MOTIVATION: The aim of quantitative structure-activity prediction (QSAR) studies is to identify novel drug-like molecules that can be suggested as lead compounds by means of two approaches, which are discussed in this article. First, to identify appropriate molecular descriptors by focusing on one feature-selection algorithms; and second to predict the biological activities of designed compounds. Recent studies have shown increased interest in the prediction of a huge number of molecules, known as Big Data, using deep learning models. However, despite all these efforts to solve critical challenges in QSAR models, such as over-fitting, massive processing procedures, is major shortcomings of deep learning models. Hence, finding the most effective molecular descriptors in the shortest possible time is an ongoing task. One of the successful methods to speed up the extraction of the best features from big datasets is the use of least absolute shrinkage and selection operator (LASSO). This algorithm is a regression model that selects a subset of molecular descriptors with the aim of enhancing prediction accuracy and interpretability because of removing inappropriate and irrelevant features. RESULTS: To implement and test our proposed model, a random forest was built to predict the molecular activities of Kaggle competition compounds. Finally, the prediction results and computation time of the suggested model were compared with the other well-known algorithms, i.e. Boruta-random forest, deep random forest and deep belief network model. The results revealed that improving output correlation through LASSO-random forest leads to appreciably reduced implementation time and model complexity, while maintaining accuracy of the predictions. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: T cells participate directly in the body's immune response to cancer, allowing immunotherapy treatments to effectively recognize and target cancer cells. We previously developed DeepCAT to demonstrate that T cells serve as a biomarker of immune response in cancer patients and can be utilized as a diagnostic tool to differentiate healthy and cancer patient samples. However, DeepCAT's reliance on tumor bulk RNA-seq samples as training data limited its further performance improvement. Here, we benchmarked a new approach, AutoCAT, to predict tumor-associated TCRs from targeted TCR-seq data as a new form of input for DeepCAT, and observed the same level of predictive accuracy. AVAILABILITY AND IMPLEMENTATION: Source code is freely available at https://github.com/cew88/AutoCAT, and data is available at 10.5281/zenodo.5176884. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Deep learning approaches have empowered single-cell omics data analysis in many ways and generated new insights from complex cellular systems. As there is an increasing need for single-cell omics data to be integrated across sources, types and features of data, the challenges of integrating single-cell omics data are rising. Here, we present an unsupervised deep learning algorithm that learns discriminative representations for single-cell data via maximizing mutual information, SMILE (Single-cell Mutual Information Learning). RESULTS: Using a unique cell-pairing design, SMILE successfully integrates multisource single-cell transcriptome data, removing batch effects and projecting similar cell types, even from different tissues, into the shared space. SMILE can also integrate data from two or more modalities, such as joint-profiling technologies using single-cell ATAC-seq, RNA-seq, DNA methylation, Hi-C and ChIP data. When paired cells are known, SMILE can integrate data with unmatched feature, such as genes for RNA-seq and genome-wide peaks for ATAC-seq. Integrated representations learned from joint-profiling technologies can then be used as a framework for comparing independent single source data. AVAILABILITY AND IMPLEMENTATION: The source code of SMILE including analyses of key results in the study can be found at: https://github.com/rpmccordlab/SMILE, implemented in Python. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Survival analysis using gene expression profiles plays a crucial role in the interpretation of clinical research and assessment of disease therapy programs. Several prediction models have been developed to explore the relationship between patients' covariates and survival. However, the high-dimensional genomic features limit the prediction performance of the survival model. Thus, an accurate and reliable prediction model is necessary for survival analysis using high-dimensional genomic data. RESULTS: In this study, we proposed an improved survival prediction model based on XGBoost framework called XGBLC, which used Lasso-Cox to enhance the ability to analyze high-dimensional genomic data. The novel first- and second-order gradient statistics of Lasso-Cox were defined to construct the loss function of XGBLC. We extensively tested our XGBLC algorithm on both simulated and real-world datasets, and estimated the performance of models with 5-fold cross-validation. Based on 20 cancer datasets from The Cancer Genome Atlas (TCGA), XGBLC outperforms five state-of-the-art survival methods in terms of C-index, Brier score and AUC. The results show that XGBLC still keeps good accuracy and robustness by comparing the performance on the simulated datasets with different scales. The developed prediction model would be beneficial for physicians to understand the effects of patient's genomic characteristics on survival and make personalized treatment decisions. AVAILABILITY AND IMPLEMENTATION: The implementation of XGBLC algorithm based on R language is available at: https://github.com/lab319/XGBLC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Nucleus detection, segmentation and classification are fundamental to high-resolution mapping of the tumor microenvironment using whole-slide histopathology images. The growing interest in leveraging the power of deep learning to achieve state-of-the-art performance often comes at the cost of explainability, yet there is general consensus that explainability is critical for trustworthiness and widespread clinical adoption. Unfortunately, current explainability paradigms that rely on pixel saliency heatmaps or superpixel importance scores are not well-suited for nucleus classification. Techniques like Grad-CAM or LIME provide explanations that are indirect, qualitative and/or nonintuitive to pathologists. RESULTS: In this article, we present techniques to enable scalable nuclear detection, segmentation and explainable classification. First, we show how modifications to the widely used Mask R-CNN architecture, including decoupling the detection and classification tasks, improves accuracy and enables learning from hybrid annotation datasets like NuCLS, which contain mixtures of bounding boxes and segmentation boundaries. Second, we introduce an explainability method called Decision Tree Approximation of Learned Embeddings (DTALE), which provides explanations for classification model behavior globally, as well as for individual nuclear predictions. DTALE explanations are simple, quantitative, and can flexibly use any measurable morphological features that make sense to practicing pathologists, without sacrificing model accuracy. Together, these techniques present a step toward realizing the promise of computational pathology in computer-aided diagnosis and discovery of morphologic biomarkers. AVAILABILITY AND IMPLEMENTATION: Relevant code can be found at github.com/CancerDataScience/NuCLS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Most existing microbiome association analyses focus on the association between microbiome and conditional mean of health or disease-related outcomes, and within this vein, vast computational tools and methods have been devised for standard binary or continuous outcomes. However, these methods tend to be limited either when the underlying microbiome-outcome association occurs somewhere other than the mean level, or when distribution of the outcome variable is irregular (e.g. zero-inflated or mixtures) such that conditional outcome mean is less meaningful. We address this gap by investigating association analysis between microbiome compositions and conditional outcome quantiles. RESULTS: We introduce a new association analysis tool named MiRKAT-IQ within the Microbiome Regression-based Kernel Association Test framework using Integrated Quantile regression models to examine the association between microbiome and the distribution of outcome. For an individual quantile, we utilize the existing kernel machine regression framework to examine the association between that conditional outcome quantile and a group of microbial features (e.g. microbiome community compositions). Then, the goal of examining microbiome association with the whole outcome distribution is achieved by integrating all outcome conditional quantiles over a process, and thus our new MiRKAT-IQ test is robust to both the location of association signals (e.g. mean, variance, median) and the heterogeneous distribution of the outcome. Extensive numerical simulation studies have been conducted to show the validity of the new MiRKAT-IQ test. We demonstrate the potential usefulness of MiRKAT-IQ with applications to actual biological data collected from a previous microbiome study. AVAILABILITY AND IMPLEMENTATION: R codes to implement the proposed methodology is provided in the MiRKAT package, which is available on CRAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Biomedical language models produce meaningful concept representations that are useful for a variety of biomedical natural language processing (bioNLP) applications such as named entity recognition, relationship extraction and question answering. Recent research trends have shown that the contextualized language models (e.g. BioBERT, BioELMo) possess tremendous representational power and are able to achieve impressive accuracy gains. However, these models are still unable to learn high-quality representations for concepts with low context information (i.e. rare words). Infusing the complementary information from knowledge-bases (KBs) is likely to be helpful when the corpus-specific information is insufficient to learn robust representations. Moreover, as the biomedical domain contains numerous KBs, it is imperative to develop approaches that can integrate the KBs in a continual fashion. RESULTS: We propose a new representation learning approach that progressively fuses the semantic information from multiple KBs into the pretrained biomedical language models. Since most of the KBs in the biomedical domain are expressed as parent-child hierarchies, we choose to model the hierarchical KBs and propose a new knowledge modeling strategy that encodes their topological properties at a granular level. Moreover, the proposed continual learning technique efficiently updates the concepts representations to accommodate the new knowledge while preserving the memory efficiency of contextualized language models. Altogether, the proposed approach generates knowledge-powered embeddings with high fidelity and learning efficiency. Extensive experiments conducted on bioNLP tasks validate the efficacy of the proposed approach and demonstrates its capability in generating robust concept representations.

