Recently, lysine lactylation (Kla), a novel post-translational modification (PTM), which can be stimulated by lactate, has been found to regulate gene expression and life activities. Therefore, it is imperative to accurately identify Kla sites. Currently, mass spectrometry is the fundamental method for identifying PTM sites. However, it is expensive and time-consuming to achieve this through experiments alone. Herein, we proposed a novel computational model, Auto-Kla, to quickly and accurately predict Kla sites in gastric cancer cells based on automated machine learning (AutoML). With stable and reliable performance, our model outperforms the recently published model in the 10-fold cross-validation. To investigate the generalizability and transferability of our approach, we evaluated the performance of our models trained on two other widely studied types of PTM, including phosphorylation sites in host cells infected with SARS-CoV-2 and lysine crotonylation sites in HeLa cells. The results show that our models achieve comparable or better performance than current outstanding models. We believe that this method will become a useful analytical tool for PTM prediction and provide a reference for the future development of related models. The web server and source code are available at http://tubic.org/Kla and https://github.com/tubic/Auto-Kla, respectively.

Protein phosphorylation, one of the main protein post-translational modifications, is required for regulating various life activities. Kinases and phosphatases that regulate protein phosphorylation in humans have been targeted to treat various diseases, particularly cancer. High-throughput experimental methods to discover protein phosphosites are laborious and time-consuming. The burgeoning databases and predictors provide essential infrastructure to the research community. To date, >60 publicly available phosphorylation databases and predictors each have been developed. In this review, we have comprehensively summarized the status and applicability of major online phosphorylation databases and predictors, thereby helping researchers rapidly select tools that are most suitable for their projects. Moreover, the organizational strategies and limitations of these databases and predictors have been highlighted, which may facilitate the development of better protein phosphorylation predictors in silico.

Protein-protein interactions (PPIs) play crucial roles in almost all biological processes from cell-signaling and membrane transport to metabolism and immune systems. Efficient characterization of PPIs at the molecular level is key to the fundamental understanding of PPI mechanisms. Even with the gigantic amount of PPI models from graphs, networks, geometry and topology, it remains as a great challenge to design functional models that efficiently characterize the complicated multiphysical information within PPIs. Here we propose persistent Tor-algebra (PTA) model for a unified algebraic representation of the multiphysical interactions. Mathematically, our PTA is inherently algebraic data analysis. In our PTA model, protein structures and interactions are described as a series of face rings and Tor modules, from which PTA model is developed. The multiphysical information within/between biomolecules are implicitly characterized by PTA and further represented as PTA barcodes. To test our PTA models, we consider PTA-based ensemble learning for PPI binding affinity prediction. The two most commonly used datasets, i.e. SKEMPI and AB-Bind, are employed. It has been found that our model outperforms all the existing models as far as we know. Mathematically, our PTA model provides a highly efficient way for the characterization of molecular structures and interactions.

Precisely calling chromatin loops has profound implications for further analysis of gene regulation and disease mechanisms. Technological advances in chromatin conformation capture (3C) assays make it possible to identify chromatin loops in the genome. However, a variety of experimental protocols have resulted in different levels of biases, which require distinct methods to call true loops from the background. Although many bioinformatics tools have been developed to address this problem, there is still a lack of special introduction to loop-calling algorithms. This review provides an overview of the loop-calling tools for various 3C-based techniques. We first discuss the background biases produced by different experimental techniques and the denoising algorithms. Then, the completeness and priority of each tool are categorized and summarized according to the data source of application. The summary of these works can help researchers select the most appropriate method to call loops and further perform downstream analysis. In addition, this survey is also useful for bioinformatics scientists aiming to develop new loop-calling algorithms.

Protein-protein interactions (PPIs) carry out the cellular processes of all living organisms. Experimental methods for PPI detection suffer from high cost and false-positive rate, hence efficient computational methods are highly desirable for facilitating PPI detection. In recent years, benefiting from the enormous amount of protein data produced by advanced high-throughput technologies, machine learning models have been well developed in the field of PPI prediction. In this paper, we present a comprehensive survey of the recently proposed machine learning-based prediction methods. The machine learning models applied in these methods and details of protein data representation are also outlined. To understand the potential improvements in PPI prediction, we discuss the trend in the development of machine learning-based methods. Finally, we highlight potential directions in PPI prediction, such as the use of computationally predicted protein structures to extend the data source for machine learning models. This review is supposed to serve as a companion for further improvements in this field.

Single-cell ribonucleic acid (RNA)-sequencing (scRNA-seq) is a powerful tool to study cellular heterogeneity. The high dimensional data generated from this technology are complex and require specialized expertise for analysis and interpretation. The core of scRNA-seq data analysis contains several key analytical steps, which include pre-processing, quality control, normalization, dimensionality reduction, integration and clustering. Each step often has many algorithms developed with varied underlying assumptions and implications. With such a diverse choice of tools available, benchmarking analyses have compared their performances and demonstrated that tools operate differentially according to the data types and complexity. Here, we present Integrated Benchmarking scRNA-seq Analytical Pipeline (IBRAP), which contains a suite of analytical components that can be interchanged throughout the pipeline alongside multiple benchmarking metrics that enable users to compare results and determine the optimal pipeline combinations for their data. We apply IBRAP to single- and multi-sample integration analysis using primary pancreatic tissue, cancer cell line and simulated data accompanied with ground truth cell labels, demonstrating the interchangeable and benchmarking functionality of IBRAP. Our results confirm that the optimal pipelines are dependent on individual samples and studies, further supporting the rationale and necessity of our tool. We then compare reference-based cell annotation with unsupervised analysis, both included in IBRAP, and demonstrate the superiority of the reference-based method in identifying robust major and minor cell types. Thus, IBRAP presents a valuable tool to integrate multiple samples and studies to create reference maps of normal and diseased tissues, facilitating novel biological discovery using the vast volume of scRNA-seq data available.

