Reproducibility of results obtained using ribonucleic acid (RNA) data across labs remains a major hurdle in cancer research. Often, molecular predictors trained on one dataset cannot be applied to another due to differences in RNA library preparation and quantification, which inhibits the validation of predictors across labs. While current RNA correction algorithms reduce these differences, they require simultaneous access to patient-level data from all datasets, which necessitates the sharing of training data for predictors when sharing predictors. Here, we describe SpinAdapt, an unsupervised RNA correction algorithm that enables the transfer of molecular models without requiring access to patient-level data. It computes data corrections only via aggregate statistics of each dataset, thereby maintaining patient data privacy. Despite an inherent trade-off between privacy and performance, SpinAdapt outperforms current correction methods, like Seurat and ComBat, on publicly available cancer studies, including TCGA and ICGC. Furthermore, SpinAdapt can correct new samples, thereby enabling unbiased evaluation on validation cohorts. We expect this novel correction paradigm to enhance research reproducibility and to preserve patient privacy.

Therapeutic peptides act on the skeletal system, digestive system and blood system, have antibacterial properties and help relieve inflammation. In order to reduce the resource consumption of wet experiments for the identification of therapeutic peptides, many computational-based methods have been developed to solve the identification of therapeutic peptides. Due to the insufficiency of traditional machine learning methods in dealing with feature noise. We propose a novel therapeutic peptide identification method called Structured Sparse Regularized Takagi-Sugeno-Kang Fuzzy System on Within-Class Scatter (SSR-TSK-FS-WCS). Our method achieves good performance on multiple therapeutic peptides and UCI datasets.

Predicting protein properties from amino acid sequences is an important problem in biology and pharmacology. Protein-protein interactions among SARS-CoV-2 spike protein, human receptors and antibodies are key determinants of the potency of this virus and its ability to evade the human immune response. As a rapidly evolving virus, SARS-CoV-2 has already developed into many variants with considerable variation in virulence among these variants. Utilizing the proteomic data of SARS-CoV-2 to predict its viral characteristics will, therefore, greatly aid in disease control and prevention. In this paper, we review and compare recent successful prediction methods based on long short-term memory (LSTM), transformer, convolutional neural network (CNN) and a similarity-based topological regression (TR) model and offer recommendations about appropriate predictive methodology depending on the similarity between training and test datasets. We compare the effectiveness of these models in predicting the binding affinity and expression of SARS-CoV-2 spike protein sequences. We also explore how effective these predictive methods are when trained on laboratory-created data and are tasked with predicting the binding affinity of the in-the-wild SARS-CoV-2 spike protein sequences obtained from the GISAID datasets. We observe that TR is a better method when the sample size is small and test protein sequences are sufficiently similar to the training sequence. However, when the training sample size is sufficiently large and prediction requires extrapolation, LSTM embedding and CNN-based predictive model show superior performance.

MOTIVATION: Drug-drug interactions (DDIs) occur during the combination of drugs. Identifying potential DDI helps us to study the mechanism behind the combination medication or adverse reactions so as to avoid the side effects. Although many artificial intelligence methods predict and mine potential DDI, they ignore the 3D structure information of drug molecules and do not fully consider the contribution of molecular substructure in DDI. RESULTS: We proposed a new deep learning architecture, 3DGT-DDI, a model composed of a 3D graph neural network and pre-trained text attention mechanism. We used 3D molecular graph structure and position information to enhance the prediction ability of the model for DDI, which enabled us to deeply explore the effect of drug substructure on DDI relationship. The results showed that 3DGT-DDI outperforms other state-of-the-art baselines. It achieved an 84.48% macro F1 score in the DDIExtraction 2013 shared task dataset. Also, our 3D graph model proves its performance and explainability through weight visualization on the DrugBank dataset. 3DGT-DDI can help us better understand and identify potential DDI, thereby helping to avoid the side effects of drug mixing. AVAILABILITY: The source code and data are available at https://github.com/hehh77/3DGT-DDI.

Ribonucleic acid (RNA) is a pivotal nucleic acid that plays a crucial role in regulating many biological activities. Recently, one study utilized a machine learning algorithm to automatically classify RNA structural events generated by a Mycobacterium smegmatis porin A nanopore trap. Although it can achieve desirable classification results, compared with deep learning (DL) methods, this classic machine learning requires domain knowledge to manually extract features, which is sophisticated, labor-intensive and time-consuming. Meanwhile, the generated original RNA structural events are not strictly equal in length, which is incompatible with the input requirements of DL models. To alleviate this issue, we propose a sequence-to-sequence (S2S) module that transforms the unequal length sequence (UELS) to the equal length sequence. Furthermore, to automatically extract features from the RNA structural events, we propose a sequence-to-sequence neural network based on DL. In addition, we add an attention mechanism to capture vital information for classification, such as dwell time and blockage amplitude. Through quantitative and qualitative analysis, the experimental results have achieved about a 2% performance increase (accuracy) compared to the previous method. The proposed method can also be applied to other nanopore platforms, such as the famous Oxford nanopore. It is worth noting that the proposed method is not only aimed at pursuing state-of-the-art performance but also provides an overall idea to process nanopore data with UELS.

Ribonucleic acid (RNA)-seq data contain not only host transcriptomes but also nonhost information that comprises transcripts from active microbiota in the host cells. Therefore, joint and integrative analyses of both host and meta-transcriptome can reveal gene expression of the microbial community in a given sample as well as the correlative and interactive dynamics of the host response to the microbiome. However, there are no convenient tools that can systemically analyze host-microbiota interactions through simultaneously quantifying the host and meta-transcriptome in the same sample at the tissue and the single-cell level. This poses a challenge for interested researchers with limited expertise in bioinformatics. Here, we developed a software pipeline that can comprehensively and synergistically analyze and correlate the host and meta-transcriptome in a single sample using bulk and single-cell RNA-seq data. This pipeline, named meta-transcriptome detector (MTD), can extensively identify and quantify microbiome, including viruses, bacteria, protozoa, fungi, plasmids and vectors, in the host cells and correlate the microbiome with the host transcriptome. MTD is easy to install and run, involving only a few lines of simple commands. It offers researchers with unique genomics insights into host responses to microorganisms.

Survival analysis is a technique for identifying prognostic biomarkers and genetic vulnerabilities in cancer studies. Large-scale consortium-based projects have profiled >11 000 adult and >4000 pediatric tumor cases with clinical outcomes and multiomics approaches. This provides a resource for investigating molecular-level cancer etiologies using clinical correlations. Although cancers often arise from multiple genetic vulnerabilities and have deregulated gene sets (GSs), existing survival analysis protocols can report only on individual genes. Additionally, there is no systematic method to connect clinical outcomes with experimental (cell line) data. To address these gaps, we developed cSurvival (https://tau.cmmt.ubc.ca/cSurvival). cSurvival provides a user-adjustable analytical pipeline with a curated, integrated database and offers three main advances: (i) joint analysis with two genomic predictors to identify interacting biomarkers, including new algorithms to identify optimal cutoffs for two continuous predictors; (ii) survival analysis not only at the gene, but also the GS level; and (iii) integration of clinical and experimental cell line studies to generate synergistic biological insights. To demonstrate these advances, we report three case studies. We confirmed findings of autophagy-dependent survival in colorectal cancers and of synergistic negative effects between high expression of SLC7A11 and SLC2A1 on outcomes in several cancers. We further used cSurvival to identify high expression of the Nrf2-antioxidant response element pathway as a main indicator for lung cancer prognosis and for cellular resistance to oxidative stress-inducing drugs. Altogether, these analyses demonstrate cSurvival's ability to support biomarker prognosis and interaction analysis via gene- and GS-level approaches and to integrate clinical and experimental biomedical studies.

Predicting the binding of peptide and major histocompatibility complex (MHC) plays a vital role in immunotherapy for cancer. The success of Alphafold of applying natural language processing (NLP) algorithms in protein secondary struction prediction has inspired us to explore the possibility of NLP methods in predicting peptide-MHC class I binding. Based on the above motivations, we propose the MHCRoBERTa method, RoBERTa pre-training approach, for predicting the binding affinity between type I MHC and peptides. Analysis of the results on benchmark dataset demonstrates that MHCRoBERTa can outperform other state-of-art prediction methods with an increase of the Spearman rank correlation coefficient (SRCC) value. Notably, our model gave a significant improvement on IC50 value. Our method has achieved SRCC value and AUC value as 0.785 and 0.817, respectively. Our SRCC value is 14.3% higher than NetMHCpan3.0 (the second highest SRCC value on pan-specific) and is 3% higher than MHCflurry (the second highest SRCC value on all methods). The AUC value is also better than any other pan-specific methods. Moreover, we visualize the multi-head self-attention for the token representation across the layers and heads by this method. Through the analysis of the representation of each layer and head, we can show whether the model has learned the syntax and semantics necessary to perform the prediction task well. All these results demonstrate that our model can accurately predict the peptide-MHC class I binding affinity and that MHCRoBERTa is a powerful tool for screening potential neoantigens for cancer immunotherapy. MHCRoBERTa is available as an open source software at github (https://github.com/FuxuWang/MHCRoBERTa).

Target prediction and virtual screening are two powerful tools of computer-aided drug design. Target identification is of great significance for hit discovery, lead optimization, drug repurposing and elucidation of the mechanism. Virtual screening can improve the hit rate of drug screening to shorten the cycle of drug discovery and development. Therefore, target prediction and virtual screening are of great importance for developing highly effective drugs against COVID-19. Here we present D3AI-CoV, a platform for target prediction and virtual screening for the discovery of anti-COVID-19 drugs. The platform is composed of three newly developed deep learning-based models i.e., MultiDTI, MPNNs-CNN and MPNNs-CNN-R models. To compare the predictive performance of D3AI-CoV with other methods, an external test set, named Test-78, was prepared, which consists of 39 newly published independent active compounds and 39 inactive compounds from DrugBank. For target prediction, the areas under the receiver operating characteristic curves (AUCs) of MultiDTI and MPNNs-CNN models are 0.93 and 0.91, respectively, whereas the AUCs of the other reported approaches range from 0.51 to 0.74. For virtual screening, the hit rate of D3AI-CoV is also better than other methods. D3AI-CoV is available for free as a web application at http://www.d3pharma.com/D3Targets-2019-nCoV/D3AI-CoV/index.php, which can serve as a rapid online tool for predicting potential targets for active compounds and for identifying active molecules against a specific target protein for COVID-19 treatment.

Characterizing the molecular identity of a cell is an essential step in single-cell RNA sequencing (scRNA-seq) data analysis. Numerous tools exist for predicting cell identity using single-cell reference atlases. However, many challenges remain, including correcting for inherent batch effects between reference and query data andinsufficient phenotype data from the reference. One solution is to project single-cell data onto established bulk reference atlases to leverage their rich phenotype information. Sincast is a computational framework to query scRNA-seq data by projection onto bulk reference atlases. Prior to projection, single-cell data are transformed to be directly comparable to bulk data, either with pseudo-bulk aggregation or graph-based imputation to address sparse single-cell expression profiles. Sincast avoids batch effect correction, and cell identity is predicted along a continuum to highlight new cell states not found in the reference atlas. In several case study scenarios, we show that Sincast projects single cells into the correct biological niches in the expression space of the bulk reference atlas. We demonstrate the effectiveness of our imputation approach that was specifically developed for querying scRNA-seq data based on bulk reference atlases. We show that Sincast is an efficient and powerful tool for single-cell profiling that will facilitate downstream analysis of scRNA-seq data.

T cell recognition of a cognate peptide-major histocompatibility complex (pMHC) presented on the surface of infected or malignant cells is of the utmost importance for mediating robust and long-term immune responses. Accurate predictions of cognate pMHC targets for T cell receptors would greatly facilitate identification of vaccine targets for both pathogenic diseases and personalized cancer immunotherapies. Predicting immunogenic peptides therefore has been at the center of intensive research for the past decades but has proven challenging. Although numerous models have been proposed, performance of these models has not been systematically evaluated and their success rate in predicting epitopes in the context of human pathology has not been measured and compared. In this study, we evaluated the performance of several publicly available models, in identifying immunogenic CD8+ T cell targets in the context of pathogens and cancers. We found that for predicting immunogenic peptides from an emerging virus such as severe acute respiratory syndrome coronavirus 2, none of the models perform substantially better than random or offer considerable improvement beyond HLA ligand prediction. We also observed suboptimal performance for predicting cancer neoantigens. Through investigation of potential factors associated with ill performance of models, we highlight several data- and model-associated issues. In particular, we observed that cross-HLA variation in the distribution of immunogenic and non-immunogenic peptides in the training data of the models seems to substantially confound the predictions. We additionally compared key parameters associated with immunogenicity between pathogenic peptides and cancer neoantigens and observed evidence for differences in the thresholds of binding affinity and stability, which suggested the need to modulate different features in identifying immunogenic pathogen versus cancer peptides. Overall, we demonstrate that accurate and reliable predictions of immunogenic CD8+ T cell targets remain unsolved; thus, we hope our work will guide users and model developers regarding potential pitfalls and unsettled questions in existing immunogenicity predictors.

Many DNA methylation (DNAm) data are from tissues composed of various cell types, and hence cell deconvolution methods are needed to infer their cell compositions accurately. However, a bottleneck for DNAm data is the lack of cell-type-specific DNAm references. On the other hand, scRNA-seq data are being accumulated rapidly with various cell-type transcriptomic signatures characterized, and also, many paired bulk RNA-DNAm data are publicly available currently. Hence, we developed the R package scDeconv to use these resources to solve the reference deficiency problem of DNAm data and deconvolve them from scRNA-seq data in a trans-omics manner. It assumes that paired samples have similar cell compositions. So the cell content information deconvolved from the scRNA-seq and paired RNA data can be transferred to the paired DNAm samples. Then an ensemble model is trained to fit these cell contents with DNAm features and adjust the paired RNA deconvolution in a co-training manner. Finally, the model can be used on other bulk DNAm data to predict their relative cell-type abundances. The effectiveness of this method is proved by its accurate deconvolution on the three testing datasets here, and if given an appropriate paired dataset, scDeconv can also deconvolve other omics, such as ATAC-seq data. Furthermore, the package also contains other functions, such as identifying cell-type-specific inter-group differential features from bulk DNAm data. scDeconv is available at: https://github.com/yuabrahamliu/scDeconv.