MOTIVATION: An accurate estimation of the quality of protein model structures typifies as a cornerstone in protein structure prediction regimes. Despite the recent groundbreaking success in the field of protein structure prediction, there are certain prospects for the improvement in model quality estimation at multiple stages of protein structure prediction and thus, to further push the prediction accuracy. Here, a novel approach, named ProFitFun, for assessing the quality of protein models is proposed by harnessing the sequence and structural features of experimental protein structures in terms of the preferences of backbone dihedral angles and relative surface accessibility of their amino acid residues at the tripeptide level. The proposed approach leverages upon the backbone dihedral angle and surface accessibility preferences of the residues by accounting for its N-terminal and C-terminal neighbors in the protein structure. These preferences are used to evaluate protein structures through a machine learning approach and tested on an extensive dataset of diverse proteins. RESULTS: The approach was extensively validated on a large test dataset (n = 25 005) of protein structures, comprising 23 661 models of 82 non-homologous proteins and 1344 non-homologous experimental structures. In addition, an external dataset of 40 000 models of 200 non-homologous proteins was also used for the validation of the proposed method. Both datasets were further used for benchmarking the proposed method with four different state-of-the-art methods for protein structure quality assessment. In the benchmarking, the proposed method outperformed some state-of-the-art methods in terms of Spearman's and Pearson's correlation coefficients, average GDT-TS loss, sum of z-scores and average absolute difference of predictions over corresponding observed values. The high accuracy of the proposed approach promises a potential use of the sequence and structural features in computational protein design. AVAILABILITY AND IMPLEMENTATION: http://github.com/KYZ-LSB/ProTerS-FitFun. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Ultrahigh-throughput next-generation sequencing instruments continue to generate vast amounts of genomic data. These data are generally stored in FASTQ format. Two important simultaneous goals are space-efficient compressed storage of the genomic data and fast query performance. Toward that end, we introduce compressed indexing to store and retrieve FASTQ files. RESULTS: We propose a compressed index for FASTQ files called CIndex. CIndex uses the Burrows-Wheeler transform and the wavelet tree, combined with hybrid encoding, succinct data structures and tables REF and Rγ, to achieve minimal space usage and fast retrieval on the compressed FASTQ files. Experiments conducted over real publicly available datasets from various sequencing instruments demonstrate that our proposed index substantially outperforms existing state-of-the-art solutions. For count, locate and extract queries on reads, our method uses 2.7-41.66% points less space and provides a speedup of 70-167.16 times, 1.44-35.57 times and 1.3-55.4 times. For extracting records in FASTQ files, our method uses 2.86-14.88% points less space and provides a speedup of 3.13-20.1 times. CIndex has an additional advantage in that it can be readily adapted to work as a general-purpose text index; experiments show that it performs very well in practice. AVAILABILITY AND IMPLEMENTATION: The software is available on Github: https://github.com/Hongweihuo-Lab/CIndex. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: To digitally reconstruct the 3D neuron morphologies has long been a major bottleneck in neuroscience. One of the obstacles to automate the procedure is the low signal-background contrast (SBC) and the large dynamic range of signal and background both within and across images. RESULTS: We developed a pipeline to enhance the neurite signal and to suppress the background, with the goal of high SBC and better within- and between-image homogeneity. The performance of the image enhancement was quantitatively verified according to the different figures of merit benchmarking the image quality. In addition, the method could improve the neuron reconstruction in approximately 1/3 of the cases, with very few cases of degrading the reconstruction. This significantly outperformed three other approaches of image enhancement. Moreover, the compression rate was increased five times by average comparing the enhanced to the raw image. All results demonstrated the potential of the proposed method in leveraging the neuroscience by providing better 3D morphological reconstruction and lower cost of data storage and transfer. AVAILABILITY AND IMPLEMENTATION: The study is conducted based on the Vaa3D platform and python 3.7.9. The Vaa3D platform is available on the GitHub (https://github.com/Vaa3D). The source code of the proposed image enhancement as a Vaa3D plugin, the source code to benchmark the image quality and the example image blocks are available under the repository of vaa3d_tools/hackathon/SGuo/imPreProcess. The original fMost images of mouse brains can be found at the BICCN's Brain Image Library (BIL) (https://www.brainimagelibrary.org). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Function-related metabolites, the terminal products of the cell regulation, show a close association with complex diseases. The identification of disease-related metabolites is critical to the diagnosis, prevention and treatment of diseases. However, most existing computational approaches build networks by calculating pairwise relationships, which is inappropriate for mining higher-order relationships. RESULTS: In this study, we presented a novel approach with hypergraph-based logistic matrix factorization, HGLMF, to predict the potential interactions between metabolites and disease. First, the molecular structures and gene associations of metabolites and the hierarchical structures and GO functional annotations of diseases were extracted to build various similarity measures of metabolites and diseases. Next, the kernel neighborhood similarity of metabolites (or diseases) was calculated according to the completed interactive network. Second, multiple networks of metabolites and diseases were fused, respectively, and the hypergraph structures of metabolites and diseases were built. Finally, a logistic matrix factorization based on hypergraph was proposed to predict potential metabolite-disease interactions. In computational experiments, HGLMF accurately predicted the metabolite-disease interaction, and performed better than other state-of-the-art methods. Moreover, HGLMF could be used to predict new metabolites (or diseases). As suggested from the case studies, the proposed method could discover novel disease-related metabolites, which has been confirmed in existing studies. AVAILABILITY AND IMPLEMENTATION: The codes and dataset are available at: https://github.com/Mayingjun20179/HGLMF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Accurate and efficient compound annotation is a long-standing challenge for LC-MS-based data (e.g. untargeted metabolomics and exposomics). Substantial efforts have been devoted to overcoming this obstacle, whereas current tools are limited by the sources of spectral information used (in-house and public databases) and are not automated and streamlined. Therefore, we developed metID, an R package that combines information from all major databases for comprehensive and streamlined compound annotation. metID is a flexible, simple and powerful tool that can be installed on all platforms, allowing the compound annotation process to be fully automatic and reproducible. A detailed tutorial and a case study are provided in Supplementary Materials. AVAILABILITY AND IMPLEMENTATION: https://jaspershen.github.io/metID. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The Unipept Visualizations library is a JavaScript package to generate interactive visualizations of both hierarchical and non-hierarchical quantitative data. It provides four different visualizations: a sunburst, a treemap, a treeview and a heatmap. Every visualization is fully configurable, supports TypeScript and uses the excellent D3.js library. AVAILABILITY AND IMPLEMENTATION: The Unipept Visualizations library is available for download on NPM: https://npmjs.com/unipept-visualizations. All source code is freely available from GitHub under the MIT license: https://github.com/unipept/unipept-visualizations.