Advances in spatial transcriptomics enlarge the use of single cell technologies to unveil the expression landscape of the tissues with valuable spatial context. Here, we propose an unsupervised and manifold learning-based algorithm, Spatial Transcriptome based cEll typE cLustering (STEEL), which identifies domains from spatial transcriptome by clustering beads exhibiting both highly similar gene expression profiles and close spatial distance in the manner of graphs. Comprehensive evaluation of STEEL on spatial transcriptomic datasets from 10X Visium platform demonstrates that it not only achieves a high resolution to characterize fine structures of mouse brain but also enables the integration of multiple tissue slides individually analyzed into a larger one. STEEL outperforms previous methods to effectively distinguish different cell types/domains of various tissues on Slide-seq datasets, featuring in higher bead density but lower transcript detection efficiency. Application of STEEL on spatial transcriptomes of early-stage mouse embryos (E9.5-E12.5) successfully delineates a progressive development landscape of tissues from ectoderm, mesoderm and endoderm layers, and further profiles dynamic changes on cell differentiation in heart and other organs. With the advancement of spatial transcriptome technologies, our method will have great applicability on domain identification and gene expression atlas reconstruction.

Proteomic studies characterize the protein composition of complex biological samples. Despite recent advancements in mass spectrometry instrumentation and computational tools, low proteome coverage and interpretability remains a challenge. To address this, we developed Proteome Support Vector Enrichment (PROSE), a fast, scalable and lightweight pipeline for scoring proteins based on orthogonal gene co-expression network matrices. PROSE utilizes simple protein lists as input, generating a standard enrichment score for all proteins, including undetected ones. In our benchmark with 7 other candidate prioritization techniques, PROSE shows high accuracy in missing protein prediction, with scores correlating strongly to corresponding gene expression data. As a further proof-of-concept, we applied PROSE to a reanalysis of the Cancer Cell Line Encyclopedia proteomics dataset, where it captures key phenotypic features, including gene dependency. We lastly demonstrated its applicability on a breast cancer clinical dataset, showing clustering by annotated molecular subtype and identification of putative drivers of triple-negative breast cancer. PROSE is available as a user-friendly Python module from https://github.com/bwbio/PROSE.

Brain imaging genomics is an emerging interdisciplinary field, where integrated analysis of multimodal medical image-derived phenotypes (IDPs) and multi-omics data, bridging the gap between macroscopic brain phenotypes and their cellular and molecular characteristics. This approach aims to better interpret the genetic architecture and molecular mechanisms associated with brain structure, function and clinical outcomes. More recently, the availability of large-scale imaging and multi-omics datasets from the human brain has afforded the opportunity to the discovering of common genetic variants contributing to the structural and functional IDPs of the human brain. By integrative analyses with functional multi-omics data from the human brain, a set of critical genes, functional genomic regions and neuronal cell types have been identified as significantly associated with brain IDPs. Here, we review the recent advances in the methods and applications of multi-omics integration in brain imaging analysis. We highlight the importance of functional genomic datasets in understanding the biological functions of the identified genes and cell types that are associated with brain IDPs. Moreover, we summarize well-known neuroimaging genetics datasets and discuss challenges and future directions in this field.

Accurate and effective drug-target interaction (DTI) prediction can greatly shorten the drug development lifecycle and reduce the cost of drug development. In the deep-learning-based paradigm for predicting DTI, robust drug and protein feature representations and their interaction features play a key role in improving the accuracy of DTI prediction. Additionally, the class imbalance problem and the overfitting problem in the drug-target dataset can also affect the prediction accuracy, and reducing the consumption of computational resources and speeding up the training process are also critical considerations. In this paper, we propose shared-weight-based MultiheadCrossAttention, a precise and concise attention mechanism that can establish the association between target and drug, making our models more accurate and faster. Then, we use the cross-attention mechanism to construct two models: MCANet and MCANet-B. In MCANet, the cross-attention mechanism is used to extract the interaction features between drugs and proteins for improving the feature representation ability of drugs and proteins, and the PolyLoss loss function is applied to alleviate the overfitting problem and the class imbalance problem in the drug-target dataset. In MCANet-B, the robustness of the model is improved by combining multiple MCANet models and prediction accuracy further increases. We train and evaluate our proposed methods on six public drug-target datasets and achieve state-of-the-art results. In comparison with other baselines, MCANet saves considerable computational resources while maintaining accuracy in the leading position; however, MCANet-B greatly improves prediction accuracy by combining multiple models while maintaining a balance between computational resource consumption and prediction accuracy.

Metagenome assembly is an efficient approach to reconstruct microbial genomes from metagenomic sequencing data. Although short-read sequencing has been widely used for metagenome assembly, linked- and long-read sequencing have shown their advancements in assembly by providing long-range DNA connectedness. Many metagenome assembly tools were developed to simplify the assembly graphs and resolve the repeats in microbial genomes. However, there remains no comprehensive evaluation of metagenomic sequencing technologies, and there is a lack of practical guidance on selecting the appropriate metagenome assembly tools. This paper presents a comprehensive benchmark of 19 commonly used assembly tools applied to metagenomic sequencing datasets obtained from simulation, mock communities or human gut microbiomes. These datasets were generated using mainstream sequencing platforms, such as Illumina and BGISEQ short-read sequencing, 10x Genomics linked-read sequencing, and PacBio and Oxford Nanopore long-read sequencing. The assembly tools were extensively evaluated against many criteria, which revealed that long-read assemblers generated high contig contiguity but failed to reveal some medium- and high-quality metagenome-assembled genomes (MAGs). Linked-read assemblers obtained the highest number of overall near-complete MAGs from the human gut microbiomes. Hybrid assemblers using both short- and long-read sequencing were promising methods to improve both total assembly length and the number of near-complete MAGs. This paper also discussed the running time and peak memory consumption of these assembly tools and provided practical guidance on selecting them.

