SUMMARY: Principal component analysis (PCA) is widely used in analyzing single-cell genomic data. Selecting the optimal number of PCs is a crucial step for downstream analyses. The elbow method is most commonly used for this task, but it requires one to visually inspect the elbow plot and manually choose the elbow point. To address this limitation, we developed six methods to automatically select the optimal number of PCs based on the elbow method. We evaluated the performance of these methods on real single-cell RNA-seq data from multiple human and mouse tissues and cell types. The perpendicular line method with 30 PCs has the best overall performance, and its results are highly consistent with the numbers of PCs identified manually. We implemented the six methods in an R package, findPC, that objectively selects the number of PCs and can be easily incorporated into any automatic analysis pipeline. AVAILABILITY AND IMPLEMENTATION: findPC R package is freely available at https://github.com/haotian-zhuang/findPC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Therapeutic peptide prediction is important for the discovery of efficient therapeutic peptides and drug development. Researchers have developed several computational methods to identify different therapeutic peptide types. However, these computational methods focus on identifying some specific types of therapeutic peptides, failing to predict the comprehensive types of therapeutic peptides. Moreover, it is still challenging to utilize different properties to predict the therapeutic peptides. RESULTS: In this study, an adaptive multi-view based on the tensor learning framework TPpred-ATMV is proposed for predicting different types of therapeutic peptides. TPpred-ATMV constructs the class and probability information based on various sequence features. We constructed the latent subspace among the multi-view features and constructed an auto-weighted multi-view tensor learning model to utilize the high correlation based on the multi-view features. Experimental results showed that the TPpred-ATMV is better than or highly comparable with the other state-of-the-art methods for predicting eight types of therapeutic peptides. AVAILABILITY: The code of TPpred-ATMV is accessed at: https://github.com/cokeyk/TPpred-ATMV. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Evaluating the blood-brain barrier (BBB) permeability of drug molecules is a critical step in brain drug development. Traditional methods for the evaluation require complicated in vitro or in vivo testing. Alternatively, in silico predictions based on machine learning have proved to be a cost-efficient way to complement the in vitro and in vivo methods. However, the performance of the established models has been limited by their incapability of dealing with the interactions between drugs and proteins, which play an important role in the mechanism behind the BBB penetrating behaviors. To address this limitation, we employed the relational graph convolutional network (RGCN) to handle the drug-protein interactions as well as the properties of each individual drug. RESULTS: The RGCN model achieved an overall accuracy of 0.872, an AUROC of 0.919 and an AUPRC of 0.838 for the testing dataset with the drug-protein interactions and the Mordred descriptors as the input. Introducing drug-drug similarity to connect structurally similar drugs in the data graph further improved the testing results, giving an overall accuracy of 0.876, an AUROC of 0.926 and an AUPRC of 0.865. In particular, the RGCN model was found to greatly outperform the LightGBM base model when evaluated with the drugs whose BBB penetration was dependent on drug-protein interactions. Our model is expected to provide high-confidence predictions of BBB permeability for drug prioritization in the experimental screening of BBB-penetrating drugs. AVAILABILITY: The data and the codes are freely available at https://github.com/dingyan20/BBB-Penetration-Prediction. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We developed BIODICA, an integrated computational environment for application of independent component analysis (ICA) to bulk and single-cell molecular profiles, interpretation of the results in terms of biological functions and correlation with metadata. The computational core is the novel Python package stabilized-ica which provides interface to several ICA algorithms, a stabilization procedure, meta-analysis and component interpretation tools. BIODICA is equipped with a user-friendly graphical user interface, allowing non-experienced users to perform the ICA-based omics data analysis. The results are provided in interactive ways, thus facilitating communication with biology experts. AVAILABILITY AND IMPLEMENTATION: BIODICA is implemented in Java, Python and JavaScript. The source code is freely available on GitHub under the MIT and the GNU LGPL licenses. BIODICA is supported on all major operating systems. URL: https://sysbio-curie.github.io/biodica-environment/.

MOTIVATION: Allelic expression analysis aids in detection of cis-regulatory mechanisms of genetic variation which produce allelic imbalance (AI) in heterozygotes. Measuring AI in bulk data lacking time or spatial resolution has the limitation that cell-type-specific (CTS), spatial-, or time-dependent AI signals may be dampened or not detected. RESULTS: We introduce a statistical method airpart for identifying differential CTS AI from single-cell RNA-sequencing (scRNA-seq) data, or other spatially- or time-resolved datasets. airpart outputs discrete partitions of data, pointing to groups of genes and cells under common mechanisms of cis-genetic regulation. In order to account for low counts in single-cell data, our method uses a Generalized Fused Lasso with Binomial likelihood for partitioning groups of cells by AI signal, and a hierarchical Bayesian model for AI statistical inference. In simulation, airpart accurately detected partitions of cell types by their AI and had lower RMSE of allelic ratio estimates than existing methods. In real data, airpart identified DAI patterns across cell states and could be used to define trends of AI signal over spatial or time axes. AVAILABILITY: The airpart package is available as an R/Bioconductor package at https://bioconductor.org/packages/airpart.

MOTIVATION: Drug repositioning is an attractive alternative to de novo drug discovery due to reduced time and costs to bring drugs to market. Computational repositioning methods, particularly non-black-box methods that can account for and predict a drug's mechanism, may provide great benefit for directing future development. By tuning both data and algorithm to utilize relationships important to drug mechanisms, a computational repositioning algorithm can be trained to both predict and explain mechanistically novel indications. RESULTS: In this work, we examined the 123 curated drug mechanism paths found in the drug mechanism database (DrugMechDB) and after identifying the most important relationships, we integrated 18 data sources to produce a heterogeneous knowledge graph, MechRepoNet, capable of capturing the information in these paths. We applied the Rephetio repurposing algorithm to MechRepoNet using only a subset of relationships known to be mechanistic in natureand found adequate predictive ability on an evaluation set with AUROC value of 0.83. The resulting repurposing model allowed us to prioritize paths in our knowledge graph to produce a predicted treatment mechanism. We found that DrugMechDB paths, when present in the network were rated highly among predicted mechanisms. We then demonstrated MechRepoNet's ability to use mechanistic insight to identify a drug's mechanistic target, with a mean reciprocal rank of 0.525 on a test set of known drug-target interactions. Finally, we walked through repurposing examples of the anti-cancer drug imatinib for use in the treatment of asthma, and metolazone for use in the treatment of osteoporosis, to demonstrate this method's utility in providing mechanistic insight into repurposing predictions it provides. AVAILABILITY: The Python code to reproduce the entirety of this analysis is available at: https://github.com/SuLab/MechRepoNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The full description of nucleic acid conformation involves eight torsion angles per nucleotide. To simplify this description, we previously developed a representation of the nucleic acid backbone that assigns each nucleotide a pair of pseudo-torsion angles (eta and theta defined by P and C4' atoms; or eta' and theta' defined by P and C1' atoms). A Java program, AMIGOS II, is currently available for calculating eta and theta angles for RNA and for performing motif searches based on eta and theta angles. However, AMIGOS II lacks the ability to parse DNA structures and to calculate eta' and theta' angles. It also has little visualization capacity for 3D structure, making it difficult for users to interpret the computational results. RESULTS: We present AMIGOS III, a PyMOL plugin that calculates the pseudo-torsion angles eta, theta, eta', and theta' for both DNA and RNA structures and performs motif searching based on these angles. Compared to AMIGOS II, AMIGOS III offers improved pseudo-torsion angle visualization for RNA and faster nucleic acid worm database generation; it also introduces pseudo-torsion angle visualization for DNA and nucleic acid worm visualization. Its integration into PyMOL enables easy preparation of tertiary structure inputs and intuitive visualization of involved structures. AVAILABILITY AND IMPLEMENTATION: https://github.com/pylelab/AMIGOSIII. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Computer inference of biological mechanisms is increasingly approachable due to dynamically rich data sources such as single-cell genomics. Inferred molecular interactions can prioritize hypotheses for wet-lab experiments to expedite biological discovery. However, complex data often come with unwanted biological or technical variations, exposing biases over marginal distribution and sample size in current methods to favor spurious causal relationships. RESULTS: Considering function direction and strength as evidence for causality, we present an adapted functional chi-squared test (AdpFunChisq) that rewards functional patterns over non-functional or independent patterns. On synthetic and three biology datasets, we demonstrate the advantages of AdpFunChisq over ten methods on overcoming biases that give rise to wide fluctuations in the performance of alternative approaches. On single-cell multiomics data of multiple phenotype acute leukemia, we found that T-cell surface glycoprotein CD3 delta chain (CD3D) may causally mediate specific genes in the viral carcinogenesis pathway. Using the causality-by-functionality principle, AdpFunChisq offers a viable option for robust causal inference in dynamical systems. AVAILABILITY: The AdpFunChisq test is implemented in the R package 'FunChisq' (2.5.2 or above) at https://cran.r-project.org/package=FunChisq. All other source code along with pre-processed data is available at Code Ocean https://doi.org/10.24433/CO.2907738.v1. SUPPLEMENTARY INFORMATION: Supplementary materials are available at Bioinformatics online.

SUMMARY: Missing regions in short-read assemblies of prokaryote genomes are often attributed to biases in sequencing technologies and to repetitive elements, the former resulting in low sequencing coverage of certain loci and the latter to unresolved loops in the de novo assembly graph. We developed SASpector, a command-line tool that compares short-read assemblies (draft genomes) to their corresponding closed assemblies and extracts missing regions to analyze them at the sequence and functional level. SASpector allows to benchmark the need for resolved genomes, can be integrated into pipelines to control the quality of assemblies, and could be used for comparative investigations of missingness in assemblies for which both short-read and long-read data are available in the public databases. AVAILABILITY AND IMPLEMENTATION: SASpector is available at https://github.com/LoGT-KULeuven/SASpector. The tool is implemented in Python3 and available through pip and Docker (0mician/saspector). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: After the outstanding breakthrough of AlphaFold in predicting protein 3D models, new questions appeared and remain unanswered. The ensemble nature of proteins, for example, challenges the structural prediction methods because the models should represent a set of conformers instead of single structures. The evolutionary and structural features captured by effective deep learning techniques may unveil the information to generate several diverse conformations from a single sequence. Here we address the performance of AlphaFold2 predictions obtained through ColabFold under this ensemble paradigm. RESULTS: Using a curated collection of apo-holo pairs of conformers, we found that AlphaFold2 predicts the holo form of a protein in ∼70% of the cases, being unable to reproduce the observed conformational diversity with the same error for both conformers. More importantly, we found that AlphaFold2's performance worsens with the increasing conformational diversity of the studied protein. This impairment is related to the heterogeneity in the degree of conformational diversity found between different members of the homologous family of the protein under study. Finally, we found that main-chain flexibility associated with apo-holo pairs of conformers negatively correlates with the predicted local model quality score plDDT, indicating that plDDT values in a single 3D model could be used to infer local conformational changes linked to ligand binding transitions. AVAILABILITY: Data and code used in this manuscript are publicly available at https://gitlab.com/sbgunq/publications/af2confdiv-oct2021. SUPPLEMENTARY INFORMATION: Supplementary data is available at the journal's web site.