Since abnormal expression of long noncoding RNAs (lncRNAs) is often closely related to various human diseases, identification of disease-associated lncRNAs is helpful for exploring the complex pathogenesis. Most of recent methods concentrate on exploiting multiple kinds of data related to lncRNAs and diseases for predicting candidate disease-related lncRNAs. These methods, however, failed to deeply integrate the topology information from the meta-paths that are composed of lncRNA, disease and microRNA (miRNA) nodes. We proposed a new method based on fully connected autoencoders and convolutional neural networks, called ACLDA, for inferring potential disease-related lncRNA candidates. A heterogeneous graph that consists of lncRNA, disease and miRNA nodes were firstly constructed to integrate similarities, associations and interactions among them. Fully connected autoencoder-based module was established to extract the low-dimensional features of lncRNA, disease and miRNA nodes in the heterogeneous graph. We designed the attention mechanisms at the node feature level and at the meta-path level to learn more informative features and meta-paths. A module based on convolutional neural networks was constructed to encode the local topologies of lncRNA and disease nodes from multiple meta-path perspectives. The comprehensive experimental results demonstrated ACLDA achieves superior performance than several state-of-the-art prediction methods. Case studies on breast, lung and colon cancers demonstrated that ACLDA is able to discover the potential disease-related lncRNAs.

Proteins with desired functions and properties are important in fields like nanotechnology and biomedicine. De novo protein design enables the production of previously unseen proteins from the ground up and is believed as a key point for handling real social challenges. Recent introduction of deep learning into design methods exhibits a transformative influence and is expected to represent a promising and exciting future direction. In this review, we retrospect the major aspects of current advances in deep-learning-based design procedures and illustrate their novelty in comparison with conventional knowledge-based approaches through noticeable cases. We not only describe deep learning developments in structure-based protein design and direct sequence design, but also highlight recent applications of deep reinforcement learning in protein design. The future perspectives on design goals, challenges and opportunities are also comprehensively discussed.

Identifying new lead molecules to treat cancer requires more than a decade of dedicated effort. Before selected drug candidates are used in the clinic, their anti-cancer activity is generally validated by in vitro cellular experiments. Therefore, accurate prediction of cancer drug response is a critical and challenging task for anti-cancer drugs design and precision medicine. With the development of pharmacogenomics, the combination of efficient drug feature extraction methods and omics data has made it possible to use computational models to assist in drug response prediction. In this study, we propose DeepTTA, a novel end-to-end deep learning model that utilizes transformer for drug representation learning and a multilayer neural network for transcriptomic data prediction of the anti-cancer drug responses. Specifically, DeepTTA uses transcriptomic gene expression data and chemical substructures of drugs for drug response prediction. Compared to existing methods, DeepTTA achieved higher performance in terms of root mean square error, Pearson correlation coefficient and Spearman's rank correlation coefficient on multiple test sets. Moreover, we discovered that anti-cancer drugs bortezomib and dactinomycin provide a potential therapeutic option with multiple clinical indications. With its excellent performance, DeepTTA is expected to be an effective method in cancer drug design.

Predicting disease progression in the initial stage to implement early intervention and treatment can effectively prevent the further deterioration of the condition. Traditional methods for medical data analysis usually fail to perform well because of their incapability for mining the correlation pattern of pathogenies. Therefore, many calculation methods have been excavated from the field of deep learning. In this study, we propose a novel method of influence hypergraph convolutional generative adversarial network (IHGC-GAN) for disease risk prediction. First, a hypergraph is constructed with genes and brain regions as nodes. Then, an influence transmission model is built to portray the associations between nodes and the transmission rule of disease information. Third, an IHGC-GAN method is constructed based on this model. This method innovatively combines the graph convolutional network (GCN) and GAN. The GCN is used as the generator in GAN to spread and update the lesion information of nodes in the brain region-gene hypergraph. Finally, the prediction accuracy of the method is improved by the mutual competition and repeated iteration between generator and discriminator. This method can not only capture the evolutionary pattern from early mild cognitive impairment (EMCI) to late MCI (LMCI) but also extract the pathogenic factors and predict the deterioration risk from EMCI to LMCI. The results on the two datasets indicate that the IHGC-GAN method has better prediction performance than the advanced methods in a variety of indicators.

Ligand molecules naturally constitute a graph structure. Recently, many excellent deep graph learning (DGL) methods have been proposed and used to model ligand bioactivities, which is critical for the virtual screening of drug hits from compound databases in interest. However, pharmacists can find that these well-trained DGL models usually are hard to achieve satisfying performance in real scenarios for virtual screening of drug candidates. The main challenges involve that the datasets for training models were small-sized and biased, and the inner active cliff cases would worsen model performance. These challenges would cause predictors to overfit the training data and have poor generalization in real virtual screening scenarios. Thus, we proposed a novel algorithm named adversarial feature subspace enhancement (AFSE). AFSE dynamically generates abundant representations in new feature subspace via bi-directional adversarial learning, and then minimizes the maximum loss of molecular divergence and bioactivity to ensure local smoothness of model outputs and significantly enhance the generalization of DGL models in predicting ligand bioactivities. Benchmark tests were implemented on seven state-of-the-art open-source DGL models with the potential of modeling ligand bioactivities, and precisely evaluated by multiple criteria. The results indicate that, on almost all 33 GPCRs datasets and seven DGL models, AFSE greatly improved their enhancement factor (top-10%, 20% and 30%), which is the most important evaluation in virtual screening of hits from compound databases, while ensuring the superior performance on RMSE and $r^2$. The web server of AFSE is freely available at http://noveldelta.com/AFSE for academic purposes.

DNA N6-methyladenine (6mA) is produced by the N6 position of the adenine being methylated, which occurs at the molecular level, and is involved in numerous vital biological processes in the rice genome. Given the shortcomings of biological experiments, researchers have developed many computational methods to predict 6mA sites and achieved good performance. However, the existing methods do not consider the occurrence mechanism of 6mA to extract features from the molecular structure. In this paper, a novel deep learning method is proposed by devising DNA molecular graph feature and residual block structure for 6mA sites prediction in rice, named MGF6mARice. Firstly, the DNA sequence is changed into a simplified molecular input line entry system (SMILES) format, which reflects chemical molecular structure. Secondly, for the molecular structure data, we construct the DNA molecular graph feature based on the principle of graph convolutional network. Then, the residual block is designed to extract higher level, distinguishable features from molecular graph features. Finally, the prediction module is used to obtain the result of whether it is a 6mA site. By means of 10-fold cross-validation, MGF6mARice outperforms the state-of-the-art approaches. Multiple experiments have shown that the molecular graph feature and residual block can promote the performance of MGF6mARice in 6mA prediction. To the best of our knowledge, it is the first time to derive a feature of DNA sequence by considering the chemical molecular structure. We hope that MGF6mARice will be helpful for researchers to analyze 6mA sites in rice.

Increasing evidences show that the occurrence of human complex diseases is closely related to microRNA (miRNA) variation and imbalance. For this reason, predicting disease-related miRNAs is essential for the diagnosis and treatment of complex human diseases. Although some current computational methods can effectively predict potential disease-related miRNAs, the accuracy of prediction should be further improved. In our study, a new computational method via deep forest ensemble learning based on autoencoder (DFELMDA) is proposed to predict miRNA-disease associations. Specifically, a new feature representation strategy is proposed to obtain different types of feature representations (from miRNA and disease) for each miRNA-disease association. Then, two types of low-dimensional feature representations are extracted by two deep autoencoders for predicting miRNA-disease associations. Finally, two prediction scores of the miRNA-disease associations are obtained by the deep random forest and combined to determine the final results. DFELMDA is compared with several classical methods on the The Human microRNA Disease Database (HMDD) dataset. Results reveal that the performance of this method is superior. The area under receiver operating characteristic curve (AUC) values obtained by DFELMDA through 5-fold and 10-fold cross-validation are 0.9552 and 0.9560, respectively. In addition, case studies on colon, breast and lung tumors of different disease types further demonstrate the excellent ability of DFELMDA to predict disease-associated miRNA-disease. Performance analysis shows that DFELMDA can be used as an effective computational tool for predicting miRNA-disease associations.

In recent years, with the rapid development of techniques in bioinformatics and life science, a considerable quantity of biomedical data has been accumulated, based on which researchers have developed various computational approaches to discover potential associations between human microbes, drugs and diseases. This paper provides a comprehensive overview of recent advances in prediction of potential correlations between microbes, drugs and diseases from biological data to computational models. Firstly, we introduced the widely used datasets relevant to the identification of potential relationships between microbes, drugs and diseases in detail. And then, we divided a series of a lot of representative computing models into five major categories including network, matrix factorization, matrix completion, regularization and artificial neural network for in-depth discussion and comparison. Finally, we analysed possible challenges and opportunities in this research area, and at the same time we outlined some suggestions for further improvement of predictive performances as well.

Prediction of antimicrobial resistance based on whole-genome sequencing data has attracted greater attention due to its rapidity and convenience. Numerous machine learning-based studies have used genetic variants to predict drug resistance in Mycobacterium tuberculosis (MTB), assuming that variants are homogeneous, and most of these studies, however, have ignored the essential correlation between variants and corresponding genes when encoding variants, and used a limited number of variants as prediction input. In this study, taking advantage of genome-wide variants for drug-resistance prediction and inspired by natural language processing, we summarize drug resistance prediction into document classification, in which variants are considered as words, mutated genes in an isolate as sentences, and an isolate as a document. We propose a novel hierarchical attentive neural network model (HANN) that helps discover drug resistance-related genes and variants and acquire more interpretable biological results. It captures the interaction among variants in a mutated gene as well as among mutated genes in an isolate. Our results show that for the four first-line drugs of isoniazid (INH), rifampicin (RIF), ethambutol (EMB) and pyrazinamide (PZA), the HANN achieves the optimal area under the ROC curve of 97.90, 99.05, 96.44 and 95.14% and the optimal sensitivity of 94.63, 96.31, 92.56 and 87.05%, respectively. In addition, without any domain knowledge, the model identifies drug resistance-related genes and variants consistent with those confirmed by previous studies, and more importantly, it discovers one more potential drug-resistance-related gene.

Single-cell RNA sequencing (scRNA-seq) measures gene transcriptome at the cell level, paving the way for the identification of cell subpopulations. Although deep learning has been successfully applied to scRNA-seq data, these algorithms are criticized for the undesirable performance and interpretability of patterns because of the noises, high-dimensionality and extraordinary sparsity of scRNA-seq data. To address these issues, a novel deep learning subspace clustering algorithm (aka scGDC) for cell types in scRNA-seq data is proposed, which simultaneously learns the deep features and topological structure of cells. Specifically, scGDC extends auto-encoder by introducing a self-representation layer to extract deep features of cells, and learns affinity graph of cells, which provide a better and more comprehensive strategy to characterize structure of cell types. To address heterogeneity of scRNA-seq data, scGDC projects cells of various types onto different subspaces, where types, particularly rare cell types, are well discriminated by utilizing generative adversarial learning. Furthermore, scGDC joins deep feature extraction, structural learning and cell type discovery, where features of cells are extracted under the guidance of cell types, thereby improving performance of algorithms. A total of 15 scRNA-seq datasets from various tissues and organisms with the number of cells ranging from 56 to 63 103 are adopted to validate performance of algorithms, and experimental results demonstrate that scGDC significantly outperforms 14 state-of-the-art methods in terms of various measurements (on average 25.51% by improvement), where (rare) cell types are significantly associated with topology of affinity graph of cells. The proposed model and algorithm provide an effective strategy for the analysis of scRNA-seq data (The software is coded using python, and is freely available for academic https://github.com/xkmaxidian/scGDC).

Inhibition of host protein functions using established drugs produces a promising antiviral effect with excellent safety profiles, decreased incidence of resistant variants and favorable balance of costs and risks. Genomic methods have produced a large number of robust host factors, providing candidates for identification of antiviral drug targets. However, there is a lack of global perspectives and systematic prioritization of known virus-targeted host proteins (VTHPs) and drug targets. There is also a need for host-directed repositioned antivirals. Here, we integrated 6140 VTHPs and grouped viral infection modes from a new perspective of enriched pathways of VTHPs. Clarifying the superiority of nonessential membrane and hub VTHPs as potential ideal targets for repositioned antivirals, we proposed 543 candidate VTHPs. We then presented a large-scale drug-virus network (DVN) based on matching these VTHPs and drug targets. We predicted possible indications for 703 approved drugs against 35 viruses and explored their potential as broad-spectrum antivirals. In vitro and in vivo tests validated the efficacy of bosutinib, maraviroc and dextromethorphan against human herpesvirus 1 (HHV-1), hepatitis B virus (HBV) and influenza A virus (IAV). Their drug synergy with clinically used antivirals was evaluated and confirmed. The results proved that low-dose dextromethorphan is better than high-dose in both single and combined treatments. This study provides a comprehensive landscape and optimization strategy for druggable VTHPs, constructing an innovative and potent pipeline to discover novel antiviral host proteins and repositioned drugs, which may facilitate their delivery to clinical application in translational medicine to combat fatal and spreading viral infections.

Given most tissues are consist of abundant and diverse (sub-)cell types, an important yet unaddressed problem in bulk RNA-seq analysis is to identify at which (sub-)cell type(s) the differential expression occurs. Single-cell RNA-sequencing (scRNA-seq) technologies can answer the question, but they are often labor-intensive and cost-prohibitive. Here, we present LRcell, a computational method aiming to identify specific (sub-)cell type(s) that drives the changes observed in a bulk RNA-seq experiment. In addition, LRcell provides pre-embedded marker genes computed from putative scRNA-seq experiments as options to execute the analyses. We conduct a simulation study to demonstrate the effectiveness and reliability of LRcell. Using three different real datasets, we show that LRcell successfully identifies known cell types involved in psychiatric disorders. Applying LRcell to bulk RNA-seq results can produce a hypothesis on which (sub-)cell type(s) contributes to the differential expression. LRcell is complementary to cell type deconvolution methods.