The discovery of drug-target interactions (DTIs) is a pivotal process in pharmaceutical development. Computational approaches are a promising and efficient alternative to tedious and costly wet-lab experiments for predicting novel DTIs from numerous candidates. Recently, with the availability of abundant heterogeneous biological information from diverse data sources, computational methods have been able to leverage multiple drug and target similarities to boost the performance of DTI prediction. Similarity integration is an effective and flexible strategy to extract crucial information across complementary similarity views, providing a compressed input for any similarity-based DTI prediction model. However, existing similarity integration methods filter and fuse similarities from a global perspective, neglecting the utility of similarity views for each drug and target. In this study, we propose a Fine-Grained Selective similarity integration approach, called FGS, which employs a local interaction consistency-based weight matrix to capture and exploit the importance of similarities at a finer granularity in both similarity selection and combination steps. We evaluate FGS on five DTI prediction datasets under various prediction settings. Experimental results show that our method not only outperforms similarity integration competitors with comparable computational costs, but also achieves better prediction performance than state-of-the-art DTI prediction approaches by collaborating with conventional base models. Furthermore, case studies on the analysis of similarity weights and on the verification of novel predictions confirm the practical ability of FGS.

Sampling circulating tumor DNA (ctDNA) using liquid biopsies offers clinically important benefits for monitoring cancer progression. A single ctDNA sample represents a mixture of shed tumor DNA from all known and unknown lesions within a patient. Although shedding levels have been suggested to hold the key to identifying targetable lesions and uncovering treatment resistance mechanisms, the amount of DNA shed by any one specific lesion is still not well characterized. We designed the Lesion Shedding Model (LSM) to order lesions from the strongest to the poorest shedding for a given patient. By characterizing the lesion-specific ctDNA shedding levels, we can better understand the mechanisms of shedding and more accurately interpret ctDNA assays to improve their clinical impact. We verified the accuracy of the LSM under controlled conditions using a simulation approach as well as testing the model on three cancer patients. The LSM obtained an accurate partial order of the lesions according to their assigned shedding levels in simulations and its accuracy in identifying the top shedding lesion was not significantly impacted by number of lesions. Applying LSM to three cancer patients, we found that indeed there were lesions that consistently shed more than others into the patients' blood. In two of the patients, the top shedding lesion was one of the only clinically progressing lesions at the time of biopsy suggesting a connection between high ctDNA shedding and clinical progression. The LSM provides a much needed framework with which to understand ctDNA shedding and to accelerate discovery of ctDNA biomarkers. The LSM source code has been available in the IBM BioMedSciAI Github (https://github.com/BiomedSciAI/Geno4SD).

Copy number alterations (CNAs) are a predominant source of genetic alterations in human cancer and play an important role in cancer progression. However comprehensive understanding of the mutational processes and signatures of CNA is still lacking. Here we developed a mechanism-agnostic method to categorize CNA based on various fragment properties, which reflect the consequences of mutagenic processes and can be extracted from different types of data, including whole genome sequencing (WGS) and single nucleotide polymorphism (SNP) array. The 14 signatures of CNA have been extracted from 2778 pan-cancer analysis of whole genomes WGS samples, and further validated with 10 851 the cancer genome atlas SNP array dataset. Novel patterns of CNA have been revealed through this study. The activities of some CNA signatures consistently predict cancer patients' prognosis. This study provides a repertoire for understanding the signatures of CNA in cancer, with potential implications for cancer prognosis, evolution and etiology.

The preprocessed initial files that feed the molecular dynamics (MD) simulation packages dramatically influence the outcome of the simulations. However, the popular MD simulation packages depend, to a great extent, on the user's experience in the preparation of MD simulation systems. In this work, we present an easy-to-use tool called MDBuilder, a PyMOL plugin that assists researchers in building the starting structures for multiple popular MD simulation packages. MDBuilder is not only designed to assist MD beginners to overcome the steep learning curve by providing a menu-oriented, point-and-click user graphic interface (GUI), but also to provide an alternative way to prepare the input files for some highly scalable CHARMM force field-based MD simulation packages. The platform-independent GUI is implemented as a PyMOL plugin using the Python language, and it has been tested on Windows and Linux platforms. The source code and documentation of MDBuilder can be downloaded freely from https://github.com/HuiLiuCode/MDBuilder under the GNU General Public License.

Phosphorylation is an essential mechanism for regulating protein activities. Determining kinase-specific phosphorylation sites by experiments involves time-consuming and expensive analyzes. Although several studies proposed computational methods to model kinase-specific phosphorylation sites, they typically required abundant experimentally verified phosphorylation sites to yield reliable predictions. Nevertheless, the number of experimentally verified phosphorylation sites for most kinases is relatively small, and the targeting phosphorylation sites are still unidentified for some kinases. In fact, there is little research related to these understudied kinases in the literature. Thus, this study aims to create predictive models for these understudied kinases. A kinase-kinase similarity network was generated by merging the sequence-, functional-, protein-domain- and 'STRING'-related similarities. Thus, besides sequence data, protein-protein interactions and functional pathways were also considered to aid predictive modelling. This similarity network was then integrated with a classification of kinase groups to yield highly similar kinases to a specific understudied type of kinase. Their experimentally verified phosphorylation sites were leveraged as positive sites to train predictive models. The experimentally verified phosphorylation sites of the understudied kinase were used for validation. Results demonstrate that 82 out of 116 understudied kinases were predicted with adequate performance via the proposed modelling strategy, achieving a balanced accuracy of 0.81, 0.78, 0.84, 0.84, 0.85, 0.82, 0.90, 0.82 and 0.85, for the 'TK', 'Other', 'STE', 'CAMK', 'TKL', 'CMGC', 'AGC', 'CK1' and 'Atypical' groups, respectively. Therefore, this study demonstrates that web-like predictive networks can reliably capture the underlying patterns in such understudied kinases by harnessing relevant sources of similarities to predict their specific phosphorylation sites.