Update of bioRxiv. 2020 Aug 14;:

SUMMARY: CellWalkR is an R package that integrates single-cell open chromatin data with cell type labels and bulk epigenetic data to identify cell type-specific regulatory regions. A Graphics Processing Unit (GPU) implementation and downsampling strategies enable thousands of cells to be processed in seconds. CellWalkR's user-friendly interface provides interactive analysis and visualization of cell labels and regulatory region mappings. AVAILABILITY AND IMPLEMENTATION: CellWalkR is freely available as an R package under a GNU GPL-2.0 License and can be accessed from https://github.com/PFPrzytycki/CellWalkR with an accompanying vignette. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Exploring drug-protein interactions (DPIs) provides a rapid and precise approach to assist in laboratory experiments for discovering new drugs. Network-based methods usually utilize a drug-protein association network and predict DPIs by the information of its associated proteins or drugs, called 'guilt-by-association' principle. However, the 'guilt-by-association' principle is not always true because sometimes similar proteins cannot interact with similar drugs. Recently, learning-based methods learn molecule properties underlying DPIs by utilizing existing databases of characterized interactions but neglect the network-level information. RESULTS: We propose a novel method, namely BridgeDPI. We devise a class of virtual nodes to bridge the gap between drugs and proteins and construct a learnable drug-protein association network. The network is optimized based on the supervised signals from the downstream task-the DPI prediction. Through information passing on this drug-protein association network, a Graph Neural Network can capture the network-level information among diverse drugs and proteins. By combining the network-level information and the learning-based method, BridgeDPI achieves significant improvement in three real-world DPI datasets. Moreover, the case study further verifies the effectiveness and reliability of BridgeDPI. AVAILABILITY AND IMPLEMENTATION: The source code of BridgeDPI can be accessed at https://github.com/SenseTime-Knowledge-Mining/BridgeDPI. The source data used in this study is available on the https://github.com/IBM/InterpretableDTIP (for the BindingDB dataset), https://github.com/masashitsubaki/CPI_prediction (for the C.ELEGANS and HUMAN) datasets, http://dude.docking.org/ (for the DUD-E dataset), repectively.

MOTIVATION: Identifying the target genes of transcription factors (TFs) is of great significance for biomedical researches. However, using biological experiments to identify TF-target gene interactions is still time consuming, expensive and limited to small scale. Existing computational methods for predicting underlying genes for TF to target is mainly proposed for their binding sites rather than the direct interaction. To bridge this gap, we in this work proposed a deep learning prediction model, named HGETGI, to identify the new TF-target gene interaction. Specifically, the proposed HGETGI model learns the patterns of the known interaction between TF and target gene complemented with their involvement in different human disease mechanisms. It performs prediction based on random walk for meta-path sampling and node embedding in a skip-gram manner. RESULTS: We evaluated the prediction performance of the proposed method on a real dataset and the experimental results show that it can achieve the average area under the curve of 0.8519 ± 0.0731 in fivefold cross validation. Besides, we conducted case studies on the prediction of two important kinds of TF, NFKB1 and TP53. As a result, 33 and 32 in the top-40 ranking lists of NFKB1 and TP53 were successfully confirmed by looking up another public database (hTftarget). It is envisioned that the proposed HGETGI method is feasible and effective for predicting TF-target gene interactions on a large scale. AVAILABILITY AND IMPLEMENTATION: The source code and dataset are available at https://github.com/PGTSING/HGETGI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Prediction of node and graph labels are prominent network science tasks. Data analyzed in these tasks are sometimes related: entities represented by nodes in a higher-level (higher scale) network can themselves be modeled as networks at a lower level. We argue that systems involving such entities should be integrated with a 'network of networks' (NoNs) representation. Then, we ask whether entity label prediction using multi-level NoN data via our proposed approaches is more accurate than using each of single-level node and graph data alone, i.e. than traditional node label prediction on the higher-level network and graph label prediction on the lower-level networks. To obtain data, we develop the first synthetic NoN generator and construct a real biological NoN. We evaluate accuracy of considered approaches when predicting artificial labels from the synthetic NoNs and proteins' functions from the biological NoN. RESULTS: For the synthetic NoNs, our NoN approaches outperform or are as good as node- and network-level ones depending on the NoN properties. For the biological NoN, our NoN approaches outperform the single-level approaches for just under half of the protein functions, and for 30% of the functions, only our NoN approaches make meaningful predictions, while node- and network-level ones achieve random accuracy. So, NoN-based data integration is important. AVAILABILITY AND IMPLEMENTATION: The software and data are available at https://nd.edu/~cone/NoNs. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: COnstraint-Based Reconstruction and Analysis of genome-scale metabolic models has become a widely used tool to understand metabolic network behavior at a large scale. However, existing reconstruction tools lack functionalities to address modellers' common objective to study metabolic networks on the pathway level. Thus, we developed CobraMod-a Python package for pathway-centric modification and extension of genome-scale metabolic networks. CobraMod can integrate data from various metabolic pathway databases as well as user-curated information. Our tool tests newly added metabolites, reactions and pathways against multiple curation criteria, suggests manual curation steps and provides the user with records of changes to ensure high quality metabolic reconstructions. CobraMod uses the visualization tool Escher for pathway representation and offers simple customization options for comparison of pathways and flux distributions. Our package enables coherent and reproducible workflows as it can be seamlessly integrated with COBRApy and Escher. AVAILABILITY AND IMPLEMENTATION: The source code can be found at https://github.com/Toepfer-Lab/cobramod/ and can be installed with pip. The documentation including tutorials is available at https://cobramod.readthedocs.io/.