The roles of brain regions activities and gene expressions in the development of Alzheimer's disease (AD) remain unclear. Existing imaging genetic studies usually has the problem of inefficiency and inadequate fusion of data. This study proposes a novel deep learning method to efficiently capture the development pattern of AD. First, we model the interaction between brain regions and genes as node-to-node feature aggregation in a brain region-gene network. Second, we propose a feature aggregation graph convolutional network (FAGCN) to transmit and update the node feature. Compared with the trivial graph convolutional procedure, we replace the input from the adjacency matrix with a weight matrix based on correlation analysis and consider common neighbor similarity to discover broader associations of nodes. Finally, we use a full-gradient saliency graph mechanism to score and extract the pathogenetic brain regions and risk genes. According to the results, FAGCN achieved the best performance among both traditional and cutting-edge methods and extracted AD-related brain regions and genes, providing theoretical and methodological support for the research of related diseases.

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

Since its launch in 2008, the European Genome-Phenome Archive (EGA) has been leading the archiving and distribution of human identifiable genomic data. In this regard, one of the community concerns is the potential usability of the stored data, as of now, data submitters are not mandated to perform any quality control (QC) before uploading their data and associated metadata information. Here, we present a new File QC Portal developed at EGA, along with QC reports performed and created for 1 694 442 files [Fastq, sequence alignment map (SAM)/binary alignment map (BAM)/CRAM and variant call format (VCF)] submitted at EGA. QC reports allow anonymous EGA users to view summary-level information regarding the files within a specific dataset, such as quality of reads, alignment quality, number and type of variants and other features. Researchers benefit from being able to assess the quality of data prior to the data access decision and thereby, increasing the reusability of data (https://ega-archive.org/blog/data-upcycling-powered-by-ega/).

Cellular senescence (CS), a state of permanent growth arrest, is intertwined with tumorigenesis. Due to the absence of specific markers, characterizing senescence levels and senescence-related phenotypes across cancer types remain unexplored. Here, we defined computational metrics of senescence levels as CS scores to delineate CS landscape across 33 cancer types and 29 normal tissues and explored CS-associated phenotypes by integrating multiplatform data from ~20 000 patients and ~212 000 single-cell profiles. CS scores showed cancer type-specific associations with genomic and immune characteristics and significantly predicted immunotherapy responses and patient prognosis in multiple cancers. Single-cell CS quantification revealed intra-tumor heterogeneity and activated immune microenvironment in senescent prostate cancer. Using machine learning algorithms, we identified three CS genes as potential prognostic predictors in prostate cancer and verified them by immunohistochemical assays in 72 patients. Our study provides a comprehensive framework for evaluating senescence levels and clinical relevance, gaining insights into CS roles in cancer- and senescence-related biomarker discovery.

Primers are critical for polymerase chain reaction (PCR) and influence PCR experimental outcomes. Designing numerous combinations of forward and reverse primers involves various primer constraints, posing a computational challenge. Most PCR primer design methods limit parameters because the available algorithms use general fitness functions. This study designed new fitness functions based on user-specified parameters and used the functions in a primer design approach based on the multiobjective particle swarm optimization (MOPSO) algorithm to address the challenge of primer design with user-specified parameters. Multicriteria evaluation was conducted simultaneously based on primer constraints. The fitness functions were evaluated using 7425 DNA sequences and compared with a predominant primer design approach based on optimization algorithms. Each DNA sequence was run 100 times to calculate the difference between the user-specified parameters and primer constraint values. The algorithms based on fitness functions with user-specified parameters outperformed the algorithms based on general fitness functions for 11 primer constraints. Moreover, MOPSO exhibited superior implementation in all experiments. Practical gel electrophoresis was conducted to verify the PCR experiments and established that MOPSO effectively designs primers based on user-specified parameters.

MOTIVATION: Identifying new uses of approved drugs is an effective way to reduce the time and cost of drug development. Recent computational approaches for predicting drug-disease associations have integrated multi-sourced data on drugs and diseases. However, neighboring topologies of various scales in multiple heterogeneous drug-disease networks have yet to be exploited and fully integrated. RESULTS: We propose a novel method for drug-disease association prediction, called MGPred, used to encode and learn multi-scale neighboring topologies of drug and disease nodes and pairwise attributes from heterogeneous networks. First, we constructed three heterogeneous networks based on multiple kinds of drug similarities. Each network comprises drug and disease nodes and edges created based on node-wise similarities and associations that reflect specific topological structures. We also propose an embedding mechanism to formulate topologies that cover different ranges of neighbors. To encode the embeddings and derive multi-scale neighboring topology representations of drug and disease nodes, we propose a module based on graph convolutional autoencoders with shared parameters for each heterogeneous network. We also propose scale-level attention to obtain an adaptive fusion of informative topological representations at different scales. Finally, a learning module based on a convolutional neural network with various receptive fields is proposed to learn multi-view attribute representations of a pair of drug and disease nodes. Comprehensive experiment results demonstrate that MGPred outperforms other state-of-the-art methods in comparison to drug-related disease prediction, and the recall rates for the top-ranked candidates and case studies on five drugs further demonstrate the ability of MGPred to retrieve potential drug-disease associations.

Nuclear receptors (NRs) are important biological targets of endocrine-disrupting chemicals (EDCs). Identifying chemicals that can act as EDCs and modulate the function of NRs is difficult because of the time and cost of in vitro and in vivo screening to determine the potential hazards of the 100 000s of chemicals that humans are exposed to. Hence, there is a need for computational approaches to prioritize chemicals for biological testing. Machine learning (ML) techniques are alternative methods that can quickly screen millions of chemicals and identify those that may be an EDC. Computational models of chemical binding to multiple NRs have begun to emerge. Recently, a Nuclear Receptor Activity (NuRA) dataset, describing experimentally derived small-molecule activity against various NRs has been created. We have used the NuRA dataset to develop an ensemble of ML-based models to predict the agonism, antagonism, binding and effector binding of small molecules to nine different human NRs. We defined the applicability domain of the ML models as a measure of Tanimoto similarity to the molecules in the training set, which enhanced the performance of the developed classifiers. We further developed a user-friendly web server named 'NR-ToxPred' to predict the binding of chemicals to the nine NRs using the best-performing models for each receptor. This web server is freely accessible at http://nr-toxpred.cchem.berkeley.edu. Users can upload individual chemicals using Simplified Molecular-Input Line-Entry System, CAS numbers or sketch the molecule in the provided space to predict the compound's activity against the different NRs and predict the binding mode for each.

Predicting differentially expressed genes (DEGs) from epigenetics signal data is the key to understand how epigenetics controls cell functional heterogeneity by gene regulation. This knowledge can help developing 'epigenetics drugs' for complex diseases like cancers. Most of existing machine learning-based methods suffer defects in prediction accuracy, interpretability or training speed. To address these problems, in this paper, we propose a Multiple Self-Attention model for predicting DEGs on Epigenetic data (Epi-MSA). Epi-MSA first uses convolutional neural networks for neighborhood bins information embedding, and then employs multiple self-attention encoders on different input epigenetics factors data to learn which locations of genes are important for predicting DEGs. Next it trains a soft attention module to pick out which epigenetics factors are significant. The attention mechanism makes the model interpretable, and the pure matrix operation of self-attention enables the model to be parallel calculated and speeds up the training. Experiments on datasets from the Roadmap Epigenome Project and BluePrint Data Analysis Portal (BDAP) show that the performance of Epi-MSA is better than existing competitive methods, and Epi-MSA also has a smaller standard deviation, which shows that Epi-MSA is effective and stable. In addition, Epi-MSA has a good interpretability, this is confirmed by referring its attention weight matrix with existing biological knowledge.

Different ribonucleic acids (RNAs) can interact to form regulatory networks that play important role in many life activities. Molecular biology experiments can confirm RNA-RNA interactions to facilitate the exploration of their biological functions, but they are expensive and time-consuming. Machine learning models can predict potential RNA-RNA interactions, which provide candidates for molecular biology experiments to save a lot of time and cost. Using a set of suitable features to represent the sample is crucial for training powerful models, but there is a lack of effective feature representation for RNA-RNA interaction. This study proposes a novel feature representation method with information enhancement and dimension reduction for RNA-RNA interaction (named RNAI-FRID). Diverse base features are first extracted from RNA data to contain more sample information. Then, the extracted base features are used to construct the complex features through an arithmetic-level method. It greatly reduces the feature dimension while keeping the relationship between molecule features. Since the dimension reduction may cause information loss, in the process of complex feature construction, the arithmetic mean strategy is adopted to enhance the sample information further. Finally, three feature ranking methods are integrated for feature selection on constructed complex features. It can adaptively retain important features and remove redundant ones. Extensive experiment results show that RNAI-FRID can provide reliable feature representation for RNA-RNA interaction with higher efficiency and the model trained with generated features obtain better performance than other deep neural network predictors.

Increasing biological evidence indicated that microRNAs (miRNAs) play a vital role in exploring the pathogenesis of various human diseases (especially in tumors). Mining disease-related miRNAs is of great significance for the clinical diagnosis and treatment of diseases. Compared with the traditional experimental methods with the significant limitations of high cost, long cycle and small scale, the methods based on computing have the advantages of being cost-effective. However, although the current methods based on computational biology can accurately predict the correlation between miRNAs and disease, they can not predict the detailed association information at a fine level. We propose a knowledge-driven approach to the fine-grained prediction of disease-related miRNAs (KDFGMDA). Different from the previous methods, this method can finely predict the clear associations between miRNA and disease, such as upregulation, downregulation or dysregulation. Specifically, KDFGMDA extracts triple information from massive experimental data and existing datasets to construct a knowledge graph and then trains a depth graph representation learning model based on knowledge graph to complete fine-grained prediction tasks. Experimental results show that KDFGMDA can predict the relationship between miRNA and disease accurately, which is of far-reaching significance for medical clinical research and early diagnosis, prevention and treatment of diseases. Additionally, the results of case studies on three types of cancers, Kaplan-Meier survival analysis and expression difference analysis further provide the effectiveness and feasibility of KDFGMDA to detect potential candidate miRNAs. Availability: Our work can be downloaded from https://github.com/ShengPengYu/KDFGMDA.

Scoring functions are important components in molecular docking for structure-based drug discovery. Traditional scoring functions, generally empirical- or force field-based, are robust and have proven to be useful for identifying hits and lead optimizations. Although multiple highly accurate deep learning- or machine learning-based scoring functions have been developed, their direct applications for docking and screening are limited. We describe a novel strategy to develop a reliable protein-ligand scoring function by augmenting the traditional scoring function Vina score using a correction term (OnionNet-SFCT). The correction term is developed based on an AdaBoost random forest model, utilizing multiple layers of contacts formed between protein residues and ligand atoms. In addition to the Vina score, the model considerably enhances the AutoDock Vina prediction abilities for docking and screening tasks based on different benchmarks (such as cross-docking dataset, CASF-2016, DUD-E and DUD-AD). Furthermore, our model could be combined with multiple docking applications to increase pose selection accuracies and screening abilities, indicating its wide usage for structure-based drug discoveries. Furthermore, in a reverse practice, the combined scoring strategy successfully identified multiple known receptors of a plant hormone. To summarize, the results show that the combination of data-driven model (OnionNet-SFCT) and empirical scoring function (Vina score) is a good scoring strategy that could be useful for structure-based drug discoveries and potentially target fishing in future.

Over the past decade, statistical methods have been developed to estimate single nucleotide polymorphism (SNP) heritability, which measures the proportion of phenotypic variance explained by all measured SNPs in the data. Estimates of SNP heritability measure the degree to which the available genetic variants influence phenotypes and improve our understanding of the genetic architecture of complex phenotypes. In this article, we review the recently developed and commonly used SNP heritability estimation methods for continuous and binary phenotypes from the perspective of model assumptions and parameter optimization. We primarily focus on their capacity to handle multiple phenotypes and longitudinal measurements, their ability for SNP heritability partition and their use of individual-level data versus summary statistics. State-of-the-art statistical methods that are scalable to the UK Biobank dataset are also elucidated in detail.

MOTIVATION: Identifying disease-related genes is an important issue in computational biology. Module structure widely exists in biomolecule networks, and complex diseases are usually thought to be caused by perturbations of local neighborhoods in the networks, which can provide useful insights for the study of disease-related genes. However, the mining and effective utilization of the module structure is still challenging in such issues as a disease gene prediction. RESULTS: We propose a hybrid disease-gene prediction method integrating multiscale module structure (HyMM), which can utilize multiscale information from local to global structure to more effectively predict disease-related genes. HyMM extracts module partitions from local to global scales by multiscale modularity optimization with exponential sampling, and estimates the disease relatedness of genes in partitions by the abundance of disease-related genes within modules. Then, a probabilistic model for integration of gene rankings is designed in order to integrate multiple predictions derived from multiscale module partitions and network propagation, and a parameter estimation strategy based on functional information is proposed to further enhance HyMM's predictive power. By a series of experiments, we reveal the importance of module partitions at different scales, and verify the stable and good performance of HyMM compared with eight other state-of-the-arts and its further performance improvement derived from the parameter estimation. CONCLUSIONS: The results confirm that HyMM is an effective framework for integrating multiscale module structure to enhance the ability to predict disease-related genes, which may provide useful insights for the study of the multiscale module structure and its application in such issues as a disease-gene prediction.

Multiple sequence alignment (MSA) is an essential cornerstone in bioinformatics, which can reveal the potential information in biological sequences, such as function, evolution and structure. MSA is widely used in many bioinformatics scenarios, such as phylogenetic analysis, protein analysis and genomic analysis. However, MSA faces new challenges with the gradual increase in sequence scale and the increasing demand for alignment accuracy. Therefore, developing an efficient and accurate strategy for MSA has become one of the research hotspots in bioinformatics. In this work, we mainly summarize the algorithms for MSA and its applications in bioinformatics. To provide a structured and clear perspective, we systematically introduce MSA's knowledge, including background, database, metric and benchmark. Besides, we list the most common applications of MSA in the field of bioinformatics, including database searching, phylogenetic analysis, genomic analysis, metagenomic analysis and protein analysis. Furthermore, we categorize and analyze classical and state-of-the-art algorithms, divided into progressive alignment, iterative algorithm, heuristics, machine learning and divide-and-conquer. Moreover, we also discuss the challenges and opportunities of MSA in bioinformatics. Our work provides a comprehensive survey of MSA applications and their relevant algorithms. It could bring valuable insights for researchers to contribute their knowledge to MSA and relevant studies.