Potential miRNA-disease associations (MDA) play an important role in the discovery of complex human disease etiology. Therefore, MDA prediction is an attractive research topic in the field of biomedical machine learning. Recently, several models have been proposed for this task, but their performance limited by over-reliance on relevant network information with noisy graph structure connections. However, the application of self-supervised graph structure learning to MDA tasks remains unexplored. Our study is the first to use multi-view self-supervised contrastive learning (MSGCL) for MDA prediction. Specifically, we generated a learner view without association labels of miRNAs and diseases as input, and utilized the known association network to generate an anchor view that provides guiding signals for the learner view. The graph structure was optimized by designing a contrastive loss to maximize the consistency between the anchor and learner views. Our model is similar to a pre-trained model that continuously optimizes upstream tasks for high-quality association graph topology, thereby enhancing the latent representation of association predictions. The experimental results show that our proposed method outperforms state-of-the-art methods by 2.79$\%$ and 3.20$\%$ in area under the receiver operating characteristic curve (AUC) and area under the precision/recall curve (AUPR), respectively.

With the emergence of multidrug-resistant bacteria, antimicrobial peptides (AMPs) offer promising options for replacing traditional antibiotics to treat bacterial infections, but discovering and designing AMPs using traditional methods is a time-consuming and costly process. Deep learning has been applied to the de novo design of AMPs and address AMP classification with high efficiency. In this study, several natural language processing models were combined to design and identify AMPs, i.e. sequence generative adversarial nets, bidirectional encoder representations from transformers and multilayer perceptron. Then, six candidate AMPs were screened by AlphaFold2 structure prediction and molecular dynamic simulations. These peptides show low homology with known AMPs and belong to a novel class of AMPs. After initial bioactivity testing, one of the peptides, A-222, showed inhibition against gram-positive and gram-negative bacteria. The structural analysis of this novel peptide A-222 obtained by nuclear magnetic resonance confirmed the presence of an alpha-helix, which was consistent with the results predicted by AlphaFold2. We then performed a structure-activity relationship study to design a new series of peptide analogs and found that the activities of these analogs could be increased by 4-8-fold against Stenotrophomonas maltophilia WH 006 and Pseudomonas aeruginosa PAO1. Overall, deep learning shows great potential in accelerating the discovery of novel AMPs and holds promise as an important tool for developing novel AMPs.

The use of stable isotope tracers and mass spectrometry (MS) is the gold standard method for the analysis of fatty acid (FA) metabolism. Yet, current state-of-the-art tools provide limited and difficult-to-interpret information about FA biosynthetic routes. Here we present FAMetA, an R package and a web-based application (www.fameta.es) that uses 13C mass isotopologue profiles to estimate FA import, de novo lipogenesis, elongation and desaturation in a user-friendly platform. The FAMetA workflow covers the required functionalities needed for MS data analyses. To illustrate its utility, different in vitro and in vivo experimental settings are used in which FA metabolism is modified. Thanks to the comprehensive characterization of FA biosynthesis and the easy-to-interpret graphical representations compared to previous tools, FAMetA discloses unnoticed insights into how cells reprogram their FA metabolism and, when combined with FASN, SCD1 and FADS2 inhibitors, it enables the identification of new FAs by the metabolic reconstruction of their synthesis route.

Bioinformatics analysis and visualization of high-throughput gene expression data require extensive computer programming skills, posing a bottleneck for many wet-lab scientists. In this work, we present an intuitive user-friendly platform for gene expression data analysis and visualization called FungiExpresZ. FungiExpresZ aims to help wet-lab scientists with little to no knowledge of computer programming to become self-reliant in bioinformatics analysis and generating publication-ready figures. The platform contains many commonly used data analysis tools and an extensive collection of pre-processed public ribonucleic acid sequencing (RNA-seq) datasets of many fungal species, including important human, plant and insect pathogens. Users may analyse their data alone or in combination with public RNA-seq data for an integrated analysis. The FungiExpresZ platform helps wet-lab scientists to overcome their limitations in genomics data analysis and can be applied to analyse data of any organism. FungiExpresZ is available as an online web-based tool (https://cparsania.shinyapps.io/FungiExpresZ/) and an offline R-Shiny package (https://github.com/cparsania/FungiExpresZ).

The adaptive immune response to foreign antigens is initiated by T-cell receptor (TCR) recognition on the antigens. Recent experimental advances have enabled the generation of a large amount of TCR data and their cognate antigenic targets, allowing machine learning models to predict the binding specificity of TCRs. In this work, we present TEINet, a deep learning framework that utilizes transfer learning to address this prediction problem. TEINet employs two separately pretrained encoders to transform TCR and epitope sequences into numerical vectors, which are subsequently fed into a fully connected neural network to predict their binding specificities. A major challenge for binding specificity prediction is the lack of a unified approach to sampling negative data. Here, we first assess the current negative sampling approaches comprehensively and suggest that the Unified Epitope is the most suitable one. Subsequently, we compare TEINet with three baseline methods and observe that TEINet achieves an average AUROC of 0.760, which outperforms baseline methods by 6.4-26%. Furthermore, we investigate the impacts of the pretraining step and notice that excessive pretraining may lower its transferability to the final prediction task. Our results and analysis show that TEINet can make an accurate prediction using only the TCR sequence (CDR3$\beta $) and the epitope sequence, providing novel insights to understand the interactions between TCRs and epitopes.