MOTIVATION: Tumor-specific antigen (TSA) identification in human cancer predicts response to immunotherapy and provides targets for cancer vaccine and adoptive T-cell therapies with curative potential, and TSAs that are highly expressed at the RNA level are more likely to be presented on major histocompatibility complex (MHC)-I. Direct measurements of the RNA expression of peptides would allow for generalized prediction of TSAs. Human leukocyte antigen (HLA)-I genotypes were predicted with seq2HLA. RNA sequencing (RNAseq) fastq files were translated into all possible peptides of length 8-11, and peptides with high and low expressions in the tumor and control samples, respectively, were tested for their MHC-I binding potential with netMHCpan-4.0. RESULTS: A novel pipeline for TSA prediction from RNAseq was used to predict all possible unique peptides size 8-11 on previously published murine and human lung and lymphoma tumors and validated on matched tumor and control lung adenocarcinoma (LUAD) samples. We show that neoantigens predicted by exomeSeq are typically poorly expressed at the RNA level, and a fraction is expressed in matched normal samples. TSAs presented in the proteomics data have higher RNA abundance and lower MHC-I binding percentile, and these attributes are used to discover high confidence TSAs within the validation cohort. Finally, a subset of these high confidence TSAs is expressed in a majority of LUAD tumors and represents attractive vaccine targets. AVAILABILITY AND IMPLEMENTATION: The datasets were derived from sources in the public domain as follows: TSAFinder is open-source software written in python and R. It is licensed under CC-BY-NC-SA and can be downloaded at https://github.com/RNAseqTSA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) technology provides the possibility to study cell heterogeneity and cell development on the resolution of individual cells. Arguably, three of the most important computational targets on scRNA-seq data analysis are data visualization, cell clustering and trajectory inference. Although a substantial number of algorithms have been developed, most of them do not treat the three targets in a systematic or consistent manner. RESULTS: In this article, we propose an efficient scRNA-seq analysis framework, which accomplishes the three targets consistently by non-uniform ε-neighborhood (NEN) network. First, a network is generated by our NEN method, which combines the advantages of both k-nearest neighbors (KNN) and ε-neighborhood (EN) to represent the manifold that data points reside in gene space. Then from such a network, we use its layout, its community and further its shortest path to achieve the purpose of scRNA-seq data visualization, clustering and trajectory inference. The results on both synthetic and real datasets indicate that our NEN method not only can visually provide the global topological structure of a dataset accurately compared with t-SNE (t-Distributed Stochastic Neighbor Embedding) and UMAP (Uniform Manifold Approximation and Projection), but also has superior performances on clustering and pseudotime ordering of cells over the existing approaches. AVAILABILITY AND IMPLEMENTATION: This analysis method has been made into a python package called ccnet and is freely available at https://github.com/Just-Jia/ccNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Here, we introduce YeastMate, a user-friendly deep learning-based application for automated detection and segmentation of Saccharomyces cerevisiae cells and their mating and budding events in microscopy images. We build upon Mask R-CNN with a custom segmentation head for the subclassification of mother and daughter cells during lifecycle transitions. YeastMate can be used directly as a Python library or through a standalone application with a graphical user interface (GUI) and a Fiji plugin as easy-to-use frontends. AVAILABILITY AND IMPLEMENTATION: The source code for YeastMate is freely available at https://github.com/hoerlteam/YeastMate under the MIT license. We offer installers for our software stack for Windows, macOS and Linux. A detailed user guide is available at https://yeastmate.readthedocs.io. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Computational tools for pangenomic analysis have gained increasing interest over the past two decades in various applications such as evolutionary studies and vaccine development. Synthetic benchmarks are essential for the systematic evaluation of their performance. Currently, benchmarking tools represent a genome as a set of genetic sequences and fail to simulate the complete information of the genomes, which is essential for evaluating pangenomic detection between fragmented genomes. RESULTS: We present PANPROVA, a benchmark tool to simulate prokaryotic pangenomic evolution by evolving the complete genomic sequence of an ancestral isolate. In this way, the possibility of operating in the preassembly phase is enabled. Gene set variations, sequence variation and horizontal acquisition from a pool of external genomes are the evolutionary features of the tool. AVAILABILITY AND IMPLEMENTATION: PANPROVA is publicly available at https://github.com/InfOmics/PANPROVA. The manuscript explicitelly refers to the github repository. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Identification and interpretation of clinically actionable variants is a critical bottleneck. Searching for evidence in the literature is mandatory according to ASCO/AMP/CAP practice guidelines; however, it is both labor-intensive and error-prone. We developed a system to perform triage of publications relevant to support an evidence-based decision. The system is also able to prioritize variants. Our system searches within pre-annotated collections such as MEDLINE and PubMed Central. RESULTS: We assess the search effectiveness of the system using three different experimental settings: literature triage; variant prioritization and comparison of Variomes with LitVar. Almost two-thirds of the publications returned in the top-5 are relevant for clinical decision-support. Our approach enabled identifying 81.8% of clinically actionable variants in the top-3. Variomes retrieves on average +21.3% more articles than LitVar and returns the same number of results or more results than LitVar for 90% of the queries when tested on a set of 803 queries; thus, establishing a new baseline for searching the literature about variants. AVAILABILITY AND IMPLEMENTATION: Variomes is publicly available at https://candy.hesge.ch/Variomes. Source code is freely available at https://github.com/variomes/sibtm-variomes. SynVar is publicly available at https://goldorak.hesge.ch/synvar. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We present NewWave, a scalable R/Bioconductor package for the dimensionality reduction and batch effect removal of single-cell RNA sequencing data. To achieve scalability, NewWave uses mini-batch optimization and can work with out-of-memory data, enabling users to analyze datasets with millions of cells. AVAILABILITY AND IMPLEMENTATION: NewWave is implemented as an open-source R package available through the Bioconductor project at https://bioconductor.org/packages/NewWave/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: A common bioinformatics task in single-cell data analysis is to purify a cell type or cell population of interest from heterogeneous datasets. Here, we present scGate, an algorithm that automatizes marker-based purification of specific cell populations, without requiring training data or reference gene expression profiles. scGate purifies a cell population of interest using a set of markers organized in a hierarchical structure, akin to gating strategies employed in flow cytometry. scGate outperforms state-of-the-art single-cell classifiers and it can be applied to multiple modalities of single-cell data (e.g. RNA-seq, ATAC-seq, CITE-seq). scGate is implemented as an R package and integrated with the Seurat framework, providing an intuitive tool to isolate cell populations of interest from heterogeneous single-cell datasets. AVAILABILITY AND IMPLEMENTATION: scGate is available as an R package at https://github.com/carmonalab/scGate (https://doi.org/10.5281/zenodo.6202614). Several reproducible workflows describing the main functions and usage of the package on different single-cell modalities, as well as the code to reproduce the benchmark, can be found at https://github.com/carmonalab/scGate.demo (https://doi.org/10.5281/zenodo.6202585) and https://github.com/carmonalab/scGate.benchmark. Test data are available at https://doi.org/10.6084/m9.figshare.16826071. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: SomaticSiMu is an in silico simulator of single and double base substitutions, and single base insertions and deletions in an input genomic sequence to mimic mutational signatures. SomaticSiMu outputs simulated DNA sequences and mutational catalogues with imposed mutational signatures. The tool is the first mutational signature simulator featuring a graphical user interface, control of mutation rates and built-in visualization tools of the simulated mutations. Simulated datasets are useful as a ground truth to test the accuracy and sensitivity of DNA sequence classification tools and mutational signature extraction tools under different experimental scenarios. The reliability of SomaticSiMu was affirmed by (i) supervised machine learning classification of simulated sequences with different mutation types and burdens, and (ii) mutational signature extraction from simulated mutational catalogues. AVAILABILITY AND IMPLEMENTATION: SomaticSiMu is written in Python 3.8.3. The open-source code, documentation and tutorials are available at https://github.com/HillLab/SomaticSiMu under the terms of the CreativeCommonsAttribution4.0InternationalLicense. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: An important step in the transcriptomic analysis of individual cells involves manually determining the cellular identities. To ease this labor-intensive annotation of cell-types, there has been a growing interest in automated cell annotation, which can be achieved by training classification algorithms on previously annotated datasets. Existing pipelines employ dataset integration methods to remove potential batch effects between source (annotated) and target (unannotated) datasets. However, the integration and classification steps are usually independent of each other and performed by different tools. We propose JIND (joint integration and discrimination for automated single-cell annotation), a neural-network-based framework for automated cell-type identification that performs integration in a space suitably chosen to facilitate cell classification. To account for batch effects, JIND performs a novel asymmetric alignment in which unseen cells are mapped onto the previously learned latent space, avoiding the need of retraining the classification model for new datasets. JIND also learns cell-type-specific confidence thresholds to identify cells that cannot be reliably classified. RESULTS: We show on several batched datasets that the joint approach to integration and classification of JIND outperforms in accuracy existing pipelines, and a smaller fraction of cells is rejected as unlabeled as a result of the cell-specific confidence thresholds. Moreover, we investigate cells misclassified by JIND and provide evidence suggesting that they could be due to outliers in the annotated datasets or errors in the original approach used for annotation of the target batch. AVAILABILITY AND IMPLEMENTATION: Implementation for JIND is available at https://github.com/mohit1997/JIND and the data underlying this article can be accessed at https://doi.org/10.5281/zenodo.6246322. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The identification of binding hotspots in protein-RNA interactions is crucial for understanding their potential recognition mechanisms and drug design. The experimental methods have many limitations, since they are usually time-consuming and labor-intensive. Thus, developing an effective and efficient theoretical method is urgently needed. RESULTS: Here, we present SREPRHot, a method to predict hotspots, defined as the residues whose mutation to alanine generate a binding free energy change ≥2.0 kcal/mol, while others use a cutoff of 1.0 kcal/mol to obtain balanced datasets. To deal with the dataset imbalance, Synthetic Minority Over-sampling Technique (SMOTE) is utilized to generate minority samples to achieve a dataset balance. Additionally, besides conventional features, we use two types of new features, residue interface propensity previously developed by us, and topological features obtained using node-weighted networks, and propose an effective Random Grouping feature selection strategy combined with a two-step method to determine an optimal feature set. Finally, a stacking ensemble classifier is adopted to build our model. The results show SREPRHot achieves a good performance with SEN, MCC and AUC of 0.900, 0.557 and 0.829 on the independent testing dataset. The comparison study indicates SREPRHot shows a promising performance. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/ChunhuaLiLab/SREPRHot. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The rapid development of scRNA-seq technologies enables us to explore the transcriptome at the cell level on a large scale. Recently, various computational methods have been developed to analyze the scRNAseq data, such as clustering and visualization. However, current visualization methods, including t-SNE and UMAP, are challenged by the limited accuracy of rendering the geometric relationship of populations with distinct functional states. Most visualization methods are unsupervised, leaving out information from the clustering results or given labels. This leads to the inaccurate depiction of the distances between the bona fide functional states. In particular, UMAP and t-SNE are not optimal to preserve the global geometric structure. They may result in a contradiction that clusters with near distance in the embedded dimensions are in fact further away in the original dimensions. Besides, UMAP and t-SNE cannot track the variance of clusters. Through the embedding of t-SNE and UMAP, the variance of a cluster is not only associated with the true variance but also is proportional to the sample size. RESULTS: We present supCPM, a robust supervised visualization method, which separates different clusters, preserves the global structure and tracks the cluster variance. Compared with six visualization methods using synthetic and real datasets, supCPM shows improved performance than other methods in preserving the global geometric structure and data variance. Overall, supCPM provides an enhanced visualization pipeline to assist the interpretation of functional transition and accurately depict population segregation. AVAILABILITY AND IMPLEMENTATION: The R package and source code are available at https://zenodo.org/record/5975977#.YgqR1PXMJjM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA sequencing technologies facilitate the characterization of transcriptomic landscapes in diverse species, tissues and cell types with unprecedented molecular resolution. In order to better understand animal development, physiology, and pathology, unsupervised clustering analysis is often used to identify relevant cell populations. Although considerable progress has been made in terms of clustering algorithms in recent years, it remains challenging to evaluate the quality of the inferred single-cell clusters, which can greatly impact downstream analysis and interpretation. RESULTS: We propose a bioinformatics tool named Phitest to analyze the homogeneity of single-cell populations. Phitest is able to distinguish between homogeneous and heterogeneous cell populations, providing an objective and automatic method to optimize the performance of single-cell clustering analysis. AVAILABILITY AND IMPLEMENTATION: The PhitestR package is freely available on both Github (https://github.com/Vivianstats/PhitestR) and the Comprehensive R Archive Network (CRAN). There is no new genomic data associated with this article. Published data used in the analysis are described in detail in the Supplementary Data. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Batch effects in omics datasets are usually a source of technical noise that masks the biological signal and hampers data analysis. Batch effect removal has been widely addressed for individual omics technologies. However, multi-omic datasets may combine data obtained in different batches where omics type and batch are often confounded. Moreover, systematic biases may be introduced without notice during data acquisition, which creates a hidden batch effect. Current methods fail to address batch effect correction in these cases. RESULTS: In this article, we introduce the MultiBaC R package, a tool for batch effect removal in multi-omics and hidden batch effect scenarios. The package includes a diversity of graphical outputs for model validation and assessment of the batch effect correction. AVAILABILITY AND IMPLEMENTATION: MultiBaC package is available on Bioconductor (https://www.bioconductor.org/packages/release/bioc/html/MultiBaC.html) and GitHub (https://github.com/ConesaLab/MultiBaC.git). The data underlying this article are available in Gene Expression Omnibus repository (accession numbers GSE11521, GSE1002, GSE56622 and GSE43747). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The collection of temporal or perturbed data is often a prerequisite for reconstructing dynamic networks in most cases. However, these types of data are seldom available for genomic studies in medicine, thus significantly limiting the use of dynamic networks to characterize the biological principles underlying human health and diseases. RESULTS: We proposed a statistical framework to recover disease risk-associated pseudo-dynamic networks (DRDNet) from steady-state data. We incorporated a varying coefficient model with multiple ordinary differential equations to learn a series of networks. We analyzed the publicly available Genotype-Tissue Expression data to construct networks associated with hypertension risk, and biological findings showed that key genes constituting these networks had pivotal and biologically relevant roles associated with the vascular system. We also provided the selection consistency of the proposed learning procedure and evaluated its utility through extensive simulations. AVAILABILITY AND IMPLEMENTATION: DRDNet is implemented in the R language, and the source codes are available at https://github.com/chencxxy28/DRDnet/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The development of microscopic imaging techniques enables us to study protein subcellular locations from the tissue level down to the cell level, contributing to the rapid development of image-based protein subcellular location prediction approaches. However, existing methods suffer from intrinsic limitations, such as poor feature representation ability, data imbalanced issue, and multi-label classification problem, greatly impacting the model performance and generalization. RESULTS: In this study, we propose MSTLoc, a novel multi-scale end-to-end deep learning model to identify protein subcellular locations in the imbalanced multi-label immunohistochemistry (IHC) images dataset. In our MSTLoc, we deploy a deep convolution neural network to extract multi-scale features from the IHC images, aggregate the high-level features and low-level features via feature fusion to sufficiently exploit the dependencies amongst various subcellular locations, and utilize Vision Transformer (ViT) to model the relationship amongst the features and enhance the feature representation ability. We demonstrate that the proposed MSTLoc achieves better performance than current state-of-the-art models in multi-label subcellular location prediction. Through feature visualization and interpretation analysis, we demonstrate that as compared with the hand-crafted features, the multi-scale deep features learnt from our model exhibit better ability in capturing discriminative patterns underlying protein subcellular locations, and the features from different scales are complementary for the improvement in performance. Finally, case study results indicate that our MSTLoc can successfully identify some biomarkers from proteins that are closely involved with cancer development. AVAILABILITY AND IMPLEMENTATION: For the convenient use of our method, we establish a user-friendly webserver available at http://server.wei-group.net/MSTLoc. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Proteins binding to specific nucleotide sequences, such as transcription factors, play key roles in the regulation of gene expression. Their binding can be indirectly observed via associated changes in transcription, chromatin accessibility, DNA methylation and histone modifications. Identifying candidate factors that are responsible for these observed experimental changes is critical to understand the underlying biological processes. Here, we present monaLisa, an R/Bioconductor package that implements approaches to identify relevant transcription factors from experimental data. The package can be easily integrated with other Bioconductor packages and enables seamless motif analyses without any software dependencies outside of R. AVAILABILITY AND IMPLEMENTATION: monaLisa is implemented in R and available on Bioconductor at https://bioconductor.org/packages/monaLisa with the development version hosted on GitHub at https://github.com/fmicompbio/monaLisa. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Biomarkers with prognostic ability and biological interpretability can be used to support decision-making in the survival analysis. Genes usually form functional modules to play synergistic roles, such as pathways. Predicting significant features from the functional level can effectively reduce the adverse effects of heterogeneity and obtain more reproducible and interpretable biomarkers. Personalized pathway activation inference can quantify the dysregulation of essential pathways involved in the initiation and progression of cancers, and can contribute to the development of personalized medical treatments. RESULTS: In this study, we propose a novel method to evaluate personalized pathway activation based on signaling entropy for survival analysis (SEPA), which is a new attempt to introduce the information-theoretic entropy in generating pathway representation for each patient. SEPA effectively integrates pathway-level information into gene expression data, converting the high-dimensional gene expression data into the low-dimensional biological pathway activation scores. SEPA shows its classification power on the prognostic pan-cancer genomic data, and the potential pathway markers identified based on SEPA have statistical significance in the discrimination of high- and low-risk cohorts and are likely to be associated with the initiation and progress of cancers. The results show that SEPA scores can be used as an indicator to precisely distinguish cancer patients with different clinical outcomes, and identify important pathway features with strong discriminative power and biological interpretability. AVAILABILITY AND IMPLEMENTATION: The MATLAB-package for SEPA is freely available from https://github.com/xingyili/SEPA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The wealth of protein structures collected in the Protein Data Bank enabled large-scale studies of their function and evolution. Such studies, however, require the generation of customized datasets combining the structural data with miscellaneous accessory resources providing functional, taxonomic and other annotations. Unfortunately, the functionality of currently available tools for the creation of such datasets is limited and their usage frequently requires laborious surveying of various data sources and resolving inconsistencies between their versions. RESULTS: To address this problem, we developed localpdb, a versatile Python library for the management of protein structures and their annotations. The library features a flexible plugin system enabling seamless unification of the structural data with diverse auxiliary resources, full version control and powerful functionality of creating highly customized datasets. The localpdb can be used in a wide range of bioinformatic tasks, in particular those involving large-scale protein structural analyses and machine learning. AVAILABILITY AND IMPLEMENTATION: localpdb is freely available at https://github.com/labstructbioinf/localpdb. Documentation along with the usage examples can be accessed at https://labstructbioinf.github.io/localpdb/.