The Cellular Thermal Shift Assay (CETSA) plays an important role in drug-target identification, and statistical analysis is a crucial step significantly affecting conclusion. We put forward ProSAP (Protein Stability Analysis Pod), an open-source, cross-platform and user-friendly software tool, which provides multiple methods for thermal proteome profiling (TPP) analysis, nonparametric analysis (NPA), proteome integral solubility alteration and isothermal shift assay (iTSA). For testing the performance of ProSAP, we processed several datasets and compare the performance of different algorithms. Overall, TPP analysis is more accurate with fewer false positive targets, but NPA methods are flexible and free from parameters. For iTSA, edgeR and DESeq2 identify more true targets than t-test and Limma, but when it comes to ranking, the four methods show not much difference. ProSAP software is available at https://github.com/hcji/ProSAP and https://zenodo.org/record/5763315.

Interaction between tumor cells and immune cells determined highly heterogeneous microenvironments across patients, leading to substantial variation in clinical benefits from immunotherapy. Somatic gene mutations were found not only to elicit adaptive immunity but also to influence the composition of tumor immune microenvironment and various processes of antitumor immunity. However, due to an incomplete view of associations between gene mutations and immunophenotypes, how tumor cells shape the immune microenvironment and further determine the clinical benefit of immunotherapy is still unclear. To address this, we proposed a computational approach, inference of mutation effect on immunophenotype by integrated gene set enrichment analysis (MEIGSEA), for tracing back the genomic factor responsible for differences in immunophenotypes. MEIGSEA was demonstrated to accurately identify the previous confirmed immune-associated gene mutations, and systematic evaluation in simulation data further supported its performance. We used MEIGSEA to investigate the influence of driver gene mutations on the infiltration of 22 immune cell types across 19 cancers from The Cancer Genome Atlas. The top associated gene mutations with infiltration of CD8 T cells, such as CASP8, KRAS and EGFR, also showed extensive impact on other immune components; meanwhile, immune effector cells shared critical gene mutations that collaboratively contribute to shaping distinct tumor immune microenvironment. Furthermore, we highlighted the predictive capacity of gene mutations that are positively associated with CD8 T cells for the clinical benefit of immunotherapy. Taken together, we present a computational framework to help illustrate the potential of somatic gene mutations in shaping the tumor immune microenvironment.

The rapid development of single-cell DNA sequencing (scDNA-seq) technology has greatly enhanced the resolution of tumor cell profiling, providing an unprecedented perspective in characterizing intra-tumoral heterogeneity and understanding tumor progression and metastasis. However, prominent algorithms for constructing tumor phylogeny based on scDNA-seq data usually only take single nucleotide variations (SNVs) as markers, failing to consider the effect caused by copy number alterations (CNAs). Here, we propose BiTSC$^2$, Bayesian inference of Tumor clonal Tree by joint analysis of Single-Cell SNV and CNA data. BiTSC$^2$ takes raw reads from scDNA-seq as input, accounts for the overlapping of CNA and SNV, models allelic dropout rate, sequencing errors and missing rate, as well as assigns single cells into subclones. By applying Markov Chain Monte Carlo sampling, BiTSC$^2$ can simultaneously estimate the subclonal scCNA and scSNV genotype matrices, subclonal assignments and tumor subclonal evolutionary tree. In comparison with existing methods on synthetic and real tumor data, BiTSC$^2$ shows high accuracy in genotype recovery, subclonal assignment and tree reconstruction. BiTSC$^2$ also performs robustly in dealing with scDNA-seq data with low sequencing depth and variant missing rate. BiTSC$^2$ software is available at https://github.com/ucasdp/BiTSC2.

It is tough to detect unexpected drug-drug interactions (DDIs) in poly-drug treatments because of high costs and clinical limitations. Computational approaches, such as deep learning-based approaches, are promising to screen potential DDIs among numerous drug pairs. Nevertheless, existing approaches neglect the asymmetric roles of two drugs in interaction. Such an asymmetry is crucial to poly-drug treatments since it determines drug priority in co-prescription. This paper designs a directed graph attention network (DGAT-DDI) to predict asymmetric DDIs. First, its encoder learns the embeddings of the source role, the target role and the self-roles of a drug. The source role embedding represents how a drug influences other drugs in DDIs. In contrast, the target role embedding represents how it is influenced by others. The self-role embedding encodes its chemical structure in a role-specific manner. Besides, two role-specific items, aggressiveness and impressionability, capture how the number of interaction partners of a drug affects its interaction tendency. Furthermore, the predictor of DGAT-DDI discriminates direction-specific interactions by the combination between two proximities and the above two role-specific items. The proximities measure the similarity between source/target embeddings and self-role embeddings. In the designated experiments, the comparison with state-of-the-art deep learning models demonstrates the superiority of DGAT-DDI across a direction-specific predicting task and a direction-blinded predicting task. An ablation study reveals how well each component of DGAT-DDI contributes to its ability. Moreover, a case study of finding novel DDIs confirms its practical ability, where 7 out of the top 10 candidates are validated in DrugBank.

MOTIVATION: Computerized methods for drug-related side effect identification can help reduce costs and speed up drug development. Multisource data about drug and side effects are widely used to predict potential drug-related side effects. Heterogeneous graphs are commonly used to associate multisourced data of drugs and side effects which can reflect similarities of the drugs from different perspectives. Effective integration and formulation of diverse similarities, however, are challenging. In addition, the specific topology of each heterogeneous graph and the common topology of multiple graphs are neglected. RESULTS: We propose a drug-side effect association prediction model, GCRS, to encode and integrate specific topologies, common topologies and pairwise attributes of drugs and side effects. First, multiple drug-side effect heterogeneous graphs are constructed using various kinds of similarities and associations related to drugs and side effects. As each heterogeneous graph has its specific topology, we establish separate module based on graph convolutional autoencoder (GCA) to learn the particular topology representation of each drug node and each side effect node, respectively. Since multiple graphs reflect the complex relationships among the drug and side effect nodes and contain common topologies, we construct a module based on GCA with sharing parameters to learn the common topology representations of each node. Afterwards, we design an attention mechanism to obtain more informative topology representations at the representation level. Finally, multi-layer convolutional neural networks with attribute-level attention are constructed to deeply integrate the similarity and association attributes of a pair of drug-side effect nodes. Comprehensive experiments show that GCRS's prediction performance is superior to other comparing state-of-the-art methods for predicting drug-side effect associations. The recall rates in top-ranked candidates and case studies on five drugs further demonstrate GCRS's ability in discovering potential drug-related side effects. CONTACT: zhang@hlju.edu.cn.

Accurate transfer learning of clinical outcomes from one cellular context to another, between cell types, developmental stages, omics modalities or species, is considered tremendously useful. When transferring a prediction task from a source domain to a target domain, what counts is the high quality of the predictions in the target domain, requiring states or processes common to both the source and the target that can be learned by the predictor reflected by shared denominators. These may form a compendium of knowledge that is learned in the source to enable predictions in the target, usually with few, if any, labeled target training samples to learn from. Transductive transfer learning refers to the learning of the predictor in the source domain, transferring its outcome label calculations to the target domain, considering the same task. Inductive transfer learning considers cases where the target predictor is performing a different yet related task as compared with the source predictor. Often, there is also a need to first map the variables in the input/feature spaces and/or the variables in the output/outcome spaces. We here discuss and juxtapose various recently published transfer learning approaches, specifically designed (or at least adaptable) to predict clinical (human in vivo) outcomes based on preclinical (mostly animal-based) molecular data, towards finding the right tool for a given task, and paving the way for a comprehensive and systematic comparison of the suitability and accuracy of transfer learning of clinical outcomes.

Drug design targeting protein-protein interactions (PPIs) associated with the development of diseases has been one of the most important therapeutic strategies. Besides interrupting the PPIs with PPI inhibitors/blockers, increasing evidence shows that stabilizing the interaction between two interacting proteins may also benefit the therapy, such as the development of various types of molecular glues/stabilizers that mostly work by stabilizing the two interacting proteins to regulate the downstream biological effects. However, characterizing the stabilization effect of a stabilizer is usually hard or too complicated for traditional experiments since it involves ternary interactions [protein-protein-stabilizer (PPS) interaction]. Thus, developing reliable computational strategies will facilitate the discovery/design of molecular glues or PPI stabilizers. Here, by fully analyzing the energetic features of the binary interactions in the PPS ternary complex, we systematically investigated the performance of molecular mechanics Poisson-Boltzmann surface area (MM/PBSA) and molecular mechanics generalized Born surface area (MM/GBSA) methods on characterizing the stabilization effects of stabilizers in 14-3-3 systems. The results show that both MM/PBSA and MM/GBSA are powerful tools in distinguishing the stabilizers from the decoys (with area under the curves of 0.90-0.93 for all tested cases) and are reasonable for ranking protein-peptide interactions in the presence or absence of stabilizers as well (with the average Pearson correlation coefficient of ~0.6 at a relatively high dielectric constant for both methods). Moreover, to give a detailed picture of the stabilization effects, the stabilization mechanism is also analyzed from the structural and energetic points of view for individual systems containing strong or weak stabilizers. This study demonstrates a potential strategy to accelerate the discovery of PPI stabilizers.

Heritability, the proportion of phenotypic variance explained by genome-wide single nucleotide polymorphisms (SNPs) in unrelated individuals, is an important measure of the genetic contribution to human diseases and plays a critical role in studying the genetic architecture of human diseases. Linear mixed model (LMM) has been widely used for SNP heritability estimation, where variance component parameters are commonly estimated by using a restricted maximum likelihood (REML) method. REML is an iterative optimization algorithm, which is computationally intensive when applied to large-scale datasets (e.g. UK Biobank). To facilitate the heritability analysis of large-scale genetic datasets, we develop a fast approach, minimum norm quadratic unbiased estimator (MINQUE) with batch training, to estimate variance components from LMM (LMM.MNQ.BCH). In LMM.MNQ.BCH, the parameters are estimated by MINQUE, which has a closed-form solution for fast computation and has no convergence issue. Batch training has also been adopted in LMM.MNQ.BCH to accelerate the computation for large-scale genetic datasets. Through simulations and real data analysis, we demonstrate that LMM.MNQ.BCH is much faster than two existing approaches, GCTA and BOLT-REML.

MOTIVATION: Biological networks topology yields important insights into biological function, occurrence of diseases and drug design. In the last few years, different types of topological measures have been introduced and applied to infer the biological relevance of network components/interactions, according to their position within the network structure. Although comparisons of such measures have been previously proposed, to what extent the topology per se may lead to the extraction of novel biological knowledge has never been critically examined nor formalized in the literature. RESULTS: We present a comparative analysis of nine outstanding topological measures, based on compact views obtained from the rank they induce on a given input biological network. The goal is to understand their ability in correctly positioning nodes/edges in the rank, according to the functional knowledge implicitly encoded in biological networks. To this aim, both internal and external (gold standard) validation criteria are taken into account, and six networks involving three different organisms (yeast, worm and human) are included in the comparison. The results show that a distinct handful of best-performing measures can be identified for each of the considered organisms, independently from the reference gold standard. AVAILABILITY: Input files and code for the computation of the considered topological measures and K-haus distance are available at https://gitlab.com/MaryBonomo/ranking. CONTACT: simona.rombo@unipa.it. SUPPLEMENTARY INFORMATION: Supplementary data are available at Briefings in Bioinformatics online.

Drug-target interaction (DTI) prediction plays an important role in drug repositioning, drug discovery and drug design. However, due to the large size of the chemical and genomic spaces and the complex interactions between drugs and targets, experimental identification of DTIs is costly and time-consuming. In recent years, the emerging graph neural network (GNN) has been applied to DTI prediction because DTIs can be represented effectively using graphs. However, some of these methods are only based on homogeneous graphs, and some consist of two decoupled steps that cannot be trained jointly. To further explore GNN-based DTI prediction by integrating heterogeneous graph information, this study regards DTI prediction as a link prediction problem and proposes an end-to-end model based on HETerogeneous graph with Attention mechanism (DTI-HETA). In this model, a heterogeneous graph is first constructed based on the drug-drug and target-target similarity matrices and the DTI matrix. Then, the graph convolutional neural network is utilized to obtain the embedded representation of the drugs and targets. To highlight the contribution of different neighborhood nodes to the central node in aggregating the graph convolution information, a graph attention mechanism is introduced into the node embedding process. Afterward, an inner product decoder is applied to predict DTIs. To evaluate the performance of DTI-HETA, experiments are conducted on two datasets. The experimental results show that our model is superior to the state-of-the-art methods. Also, the identification of novel DTIs indicates that DTI-HETA can serve as a powerful tool for integrating heterogeneous graph information to predict DTIs.

In the last few decades, antimicrobial peptides (AMPs) have been explored as an alternative to classical antibiotics, which in turn motivated the development of machine learning models to predict antimicrobial activities in peptides. The first generation of these predictors was filled with what is now known as shallow learning-based models. These models require the computation and selection of molecular descriptors to characterize each peptide sequence and train the models. The second generation, known as deep learning-based models, which no longer requires the explicit computation and selection of those descriptors, started to be used in the prediction task of AMPs just four years ago. The superior performance claimed by deep models regarding shallow models has created a prevalent inertia to using deep learning to identify AMPs. However, methodological flaws and/or modeling biases in the building of deep models do not support such superiority. Here, we analyze the main pitfalls that led to establish biased conclusions on the leading performance of deep models. Also, we analyze whether deep models truly contribute to achieve better predictions than shallow models by performing fair studies on different state-of-the-art benchmarking datasets. The experiments reveal that deep models do not outperform shallow models in the classification of AMPs, and that both types of models codify similar chemical information since their predictions are highly similar. Thus, according to the currently available datasets, we conclude that the use of deep learning could not be the most suitable approach to develop models to identify AMPs, mainly because shallow models achieve comparable-to-superior performances and are simpler (Ockham's razor principle). Even so, we suggest the use of deep learning only when its capabilities lead to obtaining significantly better performance gains worth the additional computational cost.

High-dimensional, localized ribonucleic acid (RNA) sequencing is now possible owing to recent developments in spatial transcriptomics (ST). ST is based on highly multiplexed sequence analysis and uses barcodes to match the sequenced reads to their respective tissue locations. ST expression data suffer from high noise and dropout events; however, smoothing techniques have the promise to improve the data interpretability prior to performing downstream analyses. Single-cell RNA sequencing (scRNA-seq) data similarly suffer from these limitations, and smoothing methods developed for scRNA-seq can only utilize associations in transcriptome space (also known as one-factor smoothing methods). Since they do not account for spatial relationships, these one-factor smoothing methods cannot take full advantage of ST data. In this study, we present a novel two-factor smoothing technique, spatial and pattern combined smoothing (SPCS), that employs the k-nearest neighbor (kNN) technique to utilize information from transcriptome and spatial relationships. By performing SPCS on multiple ST slides from pancreatic ductal adenocarcinoma (PDAC), dorsolateral prefrontal cortex (DLPFC) and simulated high-grade serous ovarian cancer (HGSOC) datasets, smoothed ST slides have better separability, partition accuracy and biological interpretability than the ones smoothed by preexisting one-factor methods. Source code of SPCS is provided in Github (https://github.com/Usos/SPCS).