Drug-target interaction (DTI) prediction can identify novel ligands for specific protein targets, and facilitate the rapid screening of effective new drug candidates to speed up the drug discovery process. However, the current methods are not sensitive enough to complex topological structures, and complicated relations between multiple node types are not fully captured yet. To address the above challenges, we construct a metapath-based heterogeneous bioinformatics network, and then propose a DTI prediction method with metapath-based hierarchical transformer and attention network for drug-target interaction prediction (MHTAN-DTI), applying metapath instance-level transformer, single-semantic attention and multi-semantic attention to generate low-dimensional vector representations of drugs and proteins. Metapath instance-level transformer performs internal aggregation on the metapath instances, and models global context information to capture long-range dependencies. Single-semantic attention learns the semantics of a certain metapath type, introduces the central node weight and assigns different weights to different metapath instances to obtain the semantic-specific node embedding. Multi-semantic attention captures the importance of different metapath types and performs weighted fusion to attain the final node embedding. The hierarchical transformer and attention network weakens the influence of noise data on the DTI prediction results, and enhances the robustness and generalization ability of MHTAN-DTI. Compared with the state-of-the-art DTI prediction methods, MHTAN-DTI achieves significant performance improvements. In addition, we also conduct sufficient ablation studies and visualize the experimental results. All the results demonstrate that MHTAN-DTI can offer a powerful and interpretable tool for integrating heterogeneous information to predict DTIs and provide new insights into drug discovery.

Drug resistance is one of principal limiting factors for cancer treatment. Several mechanisms, especially mutation, have been validated to implicate in drug resistance. In addition, drug resistance is heterogeneous, which makes an urgent need to explore the personalized driver genes of drug resistance. Here, we proposed an approach DRdriver to identify drug resistance driver genes in individual-specific network of resistant patients. First, we identified the differential mutations for each resistant patient. Next, the individual-specific network, which included the genes with differential mutations and their targets, was constructed. Then, the genetic algorithm was utilized to identify the drug resistance driver genes, which regulated the most differentially expressed genes and the least non-differentially expressed genes. In total, we identified 1202 drug resistance driver genes for 8 cancer types and 10 drugs. We also demonstrated that the identified driver genes were mutated more frequently than other genes and tended to be associated with the development of cancer and drug resistance. Based on the mutational signatures of all driver genes and enriched pathways of driver genes in brain lower grade glioma treated by temozolomide, the drug resistance subtypes were identified. Additionally, the subtypes showed great diversity in epithelial-mesenchyme transition, DNA damage repair and tumor mutation burden. In summary, this study developed a method DRdriver for identifying personalized drug resistance driver genes, which provides a framework for unlocking the molecular mechanism and heterogeneity of drug resistance.

Large-scale multiple perturbation experiments have the potential to reveal a more detailed understanding of the molecular pathways that respond to genetic and environmental changes. A key question in these studies is which gene expression changes are important for the response to the perturbation. This problem is challenging because (i) the functional form of the nonlinear relationship between gene expression and the perturbation is unknown and (ii) identification of the most important genes is a high-dimensional variable selection problem. To deal with these challenges, we present here a method based on the model-X knockoffs framework and Deep Neural Networks to identify significant gene expression changes in multiple perturbation experiments. This approach makes no assumptions on the functional form of the dependence between the responses and the perturbations and it enjoys finite sample false discovery rate control for the selected set of important gene expression responses. We apply this approach to the Library of Integrated Network-Based Cellular Signature data sets which is a National Institutes of Health Common Fund program that catalogs how human cells globally respond to chemical, genetic and disease perturbations. We identified important genes whose expression is directly modulated in response to perturbation with anthracycline, vorinostat, trichostatin-a, geldanamycin and sirolimus. We compare the set of important genes that respond to these small molecules to identify co-responsive pathways. Identification of which genes respond to specific perturbation stressors can provide better understanding of the underlying mechanisms of disease and advance the identification of new drug targets.

Emerging studies have shown that circular RNAs (circRNAs) are involved in a variety of biological processes and play a key role in disease diagnosing, treating and inferring. Although many methods, including traditional machine learning and deep learning, have been developed to predict associations between circRNAs and diseases, the biological function of circRNAs has not been fully exploited. Some methods have explored disease-related circRNAs based on different views, but how to efficiently use the multi-view data about circRNA is still not well studied. Therefore, we propose a computational model to predict potential circRNA-disease associations based on collaborative learning with circRNA multi-view functional annotations. First, we extract circRNA multi-view functional annotations and build circRNA association networks, respectively, to enable effective network fusion. Then, a collaborative deep learning framework for multi-view information is designed to get circRNA multi-source information features, which can make full use of the internal relationship among circRNA multi-view information. We build a network consisting of circRNAs and diseases by their functional similarity and extract the consistency description information of circRNAs and diseases. Last, we predict potential associations between circRNAs and diseases based on graph auto encoder. Our computational model has better performance in predicting candidate disease-related circRNAs than the existing ones. Furthermore, it shows the high practicability of the method that we use several common diseases as case studies to find some unknown circRNAs related to them. The experiments show that CLCDA can efficiently predict disease-related circRNAs and are helpful for the diagnosis and treatment of human disease.