MOTIVATION: Inferring the parameters of models describing biological systems is an important problem in the reverse engineering of the mechanisms underlying these systems. Much work has focused on parameter inference of stochastic and ordinary differential equation models using Approximate Bayesian Computation (ABC). While there is some recent work on inference in spatial models, this remains an open problem. Simultaneously, advances in topological data analysis (TDA), a field of computational mathematics, have enabled spatial patterns in data to be characterized. RESULTS: Here, we focus on recent work using TDA to study different regimes of parameter space for a well-studied model of angiogenesis. We propose a method for combining TDA with ABC to infer parameters in the Anderson-Chaplain model of angiogenesis. We demonstrate that this topological approach outperforms ABC approaches that use simpler statistics based on spatial features of the data. This is a first step toward a general framework of spatial parameter inference for biological systems, for which there may be a variety of filtrations, vectorizations and summary statistics to be considered. AVAILABILITY AND IMPLEMENTATION: All code used to produce our results is available as a Snakemake workflow from github.com/tt104/tabc_angio.

MOTIVATION: Sequence models based on deep neural networks have achieved state-of-the-art performance on regulatory genomics prediction tasks, such as chromatin accessibility and transcription factor binding. But despite their high accuracy, their contributions to a mechanistic understanding of the biology of regulatory elements is often hindered by the complexity of the predictive model and thus poor interpretability of its decision boundaries. To address this, we introduce seqgra, a deep learning pipeline that incorporates the rule-based simulation of biological sequence data and the training and evaluation of models, whose decision boundaries mirror the rules from the simulation process. RESULTS: We show that seqgra can be used to (i) generate data under the assumption of a hypothesized model of genome regulation, (ii) identify neural network architectures capable of recovering the rules of said model and (iii) analyze a model's predictive performance as a function of training set size and the complexity of the rules behind the simulated data. AVAILABILITY AND IMPLEMENTATION: The source code of the seqgra package is hosted on GitHub (https://github.com/gifford-lab/seqgra). seqgra is a pip-installable Python package. Extensive documentation can be found at https://kkrismer.github.io/seqgra. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: ASES is a versatile tool for assessing the impact of alternative splicing (AS), initiation and termination of transcription on protein diversity in evolution. It identifies exon and transcript orthogroups from a set of input genes/species for comparative transcriptomics analyses. It computes an evolutionary splicing graph, where the nodes are exon orthogroups, allowing for a direct evaluation of AS conservation. It also reconstructs a transcripts' phylogenetic forest to date the appearance of specific transcripts and explore the events that have shaped them. ASES web server features a highly interactive interface enabling the synchronous selection of events, exons or transcripts in the different outputs, and the visualization and retrieval of the corresponding amino acid sequences, for subsequent 3D structure prediction. AVAILABILITY AND IMPLEMENTATION: http://www.lcqb.upmc.fr/Ases. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Gene regulatory networks define regulatory relationships between transcription factors and target genes within a biological system, and reconstructing them is essential for understanding cellular growth and function. Methods for inferring and reconstructing networks from genomics data have evolved rapidly over the last decade in response to advances in sequencing technology and machine learning. The scale of data collection has increased dramatically; the largest genome-wide gene expression datasets have grown from thousands of measurements to millions of single cells, and new technologies are on the horizon to increase to tens of millions of cells and above. RESULTS: In this work, we present the Inferelator 3.0, which has been significantly updated to integrate data from distinct cell types to learn context-specific regulatory networks and aggregate them into a shared regulatory network, while retaining the functionality of the previous versions. The Inferelator is able to integrate the largest single-cell datasets and learn cell-type-specific gene regulatory networks. Compared to other network inference methods, the Inferelator learns new and informative Saccharomyces cerevisiae networks from single-cell gene expression data, measured by recovery of a known gold standard. We demonstrate its scaling capabilities by learning networks for multiple distinct neuronal and glial cell types in the developing Mus musculus brain at E18 from a large (1.3 million) single-cell gene expression dataset with paired single-cell chromatin accessibility data. AVAILABILITY AND IMPLEMENTATION: The inferelator software is available on GitHub (https://github.com/flatironinstitute/inferelator) under the MIT license and has been released as python packages with associated documentation (https://inferelator.readthedocs.io/). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Genome annotation pipelines traditionally exclude open reading frames (ORFs) shorter than 100 codons to avoid false identifications. However, studies have been showing that these may encode functional microproteins with meaningful biological roles. We developed µProteInS, a proteogenomics pipeline that combines genomics, transcriptomics and proteomics to identify novel microproteins in bacteria. Our pipeline employs a model to filter out low confidence spectra, to avoid the need for manually inspecting Mass Spectrometry data. It also overcomes the shortcomings of traditional approaches that usually exclude overlapping genes, leaderless transcripts and non-conserved sequences, characteristics that are common among small ORFs (smORFs) and hamper their identification. AVAILABILITY AND IMPLEMENTATION: µProteInS is implemented in Python 3.8 within an Ubuntu 20.04 environment. It is an open-source software distributed under the GNU General Public License v3, available as a command-line tool. It can be downloaded at https://github.com/Eduardo-vsouza/uproteins and either installed from source or executed as a Docker image. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Cancer survival prediction can greatly assist clinicians in planning patient treatments and improving their life quality. Recent evidence suggests the fusion of multimodal data, such as genomic data and pathological images, is crucial for understanding cancer heterogeneity and enhancing survival prediction. As a powerful multimodal fusion technique, Kronecker product has shown its superiority in predicting survival. However, this technique introduces a large number of parameters that may lead to high computational cost and a risk of overfitting, thus limiting its applicability and improvement in performance. Another limitation of existing approaches using Kronecker product is that they only mine relations for one single time to learn multimodal representation and therefore face significant challenges in deeply mining rich information from multimodal data for accurate survival prediction. RESULTS: To address the above limitations, we present a novel hierarchical multimodal fusion approach named HFBSurv by employing factorized bilinear model to fuse genomic and image features step by step. Specifically, with a multiple fusion strategy HFBSurv decomposes the fusion problem into different levels and each of them integrates and passes information progressively from the low level to the high level, thus leading to the more specialized fusion procedure and expressive multimodal representation. In this hierarchical framework, both modality-specific and cross-modality attentional factorized bilinear modules are designed to not only capture and quantify complex relations from multimodal data, but also dramatically reduce computational complexity. Extensive experiments demonstrate that our method performs an effective hierarchical fusion of multimodal data and achieves consistently better performance than other methods for survival prediction. AVAILABILITY AND IMPLEMENTATION: HFBSurv is freely available at https://github.com/Liruiqing-ustc/HFBSurv. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: To address the difficulty in assessing the implication of regulatory variants in diseases, a scoring scheme previously published allows the calculation of the Regulatory Variant Evidence score (RVE-score). The score represents the accumulated evidence for a causative role of a regulatory variant in a disease. Regulatory Evidence for Variants Underlying Phenotypes was built to calculate the RVE-score of regulatory variants, based on the 24 criteria, with a hybrid approach combining information retrieved from public databases and user input. AVAILABILITY AND IMPLEMENTATION: RevUP is freely available at http://www.revup-classifier.ca. The source code is available at https://github.com/wassermanlab/revup. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Drug discovery has witnessed intensive exploration of predictive modeling of drug-target physical interactions over two decades. However, a critical knowledge gap needs to be filled for correlating drug-target interactions with clinical outcomes: predicting genome-wide receptor activities or function selectivity, especially agonist versus antagonist, induced by novel chemicals. Two major obstacles compound the difficulty on this task: known data of receptor activity is far too scarce to train a robust model in light of genome-scale applications, and real-world applications need to deploy a model on data from various shifted distributions. RESULTS: To address these challenges, we have developed an end-to-end deep learning framework, DeepREAL, for multi-scale modeling of genome-wide ligand-induced receptor activities. DeepREAL utilizes self-supervised learning on tens of millions of protein sequences and pre-trained binary interaction classification to solve the data distribution shift and data scarcity problems. Extensive benchmark studies on G-protein coupled receptors (GPCRs), which simulate real-world scenarios, demonstrate that DeepREAL achieves state-of-the-art performances in out-of-distribution settings. DeepREAL can be extended to other gene families beyond GPCRs. AVAILABILITY AND IMPLEMENTATION: All data used are downloaded from Pfam (Mistry et al., 2020), GLASS (Chan et al., 2015) and IUPHAR/BPS and the data from reference (Sakamuru et al., 2021). Readers are directed to their official website for original data. Code is available on GitHub https://github.com/XieResearchGroup/DeepREAL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: High throughput chromosome conformation capture (Hi-C) contact matrices are used to predict 3D chromatin structures in eukaryotic cells. High-resolution Hi-C data are less available than low-resolution Hi-C data due to sequencing costs but provide greater insight into the intricate details of 3D chromatin structures such as enhancer-promoter interactions and sub-domains. To provide a cost-effective solution to high-resolution Hi-C data collection, deep learning models are used to predict high-resolution Hi-C matrices from existing low-resolution matrices across multiple cell types. RESULTS: Here, we present two Cascading Residual Networks called HiCARN-1 and HiCARN-2, a convolutional neural network and a generative adversarial network, that use a novel framework of cascading connections throughout the network for Hi-C contact matrix prediction from low-resolution data. Shown by image evaluation and Hi-C reproducibility metrics, both HiCARN models, overall, outperform state-of-the-art Hi-C resolution enhancement algorithms in predictive accuracy for both human and mouse 1/16, 1/32, 1/64 and 1/100 downsampled high-resolution Hi-C data. Also, validation by extracting topologically associating domains, chromosome 3D structure and chromatin loop predictions from the enhanced data shows that HiCARN can proficiently reconstruct biologically significant regions. AVAILABILITY AND IMPLEMENTATION: HiCARN can be accessed and utilized as an open-sourced software at: https://github.com/OluwadareLab/HiCARN and is also available as a containerized application that can be run on any platform. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Pathway annotation tools are indispensable for the interpretation of a wide range of experiments in life sciences. Network-based algorithms have recently been developed which are more sensitive than traditional overlap-based algorithms, but there is still a lack of good online tools for network-based pathway analysis. RESULTS: We present PathwAX II-a pathway analysis web tool based on network crosstalk analysis using the BinoX algorithm. It offers several new features compared with the first version, including interactive graphical network visualization of the crosstalk between a query gene set and an enriched pathway, and the addition of Reactome pathways. AVAILABILITY AND IMPLEMENTATION: PathwAX II is available at http://pathwax.sbc.su.se. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Medical care is becoming more and more specific to patients' needs due to the increased availability of omics data. The application to these data of sophisticated machine learning models, in particular deep learning (DL), can improve the field of precision medicine. However, their use in clinics is limited as their predictions are not accompanied by an explanation. The production of accurate and intelligible predictions can benefit from the inclusion of domain knowledge. Therefore, knowledge-based DL models appear to be a promising solution. RESULTS: In this article, we propose GraphGONet, where the Gene Ontology is encapsulated in the hidden layers of a new self-explaining neural network. Each neuron in the layers represents a biological concept, combining the gene expression profile of a patient and the information from its neighboring neurons. The experiments described in the article confirm that our model not only performs as accurately as the state-of-the-art (non-explainable ones) but also automatically produces stable and intelligible explanations composed of the biological concepts with the highest contribution. This feature allows experts to use our tool in a medical setting. AVAILABILITY AND IMPLEMENTATION: GraphGONet is freely available at https://forge.ibisc.univ-evry.fr/vbourgeais/GraphGONet.git. The microarray dataset is accessible from the ArrayExpress database under the identifier E-MTAB-3732. The TCGA datasets can be downloaded from the Genomic Data Commons (GDC) data portal. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The growing use of next-generation sequencing and enlarged sequencing throughput require efficient short-read alignment, where seeding is one of the major performance bottlenecks. The key challenge in the seeding phase is searching for exact matches of substrings of short reads in the reference DNA sequence. Existing algorithms, however, present limitations in performance due to their frequent memory accesses. RESULTS: This article presents BWA-MEME, the first full-fledged short read alignment software that leverages learned indices for solving the exact match search problem for efficient seeding. BWA-MEME is a practical and efficient seeding algorithm based on a suffix array search algorithm that solves the challenges in utilizing learned indices for SMEM search which is extensively used in the seeding phase. Our evaluation shows that BWA-MEME achieves up to 3.45× speedup in seeding throughput over BWA-MEM2 by reducing the number of instructions by 4.60×, memory accesses by 8.77× and LLC misses by 2.21×, while ensuring the identical SAM output to BWA-MEM2. AVAILABILITY AND IMPLEMENTATION: The source code and test scripts are available for academic use at https://github.com/kaist-ina/BWA-MEME/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Transgene-design is a web application to help design transgenes for use in mammalian studies. It is predicated on the recent discovery that human intronless transgenes and native retrogenes can be expressed very effectively if the GC content at exonic synonymous sites is high. In addition, as exonic splice enhancers resident in intron containing genes may have different utility in intronless genes, these can be reduced or increased in density. Input can be a native gene or a commercially 'optimised' gene. The option to leave in the first intron and to protect or avoid other motifs is also permitted. AVAILABILITY AND IMPLEMENTATION: Transgene-design is based on a ruby for rails platform. The application is available at https://transgene-design.bath.ac.uk. The code is available under GNU General Public License from GitHub (https://github.com/smuehlh/transgenes). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Amidst the continuing spread of coronavirus disease-19 (COVID-19), real-time data analysis and visualization remain critical the general public to track the pandemic's impact and to inform policy making by officials. Multiple metrics permit the evaluation of the spread, infection and mortality of infectious diseases. For example, numbers of new cases and deaths provide easily interpretable measures of absolute impact within a given population and time frame, while the effective reproduction rate provides an epidemiological measure of the rate of spread. By evaluating multiple metrics concurrently, users can leverage complementary insights into the impact and current state of the pandemic when formulating prevention and safety plans for oneself and others. We describe COVID-19 Spread Mapper, a unified framework for estimating and quantifying the uncertainty in the smoothed daily effective reproduction number, case rate and death rate in a region using log-linear models. We apply this framework to characterize COVID-19 impact at multiple geographic resolutions, including by US county and state as well as by country, demonstrating the variation across resolutions and the need for harmonized efforts to control the pandemic. We provide an open-source online dashboard for real-time analysis and visualization of multiple key metrics, which are critical to evaluate the impact of COVID-19 and make informed policy decisions. AVAILABILITY AND IMPLEMENTATION: Our model and tool are publicly available as implemented in R and hosted at https://metrics.covid19-analysis.org/. The source code is freely available from https://github.com/lin-lab/COVID19-Rt and https://github.com/lin-lab/COVID19-Viz. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Deep-learning models, such as convolutional neural networks, are able to accurately map biological sequences to associated functional readouts and properties by learning predictive de novo representations. In silico saturation mutagenesis (ISM) is a popular feature attribution technique for inferring contributions of all characters in an input sequence to the model's predicted output. The main drawback of ISM is its runtime, as it involves multiple forward propagations of all possible mutations of each character in the input sequence through the trained model to predict the effects on the output. RESULTS: We present fastISM, an algorithm that speeds up ISM by a factor of over 10× for commonly used convolutional neural network architectures. fastISM is based on the observations that the majority of computation in ISM is spent in convolutional layers, and a single mutation only disrupts a limited region of intermediate layers, rendering most computation redundant. fastISM reduces the gap between backpropagation-based feature attribution methods and ISM. It far surpasses the runtime of backpropagation-based methods on multi-output architectures, making it feasible to run ISM on a large number of sequences. AVAILABILITY AND IMPLEMENTATION: An easy-to-use Keras/TensorFlow 2 implementation of fastISM is available at https://github.com/kundajelab/fastISM. fastISM can be installed using pip install fastism. A hands-on tutorial can be found at https://colab.research.google.com/github/kundajelab/fastISM/blob/master/notebooks/colab/DeepSEA.ipynb. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Microbiome datasets provide rich information about microbial communities. However, vast library size variations across samples present great challenges for proper statistical comparisons. To deal with these challenges, rarefaction is often used in practice as a normalization technique, although there has been debate whether rarefaction should ever be used. Conventional wisdom and previous work suggested that rarefaction should never be used in practice, arguing that rarefying microbiome data is statistically inadmissible. These discussions, however, have been confined to particular parametric models and simulation studies. RESULTS: We develop a semiparametric graphical model framework for grouped microbiome data and analyze in the context of differential abundance testing the statistical trade-offs of the rarefaction procedure, accounting for latent variations and measurement errors. Under the framework, it can be shown rarefaction guarantees that subsequent permutation tests properly control the Type I error. In addition, the loss in sensitivity from rarefaction is solely due to increased measurement error; if the underlying variation in microbial composition is large among samples, rarefaction might not hurt subsequent statistical inference much. We develop the rarefaction efficiency index (REI) as an indicator for efficiency loss and illustrate it with a dataset on the effect of storage conditions for microbiome data. Simulation studies based on real data demonstrate that the impact of rarefaction on sensitivity is negligible when overdispersion is prominent, while low REI corresponds to scenarios in which rarefying might substantially lower the statistical power. Whether to rarefy or not ultimately depends on assumptions of the data generating process and characteristics of the data. AVAILABILITY AND IMPLEMENTATION: Source codes are publicly available at https://github.com/jcyhong/rarefaction. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Many genomics applications require the computation of nucleotide coverage of a reference genome or the ability to determine how many reads map to a reference region. RESULTS: BamToCov is a toolkit for rapid and flexible coverage computation that relies on the most memory efficient algorithm and is designed for integration in pipelines, given its ability to read alignment files from streams. The tools in the suite can process sorted BAM or CRAM files, allowing the user to extract coverage information via different filtering approaches and to save the output in different formats (BED, Wig or counts). The BamToCov algorithm can also handle strand-specific and/or physical coverage analyses. AVAILABILITY AND IMPLEMENTATION: This program, accessory utilities and their documentation are freely available at https://github.com/telatin/BamToCov. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Amyloid polymorphism is emerging as a key property that is differentially linked to various conformational diseases, including major neurodegenerative disorders, but also as a feature that potentially relates to complex structural mechanisms mediating transmissibility barriers and selective vulnerability of amyloids. In response to the rapidly expanding number of amyloid fibril structures formed by full-length proteins, we here have developed StAmP-DB, a public database that supports the curation and cross-comparison of experimentally determined three-dimensional amyloid polymorph structures. AVAILABILITY AND IMPLEMENTATION: StAmP-DB is freely accessible for queries and downloads at https://stamp.switchlab.org.

