype-genotype relationships unknown so far. This proof of principle study for rare diseases confirms the importance of a dedicated database, allowing data management and analysis and can be used to tailor treatments for every patient in a more effective way.

Single-cell RNA-sequencing (scRNA-seq) explores the transcriptome of genes at cell level, which sheds light on revealing the heterogeneity and dynamics of cell populations. Advances in biotechnologies make it possible to generate scRNA-seq profiles for large-scale cells, requiring effective and efficient clustering algorithms to identify cell types and informative genes. Although great efforts have been devoted to clustering of scRNA-seq, the accuracy, scalability and interpretability of available algorithms are not desirable. In this study, we solve these problems by developing a joint learning algorithm [a.k.a. joints sparse representation and clustering (jSRC)], where the dimension reduction (DR) and clustering are integrated. Specifically, DR is employed for the scalability and joint learning improves accuracy. To increase the interpretability of patterns, we assume that cells within the same type have similar expression patterns, where the sparse representation is imposed on features. We transform clustering of scRNA-seq into an optimization problem and then derive the update rules to optimize the objective of jSRC. Fifteen scRNA-seq datasets from various tissues and organisms are adopted to validate the performance of jSRC, where the number of single cells varies from 49 to 110 824. The experimental results demonstrate that jSRC significantly outperforms 12 state-of-the-art methods in terms of various measurements (on average 20.29% by improvement) with fewer running time. Furthermore, jSRC is efficient and robust across different scRNA-seq datasets from various tissues. Finally, jSRC also accurately identifies dynamic cell types associated with progression of COVID-19. The proposed model and methods provide an effective strategy to analyze scRNA-seq data (the software is coded using MATLAB and is free for academic purposes; https://github.com/xkmaxidian/jSRC).

Aging is the largest risk factor of major human diseases. Long noncoding RNAs (lncRNAs) as the key regulatory elements have shown a strong impact on multiple biological processes as well as human disease mechanisms. However, the roles of lncRNAs in aging/healthy aging processes remain largely unknown. Centenarians are good models for healthy aging studies due to avoiding major chronic diseases and disabilities. To illustrate their ubiquitous nature in the genome and the 'secrets' of healthy aging regulation from the perspective of lncRNAs, peripheral blood samples from two regions consisting 76 centenarians (CENs), 54 centenarian-children (F1) and 41 spouses of centenarian-children (F1SP) were collected for deep RNA-seq. We identified 11 CEN-specific lncRNAs that is particularly expressed in longevous individuals. By kmers clustering, hundreds of human lncRNAs show similarities with CEN-specific lncRNAs, especially with ENST00000521663 and ENST00000444998. Using F1SP as normal elder controls (age: 59.9 ± 6.6 years), eight lncRNAs that are differentially expressed in longevous elders (CEN group, age: 102.2 ± 2.4 years) were identified as candidate aging/health aging-related lncRNAs (car-lncs). We found that the expression of eight car-lncs in human diploid fibroblasts displayed dynamic changes during cell passage and/or H2O2/rapamycin treatment; of which, overexpression either of THBS1-IT1 and THBS1-AS1, two lncRNAs that highly expressed in CENs, can remarkably decrease p16, p21 and the activity of senescent related β-galactosidase, suggesting that THBS1-IT1 and THBS1-AS1 can inhibit cellular senescence. We provided the first comprehensive analysis of lncRNA expression in longevous populations, and our results hinted that dysregulated lncRNAs in CENs are potential protective factors in healthy aging process.

MOTIVATION: The developmental process of epithelial-mesenchymal transition (EMT) is abnormally activated during breast cancer metastasis. Transcriptional regulatory networks that control EMT have been well studied; however, alternative RNA splicing plays a vital regulatory role during this process and the regulating mechanism needs further exploration. Because of the huge cost and complexity of biological experiments, the underlying mechanisms of alternative splicing (AS) and associated RNA-binding proteins (RBPs) that regulate the EMT process remain largely unknown. Thus, there is an urgent need to develop computational methods for predicting potential RBP-AS event associations during EMT. RESULTS: We developed a novel model for RBP-AS target prediction during EMT that is based on inductive matrix completion (RAIMC). Integrated RBP similarities were calculated based on RBP regulating similarity, and RBP Gaussian interaction profile (GIP) kernel similarity, while integrated AS event similarities were computed based on AS event module similarity and AS event GIP kernel similarity. Our primary objective was to complete missing or unknown RBP-AS event associations based on known associations and on integrated RBP and AS event similarities. In this paper, we identify significant RBPs for AS events during EMT and discuss potential regulating mechanisms. Our computational results confirm the effectiveness and superiority of our model over other state-of-the-art methods. Our RAIMC model achieved AUC values of 0.9587 and 0.9765 based on leave-one-out cross-validation (CV) and 5-fold CV, respectively, which are larger than the AUC values from the previous models. RAIMC is a general matrix completion framework that can be adopted to predict associations between other biological entities. We further validated the prediction performance of RAIMC on the genes CD44 and MAP3K7. RAIMC can identify the related regulating RBPs for isoforms of these two genes. AVAILABILITY AND IMPLEMENTATION: The source code for RAIMC is available at https://github.com/yushanqiu/RAIMC. CONTACT: zouquan@nclab.net online.