The adaptive immune receptor repertoire (AIRR), consisting of T- and B-cell receptors, is the core component of the immune system. The AIRR sequencing is commonly used in cancer immunotherapy and minimal residual disease (MRD) detection of leukemia and lymphoma. The AIRR is captured by primers and sequenced to yield paired-end (PE) reads. The PE reads could be merged into one sequence by the overlapped region between them. However, the wide range of AIRR data raises the difficulty, so a special tool is required. We developed a software package for IMmune PE reads merger of sequencing data, named IMperm. We used the k-mer-and-vote strategy to pin down the overlapped region rapidly. IMperm could handle all types of PE reads, eliminate adapter contamination and successfully merge low-quality and minor/non-overlapping reads. Compared with existing tools, IMperm performed better in both simulated and sequencing data. Notably, IMperm was well suited to processing the data of MRD detection in leukemia and lymphoma and detected 19 novel MRD clones in 14 patients with leukemia from previously published data. Additionally, IMperm can handle PE reads from other sources, and we demonstrated its effectiveness on two genomic and one cell-free deoxyribonucleic acid datasets. IMperm is implemented in the C programming language and consumes little runtime and memory. It is freely available at https://github.com/zhangwei2015/IMperm.

Metagenomic sequencing (mNGS) is a powerful diagnostic tool to detect causative pathogens in clinical microbiological testing owing to its unbiasedness and substantially reduced costs. Rapid and accurate classification of metagenomic sequences is a critical procedure for pathogen identification in dry-lab step of mNGS test. However, clinical practices of the testing technology are hampered by the challenge of classifying sequences within a clinically relevant timeframe. Here, we present GPMeta, a novel GPU-accelerated approach to ultrarapid pathogen identification from complex mNGS data, allowing users to bypass this limitation. Using mock microbial community datasets and public real metagenomic sequencing datasets from clinical samples, we show that GPMeta has not only higher accuracy but also significantly higher speed than existing state-of-the-art tools such as Bowtie2, Bwa, Kraken2 and Centrifuge. Furthermore, GPMeta offers GPMetaC clustering algorithm, a statistical model for clustering and rescoring ambiguous alignments to improve the discrimination of highly homologous sequences from microbial genomes with average nucleotide identity >95%. GPMetaC exhibits higher precision and recall rate than others. GPMeta underlines its key role in the development of the mNGS test in infectious diseases that require rapid turnaround times. Further study will discern how to best and easily integrate GPMeta into routine clinical practices. GPMeta is freely accessible to non-commercial users at https://github.com/Bgi-LUSH/GPMeta.

Neuropeptides are a diverse and complex class of signaling molecules that regulate a variety of biological processes. Neuropeptides provide many opportunities for the discovery of new drugs and targets for the treatment of a wide range of diseases, and thus, computational tools for the rapid and accurate large-scale identification of neuropeptides are of great significance for peptide research and drug development. Although several machine learning-based prediction tools have been developed, there is room for improvement in the performance and interpretability of the proposed methods. In this work, we developed an interpretable and robust neuropeptide prediction model, named NeuroPred-PLM. First, we employed a language model (ESM) of proteins to obtain semantic representations of neuropeptides, which could reduce the complexity of feature engineering. Next, we adopted a multi-scale convolutional neural network to enhance the local feature representation of neuropeptide embeddings. To make the model interpretable, we proposed a global multi-head attention network that could be used to capture the position-wise contribution to neuropeptide prediction via the attention scores. In addition, NeuroPred-PLM was developed based on our newly constructed NeuroPep 2.0 database. Benchmarks based on the independent test set show that NeuroPred-PLM achieves superior predictive performance compared with other state-of-the-art predictors. For the convenience of researchers, we provide an easy-to-install PyPi package (https://pypi.org/project/NeuroPredPLM/) and a web server (https://huggingface.co/spaces/isyslab/NeuroPred-PLM).

In recent years, many experiments have proved that microRNAs (miRNAs) play a variety of important regulatory roles in cells, and their abnormal expression can lead to the emergence of specific diseases. Therefore, it is greatly valuable to do research on the association between miRNAs and diseases, which can effectively help prevent and treat miRNA-related diseases. At present, effective computational methods still need to be developed to better identify potential miRNA-disease associations. Inspired by graph convolutional networks, in this study, we propose a new method based on Attention aware Multi-view similarity networks and Hypergraph learning for MiRNA-Disease Associations identification (AMHMDA). First, we construct multiple similarity networks for miRNAs and diseases, and exploit the graph convolutional networks fusion attention mechanism to obtain the important information from different views. Then, in order to obtain high-quality links and richer nodes information, we introduce a kind of virtual nodes called hypernodes to construct heterogeneous hypergraph of miRNAs and diseases. Finally, we employ the attention mechanism to fuse the outputs of graph convolutional networks, predicting miRNA-disease associations. To verify the effectiveness of this method, we carry out a series of experiments on the Human MicroRNA Disease Database (HMDD v3.2). The experimental results show that AMHMDA has good performance compared with other methods. In addition, the case study results also fully demonstrate the reliable predictive performance of AMHMDA.