MOTIVATION: Live-cell microscopy has become an essential tool for analyzing dynamic processes in various biological applications. Thereby, high-throughput and automated tracking analyses allow the simultaneous evaluation of large numbers of objects. However, to critically assess the influence of individual objects on calculated summary statistics, and to detect heterogeneous dynamics or possible artifacts, such as misclassified or -tracked objects, a direct mapping of gained statistical information onto the actual image data would be necessary. RESULTS: We present VisuStatR as a platform independent software package that allows the direct visualization of time-resolved summary statistics of morphological characteristics or motility dynamics onto raw images. The software contains several display modes to compare user-defined summary statistics and the underlying image data in various levels of detail. AVAILABILITY: VisuStatR is a free and open-source R-package, containing a user-friendly graphical-user interface and is available via GitHub at https://github.com/grrchrr/VisuStatR/ under the MIT+ license. SUPPLEMENTARY INFORMATION: Examples and additional information are available online and on the project's webpage.

Erratum in Bioinformatics. 2022 Nov 30;38(23):5328.

MOTIVATION: Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Providing computational tools for the exploration of the enzyme-substrate interaction space can expedite experimentation and benefit applications such as constructing synthesis pathways for novel biomolecules, identifying products of metabolism on ingested compounds, and elucidating xenobiotic metabolism. Recommender systems (RS), which are currently unexplored for the enzyme-substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) recommender systems however hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g., hierarchical, pairwise, or groupings), remains a challenge. RESULTS: We propose an innovative general RS framework, termed Boost-RS, that enhances RS performance by "boosting" embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme-substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors. AVAILABILITY AND IMPLEMENTATION: A Python implementation for Boost-RS is provided at https://github.com/HassounLab/Boost-RS.

MOTIVATION: Single-cell RNA sequencing (scRNAseq) technologies allow for measurements of gene expression at a single-cell resolution. This provides researchers with a tremendous advantage for detecting heterogeneity, delineating cellular maps or identifying rare subpopulations. However, a critical complication remains: the low number of single-cell observations due to limitations by rarity of subpopulation, tissue degradation or cost. This absence of sufficient data may cause inaccuracy or irreproducibility of downstream analysis. In this work, we present Automated Cell-Type-informed Introspective Variational Autoencoder (ACTIVA): a novel framework for generating realistic synthetic data using a single-stream adversarial variational autoencoder conditioned with cell-type information. Within a single framework, ACTIVA can enlarge existing datasets and generate specific subpopulations on demand, as opposed to two separate models [such as single-cell GAN (scGAN) and conditional scGAN (cscGAN)]. Data generation and augmentation with ACTIVA can enhance scRNAseq pipelines and analysis, such as benchmarking new algorithms, studying the accuracy of classifiers and detecting marker genes. ACTIVA will facilitate analysis of smaller datasets, potentially reducing the number of patients and animals necessary in initial studies. RESULTS: We train and evaluate models on multiple public scRNAseq datasets. In comparison to GAN-based models (scGAN and cscGAN), we demonstrate that ACTIVA generates cells that are more realistic and harder for classifiers to identify as synthetic which also have better pair-wise correlation between genes. Data augmentation with ACTIVA significantly improves classification of rare subtypes (more than 45% improvement compared with not augmenting and 4% better than cscGAN) all while reducing run-time by an order of magnitude in comparison to both models. AVAILABILITY AND IMPLEMENTATION: The codes and datasets are hosted on Zenodo (https://doi.org/10.5281/zenodo.5879639). Tutorials are available at https://github.com/SindiLab/ACTIVA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Rapid progress in genome science requires equally rapid visualization software development so that researchers can better explore and understand novel datasets. To make developing new visualizations faster and easier, we previously re-factored the Integrated Genome Browser (IGB), a desktop Java application with dozens of features, into a pluggable application framework that can accept new functionality as plug-ins, called IGB Apps. However, developers lacked a centralized location for sharing Apps, making it hard to connect with potential users. To fill this gap, we created an App Store for IGB, a user-friendly Web site for developers to release and document Apps, and for users to find them. AVAILABILITY AND IMPLEMENTATION: The IGB App Store is available from https://bioviz.org.

SUMMARY: Correctly annotating individual cell's type is an important initial step in single-cell RNA sequencing (scRNA-seq) data analysis. Here, we present NeuCA web server, a neural network-based scRNA-seq cell annotation tool with web-app portal and graphical user interface, for automatically assigning cell labels. NeuCA algorithm is accurate and exhaustive, maximizing the usage of measured cells for downstream analysis. NeuCA web server provides over 20 ready-to-use pre-trained classifiers for commonly used tissue types. As the first web-app tool with neural-network infrastructure implemented, NeuCA web will facilitate the research community in analyzing and annotating scRNA-seq data. AVAILABILITY AND IMPLEMENTATION: NeuCA web server is implemented with R Shiny application online at https://statbioinfo.shinyapps.io/NeuCA/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The analysis of mutational signatures is becoming increasingly common in cancer genetics, with emerging implications in cancer evolution, classification, treatment decision and prognosis. Recently, several packages have been developed for mutational signature analysis, with each using different methodology and yielding significantly different results. Because of the non-trivial differences in tools' refitting results, researchers may desire to survey and compare the available tools, in order to objectively evaluate the results for their specific research question, such as which mutational signatures are prevalent in different cancer types. RESULTS: Due to the need for effective comparison of refitting mutational signatures, we introduce a user-friendly software that can aggregate and visually present results from different refitting packages. AVAILABILITY AND IMPLEMENTATION: MetaMutationalSigs is implemented using R and python and is available for installation using Docker and available at: https://github.com/EESI/MetaMutationalSigs.