The parallel measurement of transcriptome and proteome revealed unmatched profiles. Since proteomic analysis is more expensive and challenging than transcriptomic analysis, the question of how to use messenger RNA (mRNA) expression data to predict protein level is extremely important. Here, we comprehensively evaluated 13 machine learning models on inferring protein expression levels using RNA expression profile. A total of 20 proteogenomic datasets from three mainstream proteomic platforms with >2500 samples of 13 human tissues were collected for model evaluation. Our results highlighted that the appropriate feature selection methods combined with classical machine learning models could achieve excellent predictive performance. The voting ensemble model outperformed other candidate models across datasets. Adding the mRNA proxy model to the regression model further improved the prediction performance. The dataset and gene characteristics could affect the prediction performance. Finally, we applied the model to the brain transcriptome of cerebral cortex regions to infer the protein profile for better understanding the functional characteristics of the brain regions. This benchmarking work not only provides useful hints on the inherent correlation between transcriptome and proteome, but also has practical value of the transcriptome-based prediction of protein expression levels.

Cell signal networks are orchestrated directly or indirectly by various peptide-mediated protein-protein interactions, which are normally weak and transient and thus ideal for biological regulation and medicinal intervention. Here, we develop a general-purpose method for modeling and predicting the binding affinities of protein-peptide interactions (PpIs) at the structural level. The method is a hybrid strategy that employs an unsupervised approach to derive a layered PpI atom-residue interaction (ulPpI[a-r]) potential between different protein atom types and peptide residue types from thousands of solved PpI complex structures and then statistically correlates the potential descriptors with experimental affinities (KD values) over hundreds of known PpI samples in a supervised manner to create an integrated unsupervised-supervised PpI affinity (usPpIA) predictor. Although both the ulPpI[a-r] potential and usPpIA predictor can be used to calculate PpI affinities from their complex structures, the latter seems to perform much better than the former, suggesting that the unsupervised potential can be improved substantially with a further correction by supervised statistical learning. We examine the robustness and fault-tolerance of usPpIA predictor when applied to treat the coarse-grained PpI complex structures modeled computationally by sophisticated peptide docking and dynamics simulation. It is revealed that, despite developed solely based on solved structures, the integrated unsupervised-supervised method is also applicable for locally docked structures to reach a quantitative prediction but can only give a qualitative prediction on globally docked structures. The dynamics refinement seems not to change (or improve) the predictive results essentially, although it is computationally expensive and time-consuming relative to peptide docking. We also perform extrapolation of usPpIA predictor to the indirect affinity quantities of HLA-A*0201 binding epitope peptides and NHERF PDZ binding scaffold peptides, consequently resulting in a good and moderate correlation of the predicted KD with experimental IC50 and BLU on the two peptide sets, with Pearson's correlation coefficients Rp = 0.635 and 0.406, respectively.

Nitrogen is essential for life and its transformations are an important part of the global biogeochemical cycle. Being an essential nutrient, nitrogen exists in a range of oxidation states from +5 (nitrate) to -3 (ammonium and amino-nitrogen), and its oxidation and reduction reactions catalyzed by microbial enzymes determine its environmental fate. The functional annotation of the genes encoding the core nitrogen network enzymes has a broad range of applications in metagenomics, agriculture, wastewater treatment and industrial biotechnology. This study developed an alignment-free computational approach to determine the predicted nitrogen biochemical network-related enzymes from the sequence itself. We propose deepNEC, a novel end-to-end feature selection and classification model training approach for nitrogen biochemical network-related enzyme prediction. The algorithm was developed using Deep Learning, a class of machine learning algorithms that uses multiple layers to extract higher-level features from the raw input data. The derived protein sequence is used as an input, extracting sequential and convolutional features from raw encoded protein sequences based on classification rather than traditional alignment-based methods for enzyme prediction. Two large datasets of protein sequences, enzymes and non-enzymes were used to train the models with protein sequence features like amino acid composition, dipeptide composition (DPC), conformation transition and distribution, normalized Moreau-Broto (NMBroto), conjoint and quasi order, etc. The k-fold cross-validation and independent testing were performed to validate our model training. deepNEC uses a four-tier approach for prediction; in the first phase, it will predict a query sequence as enzyme or non-enzyme; in the second phase, it will further predict and classify enzymes into nitrogen biochemical network-related enzymes or non-nitrogen metabolism enzymes; in the third phase, it classifies predicted enzymes into nine nitrogen metabolism classes; and in the fourth phase, it predicts the enzyme commission number out of 20 classes for nitrogen metabolism. Among all, the DPC + NMBroto hybrid feature gave the best prediction performance (accuracy of 96.15% in k-fold training and 93.43% in independent testing) with an Matthews correlation coefficient (0.92 training and 0.87 independent testing) in phase I; phase II (accuracy of 99.71% in k-fold training and 98.30% in independent testing); phase III (overall accuracy of 99.03% in k-fold training and 98.98% in independent testing); phase IV (overall accuracy of 99.05% in k-fold training and 98.18% in independent testing), the DPC feature gave the best prediction performance. We have also implemented a homology-based method to remove false negatives. All the models have been implemented on a web server (prediction tool), which is freely available at http://bioinfo.usu.edu/deepNEC/.

Identifying the genes and mutations that drive the emergence of tumors is a critical step to improving our understanding of cancer and identifying new directions for disease diagnosis and treatment. Despite the large volume of genomics data, the precise detection of driver mutations and their carrying genes, known as cancer driver genes, from the millions of possible somatic mutations remains a challenge. Computational methods play an increasingly important role in discovering genomic patterns associated with cancer drivers and developing predictive models to identify these elements. Machine learning (ML), including deep learning, has been the engine behind many of these efforts and provides excellent opportunities for tackling remaining gaps in the field. Thus, this survey aims to perform a comprehensive analysis of ML-based computational approaches to identify cancer driver mutations and genes, providing an integrated, panoramic view of the broad data and algorithmic landscape within this scientific problem. We discuss how the interactions among data types and ML algorithms have been explored in previous solutions and outline current analytical limitations that deserve further attention from the scientific community. We hope that by helping readers become more familiar with significant developments in the field brought by ML, we may inspire new researchers to address open problems and advance our knowledge towards cancer driver discovery.

While the technologies of ribonucleic acid-sequence (RNA-seq) and transcript assembly analysis have continued to improve, a novel topology of RNA transcript was uncovered in the last decade and is called circular RNA (circRNA). Recently, researchers have revealed that they compete with messenger RNA (mRNA) and long noncoding for combining with microRNA in gene regulation. Therefore, circRNA was assumed to be associated with complex disease and discovering the relationship between them would contribute to medical research. However, the work of identifying the association between circRNA and disease in vitro takes a long time and usually without direction. During these years, more and more associations were verified by experiments. Hence, we proposed a computational method named identifying circRNA-disease association based on graph representation learning (iGRLCDA) for the prediction of the potential association of circRNA and disease, which utilized a deep learning model of graph convolution network (GCN) and graph factorization (GF). In detail, iGRLCDA first derived the hidden feature of known associations between circRNA and disease using the Gaussian interaction profile (GIP) kernel combined with disease semantic information to form a numeric descriptor. After that, it further used the deep learning model of GCN and GF to extract hidden features from the descriptor. Finally, the random forest classifier is introduced to identify the potential circRNA-disease association. The five-fold cross-validation of iGRLCDA shows strong competitiveness in comparison with other excellent prediction models at the gold standard data and achieved an average area under the receiver operating characteristic curve of 0.9289 and an area under the precision-recall curve of 0.9377. On reviewing the prediction results from the relevant literature, 22 of the top 30 predicted circRNA-disease associations were noted in recent published papers. These exceptional results make us believe that iGRLCDA can provide reliable circRNA-disease associations for medical research and reduce the blindness of wet-lab experiments.

Healthcare disparities in multiethnic medical data is a major challenge; the main reason lies in the unequal data distribution of ethnic groups among data cohorts. Biomedical data collected from different cancer genome research projects may consist of mainly one ethnic group, such as people with European ancestry. In contrast, the data distribution of other ethnic races such as African, Asian, Hispanic, and Native Americans can be less visible than the counterpart. Data inequality in the biomedical field is an important research problem, resulting in the diverse performance of machine learning models while creating healthcare disparities. Previous researches have reduced the healthcare disparities only using limited data distributions. In our study, we work on fine-tuning of deep learning and transfer learning models with different multiethnic data distributions for the prognosis of 33 cancer types. In previous studies, to reduce the healthcare disparities, only a single ethnic cohort was used as the target domain with one major source domain. In contrast, we focused on multiple ethnic cohorts as the target domain in transfer learning using the TCGA and MMRF CoMMpass study datasets. After performance comparison for experiments with new data distributions, our proposed model shows promising performance for transfer learning schemes compared to the baseline approach for old and new data distributation experiments.

Protein-ligand docking is an essential method in computer-aided drug design and structural bioinformatics. It can be used to identify active compounds and reveal molecular mechanisms of biological processes. A successful docking usually requires thorough conformation sampling and scoring, which are computationally expensive and difficult. Recent studies demonstrated that it can be beneficial to docking with the guidance of existing similar co-crystal structures. In this work, we developed a protein-ligand docking method, named FitDock, which fits initial conformation to the given template using a hierarchical multi-feature alignment approach, subsequently explores the possible conformations and finally outputs refined docking poses. In our comprehensive benchmark tests, FitDock showed 40%-60% improvement in terms of docking success rate and an order of magnitude faster over popular docking methods, if template structures exist (> 0.5 ligand similarity). FitDock has been implemented in a user-friendly program, which could serve as a convenient tool for drug design and molecular mechanism exploration. It is now freely available for academic users at http://cao.labshare.cn/fitdock/.

MOTIVATION: The human major histocompatibility complex (MHC), also known as human leukocyte antigen (HLA), plays an important role in the adaptive immune system by presenting non-self-peptides to T cell receptors. The MHC region has been shown to be associated with a variety of diseases, including autoimmune diseases, organ transplantation and tumours. However, structural analytic tools of HLA are still sparse compared to the number of identified HLA alleles, which hinders the disclosure of its pathogenic mechanism. RESULT: To provide an integrative analysis of HLA, we first collected 1296 amino acid sequences, 256 protein data bank structures, 120 000 frequency data of HLA alleles in different populations, 73 000 publications and 39 000 disease-associated single nucleotide polymorphism sites, as well as 212 modelled HLA heterodimer structures. Then, we put forward two new strategies for building up a toolkit for transplantation and tumour immunotherapy, designing risk alignment pipeline and antigenic peptide prediction pipeline by integrating different resources and bioinformatic tools. By integrating 100 000 calculated HLA conformation difference and online tools, risk alignment pipeline provides users with the functions of structural alignment, sequence alignment, residue visualization and risk report generation of mismatched HLA molecules. For tumour antigen prediction, we first predicted 370 000 immunogenic peptides based on the affinity between peptides and MHC to generate the neoantigen catalogue for 11 common tumours. We then designed an antigenic peptide prediction pipeline to provide the functions of mutation prediction, peptide prediction, immunogenicity assessment and docking simulation. We also present a case study of hepatitis B virus mutations associated with liver cancer that demonstrates the high legitimacy of our antigenic peptide prediction process. HLA3D, including different HLA analytic tools and the prediction pipelines, is available at http://www.hla3d.cn/.

The increasing prevalence of antibiotic resistance has become a global health crisis. For the purpose of safety regulation, it is of high importance to identify antibiotic resistance genes (ARGs) in bacteria. Although culture-based methods can identify ARGs relatively more accurately, the identifying process is time-consuming and specialized knowledge is required. With the rapid development of whole genome sequencing technology, researchers attempt to identify ARGs by computing sequence similarity from public databases. However, these computational methods might fail to detect ARGs due to the low sequence identity to known ARGs. Moreover, existing methods cannot effectively address the issue of multidrug resistance prediction for ARGs, which is a great challenge to clinical treatments. To address the challenges, we propose an end-to-end multi-label learning framework for predicting ARGs. More specifically, the task of ARGs prediction is modeled as a problem of multi-label learning, and a deep neural network-based end-to-end framework is proposed, in which a specific loss function is introduced to employ the advantage of multi-label learning for ARGs prediction. In addition, a dual-view modeling mechanism is employed to make full use of the semantic associations among two views of ARGs, i.e. sequence-based information and structure-based information. Extensive experiments are conducted on publicly available data, and experimental results demonstrate the effectiveness of the proposed framework on the task of ARGs prediction.

B-cell epitopes have the capability to recognize and attach to the surface of antigen receptors to stimulate the immune system against pathogens. Identification of B-cell epitopes from antigens has a great significance in several biomedical and biotechnological applications, provides support in the development of therapeutics, design and development of an epitope-based vaccine and antibody production. However, the identification of epitopes with experimental mapping approaches is a challenging job and usually requires extensive laboratory efforts. However, considerable efforts have been placed for the identification of epitopes using computational methods in the recent past but deprived of considerable achievements. In this study, we present LBCEPred, a python-based web-tool (http://lbcepred.pythonanywhere.com/), build with random forest classifier and statistical moment-based descriptors to predict the B-cell epitopes from the protein sequences. LBECPred outperforms all sequence-based available models that are currently in use for the B-cell epitopes prediction, with 0.868 accuracy value and 0.934 area under the curve. Moreover, the prediction performance of proposed models compared to other state-of-the-art models is 56.3% higher on average for Mathews Correlation Coefficient. LBCEPred is easy to use tool even for novice users and has also shown the models stability and reliability, thus we believe in its significant contribution to the research community and the area of bioinformatics.