Recent technological and computational advances have made metagenomic assembly a viable approach to achieving high-resolution views of complex microbial communities. In previous benchmarking, short-read (SR) metagenomic assemblers had the highest accuracy, long-read (LR) assemblers generated the most contiguous sequences and hybrid (HY) assemblers balanced length and accuracy. However, no assessments have specifically compared the performance of these assemblers on low-abundance species, which include clinically relevant organisms in the gut. We generated semi-synthetic LR and SR datasets by spiking small and increasing amounts of Escherichia coli isolate reads into fecal metagenomes and, using different assemblers, examined E. coli contigs and the presence of antibiotic resistance genes (ARGs). For ARG assembly, although SR assemblers recovered more ARGs with high accuracy, even at low coverages, LR assemblies allowed for the placement of ARGs within longer, E. coli-specific contigs, thus pinpointing their taxonomic origin. HY assemblies identified resistance genes with high accuracy and had lower contiguity than LR assemblies. Each assembler type's strengths were maintained even when our isolate was spiked in with a competing strain, which fragmented and reduced the accuracy of all assemblies. For strain characterization and determining gene context, LR assembly is optimal, while for base-accurate gene identification, SR assemblers outperform other options. HY assembly offers contiguity and base accuracy, but requires generating data on multiple platforms, and may suffer high misassembly rates when strain diversity exists. Our results highlight the trade-offs associated with each approach for recovering low-abundance taxa, and that the optimal approach is goal-dependent.

Lysine 2-hydroxyisobutylation (Khib), which was first reported in 2014, has been shown to play vital roles in a myriad of biological processes including gene transcription, regulation of chromatin functions, purine metabolism, pentose phosphate pathway and glycolysis/gluconeogenesis. Identification of Khib sites in protein substrates represents an initial but crucial step in elucidating the molecular mechanisms underlying protein 2-hydroxyisobutylation. Experimental identification of Khib sites mainly depends on the combination of liquid chromatography and mass spectrometry. However, experimental approaches for identifying Khib sites are often time-consuming and expensive compared with computational approaches. Previous studies have shown that Khib sites may have distinct characteristics for different cell types of the same species. Several tools have been developed to identify Khib sites, which exhibit high diversity in their algorithms, encoding schemes and feature selection techniques. However, to date, there are no tools designed for predicting cell type-specific Khib sites. Therefore, it is highly desirable to develop an effective predictor for cell type-specific Khib site prediction. Inspired by the residual connection of ResNet, we develop a deep learning-based approach, termed ResNetKhib, which leverages both the one-dimensional convolution and transfer learning to enable and improve the prediction of cell type-specific 2-hydroxyisobutylation sites. ResNetKhib is capable of predicting Khib sites for four human cell types, mouse liver cell and three rice cell types. Its performance is benchmarked against the commonly used random forest (RF) predictor on both 10-fold cross-validation and independent tests. The results show that ResNetKhib achieves the area under the receiver operating characteristic curve values ranging from 0.807 to 0.901, depending on the cell type and species, which performs better than RF-based predictors and other currently available Khib site prediction tools. We also implement an online web server of the proposed ResNetKhib algorithm together with all the curated datasets and trained model for the wider research community to use, which is publicly accessible at https://resnetkhib.erc.monash.edu/.

The rapid development of single-cell RNA sequencing (scRNA-seq) technology allows us to study gene expression heterogeneity at the cellular level. Cell annotation is the basis for subsequent downstream analysis in single-cell data mining. As more and more well-annotated scRNA-seq reference data become available, many automatic annotation methods have sprung up in order to simplify the cell annotation process on unlabeled target data. However, existing methods rarely explore the fine-grained semantic knowledge of novel cell types absent from the reference data, and they are usually susceptible to batch effects on the classification of seen cell types. Taking into consideration the limitations above, this paper proposes a new and practical task called generalized cell type annotation and discovery for scRNA-seq data whereby target cells are labeled with either seen cell types or cluster labels, instead of a unified 'unassigned' label. To accomplish this, we carefully design a comprehensive evaluation benchmark and propose a novel end-to-end algorithmic framework called scGAD. Specifically, scGAD first builds the intrinsic correspondences on seen and novel cell types by retrieving geometrically and semantically mutual nearest neighbors as anchor pairs. Together with the similarity affinity score, a soft anchor-based self-supervised learning module is then designed to transfer the known label information from reference data to target data and aggregate the new semantic knowledge within target data in the prediction space. To enhance the inter-type separation and intra-type compactness, we further propose a confidential prototype self-supervised learning paradigm to implicitly capture the global topological structure of cells in the embedding space. Such a bidirectional dual alignment mechanism between embedding space and prediction space can better handle batch effect and cell type shift. Extensive results on massive simulation datasets and real datasets demonstrate the superiority of scGAD over various state-of-the-art clustering and annotation methods. We also implement marker gene identification to validate the effectiveness of scGAD in clustering novel cell types and their biological significance. To the best of our knowledge, we are the first to introduce this new and practical task and propose an end-to-end algorithmic framework to solve it. Our method scGAD is implemented in Python using the Pytorch machine-learning library, and it is freely available at https://github.com/aimeeyaoyao/scGAD.

Cell-state transition can reveal additional information from single-cell ribonucleic acid (RNA)-sequencing data in time-resolved biological phenomena. However, most of the current methods are based on the time derivative of the gene expression state, which restricts them to the short-term evolution of cell states. Here, we present single-cell State Transition Across-samples of RNA-seq data (scSTAR), which overcomes this limitation by constructing a paired-cell projection between biological conditions with an arbitrary time span by maximizing the covariance between two feature spaces using partial least square and minimum squared error methods. In mouse ageing data, the response to stress in CD4+ memory T cell subtypes was found to be associated with ageing. A novel Treg subtype characterized by mTORC activation was identified to be associated with antitumour immune suppression, which was confirmed by immunofluorescence microscopy and survival analysis in 11 cancers from The Cancer Genome Atlas Program. On melanoma data, scSTAR improved immunotherapy-response prediction accuracy from 0.8 to 0.96.