MOTIVATION: Diagnosis and treatment decisions on genomic data have become widespread as the cost of genome sequencing decreases gradually. In this context, disease-gene association studies are of great importance. However, genomic data are very sensitive when compared to other data types and contains information about individuals and their relatives. Many studies have shown that this information can be obtained from the query-response pairs on genomic databases. In this work, we propose a method that uses secure multi-party computation to query genomic databases in a privacy-protected manner. The proposed solution privately outsources genomic data from arbitrarily many sources to the two non-colluding proxies and allows genomic databases to be safely stored in semi-honest cloud environments. It provides data privacy, query privacy and output privacy by using XOR-based sharing and unlike previous solutions, it allows queries to run efficiently on hundreds of thousands of genomic data. RESULTS: We measure the performance of our solution with parameters similar to real-world applications. It is possible to query a genomic database with 3 000 000 variants with five genomic query predicates under 400 ms. Querying 1 048 576 genomes, each containing 1 000 000 variants, for the presence of five different query variants can be achieved approximately in 6 min with a small amount of dedicated hardware and connectivity. These execution times are in the right range to enable real-world applications in medical research and healthcare. Unlike previous studies, it is possible to query multiple databases with response times fast enough for practical application. To the best of our knowledge, this is the first solution that provides this performance for querying large-scale genomic data. AVAILABILITY AND IMPLEMENTATION: https://gitlab.com/DIFUTURE/privacy-preserving-variant-queries. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The identification of pathways and biological processes from differential gene expression is central for interpretation of data collected by transcriptomics assays. Gene set enrichment analysis (GSEA) is the most commonly used algorithm to calculate the significance of the relevancy of an annotated gene set with a differential expression signature. To compute significance, GSEA implements permutation tests which are slow and inaccurate for comparing many differential expression signatures to thousands of annotated gene sets. RESULTS: Here, we present blitzGSEA, an algorithm that is based on the same running sum statistic as GSEA, but instead of performing permutations, blitzGSEA approximates the enrichment score probabilities based on Gamma distributions. blitzGSEA achieves significant improvement in performance compared with prior GSEA implementations, while approximating small P-values more accurately. AVAILABILITY AND IMPLEMENTATION: The data, a python package, together with all source code, and a detailed user guide are available from GitHub at: https://github.com/MaayanLab/blitzgsea. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Over the past decade, short-read sequence alignment has become a mature technology. Optimized algorithms, careful software engineering and high-speed hardware have contributed to greatly increased throughput and accuracy. With these improvements, many opportunities for performance optimization have emerged. In this review, we examine three general-purpose short-read alignment tools-BWA-MEM, Bowtie 2 and Arioc-with a focus on performance optimization. We analyze the performance-related behavior of the algorithms and heuristics each tool implements, with the goal of arriving at practical methods of improving processing speed and accuracy. We indicate where an aligner's default behavior may result in suboptimal performance, explore the effects of computational constraints such as end-to-end mapping and alignment scoring threshold, and discuss sources of imprecision in the computation of alignment scores and mapping quality. With this perspective, we describe an approach to tuning short-read aligner performance to meet specific data-analysis and throughput requirements while avoiding potential inaccuracies in subsequent analysis of alignment results. Finally, we illustrate how this approach avoids easily overlooked pitfalls and leads to verifiable improvements in alignment speed and accuracy. CONTACT: richard.wilton@jhu.edu. SUPPLEMENTARY INFORMATION: Appendices referenced in this article are available at Bioinformatics online.

MOTIVATION: Limited data access has hindered the field of precision medicine from exploring its full potential, e.g. concerning machine learning and privacy and data protection rules.Our study evaluates the efficacy of federated Random Forests (FRF) models, focusing particularly on the heterogeneity within and between datasets. We addressed three common challenges: (i) number of parties, (ii) sizes of datasets and (iii) imbalanced phenotypes, evaluated on five biomedical datasets. RESULTS: The FRF outperformed the average local models and performed comparably to the data-centralized models trained on the entire data. With an increasing number of models and decreasing dataset size, the performance of local models decreases drastically. The FRF, however, do not decrease significantly. When combining datasets of different sizes, the FRF vastly improve compared to the average local models. We demonstrate that the FRF remain more robust and outperform the local models by analyzing different class-imbalances.Our results support that FRF overcome boundaries of clinical research and enables collaborations across institutes without violating privacy or legal regulations. Clinicians benefit from a vast collection of unbiased data aggregated from different geographic locations, demographics and other varying factors. They can build more generalizable models to make better clinical decisions, which will have relevance, especially for patients in rural areas and rare or geographically uncommon diseases, enabling personalized treatment. In combination with secure multi-party computation, federated learning has the power to revolutionize clinical practice by increasing the accuracy and robustness of healthcare AI and thus paving the way for precision medicine. AVAILABILITY AND IMPLEMENTATION: The implementation of the federated random forests can be found at https://featurecloud.ai/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Self-supervised deep language modeling has shown unprecedented success across natural language tasks, and has recently been repurposed to biological sequences. However, existing models and pretraining methods are designed and optimized for text analysis. We introduce ProteinBERT, a deep language model specifically designed for proteins. Our pretraining scheme combines language modeling with a novel task of Gene Ontology (GO) annotation prediction. We introduce novel architectural elements that make the model highly efficient and flexible to long sequences. The architecture of ProteinBERT consists of both local and global representations, allowing end-to-end processing of these types of inputs and outputs. ProteinBERT obtains near state-of-the-art performance, and sometimes exceeds it, on multiple benchmarks covering diverse protein properties (including protein structure, post-translational modifications and biophysical attributes), despite using a far smaller and faster model than competing deep-learning methods. Overall, ProteinBERT provides an efficient framework for rapidly training protein predictors, even with limited labeled data. AVAILABILITY AND IMPLEMENTATION: Code and pretrained model weights are available at https://github.com/nadavbra/protein_bert. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction. RESULTS: To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis, and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion module to conduct predictions. For model interpretation, a novel full-gradient graph saliency mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG/TCGA-GBM and proteomic data from coronavirus disease 2019 (COVID-19)/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding. AVAILABILITYAND IMPLEMENTATION: The codes are available at https://github.com/TencentAILabHealthcare/MLA-GNN.

SUMMARY: Recent years have seen an increase in the number of structures available, not only for new proteins but also for the same protein crystallized with different molecules and proteins. While protein design software has proven to be successful in designing and modifying proteins, they can also be overly sensitive to small conformational differences between structures of the same protein. To cope with this, we introduce here pyFoldX, a python library that allows the integrative analysis of structures of the same protein using FoldX, an established forcefield and modelling software. The library offers new functionalities for handling different structures of the same protein, an improved molecular parametrization module and an easy integration with the data analysis ecosystem of the python programming language. AVAILABILITY AND IMPLEMENTATION: pyFoldX rely on the FoldX software for energy calculations and modelling, which can be downloaded upon registration in http://foldxsuite.crg.eu/ and its licence is free of charge for academics. The pyFoldX library is open-source. Full details on installation, tutorials covering the library functionality and the scripts used to generate the data and figures presented in this paper are available at https://github.com/leandroradusky/pyFoldX. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Cross-sectional analyses of primary cancer genomes have identified regions of recurrent somatic copy-number alteration, many of which result from positive selection during cancer formation and contain driver genes. However, no effective approach exists for identifying genomic loci under significantly different degrees of selection in cancers of different subtypes, anatomic sites or disease stages. RESULTS: CNGPLD is a new tool for performing case-control somatic copy-number analysis that facilitates the discovery of differentially amplified or deleted copy-number aberrations in a case group of cancer compared with a control group of cancer. This tool uses a Gaussian process statistical framework in order to account for the covariance structure of copy-number data along genomic coordinates and to control the false discovery rate at the region level. AVAILABILITY AND IMPLEMENTATION: CNGPLD is freely available at https://bitbucket.org/djhshih/cngpld as an R package. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Graphs or networks are widely utilized to model the interactions between different entities (e.g. proteins, drugs, etc.) for biomedical applications. Predicting potential interactions/links in biomedical networks is important for understanding the pathological mechanisms of various complex human diseases, as well as screening compound targets for drug discovery. Graph neural networks (GNNs) have been utilized for link prediction in various biomedical networks, which rely on the node features extracted from different data sources, e.g. sequence, structure and network data. However, it is challenging to effectively integrate these data sources and automatically extract features for different link prediction tasks. RESULTS: In this article, we propose a novel Pre-Training Graph Neural Networks-based framework named PT-GNN to integrate different data sources for link prediction in biomedical networks. First, we design expressive deep learning methods [e.g. convolutional neural network and graph convolutional network (GCN)] to learn features for individual nodes from sequence and structure data. Second, we further propose a GCN-based encoder to effectively refine the node features by modelling the dependencies among nodes in the network. Third, the node features are pre-trained based on graph reconstruction tasks. The pre-trained features can be used for model initialization in downstream tasks. Extensive experiments have been conducted on two critical link prediction tasks, i.e. synthetic lethality (SL) prediction and drug-target interaction (DTI) prediction. Experimental results demonstrate PT-GNN outperforms the state-of-the-art methods for SL prediction and DTI prediction. In addition, the pre-trained features benefit improving the performance and reduce the training time of existing models. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at: https://github.com/longyahui/PT-GNN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: High-throughput single-cell molecular profiling is revolutionizing biology and medicine by unveiling the diversity of cell types and states contributing to development and disease. The identification and characterization of cellular heterogeneity are typically achieved through unsupervised clustering, which crucially relies on a similarity metric. RESULTS: We here propose the use of Optimal Transport (OT) as a cell-cell similarity metric for single-cell omics data. OT defines distances to compare high-dimensional data represented as probability distributions. To speed up computations and cope with the high dimensionality of single-cell data, we consider the entropic regularization of the classical OT distance. We then extensively benchmark OT against state-of-the-art metrics over 13 independent datasets, including simulated, scRNA-seq, scATAC-seq and single-cell DNA methylation data. First, we test the ability of the metrics to detect the similarity between cells belonging to the same groups (e.g. cell types, cell lines of origin). Then, we apply unsupervised clustering and test the quality of the resulting clusters. OT is found to improve cell-cell similarity inference and cell clustering in all simulated and real scRNA-seq data, as well as in scATAC-seq and single-cell DNA methylation data. AVAILABILITY AND IMPLEMENTATION: All our analyses are reproducible through the OT-scOmics Jupyter notebook available at https://github.com/ComputationalSystemsBiology/OT-scOmics. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: With the analysis of the characteristic and function of circular RNAs (circRNAs), people have realized that they play a critical role in the diseases. Exploring the relationship between circRNAs and diseases is of far-reaching significance for searching the etiopathogenesis and treatment of diseases. Nevertheless, it is inefficient to learn new associations only through biotechnology. RESULTS: Consequently, we present a computational method, GMNN2CD, which employs a graph Markov neural network (GMNN) algorithm to predict unknown circRNA-disease associations. First, used verified associations, we calculate semantic similarity and Gaussian interactive profile kernel similarity (GIPs) of the disease and the GIPs of circRNA and then merge them to form a unified descriptor. After that, GMNN2CD uses a fusion feature variational map autoencoder to learn deep features and uses a label propagation map autoencoder to propagate tags based on known associations. Based on variational inference, GMNN alternate training enhances the ability of GMNN2CD to obtain high-efficiency high-dimensional features from low-dimensional representations. Finally, 5-fold cross-validation of five benchmark datasets shows that GMNN2CD is superior to the state-of-the-art methods. Furthermore, case studies have shown that GMNN2CD can detect potential associations. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/nmt315320/GMNN2CD.git.