SUMMARY: We present HoPhage (Host of Phage) to identify the host of a given phage fragment from metavirome data at the genus level. HoPhage integrates two modules using a deep learning algorithm and a Markov chain model, respectively. HoPhage achieves 47.90% and 82.47% mean accuracy at the genus and phylum levels for ∼1-kb long artificial phage fragments when predicting host among 50 genera, representing 7.54-20.22% and 13.55-24.31% improvement, respectively. By testing on three real virome samples, HoPhage yields 81.11% mean accuracy at the genus level within a much broader candidate host range. AVAILABILITY AND IMPLEMENTATION: HoPhage is available at http://cqb.pku.edu.cn/ZhuLab/HoPhage/data/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The NCI Transcriptional Pharmacodynamics Workbench (NCI TPW) is an extensive compilation of directly measured transcriptional responses to anti-cancer agents across the well-characterized NCI-60 cancer cell lines. The NCI TPW data are publicly available through a web interface that allows limited user interaction with the data. We developed 'TPWshiny' as a standalone, easy to install, R application to facilitate more interactive data exploration.With no programming skills required, TPWshiny provides an intuitive and comprehensive graphical interface to help researchers understand the response of tumor cell lines to 15 therapeutic agents. The data are presented in interactive scatter plots, heatmaps, time series and Venn diagrams. Data can be queried by drug concentration, time point, gene and tissue type. Researchers can download the data for further analysis. AVAILABILITY AND IMPLEMENTATION: Users can download the ready-to-use, self-extracting package for Windows or macOS, and R source code from the project website (https://brb.nci.nih.gov/TPWshiny/). TPWshiny documentation and additional information can be found on the project website.

MOTIVATION: Functional annotation is a common part of microRNA (miRNA)-related research, typically carried as pathway enrichment analysis of the selected miRNA targets. Here, we propose miRAnno, a fast and easy-to-use web application for miRNA annotation. RESULTS: miRAnno uses comprehensive molecular interaction network and random walks with restart to measure the association between miRNAs and individual pathways. Independent validation shows that miRAnno achieves higher signal-to-noise ratio compared to the standard enrichment analysis. AVAILABILITY AND IMPLEMENTATION: miRAnno is freely available at https://ophid.utoronto.ca/miRAnno/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Over the past decades, vast amounts of genome sequencing data have been produced, requiring an enormous level of storage capacity. The time and resources needed to store and transfer such data cause bottlenecks in genome sequencing analysis. To resolve this issue, various compression techniques have been proposed to reduce the size of original FASTQ raw sequencing data, but these remain suboptimal. Long-read sequencing has become dominant in genomics, whereas most existing compression methods focus on short-read sequencing only. RESULTS: We designed a compression algorithm based on read reordering using a novel scoring model for reducing FASTQ file size with no information loss. We integrated all data processing steps into a software package called FastqCLS and provided it as a Docker image for ease of installation and execution to help users easily install and run. We compared our method with existing major FASTQ compression tools using benchmark datasets. We also included new long-read sequencing data in this validation. As a result, FastqCLS outperformed in terms of compression ratios for storing long-read sequencing data. AVAILABILITY AND IMPLEMENTATION: FastqCLS can be downloaded from https://github.com/krlucete/FastqCLS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Multiplexed immunofluorescence bioimaging of single-cells and their spatial organization in tissue holds great promise to the development of future precision diagnostics and therapeutics. Current multiplexing pipelines typically involve multiple rounds of immunofluorescence staining across multiple tissue slides. This introduces experimental batch effects that can hide underlying biological signal. It is important to have robust algorithms that can correct for the batch effects while not introducing biases into the data. Performance of data normalization methods can vary among different assay pipelines. To evaluate differences, it is critical to have a ground truth dataset that is representative of the assay. RESULTS: A new immunoFLuorescence Image NOrmalization method is presented and evaluated against alternative methods and workflows. Multiround immunofluorescence staining of the same tissue with the nuclear dye DAPI was used to represent virtual slides and a ground truth. DAPI was restained on a given tissue slide producing multiple images of the same underlying structure but undergoing multiple representative tissue handling steps. This ground truth dataset was used to evaluate and compare multiple normalization methods including median, quantile, smooth quantile, median ratio normalization and trimmed mean of the M-values. These methods were applied in both an unbiased grid object and segmented cell object workflow to 24 multiplexed biomarkers. An upper quartile normalization of grid objects in log space was found to obtain almost equivalent performance to directly normalizing segmented cell objects by the middle quantile. The developed grid-based technique was then applied with on-slide controls for evaluation. Using five or fewer controls per slide can introduce biases into the data. Ten or more on-slide controls were able to robustly correct for batch effects. AVAILABILITY AND IMPLEMENTATION: The data underlying this article along with the FLINO R-scripts used to perform the evaluation of image normalizations methods and workflows can be downloaded from https://github.com/GE-Bio/FLINO. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Drug response prediction (DRP) plays an important role in precision medicine (e.g. for cancer analysis and treatment). Recent advances in deep learning algorithms make it possible to predict drug responses accurately based on genetic profiles. However, existing methods ignore the potential relationships among genes. In addition, similarity among cell lines/drugs was rarely considered explicitly. RESULTS: We propose a novel DRP framework, called TGSA, to make better use of prior domain knowledge. TGSA consists of Twin Graph neural networks for Drug Response Prediction (TGDRP) and a Similarity Augmentation (SA) module to fuse fine-grained and coarse-grained information. Specifically, TGDRP abstracts cell lines as graphs based on STRING protein-protein association networks and uses Graph Neural Networks (GNNs) for representation learning. SA views DRP as an edge regression problem on a heterogeneous graph and utilizes GNNs to smooth the representations of similar cell lines/drugs. Besides, we introduce an auxiliary pre-training strategy to remedy the identified limitations of scarce data and poor out-of-distribution generalization. Extensive experiments on the GDSC2 dataset demonstrate that our TGSA consistently outperforms all the state-of-the-art baselines under various experimental settings. We further evaluate the effectiveness and contributions of each component of TGSA via ablation experiments. The promising performance of TGSA shows enormous potential for clinical applications in precision medicine. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/violet-sto/TGSA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Here, we present Viola, a Python package that provides structural variant (SV; large scale genome DNA variations that can result in disease, e.g. cancer) signature analytical functions and utilities for custom SV classification, merging multi-SV-caller output files and SV annotation. We demonstrate that Viola can extract biologically meaningful SV signatures from publicly available SV data for cancer and we evaluate the computational time necessary for annotation of the data. AVAILABILITY AND IMPLEMENTATION: Viola is available on pip (https://pypi.org/project/Viola-SV/) and the source code is on GitHub (https://github.com/dermasugita/Viola-SV). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The 'Subgroup Identification' (SGI) toolbox provides an algorithm to automatically detect clinical subgroups of samples in large-scale omics datasets. It is based on hierarchical clustering trees in combination with a specifically designed association testing and visualization framework that can process an arbitrary number of clinical parameters and outcomes in a systematic fashion. A multi-block extension allows for the simultaneous use of multiple omics datasets on the same samples. In this article, we first describe the functionality of the toolbox and then demonstrate its capabilities through application examples on a type 2 diabetes metabolomics study as well as two copy number variation datasets from The Cancer Genome Atlas. AVAILABILITY AND IMPLEMENTATION: SGI is an open-source package implemented in R. Package source codes and hands-on tutorials are available at https://github.com/krumsieklab/sgi. The QMdiab metabolomics data is included in the package and can be downloaded from https://doi.org/10.6084/m9.figshare.5904022. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Drug repositioning reveals novel indications for existing drugs and in particular, diseases with no available drugs. Diverse computational drug repositioning methods have been proposed by measuring either drug-treated gene expression signatures or the proximity of drug targets and disease proteins found in prior networks. However, these methods do not explain which signaling subparts allow potential drugs to be selected, and do not consider polypharmacology, i.e. multiple targets of a known drug, in specific subparts. RESULTS: Here, to address the limitations, we developed a subpathway-based polypharmacology drug repositioning method, PATHOME-Drug, based on drug-associated transcriptomes. Specifically, this tool locates subparts of signaling cascading related to phenotype changes (e.g. disease status changes), and identifies existing approved drugs such that their multiple targets are enriched in the subparts. We show that our method demonstrated better performance for detecting signaling context and specific drugs/compounds, compared to WebGestalt and clusterProfiler, for both real biological and simulated datasets. We believe that our tool can successfully address the current shortage of targeted therapy agents. AVAILABILITY AND IMPLEMENTATION: The web-service is available at http://statgen.snu.ac.kr/software/pathome. The source codes and data are available at https://github.com/labnams/pathome-drug. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell transcriptomics profiling technologies enable genome-wide gene expression measurements in individual cells but can currently only provide a static snapshot of cellular transcriptional states. RNA velocity analysis can help infer cell state changes using such single-cell transcriptomics data. To interpret these cell state changes inferred from RNA velocity analysis as part of underlying cellular trajectories, current approaches rely on visualization with principal components, t-distributed stochastic neighbor embedding and other 2D embeddings derived from the observed single-cell transcriptional states. However, these 2D embeddings can yield different representations of the underlying cellular trajectories, hindering the interpretation of cell state changes. RESULTS: We developed VeloViz to create RNA velocity-informed 2D and 3D embeddings from single-cell transcriptomics data. Using both real and simulated data, we demonstrate that VeloViz embeddings are able to capture underlying cellular trajectories across diverse trajectory topologies, even when intermediate cell states may be missing. By considering the predicted future transcriptional states from RNA velocity analysis, VeloViz can help visualize a more reliable representation of underlying cellular trajectories. AVAILABILITY AND IMPLEMENTATION: Source code is available on GitHub (https://github.com/JEFworks-Lab/veloviz) and Bioconductor (https://bioconductor.org/packages/veloviz) with additional tutorials at https://JEF.works/veloviz/. Datasets used can be found on Zenodo (https://doi.org/10.5281/zenodo.4632471). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Mendelian randomization (MR) is a valuable tool to examine the causal relationships between health risk factors and outcomes from observational studies. Along with the proliferation of genome-wide association studies, a variety of two-sample MR methods for summary data have been developed to account for horizontal pleiotropy (HP), primarily based on the assumption that the effects of variants on exposure (γ) and HP (α) are independent. In practice, this assumption is too strict and can be easily violated because of the correlated HP. RESULTS: To account for this correlated HP, we propose a Bayesian approach, MR-Corr2, that uses the orthogonal projection to reparameterize the bivariate normal distribution for γ and α, and a spike-slab prior to mitigate the impact of correlated HP. We have also developed an efficient algorithm with paralleled Gibbs sampling. To demonstrate the advantages of MR-Corr2 over existing methods, we conducted comprehensive simulation studies to compare for both type-I error control and point estimates in various scenarios. By applying MR-Corr2 to study the relationships between exposure-outcome pairs in complex traits, we did not identify the contradictory causal relationship between HDL-c and CAD. Moreover, the results provide a new perspective of the causal network among complex traits. AVAILABILITY AND IMPLEMENTATION: The developed R package and code to reproduce all the results are available at https://github.com/QingCheng0218/MR.Corr2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Tools used to identify genes in microbial sequences using a reference database generally report matches as a percent identity, which can be difficult to interpret in cases with <100% sequence identity, as changes to specific amino acids can have dramatic effects on protein function, such as when they occur in substrate binding regions or enzyme active sites, which in turn can have dramatic effects on phenotypes like antimicrobial resistance or virulence. RESULTS: Here, we present GAMMA, an open-source tool for Gene Allele Mutation Microbial Assessment, which uses protein coding-level identity to make gene calls from any gene database and generates a classification (e.g. mutant, truncation) and translated annotation (e.g. Y190S mutation, truncation at residue 110) for these calls. GAMMA accurately called antimicrobial resistance genes from a large set of genomes faster than three other tools. It can also be used with any gene database, as we demonstrated by identifying virulence genes in the same genome set. Because of its speed and flexibility, GAMMA can be used to rapidly find and annotate any gene matches of interest in microbial sequencing data. AVAILABILITY AND IMPLEMENTATION: GAMMA is freely available as a Bioconda package (https://bioconda.github.io/recipes/gamma/README.html) and as a command line script (https://github.com/rastanton/GAMMA). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We present ksrates, a user-friendly command-line tool to position ancient whole-genome duplication events with respect to speciation events in a phylogeny by comparing paralog and ortholog KS distributions derived from genomic or transcriptomic sequences, while adjusting for substitution rate differences among the lineages involved. AVAILABILITY AND IMPLEMENTATION: ksrates is implemented in Python 3 and as a Nextflow pipeline. The source code, Singularity and Docker containers, documentation and tutorial are available via https://github.com/VIB-PSB/ksrates. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Inbreeding depression and genetic purging are important processes shaping the survivability and evolution of small populations. However, detecting purging is challenging in practice, in part because there are limited tools dedicated to it. I present a new R package to assist population analyses on detection and quantification of the inbreeding depression and genetic purging of biological fitness in pedigreed populations. It includes a collection of methods to estimate different measurements of inbreeding (Wright's, partial and ancestral inbreeding coefficients) as well as purging parameters (purged inbreeding, and opportunity of purging coefficients). Additional functions are also included to estimate population parameters, allowing to contextualize inbreeding and purging these results in terms of the population demographic history. purgeR is a valuable tool to gain insight into processes related to inbreeding and purging, and to better understand fitness and inbreeding load evolution in small populations. AVAILABILITY AND IMPLEMENTATION: purgeR is an R package available at CRAN, and can be installed via install.packages("purgeR"). Source code is maintained at a GitLab repository (https://gitlab.com/elcortegano/purgeR). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Characterizing cells with rare molecular phenotypes is one of the promises of high throughput single-cell RNA sequencing (scRNA-seq) techniques. However, collecting enough cells with the desired molecular phenotype in a single experiment is challenging, requiring several samples preprocessing steps to filter and collect the desired cells experimentally before sequencing. Data integration of multiple public single-cell experiments stands as a solution for this problem, allowing the collection of enough cells exhibiting the desired molecular signatures. By increasing the sample size of the desired cell type, this approach enables a robust cell type transcriptome characterization. RESULTS: Here, we introduce rPanglaoDB, an R package to download and merge the uniformly processed and annotated scRNA-seq data provided by the PanglaoDB database. To show the potential of rPanglaoDB for collecting rare cell types by integrating multiple public datasets, we present a biological application collecting and characterizing a set of 157 fibrocytes. Fibrocytes are a rare monocyte-derived cell type, that exhibits both the inflammatory features of macrophages and the tissue remodeling properties of fibroblasts. This constitutes the first fibrocytes' unbiased transcriptome profile report. We compared the transcriptomic profile of the fibrocytes against the fibroblasts collected from the same tissue samples and confirm their associated relationship with healing processes in tissue damage and infection through the activation of the prostaglandin biosynthesis and regulation pathway. AVAILABILITY AND IMPLEMENTATION: rPanglaoDB is implemented as an R package available through the CRAN repositories https://CRAN.R-project.org/package=rPanglaoDB.