Immune checkpoint inhibitor (ICI) treatment has created the opportunity of improved outcome for patients with hepatocellular carcinoma (HCC). However, only a minority of HCC patients benefit from ICI treatment owing to poor treatment efficacy and safety concerns. There are few predictive factors that precisely stratify HCC responders to immunotherapy. In this study, we developed a tumour microenvironment risk (TMErisk) model to divide HCC patients into different immune subtypes and evaluated their prognosis. Our results indicated that virally mediated HCC patients who had more common tumour protein P53 (TP53) alterations with lower TMErisk scores were appropriate for ICI treatment. HCC patients with alcoholic hepatitis who more commonly harboured catenin beta 1 (CTNNB1) alterations with higher TMErisk scores could benefit from treatment with multi-tyrosine kinase inhibitors. The developed TMErisk model represents the first attempt to anticipate tumour tolerance of ICIs in the TME through the degree of immune infiltration in HCCs.

Discovering pre-microRNAs (miRNAs) is the core of miRNA discovery. Using traditional sequence/structural features, many tools have been published to discover miRNAs. However, in practical applications like genomic annotations, their actual performance has been very low. This becomes more grave in plants where unlike animals pre-miRNAs are much more complex and difficult to identify. A huge gap exists between animals and plants for the available software for miRNA discovery and species-specific miRNA information. Here, we present miWords, a composite deep learning system of transformers and convolutional neural networks which sees genome as a pool of sentences made of words with specific occurrence preferences and contexts, to accurately identify pre-miRNA regions across plant genomes. A comprehensive benchmarking was done involving >10 software representing different genre and many experimentally validated datasets. miWords emerged as the best one while breaching accuracy of 98% and performance lead of ~10%. miWords was also evaluated across Arabidopsis genome where also it outperformed the compared tools. As a demonstration, miWords was run across the tea genome, reporting 803 pre-miRNA regions, all validated by small RNA-seq reads from multiple samples, and most of them were functionally supported by the degradome sequencing data. miWords is freely available as stand-alone source codes at https://scbb.ihbt.res.in/miWords/index.php.

Alignment is the cornerstone of many long-read pipelines and plays an essential role in resolving structural variants (SVs). However, forced alignments of SVs embedded in long reads, inflexibility of integrating novel SVs models and computational inefficiency remain problems. Here, we investigate the feasibility of resolving long-read SVs with alignment-free algorithms. We ask: (1) Is it possible to resolve long-read SVs with alignment-free approaches? and (2) Does it provide an advantage over existing approaches? To this end, we implemented the framework named Linear, which can flexibly integrate alignment-free algorithms such as the generative model for long-read SV detection. Furthermore, Linear addresses the problem of compatibility of alignment-free approaches with existing software. It takes as input long reads and outputs standardized results existing software can directly process. We conducted large-scale assessments in this work and the results show that the sensitivity, and flexibility of Linear outperform alignment-based pipelines. Moreover, the computational efficiency is orders of magnitude faster.

MOTIVATION: With the rapid development of modern technologies, massive data are available for the systematic study of Alzheimer's disease (AD). Though many existing AD studies mainly focus on single-modality omics data, multi-omics datasets can provide a more comprehensive understanding of AD. To bridge this gap, we proposed a novel structural Bayesian factor analysis framework (SBFA) to extract the information shared by multi-omics data through the aggregation of genotyping data, gene expression data, neuroimaging phenotypes and prior biological network knowledge. Our approach can extract common information shared by different modalities and encourage biologically related features to be selected, guiding future AD research in a biologically meaningful way. METHOD: Our SBFA model decomposes the mean parameters of the data into a sparse factor loading matrix and a factor matrix, where the factor matrix represents the common information extracted from multi-omics and imaging data. Our framework is designed to incorporate prior biological network information. Our simulation study demonstrated that our proposed SBFA framework could achieve the best performance compared with the other state-of-the-art factor-analysis-based integrative analysis methods. RESULTS: We apply our proposed SBFA model together with several state-of-the-art factor analysis models to extract the latent common information from genotyping, gene expression and brain imaging data simultaneously from the ADNI biobank database. The latent information is then used to predict the functional activities questionnaire score, an important measurement for diagnosis of AD quantifying subjects' abilities in daily life. Our SBFA model shows the best prediction performance compared with the other factor analysis models. AVAILABILITY: Code are publicly available at https://github.com/JingxuanBao/SBFA. CONTACT: qlong@upenn.edu.

Interactions between Tumor microenvironment (TME) cells shape the unique growth environment, sustaining tumor growth and causing the immune escape of tumor cells. Nonetheless, no studies have reported a systematic analysis of cellular interactions in the identification of cancer-related TME cells. Here, we proposed a novel network-based computational method, named as iATMEcell, to identify the abnormal TME cells associated with the biological outcome of interest based on a cell-cell crosstalk network. In the method, iATMEcell first manually collected TME cell types from multiple published studies and obtained their corresponding gene signatures. Then, a weighted cell-cell crosstalk network was constructed in the context of a specific cancer bulk tissue transcriptome data, where the weight between cells reflects both their biological function similarity and the transcriptional dysregulated activities of gene signatures shared by them. Finally, it used a network propagation algorithm to identify significantly dysregulated TME cells. Using the cancer genome atlas (TCGA) Bladder Urothelial Carcinoma training set and two independent validation sets, we illustrated that iATMEcell could identify significant abnormal cells associated with patient survival and immunotherapy response. iATMEcell was further applied to a pan-cancer analysis, which revealed that four common abnormal immune cells play important roles in the patient prognosis across multiple cancer types. Collectively, we demonstrated that iATMEcell could identify potentially abnormal TME cells based on a cell-cell crosstalk network, which provided a new insight into understanding the effect of TME cells in cancer. iATMEcell is developed as an R package, which is freely available on GitHub (https://github.com/hanjunwei-lab/iATMEcell).