With an in-depth understanding of noncoding ribonucleic acid (RNA), many studies have shown that microRNA (miRNA) plays an important role in human diseases. Because traditional biological experiments are time-consuming and laborious, new calculation methods have recently been developed to predict associations between miRNA and diseases. In this review, we collected various miRNA-disease association prediction models proposed in recent years and used two common data sets to evaluate the performance of the prediction models. First, we systematically summarized the commonly used databases and similarity data for predicting miRNA-disease associations, and then divided the various calculation models into four categories for summary and detailed introduction. In this study, two independent datasets (D5430 and D6088) were compiled to systematically evaluate 11 publicly available prediction tools for miRNA-disease associations. The experimental results indicate that the methods based on information dissemination and the method based on scoring function require shorter running time. The method based on matrix transformation often requires a longer running time, but the overall prediction result is better than the previous two methods. We hope that the summary of work related to miRNA and disease will provide comprehensive knowledge for predicting the relationship between miRNA and disease and contribute to advanced computation tools in the future.

Explosively emerging SARS-CoV-2 variants challenge current nomenclature schemes based on genetic diversity and biological significance. Genomic composition-based machine learning methods have recently performed well in identifying phenotype-genotype relationships. We introduced a framework involving dinucleotide (DNT) composition representation (DCR) to parse the general human adaptation of RNA viruses and applied a three-dimensional convolutional neural network (3D CNN) analysis to learn the human adaptation of other existing coronaviruses (CoVs) and predict the adaptation of SARS-CoV-2 variants of concern (VOCs). A markedly separable, linear DCR distribution was observed in two major genes-receptor-binding glycoprotein and RNA-dependent RNA polymerase (RdRp)-of six families of single-stranded (ssRNA) viruses. Additionally, there was a general host-specific distribution of both the spike proteins and RdRps of CoVs. The 3D CNN based on spike DCR predicted a dominant type II adaptation of most Beta, Delta and Omicron VOCs, with high transmissibility and low pathogenicity. Type I adaptation with opposite transmissibility and pathogenicity was predicted for SARS-CoV-2 Alpha VOCs (77%) and Kappa variants of interest (58%). The identified adaptive determinants included D1118H and A570D mutations and local DNTs. Thus, the 3D CNN model based on DCR features predicts SARS-CoV-2, a major type II human adaptation and is qualified to predict variant adaptation in real time, facilitating the risk-assessment of emerging SARS-CoV-2 variants and COVID-19 control.

SARS-CoV-2 is a novel positive-sense single-stranded RNA virus from the Coronaviridae family (genus Betacoronavirus), which has been established as causing the COVID-19 pandemic. The genome of SARS-CoV-2 is one of the largest among known RNA viruses, comprising of at least 26 known protein-coding loci. Studies thus far have outlined the coding capacity of the positive-sense strand of the SARS-CoV-2 genome, which can be used directly for protein translation. However, it has been recently shown that transcribed negative-sense viral RNA intermediates that arise during viral genome replication from positive-sense viruses can also code for proteins. No studies have yet explored the potential for negative-sense SARS-CoV-2 RNA intermediates to contain protein-coding loci. Thus, using sequence and structure-based bioinformatics methodologies, we have investigated the presence and validity of putative negative-sense ORFs (nsORFs) in the SARS-CoV-2 genome. Nine nsORFs were discovered to contain strong eukaryotic translation initiation signals and high codon adaptability scores, and several of the nsORFs were predicted to interact with RNA-binding proteins. Evolutionary conservation analyses indicated that some of the nsORFs are deeply conserved among related coronaviruses. Three-dimensional protein modeling revealed the presence of higher order folding among all putative SARS-CoV-2 nsORFs, and subsequent structural mimicry analyses suggest similarity of the nsORFs to DNA/RNA-binding proteins and proteins involved in immune signaling pathways. Altogether, these results suggest the potential existence of still undescribed SARS-CoV-2 proteins, which may play an important role in the viral lifecycle and COVID-19 pathogenesis.

Identifying the potential compound-protein interactions (CPIs) plays an essential role in drug development. The computational approaches for CPI prediction can reduce time and costs of experimental methods and have benefited from the continuously improved graph representation learning. However, most of the network-based methods use heterogeneous graphs, which is challenging due to their complex structures and heterogeneous attributes. Therefore, in this work, we transformed the compound-protein heterogeneous graph to a homogeneous graph by integrating the ligand-based protein representations and overall similarity associations. We then proposed an Inductive Graph AggrEgator-based framework, named CPI-IGAE, for CPI prediction. CPI-IGAE learns the low-dimensional representations of compounds and proteins from the homogeneous graph in an end-to-end manner. The results show that CPI-IGAE performs better than some state-of-the-art methods. Further ablation study and visualization of embeddings reveal the advantages of the model architecture and its role in feature extraction, and some of the top ranked CPIs by CPI-IGAE have been validated by a review of recent literature. The data and source codes are available at https://github.com/wanxiaozhe/CPI-IGAE.

BACKGROUND: The long reads of the third-generation sequencing significantly benefit the quality of the de novo genome assembly. However, its relatively high single-base error rate has been criticized. Currently, sequencing accuracy and throughput continue to improve, and many advanced tools are constantly emerging. PacBio HiFi sequencing and Oxford Nanopore Technologies (ONT) PromethION are two up-to-date platforms with low error rates and ultralong high-throughput reads. Therefore, it is urgently needed to select the appropriate sequencing platforms, depths and genome assembly tools for high-quality genomes in the era of explosive data production. METHODS: We performed 455 (7 assemblers with 4 polishing pipelines or without polishing on 13 subsets with different depths) and 88 (4 assemblers with or without polishing on 11 subsets with different depths) de novo assemblies of Yeast S288C on high-coverage ONT and HiFi datasets, respectively. The assembly quality was evaluated by Quality Assessment Tool (QUAST), Benchmarking Universal Single-Copy Orthologs (BUSCO) and the newly proposed Comprehensive_score (C_score). In addition, we applied four preferable pipelines to assemble the genome of nonreference yeast strains. RESULTS: The assembler plays an essential role in genome construction, especially for low-depth datasets. For ONT datasets, Flye is superior to other tools through C_score evaluation. Polishing by Pilon and Medaka improve accuracy and continuity of the preassemblies, respectively, and their combination pipeline worked well in most quality metrics. For HiFi datasets, Flye and NextDenovo performed better than other tools, and polishing is also necessary. Enough data depth is required for high-quality genome construction by ONT (>80X) and HiFi (>20X) datasets.

MOTIVATION: Interaction between transcription factor (TF) and its target genes establishes the knowledge foundation for biological researches in transcriptional regulation, the number of which is, however, still limited by biological techniques. Existing computational methods relevant to the prediction of TF-target interactions are mostly proposed for predicting binding sites, rather than directly predicting the interactions. To this end, we propose here a graph attention-based autoencoder model to predict TF-target gene interactions using the information of the known TF-target gene interaction network combined with two sequential and chemical gene characters, considering that the unobserved interactions between transcription factors and target genes can be predicted by learning the pattern of the known ones. To the best of our knowledge, the proposed model is the first attempt to solve this problem by learning patterns from the known TF-target gene interaction network. RESULTS: In this paper, we formulate the prediction task of TF-target gene interactions as a link prediction problem on a complex knowledge graph and propose a deep learning model called GraphTGI, which is composed of a graph attention-based encoder and a bilinear decoder. We evaluated the prediction performance of the proposed method on a real dataset, and the experimental results show that the proposed model yields outstanding performance with an average AUC value of 0.8864 +/- 0.0057 in the 5-fold cross-validation. It is anticipated that the GraphTGI model can effectively and efficiently predict TF-target gene interactions on a large scale. AVAILABILITY: Python code and the datasets used in our studies are made available at https://github.com/YanghanWu/GraphTGI.

Host-pathogen protein interactions (HPPIs) play vital roles in many biological processes and are directly involved in infectious diseases. With the outbreak of more frequent pandemics in the last couple of decades, such as the recent outburst of Covid-19 causing millions of deaths, it has become more critical to develop advanced methods to accurately predict pathogen interactions with their respective hosts. During the last decade, experimental methods to identify HPIs have been used to decipher host-pathogen systems with the caveat that those techniques are labor-intensive, expensive and time-consuming. Alternatively, accurate prediction of HPIs can be performed by the use of data-driven machine learning. To provide a more robust and accurate solution for the HPI prediction problem, we have developed a deepHPI tool based on deep learning. The web server delivers four host-pathogen model types: plant-pathogen, human-bacteria, human-virus and animal-pathogen, leveraging its operability to a wide range of analyses and cases of use. The deepHPI web tool is the first to use convolutional neural network models for HPI prediction. These models have been selected based on a comprehensive evaluation of protein features and neural network architectures. The best prediction models have been tested on independent validation datasets, which achieved an overall Matthews correlation coefficient value of 0.87 for animal-pathogen using the combined pseudo-amino acid composition and conjoint triad (PAAC_CT) features, 0.75 for human-bacteria using the combined pseudo-amino acid composition, conjoint triad and normalized Moreau-Broto feature (PAAC_CT_NMBroto), 0.96 for human-virus using PAAC_CT_NMBroto and 0.94 values for plant-pathogen interactions using the combined pseudo-amino acid composition, composition and transition feature (PAAC_CTDC_CTDT). Our server running deepHPI is deployed on a high-performance computing cluster that enables large and multiple user requests, and it provides more information about interactions discovered. It presents an enriched visualization of the resulting host-pathogen networks that is augmented with external links to various protein annotation resources. We believe that the deepHPI web server will be very useful to researchers, particularly those working on infectious diseases. Additionally, many novel and known host-pathogen systems can be further investigated to significantly advance our understanding of complex disease-causing agents. The developed models are established on a web server, which is freely accessible at http://bioinfo.usu.edu/deepHPI/.

The three-dimensional organization of chromatin plays a critical role in gene regulation. Recently developed technologies, such as HiChIP and proximity ligation-assisted ChIP-Seq (PLAC-seq) (hereafter referred to as HP for brevity), can measure chromosome spatial organization by interrogating chromatin interactions mediated by a protein of interest. While offering cost-efficiency over genome-wide unbiased high-throughput chromosome conformation capture (Hi-C) data, HP data remain sparse at kilobase (Kb) resolution with the current sequencing depth in the order of 108 reads per sample. Deep learning models, including HiCPlus, HiCNN, HiCNN2, DeepHiC and Variationally Encoded Hi-C Loss Enhancer (VEHiCLE), have been developed to enhance the sequencing depth of Hi-C data, but their performance on HP data has not been benchmarked. Here, we performed a comprehensive evaluation of HP data sequencing depth enhancement using models developed for Hi-C data. Specifically, we analyzed various HP data, including Smc1a HiChIP data of the human lymphoblastoid cell line GM12878, H3K4me3 PLAC-seq data of four human neural cell types as well as of mouse embryonic stem cells (mESC), and mESC CCCTC-binding factor (CTCF) PLAC-seq data. Our evaluations lead to the following three findings: (i) most models developed for Hi-C data achieve reasonable performance when applied to HP data (e.g. with Pearson correlation ranging 0.76-0.95 for pairs of loci within 300 Kb), and the enhanced datasets lead to improved statistical power for detecting long-range chromatin interactions, (ii) models trained on HP data outperform those trained on Hi-C data and (iii) most models are transferable across cell types. Our results provide a general guideline for HP data enhancement using existing methods designed for Hi-C data.

Drug-drug interactions (DDIs) are known as the main cause of life-threatening adverse events, and their identification is a key task in drug development. Existing computational algorithms mainly solve this problem by using advanced representation learning techniques. Though effective, few of them are capable of performing their tasks on biomedical knowledge graphs (KGs) that provide more detailed information about drug attributes and drug-related triple facts. In this work, an attention-based KG representation learning framework, namely DDKG, is proposed to fully utilize the information of KGs for improved performance of DDI prediction. In particular, DDKG first initializes the representations of drugs with their embeddings derived from drug attributes with an encoder-decoder layer, and then learns the representations of drugs by recursively propagating and aggregating first-order neighboring information along top-ranked network paths determined by neighboring node embeddings and triple facts. Last, DDKG estimates the probability of being interacting for pairwise drugs with their representations in an end-to-end manner. To evaluate the effectiveness of DDKG, extensive experiments have been conducted on two practical datasets with different sizes, and the results demonstrate that DDKG is superior to state-of-the-art algorithms on the DDI prediction task in terms of different evaluation metrics across all datasets.

Pathway enrichment analysis has become a widely used knowledge-based approach for the interpretation of biomedical data. Its popularity has led to an explosion of both enrichment methods and pathway databases. While the elegance of pathway enrichment lies in its simplicity, multiple factors can impact the results of such an analysis, which may not be accounted for. Researchers may fail to give influential aspects their due, resorting instead to popular methods and gene set collections, or default settings. Despite ongoing efforts to establish set guidelines, meaningful results are still hampered by a lack of consensus or gold standards around how enrichment analysis should be conducted. Nonetheless, such concerns have prompted a series of benchmark studies specifically focused on evaluating the influence of various factors on pathway enrichment results. In this review, we organize and summarize the findings of these benchmarks to provide a comprehensive overview on the influence of these factors. Our work covers a broad spectrum of factors, spanning from methodological assumptions to those related to prior biological knowledge, such as pathway definitions and database choice. In doing so, we aim to shed light on how these aspects can lead to insignificant, uninteresting or even contradictory results. Finally, we conclude the review by proposing future benchmarks as well as solutions to overcome some of the challenges, which originate from the outlined factors.

Molecular property prediction models based on machine learning algorithms have become important tools to triage unpromising lead molecules in the early stages of drug discovery. Compared with the mainstream descriptor- and graph-based methods for molecular property predictions, SMILES-based methods can directly extract molecular features from SMILES without human expert knowledge, but they require more powerful algorithms for feature extraction and a larger amount of data for training, which makes SMILES-based methods less popular. Here, we show the great potential of pre-training in promoting the predictions of important pharmaceutical properties. By utilizing three pre-training tasks based on atom feature prediction, molecular feature prediction and contrastive learning, a new pre-training method K-BERT, which can extract chemical information from SMILES like chemists, was developed. The calculation results on 15 pharmaceutical datasets show that K-BERT outperforms well-established descriptor-based (XGBoost) and graph-based (Attentive FP and HRGCN+) models. In addition, we found that the contrastive learning pre-training task enables K-BERT to 'understand' SMILES not limited to canonical SMILES. Moreover, the general fingerprints K-BERT-FP generated by K-BERT exhibit comparative predictive power to MACCS on 15 pharmaceutical datasets and can also capture molecular size and chirality information that traditional binary fingerprints cannot capture. Our results illustrate the great potential of K-BERT in the practical applications of molecular property predictions in drug discovery.