MOTIVATION: Accurate diagnostic classification and biological interpretation are important in biology and medicine, which are data-rich sciences. Thus, integration of different data types is necessary for the high predictive accuracy of clinical phenotypes, and more comprehensive analyses for predicting the prognosis of complex diseases are required. RESULTS: Here, we propose a novel multi-task attention learning algorithm for multi-omics data, termed MOMA, which captures important biological processes for high diagnostic performance and interpretability. MOMA vectorizes features and modules using a geometric approach and focuses on important modules in multi-omics data via an attention mechanism. Experiments using public data on Alzheimer's disease and cancer with various classification tasks demonstrated the superior performance of this approach. The utility of MOMA was also verified using a comparison experiment with an attention mechanism that was turned on or off and biological analysis. AVAILABILITY AND IMPLEMENTATION: The source codes are available at https://github.com/dmcb-gist/MOMA. SUPPLEMENTARY INFORMATION: Supplementary materials are available at Bioinformatics online.

MOTIVATION: Most RNA viruses lack strict proofreading during replication. Coupled with a high replication rate, some RNA viruses can form a virus population containing a group of genetically related but different haplotypes. Characterizing the haplotype composition in a virus population is thus important to understand viruses' evolution. Many attempts have been made to reconstruct viral haplotypes using next-generation sequencing (NGS) reads. However, the short length of NGS reads cannot cover distant single-nucleotide variants, making it difficult to reconstruct complete or near-complete haplotypes. Given the fast developments of third-generation sequencing technologies, a new opportunity has arisen for reconstructing full-length haplotypes with long reads. RESULTS: In this work, we developed a new tool, RVHaplo to reconstruct haplotypes for known viruses from long reads. We tested it rigorously on both simulated and real viral sequencing data and compared it against other popular haplotype reconstruction tools. The results demonstrated that RVHaplo outperforms the state-of-the-art tools for viral haplotype reconstruction from long reads. Especially, RVHaplo can reconstruct the rare (1% abundance) haplotypes that other tools usually missed. AVAILABILITY AND IMPLEMENTATION: The source code and the documentation of RVHaplo are available at https://github.com/dhcai21/RVHaplo. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A phylogenetic network is a powerful model to represent entangled evolutionary histories with both divergent (speciation) and convergent (e.g. hybridization, reassortment, recombination) evolution. The standard approach to inference of hybridization networks is to (i) reconstruct rooted gene trees and (ii) leverage gene tree discordance for network inference. Recently, we introduced a method called RF-Net for accurate inference of virus reassortment and hybridization networks from input gene trees in the presence of errors commonly found in phylogenetic trees. While RF-Net demonstrated the ability to accurately infer networks with up to four reticulations from erroneous input gene trees, its application was limited by the number of reticulations it could handle in a reasonable amount of time. This limitation is particularly restrictive in the inference of the evolutionary history of segmented RNA viruses such as influenza A virus (IAV), where reassortment is one of the major mechanisms shaping the evolution of these pathogens. RESULTS: Here, we expand the functionality of RF-Net that makes it significantly more applicable in practice. Crucially, we introduce a fast extension to RF-Net, called Fast-RF-Net, that can handle large numbers of reticulations without sacrificing accuracy. In addition, we develop automatic stopping criteria to select the appropriate number of reticulations heuristically and implement a feature for RF-Net to output error-corrected input gene trees. We then conduct a comprehensive study of the original method and its novel extensions and confirm their efficacy in practice using extensive simulation and empirical IAV evolutionary analyses. AVAILABILITY AND IMPLEMENTATION: RF-Net 2 is available at https://github.com/flu-crew/rf-net-2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The interactions between proteins and other molecules are essential to many biological and cellular processes. Experimental identification of interface residues is a time-consuming, costly and challenging task, while protein sequence data are ubiquitous. Consequently, many computational and machine learning approaches have been developed over the years to predict such interface residues from sequence. However, the effectiveness of different Deep Learning (DL) architectures and learning strategies for protein-protein, protein-nucleotide and protein-small molecule interface prediction has not yet been investigated in great detail. Therefore, we here explore the prediction of protein interface residues using six DL architectures and various learning strategies with sequence-derived input features. RESULTS: We constructed a large dataset dubbed BioDL, comprising protein-protein interactions from the PDB, and DNA/RNA and small molecule interactions from the BioLip database. We also constructed six DL architectures, and evaluated them on the BioDL benchmarks. This shows that no single architecture performs best on all instances. An ensemble architecture, which combines all six architectures, does consistently achieve peak prediction accuracy. We confirmed these results on the published benchmark set by Zhang and Kurgan (ZK448), and on our own existing curated homo- and heteromeric protein interaction dataset. Our PIPENN sequence-based ensemble predictor outperforms current state-of-the-art sequence-based protein interface predictors on ZK448 on all interaction types, achieving an AUC-ROC of 0.718 for protein-protein, 0.823 for protein-nucleotide and 0.842 for protein-small molecule. AVAILABILITY AND IMPLEMENTATION: Source code and datasets are available at https://github.com/ibivu/pipenn/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Active module identification (AMI) is an essential step in many omics analyses. Such algorithms receive a gene network and a gene activity profile as input and report subnetworks that show significant over-representation of accrued activity signal ('active modules'). Such modules can point out key molecular processes in the analyzed biological conditions. RESULTS: We recently introduced a novel AMI algorithm called DOMINO and demonstrated that it detects active modules that capture biological signals with markedly improved rate of empirical validation. Here, we provide an online server that executes DOMINO, making it more accessible and user-friendly. To help the interpretation of solutions, the server provides GO enrichment analysis, module visualizations and accessible output formats for customized downstream analysis. It also enables running DOMINO with various gene identifiers of different organisms. AVAILABILITY AND IMPLEMENTATION: The server is available at http://domino.cs.tau.ac.il. Its codebase is available at https://github.com/Shamir-Lab.

MOTIVATION: Ubiquitination is widely involved in protein homeostasis and cell signaling. Ubiquitin E3 ligases are critical regulators of ubiquitination that recognize and recruit specific ubiquitination targets for the final rate-limiting step of ubiquitin transfer reactions. Understanding the ubiquitin E3 ligase activities will provide knowledge in the upstream regulator of the ubiquitination pathway and reveal potential mechanisms in biological processes and disease progression. Recent advances in mass spectrometry-based proteomics have enabled deep profiling of ubiquitylome in a quantitative manner. Yet, functional analysis of ubiquitylome dynamics and pathway activity remains challenging. RESULTS: Here, we developed a UbE3-APA, a computational algorithm and stand-alone python-based software for Ub E3 ligase Activity Profiling Analysis. Combining an integrated annotation database with statistical analysis, UbE3-APA identifies significantly activated or suppressed E3 ligases based on quantitative ubiquitylome proteomics datasets. Benchmarking the software with published quantitative ubiquitylome analysis confirms the genetic manipulation of SPOP enzyme activity through overexpression and mutation. Application of the algorithm in the re-analysis of a large cohort of ubiquitination proteomics study revealed the activation of PARKIN and the co-activation of other E3 ligases in mitochondria depolarization-induced mitophagy process. We further demonstrated the application of the algorithm in the DIA (data-independent acquisition)-based quantitative ubiquitylome analysis. AVAILABILITY AND IMPLEMENTATION: Source code and binaries are freely available for download at URL: https://github.com/Chenlab-UMN/Ub-E3-ligase-Activity-Profiling-Analysis, implemented in python and supported on Linux and MS Windows. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recombination is one of the essential genetic processes for sexually reproducing organisms, which can happen more frequently in some regions, called recombination hotspots. Although several factors, such as PRDM9 binding motifs, are known to be related to the hotspots, their contributions to the recombination hotspots have not been quantified, and other determinants are yet to be elucidated. Here, we propose a computational method, RHSNet, based on deep learning and signal processing, to identify and quantify the hotspot determinants in a purely data-driven manner, utilizing datasets from various studies, populations, sexes, and species. RESULTS: RHSNet can significantly outperforms other sequence-based methods on multiple datasets across different species, sexes, and studies. In addition to being able to identify hotspot regions and the well-known determinants accurately, more importantly, RHSNet can quantify the determinants that contribute significantly to the recombination hotspot formation in the relation between PRDM9 binding motif, histone modification, and GC content. Further cross-sex, cross-population, and cross-species studies suggest that the proposed method has the generalization power and potential to identify and quantify the evolutionary determinant motifs. AVAILABILITY: https://github.com/frankchen121212/RHSNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Direct reprogramming involves the direct conversion of fully differentiated mature cell types into various other cell types while bypassing an intermediate pluripotent state (e.g., induced pluripotent stem cells). Cell differentiation by direct reprogramming is determined by two types of transcription factors (TFs): pioneer factors (PFs) and cooperative TFs. PFs have the distinct ability to open chromatin aggregations, assemble a collective of cooperative TFs, and activate gene expression. The experimental determination of two types of TFs is extremely difficult and costly. RESULTS: In this study, we developed a novel computational method, TRANSDIRE (TRANS-omics-based approach for DIrect REprogramming), to predict the TFs that induce direct reprogramming in various human cell types using multiple omics data. In the algorithm, potential PFs were predicted based on low signal chromatin regions, and the cooperative TFs were predicted through a trans-omics analysis of genomic data (e.g., enhancers), transcriptome data (e.g., gene expression profiles in human cells), epigenome data (e.g., chromatin immunoprecipitation sequencing data), and interactome data. We applied the proposed methods to the reconstruction of TFs that induce direct reprogramming from fibroblasts to six other cell types: hepatocytes, cartilaginous cells, neurons, cardiomyocytes, pancreatic cells, and Paneth cells. We demonstrated that the methods successfully predicted TFs for most cell conversions with high accuracy. Thus, the proposed methods are expected to be useful for various practical applications in regenerative medicine. AVAILABILITY: The source code and data are available at the following website: http://figshare.com/s/b653781a5b9e6639972b.

SUMMARY: We present MitoVisualize, a new tool for analysis of the human mitochondrial DNA (mtDNA). MitoVisualize enables visualization of: (1) the position and effect of variants in mitochondrial transfer RNA (tRNA) and ribosomal RNA (rRNA) secondary structures alongside curated variant annotations, (2) data across RNA structures, such as to show all positions with disease-associated variants or with post-transcriptional modifications, and (3) the position of a base, gene or region in the circular mtDNA map, such as to show the location of a large deletion. All visualizations can be easily downloaded as figures for reuse. MitoVisualize can be useful for anyone interested in exploring mtDNA variation, though is designed to facilitate mtDNA variant interpretation in particular. AVAILABILITY AND IMPLEMENTATION: MitoVisualize can be accessed via https://www.mitovisualize.org/. The source code is available at https://github.com/leklab/mito_visualize/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Inferring an accurate gene regulatory network (GRN) has long been a key goal in the field of systems biology. To do this, it is important to find a suitable balance between the maximum number of true positive and the minimum number of false-positive interactions. Another key feature is that the inference method can handle the large size of modern experimental data, meaning the method needs to be both fast and accurate. The Least Squares Cut-Off (LSCO) method can fulfill both these criteria, however as it is based on least squares it is vulnerable to known issues of amplifying extreme values, small or large. In GRN this manifests itself with genes that are erroneously hyper-connected to a large fraction of all genes due to extremely low value fold changes. RESULTS: We developed a GRN inference method called Least Squares Cut-Off with Normalization (LSCON) that tackles this problem. LSCON extends the LSCO algorithm by regularization to avoid hyper-connected genes and thereby reduce false positives. The regularization used is based on normalization, which removes effects of extreme values on the fit. We benchmarked LSCON and compared it to Genie3, LASSO, LSCO and Ridge regression, in terms of accuracy, speed and tendency to predict hyper-connected genes. The results show that LSCON achieves better or equal accuracy compared to LASSO, the best existing method, especially for data with extreme values. Thanks to the speed of least squares regression, LSCON does this an order of magnitude faster than LASSO. AVAILABILITY AND IMPLEMENTATION: Data: https://bitbucket.org/sonnhammergrni/lscon; Code: https://bitbucket.org/sonnhammergrni/genespider. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Polypharmacy is the combined use of drugs for the treatment of diseases. However, it often shows a high risk of side effects. Due to unnecessary interactions of combined drugs, the side effects of polypharmacy increase the risk of disease and even lead to death. Thus, obtaining abundant and comprehensive information on the side effects of polypharmacy is a vital task in the healthcare industry. Early traditional methods used machine learning techniques to predict side effects. However, they often make costly efforts to extract features of drugs for prediction. Later, several methods based on knowledge graphs are proposed. They are reported to outperform traditional methods. However, they still show limited performance by failing to model complex relations of side effects among drugs. RESULTS: To resolve the above problems, we propose a novel model by further incorporating complex relations of side effects into knowledge graph embeddings. Our model can translate and transmit multidirectional semantics with fewer parameters, leading to better scalability in large-scale knowledge graphs. Experimental evaluation shows that our model outperforms state-of-the-art models in terms of the average area under the ROC and precision-recall curves. AVAILABILITY AND IMPLEMENTATION: Code and data are available at: https://github.com/galaxysunwen/MSTE-master.