MOTIVATION: Over the past decade, the field of next-generation sequencing (NGS) has seen dramatic advances in methods and a decrease in costs. Consequently, a large expansion of data has been generated by NGS, most of which have originated from RNA-sequencing (RNA-seq) experiments. Because mitochondrial genes are expressed in most eukaryotic cells, mitochondrial mRNA sequences are usually co-sequenced within the target transcriptome, generating data that are commonly underused or discarded. Here, we present MITGARD, an automated pipeline that reliably recovers the mitochondrial genome from RNA-seq data from various sources. The pipeline identifies mitochondrial sequence reads based on a phylogenetically related reference, assembles them into contigs, and extracts a complete mtDNA for the target species. RESULTS: We demonstrate that MITGARD can reconstruct the mitochondrial genomes of several species throughout the tree of life. We noticed that MITGARD can recover the mitogenomes in different sequencing schemes and even in a scenario of low-sequencing depth. Moreover, we showed that the use of references from congeneric species diverging up to 30 million years ago (MYA) from the target species is sufficient to recover the entire mitogenome, whereas the use of species diverging between 30 and 60 MYA allows the recovery of most mitochondrial genes. Additionally, we provide a case study with original data in which we estimate a phylogenetic tree of snakes from the genus Bothrops, further demonstrating that MITGARD is suitable for use on biodiversity projects. MITGARD is then a valuable tool to obtain high-quality information for studies focusing on the phylogenetic and evolutionary aspects of eukaryotes and provides data for easily identifying a sample using barcoding, and to check for cross-contamination using third-party tools.

Neopeptide-based immunotherapy has been recognised as a promising approach for the treatment of cancers. For neopeptides to be recognised by CD8+ T cells and induce an immune response, their binding to human leukocyte antigen class I (HLA-I) molecules is a necessary first step. Most epitope prediction tools thus rely on the prediction of such binding. With the use of mass spectrometry, the scale of naturally presented HLA ligands that could be used to develop such predictors has been expanded. However, there are rarely efforts that focus on the integration of these experimental data with computational algorithms to efficiently develop up-to-date predictors. Here, we present Anthem for accurate HLA-I binding prediction. In particular, we have developed a user-friendly framework to support the development of customisable HLA-I binding prediction models to meet challenges associated with the rapidly increasing availability of large amounts of immunopeptidomic data. Our extensive evaluation, using both independent and experimental datasets shows that Anthem achieves an overall similar or higher area under curve value compared with other contemporary tools. It is anticipated that Anthem will provide a unique opportunity for the non-expert user to analyse and interpret their own in-house or publicly deposited datasets.

Haploinsufficiency, wherein a single allele is not enough to maintain normal functions, can lead to many diseases including cancers and neurodevelopmental disorders. Recently, computational methods for identifying haploinsufficiency have been developed. However, most of those computational methods suffer from study bias, experimental noise and instability, resulting in unsatisfactory identification of haploinsufficient genes. To address those challenges, we propose a deep forest model, called HaForest, to identify haploinsufficient genes. The multiscale scanning is proposed to extract local contextual representations from input features under Linear Discriminant Analysis. After that, the cascade forest structure is applied to obtain the concatenated features directly by integrating decision-tree-based forests. Meanwhile, to exploit the complex dependency structure among haploinsufficient genes, the LightGBM library is embedded into HaForest to reveal the highly expressive features. To validate the effectiveness of our method, we compared it to several computational methods and four deep learning algorithms on five epigenomic data sets. The results reveal that HaForest achieves superior performance over the other algorithms, demonstrating its unique and complementary performance in identifying haploinsufficient genes. The standalone tool is available at https://github.com/yangyn533/HaForest.

Relationship of accurate associations between non-coding RNAs and diseases could be of great help in the treatment of human biomedical research. However, the traditional technology is only applied on one type of non-coding RNA or a specific disease, and the experimental method is time-consuming and expensive. More computational tools have been proposed to detect new associations based on known ncRNA and disease information. Due to the ncRNAs (circRNAs, miRNAs and lncRNAs) having a close relationship with the progression of various human diseases, it is critical for developing effective computational predictors for ncRNA-disease association prediction. In this paper, we propose a new computational method of three-matrix factorization with hypergraph regularization terms (HGRTMF) based on central kernel alignment (CKA), for identifying general ncRNA-disease associations. In the process of constructing the similarity matrix, various types of similarity matrices are applicable to circRNAs, miRNAs and lncRNAs. Our method achieves excellent performance on five datasets, involving three types of ncRNAs. In the test, we obtain best area under the curve scores of $0.9832$, $0.9775$, $0.9023$, $0.8809$ and $0.9185$ via 5-fold cross-validation and $0.9832$, $0.9836$, $0.9198$, $0.9459$ and $0.9275$ via leave-one-out cross-validation on five datasets. Furthermore, our novel method (CKA-HGRTMF) is also able to discover new associations between ncRNAs and diseases accurately. Availability: Codes and data are available: https://github.com/hzwh6910/ncRNA2Disease.git. Contact:fguo@tju.edu.cn.