Each type of cancer usually has several subtypes with distinct clinical implications, and therefore the discovery of cancer subtypes is an important and urgent task in disease diagnosis and therapy. Using single-omics data to predict cancer subtypes is difficult because genomes are dysregulated and complicated by multiple molecular mechanisms, and therefore linking cancer genomes to cancer phenotypes is not an easy task. Using multi-omics data to effectively predict cancer subtypes is an area of much interest; however, integrating multi-omics data is challenging. Here, we propose a novel method of multi-omics data integration for clustering to identify cancer subtypes (MDICC) that integrates new affinity matrix and network fusion methods. Our experimental results show the effectiveness and generalization of the proposed MDICC model in identifying cancer subtypes, and its performance was better than those of currently available state-of-the-art clustering methods. Furthermore, the survival analysis demonstrates that MDICC delivered comparable or even better results than many typical integrative methods.

Limitations of bulk sequencing techniques on cell heterogeneity and diversity analysis have been pushed with the development of single-cell RNA-sequencing (scRNA-seq). To detect clusters of cells is a key step in the analysis of scRNA-seq. However, the high-dimensionality of scRNA-seq data and the imbalances in the number of different subcellular types are ubiquitous in real scRNA-seq data sets, which poses a huge challenge to the single-cell-type detection.We propose a meta-learning-based model, SiaClust, which is the combination of Siamese Convolutional Neural Network (CNN) and improved spectral clustering, to achieve scRNA-seq cell type detection. To be specific, with the help of the constrained Sigmoid kernel, the raw high-dimensionality data is mapped to a low-dimensional space, and the Siamese CNN learns the differences between the cell types in the low-dimensional feature space. The similarity matrix learned by Siamese CNN is used in combination with improved spectral clustering and t-distribution Stochastic Neighbor Embedding (t-SNE) for visualization. SiaClust highlights the differences between cell types by comparing the similarity of the samples, whereas blurring the differences within the cell types is better in processing high-dimensional and imbalanced data. SiaClust significantly improves clustering accuracy by using data generated by nine different species and tissues through different scNA-seq protocols for extensive evaluation, as well as analogies to state-of-the-art single-cell clustering models. More importantly, SiaClust accurately locates the exact site of dropout gene, and is more flexible with data size and cell type.

Gene Ontology (GO) is widely used in the biological domain. It is the most comprehensive ontology providing formal representation of gene functions (GO concepts) and relations between them. However, unintentional quality defects (e.g. missing or erroneous relations) in GO may exist due to the large size of GO concepts and complexity of GO structures. Such quality defects would impact the results of GO-based analyses and applications. In this work, we introduce a novel evidence-based lexical pattern approach for quality assurance of GO relations. We leverage two layers of evidence to suggest potentially missing relations in GO as follows. We first utilize related concept pairs (i.e. existing relations) in GO to extract relationship-specific lexical patterns, which serve as the first layer evidence to automatically suggest potentially missing relations between unrelated concept pairs. For each suggested missing relation, we further identify two other existing relations as the second layer of evidence that resemble the difference between the missing relation and the existing relation based on which the missing relation is suggested. Applied to the 15 December 2021 release of GO, this approach suggested a total of 866 potentially missing relations. Local domain experts evaluated the entire set of potentially missing relations, and identified 821 as missing relations and 45 indicate erroneous existing relations. We submitted these findings to the GO consortium for further validation and received encouraging feedback. These indicate that our evidence-based approach can be utilized to uncover missing relations and erroneous existing relations in GO.

Immune checkpoint inhibitors (ICIs) have completely changed the approach pertaining to tumor diagnostics and treatment. Similarly, immunotherapy has also provided much needed data about mutation, expression and prognosis, affording an unprecedented opportunity for discovering candidate drug targets and screening for immunotherapy-relevant biomarkers. Although existing web tools enable biologists to analyze the expression, mutation and prognostic data of tumors, they are currently unable to facilitate data mining and mechanism analyses specifically related to immunotherapy. Thus, we effectively developed our own web-based tool, called Comprehensive Analysis on Multi-Omics of Immunotherapy in Pan-cancer (CAMOIP), in which we are able to successfully screen various prognostic markers and analyze the mechanisms involved in biomarker expression and function, as well as immunotherapy. The analyses include information relevant to survival analysis, expression analysis, mutational landscape analysis, immune infiltration analysis, immunogenicity analysis and pathway enrichment analysis. This comprehensive analysis of biomarkers for immunotherapy can be carried out by a click of CAMOIP, and the software should greatly encourage the further development of immunotherapy. CAMOIP provides invaluable evidence that bridges the information between the data of cancer genomics based on immunotherapy, providing comprehensive information to users and assisting in making the value of current ICI-treated data available to all users. CAMOIP is available at https://www.camoip.net.

With the advances in sequencing technologies, a huge amount of biological data is extracted nowadays. Analyzing this amount of data is beyond the ability of human beings, creating a splendid opportunity for machine learning methods to grow. The methods, however, are practical only when the sequences are converted into feature vectors. Many tools target this task including iLearnPlus, a Python-based tool which supports a rich set of features. In this paper, we propose a holistic tool that extracts features from biological sequences (i.e. DNA, RNA and Protein). These features are the inputs to machine learning models that predict properties, structures or functions of the input sequences. Our tool not only supports all features in iLearnPlus but also 30 additional features which exist in the literature. Moreover, our tool is based on R language which makes an alternative for bioinformaticians to transform sequences into feature vectors. We have compared the conversion time of our tool with that of iLearnPlus: we transform the sequences much faster. We convert small nucleotides by a median of 2.8X faster, while we outperform iLearnPlus by a median of 6.3X for large sequences. Finally, in amino acids, our tool achieves a median speedup of 23.9X.

The single-cell multiomics technologies provide an unprecedented opportunity to study the cellular heterogeneity from different layers of transcriptional regulation. However, the datasets generated from these technologies tend to have high levels of noise, making data analysis challenging. Here, we propose jointly semi-orthogonal nonnegative matrix factorization (JSNMF), which is a versatile toolkit for the integrative analysis of transcriptomic and epigenomic data profiled from the same cell. JSNMF enables data visualization and clustering of the cells and also facilitates downstream analysis, including the characterization of markers and functional pathway enrichment analysis. The core of JSNMF is an unsupervised method based on JSNMF, where it assumes different latent variables for the two molecular modalities, and integrates the information of transcriptomic and epigenomic data with consensus graph fusion, which better tackles the distinct characteristics and levels of noise across different molecular modalities in single-cell multiomics data. We applied JSNMF to single-cell multiomics datasets from different tissues and different technologies. The results demonstrate the superior performance of JSNMF in clustering and data visualization of the cells. JSNMF also allows joint analysis of multiple single-cell multiomics experiments and single-cell multiomics data with more than two modalities profiled on the same cell. JSNMF also provides rich biological insight on the markers, cell-type-specific region-gene associations and the functions of the identified cell subpopulation.

Computational methods have been widely applied to resolve various core issues in drug discovery, such as molecular property prediction. In recent years, a data-driven computational method-deep learning had achieved a number of impressive successes in various domains. In drug discovery, graph neural networks (GNNs) take molecular graph data as input and learn graph-level representations in non-Euclidean space. An enormous amount of well-performed GNNs have been proposed for molecular graph learning. Meanwhile, efficient use of molecular data during training process, however, has not been paid enough attention. Curriculum learning (CL) is proposed as a training strategy by rearranging training queue based on calculated samples' difficulties, yet the effectiveness of CL method has not been determined in molecular graph learning. In this study, inspired by chemical domain knowledge and task prior information, we proposed a novel CL-based training strategy to improve the training efficiency of molecular graph learning, called CurrMG. Consisting of a difficulty measurer and a training scheduler, CurrMG is designed as a plug-and-play module, which is model-independent and easy-to-use on molecular data. Extensive experiments demonstrated that molecular graph learning models could benefit from CurrMG and gain noticeable improvement on five GNN models and eight molecular property prediction tasks (overall improvement is 4.08%). We further observed CurrMG's encouraging potential in resource-constrained molecular property prediction. These results indicate that CurrMG can be used as a reliable and efficient training strategy for molecular graph learning. Availability: The source code is available in https://github.com/gu-yaowen/CurrMG.

Liquid chromatography-mass spectrometry-based quantitative proteomics can measure the expression of thousands of proteins from biological samples and has been increasingly applied in cancer research. Identifying differentially expressed proteins (DEPs) between tumors and normal controls is commonly used to investigate carcinogenesis mechanisms. While differential expression analysis (DEA) at an individual level is desired to identify patient-specific molecular defects for better patient stratification, most statistical DEP analysis methods only identify deregulated proteins at the population level. To date, robust individualized DEA algorithms have been proposed for ribonucleic acid data, but their performance on proteomics data is underexplored. Herein, we performed a systematic evaluation on five individualized DEA algorithms for proteins on cancer proteomic datasets from seven cancer types. Results show that the within-sample relative expression orderings (REOs) of protein pairs in normal tissues were highly stable, providing the basis for individualized DEA for proteins using REOs. Moreover, individualized DEA algorithms achieve higher precision in detecting sample-specific deregulated proteins than population-level methods. To facilitate the utilization of individualized DEA algorithms in proteomics for prognostic biomarker discovery and personalized medicine, we provide Individualized DEP Analysis IDEPAXMBD (XMBD: Xiamen Big Data, a biomedical open software initiative in the National Institute for Data Science in Health and Medicine, Xiamen University, China.) (https://github.com/xmuyulab/IDEPA-XMBD), which is a user-friendly and open-source Python toolkit that integrates individualized DEA algorithms for DEP-associated deregulation pattern recognition.

Coronavirus disease 2019 pandemic continues globally with a growing number of infections, but there are currently no effective antibody drugs against the virus. In addition, 90% amino acid sequence identity between the S2 subunit of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and SARS-CoV S proteins attracts us to examine S2-targeted cross-neutralizing antibodies that are not yet well defined. We therefore immunized RenMab mice with the full-length S protein and constructed a high-throughput antibody discovery method based on single-cell sequencing technology to isolate SARS-CoV-2 S-targeted neutralizing antibodies and cross-neutralizing antibodies against the S2 region of SARS-CoV-2/SARS-CoV S. Diversity of antibody sequences in RenMab mice and consistency in B-cell immune responses between RenMab mice and humans enabled screening of fully human virus-neutralizing antibodies. From all the frequency >1 paired clonotypes obtained from single-cell V(D)J sequencing, 215 antibodies with binding affinities were identified and primarily bound S2. However, only two receptor-binding domain-targeted clonotypes had neutralizing activity against SARS-CoV-2. Moreover, 5' single-cell RNA sequencing indicated that these sorted splenic B cells are mainly plasmablasts, germinal center (GC)-dependent memory B-cells and GC B-cells. Among them, plasmablasts and GC-dependent memory B-cells were considered the most significant possibility of producing virus-specific antibodies. Altogether, using a high-throughput single cell-based antibody discovery approach, our study highlighted the challenges of developing S2-binding neutralizing antibodies against SARS-CoV-2 and provided a novel direction for the enrichment of antigen-specific B-cells.

Network medicine provides network theoretical tools, methods and properties to study underlying laws governing human interactome to identify disease states and disease complexity leading to drug discovery. Within this framework, we investigated the topological properties of ovarian cancer network (OCN) and the roles of hubs to understand OCN organization to address disease states and complexity. The OCN constructed from the experimentally verified genes exhibits fractal nature in the topological properties with deeply rooted functional communities indicating self-organizing behavior. The network properties at all levels of organization obey one parameter scaling law which lacks centrality lethality rule. We showed that $\langle k\rangle $ can be taken as a scaling parameter, where, power law exponent can be estimated from the ratio of network diameters. The betweenness centrality $C_B$ shows two distinct behaviors one shown by high degree hubs and the other by segregated low degree nodes. The $C_B$ power law exponent is found to connect the exponents of distributions of high and low degree nodes. OCN showed the absence of rich-club formation which leads to the missing of a number of attractors in the network causing formation of weakly tied diverse functional modules to keep optimal network efficiency. In OCN, provincial and connector hubs, which includes identified key regulators, take major responsibility to keep the OCN integrity and organization. Further, most of the key regulators are found to be over expressed and positively correlated with immune infiltrates. Finally, few potential drugs are identified related to the key regulators.

Synthetic lethality (SL) occurs between two genes when the inactivation of either gene alone has no effect on cell survival but the inactivation of both genes results in cell death. SL-based therapy has become one of the most promising targeted cancer therapies in the last decade as PARP inhibitors achieve great success in the clinic. The key point to exploiting SL-based cancer therapy is the identification of robust SL pairs. Although many wet-lab-based methods have been developed to screen SL pairs, known SL pairs are less than 0.1% of all potential pairs due to large number of human gene combinations. Computational prediction methods complement wet-lab-based methods to effectively reduce the search space of SL pairs. In this paper, we review the recent applications of computational methods and commonly used databases for SL prediction. First, we introduce the concept of SL and its screening methods. Second, various SL-related data resources are summarized. Then, computational methods including statistical-based methods, network-based methods, classical machine learning methods and deep learning methods for SL prediction are summarized. In particular, we elaborate on the negative sampling methods applied in these models. Next, representative tools for SL prediction are introduced. Finally, the challenges and future work for SL prediction are discussed.

Characterizing RNA structures and functions have mostly been focused on 2D, secondary and 3D, tertiary structures. Recent advances in experimental and computational techniques for probing or predicting RNA solvent accessibility make this 1D representation of tertiary structures an increasingly attractive feature to explore. Here, we provide a survey of these recent developments, which indicate the emergence of solvent accessibility as a simple 1D property, adding to secondary and tertiary structures for investigating complex structure-function relations of RNAs.

We propose TWO-SIGMA-G, a competitive gene set test for scRNA-seq data. TWO-SIGMA-G uses a mixed-effects regression model based on our previously published TWO-SIGMA to test for differential expression at the gene-level. This regression-based model provides flexibility and rigor at the gene-level in (1) handling complex experimental designs, (2) accounting for the correlation between biological replicates and (3) accommodating the distribution of scRNA-seq data to improve statistical inference. Moreover, TWO-SIGMA-G uses a novel approach to adjust for inter-gene-correlation (IGC) at the set-level to control the set-level false positive rate. Simulations demonstrate that TWO-SIGMA-G preserves type-I error and increases power in the presence of IGC compared with other methods. Application to two datasets identified HIV-associated interferon pathways in xenograft mice and pathways associated with Alzheimer's disease progression in humans.