MOTIVATION: Drawing peaks in a data window of an MS dataset happens at all time in MS data visualization applications. This asks to retrieve from an MS dataset some selected peaks in a data window whose image in a display window reflects the visual feature of all peaks in the data window. If an algorithm for this purpose is asked to output high-quality solutions in real time, then the most fundamental dependence of it is on the storage format of the MS dataset. RESULTS: We present mzMD, a new storage format of MS datasets and an algorithm to query this format of a storage system for a summary (a set of selected representative peaks) of a given data window. We propose a criterion Q-score to examine the quality of data window summaries. Experimental statistics on real MS datasets verified the high speed of mzMD in retrieving high-quality data window summaries. mzMD reported summaries of data windows whose Q-score outperforms those mzTree reported. The query speed of mzMD is the same as that of mzTree whereas its query speed stability is better than that of mzTree. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at https://github.com/yrm9837/mzMD-java. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Ribosome profiling, or Ribo-seq, is the state-of-the-art method for quantifying protein synthesis in living cells. Computational analysis of Ribo-seq data remains challenging due to the complexity of the procedure, as well as variations introduced for specific organisms or specialized analyses. RESULTS: We present riboviz 2, an updated riboviz package, for the comprehensive transcript-centric analysis and visualization of Ribo-seq data. riboviz 2 includes an analysis workflow built on the Nextflow workflow management system for end-to-end processing of Ribo-seq data. riboviz 2 has been extensively tested on diverse species and library preparation strategies, including multiplexed samples. riboviz 2 is flexible and uses open, documented file formats, allowing users to integrate new analyses with the pipeline. AVAILABILITY AND IMPLEMENTATION: riboviz 2 is freely available at github.com/riboviz/riboviz.

MOTIVATION: Type-III secretion systems are utilized by many Gram-negative bacteria to inject type-3 effectors (T3Es) to eukaryotic cells. These effectors manipulate host processes for the benefit of the bacteria and thus promote disease. They can also function as host-specificity determinants through their recognition as avirulence proteins that elicit immune response. Identifying the full effector repertoire within a set of bacterial genomes is of great importance to develop appropriate treatments against the associated pathogens. RESULTS: We present Effectidor, a user-friendly web server that harnesses several machine-learning techniques to predict T3Es within bacterial genomes. We compared the performance of Effectidor to other available tools for the same task on three pathogenic bacteria. Effectidor outperformed these tools in terms of classification accuracy (area under the precision-recall curve above 0.98 in all cases). AVAILABILITY AND IMPLEMENTATION: Effectidor is available at: https://effectidor.tau.ac.il, and the source code is available at: https://github.com/naamawagner/Effectidor. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Human immunodeficiency virus (HIV) drug resistance is a global healthcare issue. The emergence of drug resistance influenced the efficacy of treatment regimens, thus stressing the importance of treatment adaptation. Computational methods predicting the drug resistance profile from genomic data of HIV isolates are advantageous for monitoring drug resistance in patients. However, existing computational methods for drug resistance prediction are either not suitable for emerging HIV strains with complex mutational patterns or lack interpretability, which is of paramount importance in clinical practice. The approach reported here overcomes these limitations and combines high accuracy of predictions and interpretability of the models. RESULTS: In this work, a new methodology based on generative topographic mapping (GTM) for biological sequence space representation and quantitative genotype-phenotype relationships prediction purposes was introduced. The GTM-based resistance landscapes allowed us to predict the resistance of HIV strains based on sequencing and drug resistance data for three viral proteins [integrase (IN), protease (PR) and reverse transcriptase (RT)] from Stanford HIV drug resistance database. The average balanced accuracy for PR inhibitors was 0.89 ± 0.01, for IN inhibitors 0.85 ± 0.01, for non-nucleoside RT inhibitors 0.73 ± 0.01 and for nucleoside RT inhibitors 0.84 ± 0.01. We have demonstrated in several case studies that GTM-based resistance landscapes are useful for visualization and analysis of sequence space as well as for treatment optimization purposes. Here, GTMs were applied for the in-depth analysis of the relationships between mutation pattern and drug resistance using mutation landscapes. This allowed us to predict retrospectively the importance of the presence of particular mutations (e.g. V32I, L10F and L33F in HIV PR) for the resistance development. This study highlights some perspectives of GTM applications in clinical informatics and particularly in the field of sequence space exploration. AVAILABILITY AND IMPLEMENTATION: https://github.com/karinapikalyova/ISIDASeq. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Logistic regression models are used in genomic studies to analyze the genetic data linked to electronic health records (EHRs), and do not take full usage of the time-to-event information available in EHRs. Previous work has shown that Cox regression, which can account for left truncation and right censoring in EHRs, increased the power to detect genotype-phenotype associations compared to logistic regression. We extend this to evaluate the relative performance of Cox regression and various logistic regression models in the presence of positive errors in event time (delayed event time), relating to recorded event time accuracy. RESULTS: One Cox model and three logistic regression models were considered under different scenarios of delayed event time. Extensive simulations and a genomic study application were used to evaluate the impact of delayed event time. While logistic regression does not model the time-to-event directly, various logistic regression models used in the literature were more sensitive to delayed event time than Cox regression. Results highlighted the importance to identify and exclude the patients diagnosed before entry time. Cox regression had similar or modest improvement in statistical power over various logistic regression models at controlled type I error. This was supported by the empirical data, where the Cox models steadily had the highest sensitivity to detect known genotype-phenotype associations under all scenarios of delayed event time. AVAILABILITY AND IMPLEMENTATION: Access to individual-level EHR and genotype data is restricted by the IRB. Simulation code and R script for data process are at: https://github.com/QingxiaCindyChen/CoxRobustEHR.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Many studies have shown that microRNAs (miRNAs) play a key role in human diseases. Meanwhile, traditional experimental methods for miRNA-disease association identification are extremely costly, time-consuming and challenging. Therefore, many computational methods have been developed to predict potential associations between miRNAs and diseases. However, those methods mainly predict the existence of miRNA-disease associations, and they cannot predict the deep-level miRNA-disease association types. RESULTS: In this study, we propose a new end-to-end deep learning method (called PDMDA) to predict deep-level miRNA-disease associations with graph neural networks (GNNs) and miRNA sequence features. Based on the sequence and structural features of miRNAs, PDMDA extracts the miRNA feature representations by a fully connected network (FCN). The disease feature representations are extracted from the disease-gene network and gene-gene interaction network by GNN model. Finally, a multilayer with three fully connected layers and a softmax layer is designed to predict the final miRNA-disease association scores based on the concatenated feature representations of miRNAs and diseases. Note that PDMDA does not take the miRNA-disease association matrix as input to compute the Gaussian interaction profile similarity. We conduct three experiments based on six association type samples (including circulations, epigenetics, target, genetics, known association of which their types are unknown and unknown association samples). We conduct fivefold cross-validation validation to assess the prediction performance of PDMDA. The area under the receiver operating characteristic curve scores is used as metric. The experiment results show that PDMDA can accurately predict the deep-level miRNA-disease associations. AVAILABILITY AND IMPLEMENTATION: Data and source codes are available at https://github.com/27167199/PDMDA.

MOTIVATION: Protein-RNA interactions play essential roles in many biological processes, including pre-mRNA processing, post-transcriptional gene regulation and RNA degradation. Accurate identification of binding sites on RNA-binding proteins (RBPs) is important for functional annotation and site-directed mutagenesis. Experimental assays to sparse RBPs are precise and convincing but also costly and time consuming. Therefore, flexible and reliable computational methods are required to recognize RNA-binding residues. RESULTS: In this work, we propose PST-PRNA, a novel model for predicting RNA-binding sites (PRNA) based on protein surface topography (PST). Taking full advantage of the 3D structural information of protein, PST-PRNA creates representative topography images of the entire protein surface by mapping it onto a unit spherical surface. Four kinds of descriptors are encoded to represent residues on the surface. Then, the potential features are integrated and optimized by using deep learning models. We compile a comprehensive non-redundant RBP dataset to train and test PST-PRNA using 10-fold cross-validation. Numerous experiments demonstrate PST-PRNA learns successfully the latent structural information of protein surface. On the non-redundant dataset with sequence identity of 0.3, PST-PRNA achieves area under the receiver operating characteristic curves (AUC) value of 0.860 and Matthew's correlation coefficient value of 0.420. Furthermore, we construct a completely independent test dataset for justification and comparison. PST-PRNA achieves AUC value of 0.913 on the independent dataset, which is superior to the other state-of-the-art methods. AVAILABILITY AND IMPLEMENTATION: The code and data are available at https://www.github.com/zpliulab/PST-PRNA. A web server is freely available at http://www.zpliulab.cn/PSTPRNA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The goal of oligonucleotide (oligo) design is to select oligos that optimize a set of design criteria. Oligo design problems are combinatorial in nature and require computationally intensive models to evaluate design criteria. Even relatively small problems can be intractable for brute-force approaches that test every possible combination of oligos, so heuristic approaches must be used to find near-optimal solutions. RESULTS: We present a general reinforcement learning (RL) framework, called OligoRL, to solve oligo design problems with complex constraints. OligoRL allows 'black-box' design criteria and can be adapted to solve many oligo design problems. We highlight the flexibility of OligoRL by building tools to solve three distinct design problems: (i) finding pools of random DNA barcodes that lack restriction enzyme recognition sequences (CutFreeRL); (ii) compressing large, non-degenerate oligo pools into smaller degenerate ones (OligoCompressor) and (iii) finding Not-So-Random hexamer primer pools that avoid rRNA and other unwanted transcripts during RNA-seq library preparation (NSR-RL). OligoRL demonstrates how RL offers a general solution for complex oligo design problems. AVAILABILITY AND IMPLEMENTATION: OligoRL and all simulation codes are available as a Julia package at http://jensenlab.net/tools and archived at https://archive.softwareheritage.org/browse/origin/directory/?origin_url=https://github.com/bmdavid2/OligoRL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Machine learning algorithms for link prediction can be valuable tools for hypothesis generation. However, many current algorithms are black boxes or lack good user interfaces that could facilitate insight into why predictions are made. We present LinkExplorer, a software suite for predicting, explaining and exploring links in large biomedical knowledge graphs. LinkExplorer integrates our novel, rule-based link prediction engine SAFRAN, which was recently shown to outcompete other explainable algorithms and established black-box algorithms. Here, we demonstrate highly competitive evaluation results of our algorithm on multiple large biomedical knowledge graphs, and release a web interface that allows for interactive and intuitive exploration of predicted links and their explanations. AVAILABILITY AND IMPLEMENTATION: A publicly hosted instance, source code and further documentation can be found at https://github.com/OpenBioLink/Explorer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.