DNA methylation plays crucial roles in many biological processes and abnormal DNA methylation patterns are often observed in diseases. Recent studies have shed light on cis-acting DNA elements that regulate locus-specific DNA methylation, which involves transcription factors, histone modification and DNA secondary structures. In addition, several recent studies have surveyed DNA motifs that regulate DNA methylation and suggest potential applications in diagnosis and prognosis. Here, we discuss the current biological foundation for the cis-acting genetic code that regulates DNA methylation. We review the computational models that predict DNA methylation with genetic features and discuss the biological insights revealed from these models. We also provide an in-depth discussion on how to leverage such knowledge in clinical applications, particularly in the context of liquid biopsy for early cancer diagnosis and treatment.

OBJECTIVE: Development of novel informatics methods focused on improving pregnancy outcomes remains an active area of research. The purpose of this study is to systematically review the ways that artificial intelligence (AI) and machine learning (ML), including deep learning (DL), methodologies can inform patient care during pregnancy and improve outcomes. MATERIALS AND METHODS: We searched English articles on EMBASE, PubMed and SCOPUS. Search terms included ML, AI, pregnancy and informatics. We included research articles and book chapters, excluding conference papers, editorials and notes. RESULTS: We identified 127 distinct studies from our queries that were relevant to our topic and included in the review. We found that supervised learning methods were more popular (n = 69) than unsupervised methods (n = 9). Popular methods included support vector machines (n = 30), artificial neural networks (n = 22), regression analysis (n = 17) and random forests (n = 16). Methods such as DL are beginning to gain traction (n = 13). Common areas within the pregnancy domain where AI and ML methods were used the most include prenatal care (e.g. fetal anomalies, placental functioning) (n = 73); perinatal care, birth and delivery (n = 20); and preterm birth (n = 13). Efforts to translate AI into clinical care include clinical decision support systems (n = 24) and mobile health applications (n = 9). CONCLUSIONS: Overall, we found that ML and AI methods are being employed to optimize pregnancy outcomes, including modern DL methods (n = 13). Future research should focus on less-studied pregnancy domain areas, including postnatal and postpartum care (n = 2). Also, more work on clinical adoption of AI methods and the ethical implications of such adoption is needed.

As important post-translational modifications, protein cysteine modifications (PCMs) occurring at cysteine thiol group play critical roles in the regulation of various biological processes in eukaryotes. Due to the rapid advancement of high-throughput proteomics technologies, a large number of PCM events have been identified but remain to be curated. Thus, an integrated resource of eukaryotic PCMs will be useful for the research community. In this work, we developed an integrative database for protein cysteine modifications in eukaryotes (iCysMod), which curated and hosted 108 030 PCM events for 85 747 experimentally identified sites on 31 483 proteins from 48 eukaryotes for 8 types of PCMs, including oxidation, S-nitrosylation (-SNO), S-glutathionylation (-SSG), disulfide formation (-SSR), S-sulfhydration (-SSH), S-sulfenylation (-SOH), S-sulfinylation (-SO2H) and S-palmitoylation (-S-palm). Then, browse and search options were provided for accessing the dataset, while various detailed information about the PCM events was well organized for visualization. With human dataset in iCysMod, the sequence features around the cysteine modification sites for each PCM type were analyzed, and the results indicated that various types of PCMs presented distinct sequence recognition preferences. Moreover, different PCMs can crosstalk with each other to synergistically orchestrate specific biological processes, and 37 841 PCM events involved in 119 types of PCM co-occurrences at the same cysteine residues were finally obtained. Taken together, we anticipate that the database of iCysMod would provide a useful resource for eukaryotic PCMs to facilitate related researches, while the online service is freely available at http://icysmod.omicsbio.info.

MOTIVATION: mRNA location corresponds to the location of protein translation and contributes to precise spatial and temporal management of the protein function. However, current assignment of subcellular localization of eukaryotic mRNA reveals important limitations: (1) turning multiple classifications into multiple dichotomies makes the training process tedious; (2) the majority of the models trained by classical algorithm are based on the extraction of single sequence information; (3) the existing state-of-the-art models have not reached an ideal level in terms of prediction and generalization ability. To achieve better assignment of subcellular localization of eukaryotic mRNA, a better and more comprehensive model must be developed. RESULTS: In this paper, SubLocEP is proposed as a two-layer integrated prediction model for accurate prediction of the location of sequence samples. Unlike the existing models based on limited features, SubLocEP comprehensively considers additional feature attributes and is combined with LightGBM to generated single feature classifiers. The initial integration model (single-layer model) is generated according to the categories of a feature. Subsequently, two single-layer integration models are weighted (sequence-based: physicochemical properties = 3:2) to produce the final two-layer model. The performance of SubLocEP on independent datasets is sufficient to indicate that SubLocEP is an accurate and stable prediction model with strong generalization ability. Additionally, an online tool has been developed that contains experimental data and can maximize the user convenience for estimation of subcellular localization of eukaryotic mRNA.