There are a large number of unannotated proteins with unknown functions in rice, which are difficult to be verified by biological experiments. Therefore, computational method is one of the mainstream methods for rice proteins function prediction. Two representative rice proteins, indica protein and japonica protein, are selected as the experimental dataset. In this paper, two feature extraction methods (the residue couple model method and the pseudo amino acid composition method) and the Principal Component Analysis method are combined to design protein descriptive features. Moreover, based on the state-of-the-art MIML algorithm EnMIMLNN, a novel MIML learning framework MK-EnMIMLNN is proposed. And the MK-EnMIMLNN algorithm is designed by learning multiple kernel fusion function neural network. The experimental results show that the hybrid feature extraction method is better than the single feature extraction method. More importantly, the MK-EnMIMLNN algorithm is superior to most classic MIML learning algorithms, which proves the effectiveness of the MK-EnMIMLNN algorithm in rice proteins function prediction.

MOTIVATION: MicroRNAs (miRNAs), as critical regulators, are involved in various fundamental and vital biological processes, and their abnormalities are closely related to human diseases. Predicting disease-related miRNAs is beneficial to uncovering new biomarkers for the prevention, detection, prognosis, diagnosis and treatment of complex diseases. RESULTS: In this study, we propose a multi-view Laplacian regularized deep factorization machine (DeepFM) model, MLRDFM, to predict novel miRNA-disease associations while improving the standard DeepFM. Specifically, MLRDFM improves DeepFM from two aspects: first, MLRDFM takes the relationships among items into consideration by regularizing their embedding features via their similarity-based Laplacians. In this study, miRNA Laplacian regularization integrates four types of miRNA similarity, while disease Laplacian regularization integrates two types of disease similarity. Second, to judiciously train our model, Laplacian eigenmaps are utilized to initialize the weights in the dense embedding layer. The experimental results on the latest HMDD v3.2 dataset show that MLRDFM improves the performance and reduces the overfitting phenomenon of DeepFM. Besides, MLRDFM is greatly superior to the state-of-the-art models in miRNA-disease association prediction in terms of different evaluation metrics with the 5-fold cross-validation. Furthermore, case studies further demonstrate the effectiveness of MLRDFM.

Mutations, which result in amino acid substitutions, influence the stability of proteins and their binding to biomolecules. A molecular understanding of the effects of protein mutations is both of biotechnological and medical relevance. Empirical free energy functions that quickly estimate the free energy change upon mutation (ΔΔG) can be exploited for systematic screenings of proteins and protein complexes. In silico saturation mutagenesis can guide the design of new experiments or rationalize the consequences of known mutations. Often software such as FoldX, while fast and reliable, lack the necessary automation features to apply them in a high-throughput manner. We introduce MutateX, a software to automate the prediction of ΔΔGs associated with the systematic mutation of each residue within a protein, or protein complex to all other possible residue types, using the FoldX energy function. MutateX also supports ΔΔG calculations over protein ensembles, upon post-translational modifications and in multimeric assemblies. At the heart of MutateX lies an automated pipeline engine that handles input preparation, parallelization and outputs publication-ready figures. We illustrate the MutateX protocol applied to different case studies. The results of the high-throughput scan provided by our tools can help in different applications, such as the analysis of disease-associated mutations, to complement experimental deep mutational scans, or assist the design of variants for industrial applications. MutateX is a collection of Python tools that relies on open-source libraries. It is available free of charge under the GNU General Public License from https://github.com/ELELAB/mutatex.

Combinational pharmacotherapy with the synergistic/additive effect is a powerful treatment strategy for complex diseases such as malignancies. Identifying synergistic combinations with various compounds and structures requires testing a large number of compound combinations. However, in practice, examining different compounds by in vivo and in vitro approaches is costly, infeasible and challenging. In the last decades, significant success has been achieved by expanding computational methods in different pharmacological and bioinformatics domains. As promising tools, computational approaches such as machine learning algorithms (MLAs) are used for prioritizing combinational pharmacotherapies. This review aims to provide the models developed to predict synergistic drug combinations in cancer by MLAs with various information, including gene expression, protein-protein interactions, metabolite interactions, pathways and pharmaceutical information such as chemical structure, molecular descriptor and drug-target interactions.

Consensus partitioning is an unsupervised method widely used in high-throughput data analysis for revealing subgroups and assigning stability for the classification. However, standard consensus partitioning procedures are weak for identifying large numbers of stable subgroups. There are two major issues. First, subgroups with small differences are difficult to be separated if they are simultaneously detected with subgroups with large differences. Second, stability of classification generally decreases as the number of subgroups increases. In this work, we proposed a new strategy to solve these two issues by applying consensus partitioning in a hierarchical procedure. We demonstrated hierarchical consensus partitioning can be efficient to reveal more meaningful subgroups. We also tested the performance of hierarchical consensus partitioning on revealing a great number of subgroups with a large deoxyribonucleic acid methylation dataset. The hierarchical consensus partitioning is implemented in the R package cola with comprehensive functionalities for analysis and visualization. It can also automate the analysis only with a minimum of two lines of code, which generates a detailed HTML report containing the complete analysis. The cola package is available at https://bioconductor.org/packages/cola/.

Determining drug indications is a critical part of the drug development process. However, traditional drug discovery is expensive and time-consuming. Drug repositioning aims to find potential indications for existing drugs, which is considered as an important alternative to the traditional drug discovery. In this article, we propose a multi-view learning with matrix completion (MLMC) method to predict the potential associations between drugs and diseases. Specifically, MLMC first learns the comprehensive similarity matrices from five drug similarity matrices and two disease similarity matrices based on the multi-view learning (ML) with Laplacian graph regularization, and updates the drug-disease association matrix simultaneously. Then, we introduce matrix completion (MC) to add some positive entries in original association matrix based on low-rank structure, and re-execute the multi-view learning algorithm for association prediction. At last, the prediction results of the above two operations are integrated as the final output. Evaluated by 10-fold cross-validation and de novo tests, MLMC achieves higher prediction accuracy than the current state-of-the-art methods. Moreover, case studies confirm the ability of our method in novel drug-disease association discovery. The codes of MLMC are available at https://github.com/BioinformaticsCSU/MLMC. Contact: jxwang@mail.csu.edu.cn.

Although remarkable achievements, such as AlphaFold2, have been made in end-to-end structure prediction, fragment libraries remain essential for de novo protein structure prediction, which can help explore and understand the protein-folding mechanism. In this work, we developed a variable-length fragment library (VFlib). In VFlib, a master structure database was first constructed from the Protein Data Bank through sequence clustering. The hidden Markov model (HMM) profile of each protein in the master structure database was generated by HHsuite, and the secondary structure of each protein was calculated by DSSP. For the query sequence, the HMM-profile was first constructed. Then, variable-length fragments were retrieved from the master structure database through dynamically variable-length profile-profile comparison. A complete method for chopping the query HMM-profile during this process was proposed to obtain fragments with increased diversity. Finally, secondary structure information was used to further screen the retrieved fragments to generate the final fragment library of specific query sequence. The experimental results obtained with a set of 120 nonredundant proteins show that the global precision and coverage of the fragment library generated by VFlib were 55.04% and 94.95% at the RMSD cutoff of 1.5 Å, respectively. Compared with the benchmark method of NNMake, the global precision of our fragment library had increased by 62.89% with equivalent coverage. Furthermore, the fragments generated by VFlib and NNMake were used to predict structure models through fragment assembly. Controlled experimental results demonstrate that the average TM-score of VFlib was 16.00% higher than that of NNMake.

Accurate prediction of drug-target interactions (DTIs) can reduce the cost and time of drug repositioning and drug discovery. Many current methods integrate information from multiple data sources of drug and target to improve DTIs prediction accuracy. However, these methods do not consider the complex relationship between different data sources. In this study, we propose a novel computational framework, called MccDTI, to predict the potential DTIs by multiview network embedding, which can integrate the heterogenous information of drug and target. MccDTI learns high-quality low-dimensional representations of drug and target by preserving the consistent and complementary information between multiview networks. Then MccDTI adopts matrix completion scheme for DTIs prediction based on drug and target representations. Experimental results on two datasets show that the prediction accuracy of MccDTI outperforms four state-of-the-art methods for DTIs prediction. Moreover, literature verification for DTIs prediction shows that MccDTI can predict the reliable potential DTIs. These results indicate that MccDTI can provide a powerful tool to predict new DTIs and accelerate drug discovery. The code and data are available at: https://github.com/ShangCS/MccDTI.

Drug resistance is a major threat to the global health and a significant concern throughout the clinical treatment of diseases and drug development. The mutation in proteins that is related to drug binding is a common cause for adaptive drug resistance. Therefore, quantitative estimations of how mutations would affect the interaction between a drug and the target protein would be of vital significance for the drug development and the clinical practice. Computational methods that rely on molecular dynamics simulations, Rosetta protocols, as well as machine learning methods have been proven to be capable of predicting ligand affinity changes upon protein mutation. However, the severely limited sample size and heavy noise induced overfitting and generalization issues have impeded wide adoption of machine learning for studying drug resistance. In this paper, we propose a robust machine learning method, termed SPLDExtraTrees, which can accurately predict ligand binding affinity changes upon protein mutation and identify resistance-causing mutations. Especially, the proposed method ranks training data following a specific scheme that starts with easy-to-learn samples and gradually incorporates harder and diverse samples into the training, and then iterates between sample weight recalculations and model updates. In addition, we calculate additional physics-based structural features to provide the machine learning model with the valuable domain knowledge on proteins for these data-limited predictive tasks. The experiments substantiate the capability of the proposed method for predicting kinase inhibitor resistance under three scenarios and achieve predictive accuracy comparable with that of molecular dynamics and Rosetta methods with much less computational costs.

Single-particle cryo-electron microscopy (cryo-EM) has become one of the mainstream technologies in the field of structural biology to determine the three-dimensional (3D) structures of biological macromolecules. Heterogeneous cryo-EM projection image classification is an effective way to discover conformational heterogeneity of biological macromolecules in different functional states. However, due to the low signal-to-noise ratio of the projection images, the classification of heterogeneous cryo-EM projection images is a very challenging task. In this paper, two novel distance measures between projection images integrating the reliability of common lines, pixel intensity and class averages are designed, and then a two-stage spectral clustering algorithm based on the two distance measures is proposed for heterogeneous cryo-EM projection image classification. In the first stage, the novel distance measure integrating common lines and pixel intensities of projection images is used to obtain preliminary classification results through spectral clustering. In the second stage, another novel distance measure integrating the first novel distance measure and class averages generated from each group of projection images is used to obtain the final classification results through spectral clustering. The proposed two-stage spectral clustering algorithm is applied on a simulated and a real cryo-EM dataset for heterogeneous reconstruction. Results show that the two novel distance measures can be used to improve the classification performance of spectral clustering, and using the proposed two-stage spectral clustering algorithm can achieve higher classification and reconstruction accuracy than using RELION and XMIPP.

With recent advances in high-throughput next-generation sequencing, it is possible to describe the regulation and expression of genes at multiple levels. An assay for transposase-accessible chromatin using sequencing (ATAC-seq), which uses Tn5 transposase to sequence protein-free binding regions of the genome, can be combined with chromatin immunoprecipitation coupled with deep sequencing (ChIP-seq) and ribonucleic acid sequencing (RNA-seq) to provide a detailed description of gene expression. Here, we reviewed the literature on ATAC-seq and described the characteristics of ATAC-seq publications. We then briefly introduced the principles of RNA-seq, ChIP-seq and ATAC-seq, focusing on the main features of the techniques. We built a phylogenetic tree from species that had been previously studied by using ATAC-seq. Studies of Mus musculus and Homo sapiens account for approximately 90% of the total ATAC-seq data, while other species are still in the process of accumulating data. We summarized the findings from human diseases and other species, illustrating the cutting-edge discoveries and the role of multi-omics data analysis in current research. Moreover, we collected and compared ATAC-seq analysis pipelines, which allowed biological researchers who lack programming skills to better analyze and explore ATAC-seq data. Through this review, it is clear that multi-omics analysis and single-cell sequencing technology will become the mainstream approach in future research.

Coronavirus disease 2019 (COVID-19) is a global pandemic and there is an urgent need to discover the therapy for COVID-19. In our original article, we first obtained the target proteins of acupuncture and related target genes of COVID-19 by searching English and Chinese databases, then Gene Ontology biological processes and enrichment analysis were performed on the overlapping targets of acupuncture with COVID-19. Moreover, the compound-target and compound-disease-target network was constructed. This is an innovative attempt to predict the potential benefits of acupuncture treatment for COVID-19. In this letter, we answered reader Zheng's comments.

Data analysis is a critical part of quantitative proteomics studies in interpreting biological questions. Numerous computational tools for protein quantification, imputation and differential expression (DE) analysis were generated in the past decade and the search for optimal tools is still going on. Moreover, due to the rapid development of RNA sequencing (RNA-seq) technology, a vast number of DE analysis methods were created for that purpose. The applicability of these newly developed RNA-seq-oriented tools to proteomics data remains in doubt. In order to benchmark these analysis methods, a proteomics dataset consisting of proteins derived from humans, yeast and drosophila, in defined ratios, was generated in this study. Based on this dataset, DE analysis tools, including microarray- and RNA-seq-based ones, imputation algorithms and protein quantification methods were compared and benchmarked. Furthermore, applying these approaches to two public datasets showed that RNA-seq-based DE tools achieved higher accuracy (ACC) in identifying DEPs. This study provides useful guidelines for analyzing quantitative proteomics datasets. All the methods used in this study were integrated into the Perseus software, version 2.0.3.0, which is available at https://www.maxquant.org/perseus.

Integrated modelling of biological systems is becoming a necessity for constructing models containing the major biochemical processes of such systems in order to obtain a holistic understanding of their dynamics and to elucidate emergent behaviours. Hybrid modelling methods are crucial to achieve integrated modelling of biological systems. This paper reviews currently popular hybrid modelling methods, developed for systems biology, mainly revealing why they are proposed, how they are formed from single modelling formalisms and how to simulate them. By doing this, we identify future research requirements regarding hybrid approaches for further promoting integrated modelling of biological systems.