MOTIVATION: Solubility and expression levels of proteins can be a limiting factor for large-scale studies and industrial production. By determining the solubility and expression directly from the protein sequence, the success rate of wet-lab experiments can be increased. RESULTS: In this study, we focus on predicting the solubility and usability for purification of proteins expressed in Escherichia coli directly from the sequence. Our model NetSolP is based on deep learning protein language models called transformers and we show that it achieves state-of-the-art performance and improves extrapolation across datasets. As we find current methods are built on biased datasets, we curate existing datasets by using strict sequence-identity partitioning and ensure that there is minimal bias in the sequences. AVAILABILITY AND IMPLEMENTATION: The predictor and data are available at https://services.healthtech.dtu.dk/service.php?NetSolP and the open-sourced code is available at https://github.com/tvinet/NetSolP-1.0. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Accumulated clinical studies show that microbes living in humans interact closely with human hosts, and get involved in modulating drug efficacy and drug toxicity. Microbes have become novel targets for the development of antibacterial agents. Therefore, screening of microbe-drug associations can benefit greatly drug research and development. With the increase of microbial genomic and pharmacological datasets, we are greatly motivated to develop an effective computational method to identify new microbe-drug associations. RESULTS: In this article, we proposed a novel method, Graph2MDA, to predict microbe-drug associations by using variational graph autoencoder (VGAE). We constructed multi-modal attributed graphs based on multiple features of microbes and drugs, such as molecular structures, microbe genetic sequences and function annotations. Taking as input the multi-modal attribute graphs, VGAE was trained to learn the informative and interpretable latent representations of each node and the whole graph, and then a deep neural network classifier was used to predict microbe-drug associations. The hyperparameter analysis and model ablation studies showed the sensitivity and robustness of our model. We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods. We also explored the meaning of the learned latent representations of drugs and found that the drugs show obvious clustering patterns that are significantly consistent with drug ATC classification. Moreover, we conducted case studies on two microbes and two drugs and found 75-95% predicted associations have been reported in PubMed literature. Our extensive performance evaluations validated the effectiveness of our proposed method. AVAILABILITY AND IMPLEMENTATION: Source codes and preprocessed data are available at https://github.com/moen-hyb/Graph2MDA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The k-mer frequency in whole genome sequences provides researchers with an insightful perspective on genomic complexity, comparative genomics, metagenomics and phylogeny. The current k-mer counting tools are typically slow, and they require large memory and hard disk for assembled genome analysis. RESULTS: We propose a novel and ultra-fast k-mer counting algorithm, KCOSS, to fulfill k-mer counting mainly for assembled genomes with segmented Bloom filter, lock-free queue, lock-free thread pool and cuckoo hash table. We optimize running time and memory consumption by recycling memory blocks, merging multiple consecutive first-occurrence k-mers into C-read, and writing a set of C-reads to disk asynchronously. KCOSS was comparatively tested with Jellyfish2, CHTKC and KMC3 on seven assembled genomes and three sequencing datasets in running time, memory consumption, and hard disk occupation. The experimental results show that KCOSS counts k-mer with less memory and disk while having a shorter running time on assembled genomes. KCOSS can be used to calculate the k-mer frequency not only for assembled genomes but also for sequencing data. AVAILABILITYAND IMPLEMENTATION: The KCOSS software is implemented in C++. It is freely available on GitHub: https://github.com/kcoss-2021/KCOSS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: With the increasing availability of 3D-data, the focus of comparative bioinformatic analysis is shifting from protein sequence alignments toward more content-rich 3D-alignments. This raises the need for new ways to improve the accuracy of 3D-superimposition. RESULTS: We proposed guide tree optimization with genetic algorithm (GA) as a universal tool to improve the alignment quality of multiple protein 3D-structures systematically. As a proof of concept, we implemented the suggested GA-based approach in popular Matt and Caretta multiple protein 3D-structure alignment (M3DSA) algorithms, leading to a statistically significant improvement of the TM-score quality indicator by up to 220-1523% on 'SABmark Superfamilies' (in 49-77% of cases) and 'SABmark Twilight' (in 59-80% of cases) datasets. The observed improvement in collections of distant homologies highlights the potentials of GA to optimize 3D-alignments of diverse protein superfamilies as one plausible tool to study the structure-function relationship. AVAILABILITY AND IMPLEMENTATION: The source codes of patched gaCaretta and gaMatt programs are available open-access at https://github.com/n-canter/gamaps. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: COBREXA.jl is a Julia package for scalable, high-performance constraint-based reconstruction and analysis of very large-scale biological models. Its primary purpose is to facilitate the integration of modern high performance computing environments with the processing and analysis of large-scale metabolic models of challenging complexity. We report the architecture of the package, and demonstrate how the design promotes analysis scalability on several use-cases with multi-organism community models. AVAILABILITY AND IMPLEMENTATION: https://doi.org/10.17881/ZKCR-BT30. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: minoTour offers a Laboratory Informations Management System (LIMS) system for Oxford Nanopore Technology sequencers, with real-time metrics and analysis available permanently for review. Integration of unique real-time automated analysis can reduce the time required to answer biological questions, including mapping and classification of sequence while a run is in progress. Real-time sequence data require new methods of analysis which do not wait for the completion of a run and minoTour provides a framework to allow users to exploit these features. AVAILABILITY AND IMPLEMENTATION: Source code and documentation are available at https://github.com/LooseLab/minotourcli and https://github.com/LooseLab/minotourapp. Docker images are available from https://hub.docker.com/r/adoni5/, and can be installed using a preconfigured docker-compose script at https://github.com/LooseLab/minotour-docker. An example server is available at http://137.44.59.170. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Significant progress has been achieved in distance-based protein folding, due to improved prediction of inter-residue distance by deep learning. Many efforts are thus made to improve distance prediction in recent years. However, it remains unknown what is the best way of objectively assessing the accuracy of predicted distance. RESULTS: A total of 19 metrics were proposed to measure the accuracy of predicted distance. These metrics were discussed and compared quantitatively on three benchmark datasets, with distance and structure models predicted by the trRosetta pipeline. The experiments show that a few metrics, such as distance precision, have a high correlation with the model accuracy measure TM-score (Pearson's correlation coefficient >0.7). In addition, the metrics are applied to rank the distance prediction groups in CASP14. The ranking by our metrics coincides largely with the official version. These data suggest that the proposed metrics are effective for measuring distance prediction. We anticipate that this study paves the way for objectively monitoring the progress of inter-residue distance prediction. A web server and a standalone package are provided to implement the proposed metrics. AVAILABILITY AND IMPLEMENTATION: http://yanglab.nankai.edu.cn/APD. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Deep learning (DL) can significantly accelerate virtual screening of ultra-large chemical libraries, enabling the evaluation of billions of compounds at a fraction of the computational cost and time required by conventional docking. Here, we introduce DD-GUI, the graphical user interface for such DL approach we have previously developed, termed Deep Docking (DD). The DD-GUI allows for quick setups of large-scale virtual screens in an intuitive way, and provides convenient tools to track the progress and analyze the outcomes of a drug discovery project. AVAILABILITY AND IMPLEMENTATION: DD-GUI is freely available with an MIT license on GitHub at https://github.com/jamesgleave/DeepDockingGUI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Molecular signatures are critical for inferring the proportions of cell types from bulk transcriptomics data. However, the identification of these signatures is based on a methodology that relies on prior biological knowledge of the cell types being studied. When working with less known biological material, a data-driven approach is required to uncover the underlying classes and generate ad hoc signatures from healthy or pathogenic tissue. RESULTS: We present a new approach, A2Sign: Agnostic Algorithms for Signatures, based on a non-negative tensor factorization (NTF) strategy that allows us to identify cell-type-specific molecular signatures, greatly reduce collinearities and also account for inter-individual variability. We propose a global framework that can be applied to uncover molecular signatures for cell-type deconvolution in arbitrary tissues using bulk transcriptome data. We also present two new molecular signatures for deconvolution of up to 16 immune cell types using microarray or RNA-seq data. AVAILABILITY AND IMPLEMENTATION: All steps of our analysis were implemented in annotated Python notebooks (https://github.com/paulfogel/A2SIGN). To perform NTF, we used the NMTF package, which can be downloaded using Python pip install. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Biological data is ever-increasing in amount and complexity. The mapping of this data to biological entities such as nucleotide and amino acid sequences supports biological data analysis, classification and prediction. Sequence alignments and comparison allow the transfer of knowledge to evolutionary-related entities, the mapping of functional domains, the identification of binding and modification sites. To support these types of studies, we developed ProSeqViewer, a tool to visualize annotation on single sequences and multiple sequence alignments. This state-of-the-art multifunctional library was developed as a modular component to be integrated into static or dynamic web resources and support intuitive visualization of sequence features. ProseSeqViewer is extremely lightweight, fast, interactive, dynamic, responsive and works at any screen size. It generates pure HTML which is compatible with any browser and operating system. ProSeqViewer can exchange events with other visualization components and is already used by multiple biological databases. AVAILABILITY AND IMPLEMENTATION: ProSeqViewer is an open-source TypeScript library compatible with state-of-the-art website environments. The source code and an extensive documentation including use cases are available from the URL: https://github.com/BioComputingUP/ProSeqViewer.

MOTIVATION: First-line data quality assessment and exploratory data analysis are integral parts of any data analysis workflow. In high-throughput quantitative omics experiments (e.g. transcriptomics, proteomics and metabolomics), after initial processing, the data are typically presented as a matrix of numbers (feature IDs × samples). Efficient and standardized data quality metrics calculation and visualization are key to track the within-experiment quality of these rectangular data types and to guarantee for high-quality datasets and subsequent biological question-driven inference. RESULTS: We present MatrixQCvis, which provides interactive visualization of data quality metrics at the per-sample and per-feature level using R's shiny framework. It provides efficient and standardized ways to analyze data quality of quantitative omics data types that come in a matrix-like format (features IDs × samples). MatrixQCvis builds upon the Bioconductor SummarizedExperiment S4 class and thus facilitates the integration into existing workflows. AVAILABILITY AND IMPLEMENTATION: MatrixQCVis is implemented in R. It is available via Bioconductor and released under the GPL v3.0 license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Significant effort has been spent by curators to create coding systems for phenotypes such as the Human Phenotype Ontology, as well as disease-phenotype annotations. We aim to support the discovery of literature-based phenotypes and integrate them into the knowledge discovery process. RESULTS: PheneBank is a Web-portal for retrieving human phenotype-disease associations that have been text-mined from the whole of Medline. Our approach exploits state-of-the-art machine learning for concept identification by utilizing an expert annotated rare disease corpus from the PMC Text Mining subset. Evaluation of the system for entities is conducted on a gold-standard corpus of rare disease sentences and for associations against the Monarch initiative data. AVAILABILITY AND IMPLEMENTATION: The PheneBank Web-portal freely available at http://www.phenebank.org. Annotated Medline data is available from Zenodo at DOI: 10.5281/zenodo.1408800. Semantic annotation software is freely available for non-commercial use at GitHub: https://github.com/pilehvar/phenebank. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: bollito is an automated, flexible and parallelizable computational pipeline for the comprehensive analysis of single-cell RNA-seq data. Starting from FASTQ files or preprocessed expression matrices, bollito performs both basic and advanced tasks in single-cell analysis integrating >30 state-of-the-art tools. This includes quality control, read alignment, dimensionality reduction, clustering, cell-marker detection, differential expression, functional analysis, trajectory inference and RNA velocity. bollito is built using the Snakemake workflow management system, which easily connects each execution step and facilitates the reproducibility of results. bollito's modular design makes it easy to incorporate other packages into the pipeline enabling its expansion with new functionalities. AVAILABILITY AND IMPLEMENTATION: Source code is freely available at https://gitlab.com/bu_cnio/bollito under the MIT license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Gene expression-based multiclass prediction, such as tumor subtyping, is a non-trivial bioinformatic problem. Most classifier methods operate by comparing expression levels relative to other samples. Methods that base predictions on the expression pattern within a sample have been proposed as an alternative. As these methods are invariant to the cohort composition and can be applied to a sample in isolation, they can collectively be termed single sample predictors (SSP). Such predictors could potentially be used for preprocessing-free classification of new samples and be built to function across different expression platforms where proper batch and dataset normalization is challenging. Here, we evaluate the behavior of several multiclass SSPs based on binary gene-pair rules (k-Top Scoring Pairs, Absolute Intrinsic Molecular Subtyping and a new Random Forest approach) and compare them to centroids built with centered or raw expression values, with the criteria that an optimal predictor should have high accuracy, overcome differences in tumor purity, be robust across expression platforms and provide an informative prediction output score. RESULTS: We found that gene-pair-based SSPs showed excellent performance on many expression-based classification tasks. The three methods differed in prediction score output, handling of tied scores and behavior in low purity samples. The k-Top Scoring Pairs and Random Forest approach both achieved high classification accuracy while providing an informative prediction score. Although gene-pair-based SSPs have been touted as being cross-platform compatible (through training on mixed platform data), out-of-the-box compatibility with a new dataset remains a potential issue that warrants cohort-to-cohort verification. AVAILABILITY AND IMPLEMENTATION: Our R package 'multiclassPairs' (https://cran.r-project.org/package=multiclassPairs) (https://doi.org/10.1093/bioinformatics/btab088) is freely available and enables easy training, prediction, and visualization using the gene-pair rule-based Random Forest SSP method and provides additional multiclass functionalities to the switchBox k-Top-Scoring Pairs package. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Inter-protein (interfacial) contact prediction is very useful for in silico structural characterization of protein-protein interactions. Although deep learning has been applied to this problem, its accuracy is not as good as intra-protein contact prediction. RESULTS: We propose a new deep learning method GLINTER (Graph Learning of INTER-protein contacts) for interfacial contact prediction of dimers, leveraging a rotational invariant representation of protein tertiary structures and a pretrained language model of multiple sequence alignments. Tested on the 13th and 14th CASP-CAPRI datasets, the average top L/10 precision achieved by GLINTER is 54% on the homodimers and 52% on all the dimers, much higher than 30% obtained by the latest deep learning method DeepHomo on the homodimers and 15% obtained by BIPSPI on all the dimers. Our experiments show that GLINTER-predicted contacts help improve selection of docking decoys. AVAILABILITY AND IMPLEMENTATION: The software is available at https://github.com/zw2x/glinter. The datasets are available at https://github.com/zw2x/glinter/data. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This article presents maplet, an open-source R package for the creation of highly customizable, fully reproducible statistical pipelines for metabolomics data analysis. It builds on the SummarizedExperiment data structure to create a centralized pipeline framework for storing data, analysis steps, results and visualizations. maplet's key design feature is its modularity, which offers several advantages, such as ensuring code quality through the maintenance of individual functions and promoting collaborative development by removing technical barriers to code contribution. With over 90 functions, the package includes a wide range of functionalities, covering many widely used statistical approaches and data visualization techniques. AVAILABILITY AND IMPLEMENTATION: The maplet package is implemented in R and freely available at https://github.com/krumsieklab/maplet.

MOTIVATION: The increasing availability of multi-omic data has enabled the discovery of disease biomarkers in different scales. Understanding the functional interaction between multi-omic biomarkers is becoming increasingly important due to its great potential for providing insights of the underlying molecular mechanism. RESULTS: Leveraging multiple biological network databases, we integrated the relationship between single nucleotide polymorphisms (SNPs), genes/proteins and metabolites, and developed an R package Multi-omic Network Explorer Tool (MoNET) for multi-omic network analysis. This new tool enables users to not only track down the interaction of SNPs/genes with metabolome level, but also trace back for the potential risk variants/regulators given altered genes/metabolites. MoNET is expected to advance our understanding of the multi-omic findings by unveiling their transomic interactions and is likely to generate new hypotheses for further validation. AVAILABILITY AND IMPLEMENTATION: The MoNET package is freely available on https://github.com/JW-Yan/MONET. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images help in resolving the structures of macromolecules and determining their spatial relationship in a single cell, which has broad significance in cell and structural biology. Subtomogram classification and recognition constitute a primary step in the systematic recovery of these macromolecular structures. Supervised deep learning methods have been proven to be highly accurate and efficient for subtomogram classification, but suffer from limited applicability due to scarcity of annotated data. While generating simulated data for training supervised models is a potential solution, a sizeable difference in the image intensity distribution in generated data as compared with real experimental data will cause the trained models to perform poorly in predicting classes on real subtomograms. RESULTS: In this work, we present Cryo-Shift, a fully unsupervised domain adaptation and randomization framework for deep learning-based cross-domain subtomogram classification. We use unsupervised multi-adversarial domain adaption to reduce the domain shift between features of simulated and experimental data. We develop a network-driven domain randomization procedure with 'warp' modules to alter the simulated data and help the classifier generalize better on experimental data. We do not use any labeled experimental data to train our model, whereas some of the existing alternative approaches require labeled experimental samples for cross-domain classification. Nevertheless, Cryo-Shift outperforms the existing alternative approaches in cross-domain subtomogram classification in extensive evaluation studies demonstrated herein using both simulated and experimental data. AVAILABILITYAND IMPLEMENTATION: https://github.com/xulabs/aitom. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA-seq (scRNAseq) datasets are characterized by large ambient dimensionality, and their analyses can be affected by various manifestations of the dimensionality curse. One of these manifestations is the hubness phenomenon, i.e. existence of data points with surprisingly large incoming connectivity degree in the datapoint neighbourhood graph. Conventional approach to dampen the unwanted effects of high dimension consists in applying drastic dimensionality reduction. It remains unexplored if this step can be avoided thus retaining more information than contained in the low-dimensional projections, by correcting directly hubness. RESULTS: We investigated hubness in scRNAseq data. We show that hub cells do not represent any visible technical or biological bias. The effect of various hubness reduction methods is investigated with respect to the clustering, trajectory inference and visualization tasks in scRNAseq datasets. We show that hubness reduction generates neighbourhood graphs with properties more suitable for applying machine learning methods; and that it outperforms other state-of-the-art methods for improving neighbourhood graphs. As a consequence, clustering, trajectory inference and visualization perform better, especially for datasets characterized by large intrinsic dimensionality. Hubness is an important phenomenon characterizing data point neighbourhood graphs computed for various types of sequencing datasets. Reducing hubness can be beneficial for the analysis of scRNAseq data with large intrinsic dimensionality in which case it can be an alternative to drastic dimensionality reduction. AVAILABILITY AND IMPLEMENTATION: The code used to analyze the datasets and produce the figures of this article is available from https://github.com/sysbio-curie/schubness. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome-wide association studies show that variants in individual genomic loci alone are not sufficient to explain the heritability of complex, quantitative phenotypes. Many computational methods have been developed to address this issue by considering subsets of loci that can collectively predict the phenotype. This problem can be considered a challenging instance of feature selection in which the number of dimensions (loci that are screened) is much larger than the number of samples. While currently available methods can achieve decent phenotype prediction performance, they either do not scale to large datasets or have parameters that require extensive tuning. RESULTS: We propose a fast and simple algorithm, Macarons, to select a small, complementary subset of variants by avoiding redundant pairs that are likely to be in linkage disequilibrium. Our method features two interpretable parameters that control the time/performance trade-off without requiring parameter tuning. In our computational experiments, we show that Macarons consistently achieves similar or better prediction performance than state-of-the-art selection methods while having a simpler premise and being at least two orders of magnitude faster. Overall, Macarons can seamlessly scale to the human genome with ∼107 variants in a matter of minutes while taking the dependencies between the variants into account. AVAILABILITYAND IMPLEMENTATION: Macarons is available in Matlab and Python at https://github.com/serhan-yilmaz/macarons. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In recent years, cyclic peptide drugs have been receiving increasing attention because they can target proteins that are difficult to be tackled by conventional small-molecule drugs or antibody drugs. Plasma protein binding rate (%PPB) is a significant pharmacokinetic property of a compound in drug discovery and design. However, due to structural differences, previous computational prediction methods developed for small-molecule compounds cannot be successfully applied to cyclic peptides, and methods for predicting the PPB rate of cyclic peptides with high accuracy are not yet available. RESULTS: Cyclic peptides are larger than small molecules, and their local structures have a considerable impact on PPB; thus, molecular descriptors expressing residue-level local features of cyclic peptides, instead of those expressing the entire molecule, as well as the circularity of the cyclic peptides should be considered. Therefore, we developed a prediction method named CycPeptPPB using deep learning that considers both factors. First, the macrocycle ring of cyclic peptides was decomposed residue by residue. The residue-based descriptors were arranged according to the sequence information of the cyclic peptide. Furthermore, the circular data augmentation method was used, and the circular convolution method CyclicConv was devised to express the cyclic structure. CycPeptPPB exhibited excellent performance, with mean absolute error (MAE) of 4.79% and correlation coefficient (R) of 0.92 for the public drug dataset, compared to the prediction performance of the existing PPB rate prediction software (MAE=15.08%, R=0.63). AVAILABILITY AND IMPLEMENTATION: The data underlying this article are available in the online supplementary material. The source code of CycPeptPPB is available at https://github.com/akiyamalab/cycpeptppb. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: It is more and more common to perform multi-omics analyses to explore the genome at diverse levels and not only at a single level. Through integrative statistical methods, multi-omics data have the power to reveal new biological processes, potential biomarkers and subgroups in a cohort. Matrix factorization (MF) is an unsupervised statistical method that allows a clustering of individuals, but also reveals relevant omics variables from the various blocks. RESULTS: Here, we present PIntMF (Penalized Integrative Matrix Factorization), an MF model with sparsity, positivity and equality constraints. To induce sparsity in the model, we used a classical Lasso penalization on variable and individual matrices. For the matrix of samples, sparsity helps in the clustering, while normalization (matching an equality constraint) of inferred coefficients is added to improve interpretation. Moreover, we added an automatic tuning of the sparsity parameters using the famous glmnet package. We also proposed three criteria to help the user to choose the number of latent variables. PIntMF was compared with other state-of-the-art integrative methods including feature selection techniques in both synthetic and real data. PIntMF succeeds in finding relevant clusters as well as variables in two types of simulated data (correlated and uncorrelated). Next, PIntMF was applied to two real datasets (Diet and cancer), and it revealed interpretable clusters linked to available clinical data. Our method outperforms the existing ones on two criteria (clustering and variable selection). We show that PIntMF is an easy, fast and powerful tool to extract patterns and cluster samples from multi-omics data. AVAILABILITY AND IMPLEMENTATION: An R package is available at https://github.com/mpierrejean/pintmf. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Multiple sequence alignment is an initial step in many bioinformatics pipelines, including phylogeny estimation, protein structure prediction and taxonomic identification of reads produced in amplicon or metagenomic datasets, etc. Yet, alignment estimation is challenging on datasets that exhibit substantial sequence length heterogeneity, and especially when the datasets have fragmentary sequences as a result of including reads or contigs generated by next-generation sequencing technologies. Here, we examine techniques that have been developed to improve alignment estimation when datasets contain substantial numbers of fragmentary sequences. We find that MAGUS, a recently developed MSA method, is fairly robust to fragmentary sequences under many conditions, and that using a two-stage approach where MAGUS is used to align selected 'backbone sequences' and the remaining sequences are added into the alignment using ensembles of Hidden Markov Models further improves alignment accuracy. The combination of MAGUS with the ensemble of eHMMs (i.e. MAGUS+eHMMs) clearly improves on UPP, the previous leading method for aligning datasets with high levels of fragmentation. AVAILABILITY AND IMPLEMENTATION: UPP is available on https://github.com/smirarab/sepp, and MAGUS is available on https://github.com/vlasmirnov/MAGUS. MAGUS+eHMMs can be performed by running MAGUS to obtain the backbone alignment, and then using the backbone alignment as an input to UPP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Taxonomic analysis of microbial communities is well supported at the level of species and strains. However, species can contain significant phenotypic diversity and strains are rarely widely shared across global populations. Stratifying the diversity between species and strains can identify 'subspecies', which are a useful intermediary. High-throughput identification and profiling of subspecies is not yet supported in the microbiome field. Here, we use an operational definition of subspecies based on single nucleotide variant (SNV) patterns within species to identify and profile subspecies in metagenomes, along with their distinctive SNVs and genes. We incorporate this method into metaSNV v2, which extends existing SNV-calling software to support further SNV interpretation for population genetics. These new features support microbiome analyses to link SNV profiles with host phenotype or environment and niche-specificity. We demonstrate subspecies identification in marine and fecal metagenomes. In the latter, we analyze 70 species in 7524 adult and infant subjects, supporting a common subspecies population structure in the human gut microbiome and illustrating some limits in subspecies calling. AVAILABILITY AND IMPLEMENTATION: Source code, documentation, tutorials and test data are available at https://github.com/metasnv-tool/metaSNV and https://metasnv.embl.de. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In the last decade, de novo protein structure prediction accuracy for individual proteins has improved significantly by utilising deep learning (DL) methods for harvesting the co-evolution information from large multiple sequence alignments (MSAs). The same approach can, in principle, also be used to extract information about evolutionary-based contacts across protein-protein interfaces. However, most earlier studies have not used the latest DL methods for inter-chain contact distance prediction. This article introduces a fold-and-dock method based on predicted residue-residue distances with trRosetta. RESULTS: The method can simultaneously predict the tertiary and quaternary structure of a protein pair, even when the structures of the monomers are not known. The straightforward application of this method to a standard dataset for protein-protein docking yielded limited success. However, using alternative methods for generating MSAs allowed us to dock accurately significantly more proteins. We also introduced a novel scoring function, PconsDock, that accurately separates 98% of correctly and incorrectly folded and docked proteins. The average performance of the method is comparable to the use of traditional, template-based or ab initio shape-complementarity-only docking methods. Moreover, the results of conventional and fold-and-dock approaches are complementary, and thus a combined docking pipeline could increase overall docking success significantly. This methodology contributed to the best model for one of the CASP14 oligomeric targets, H1065. AVAILABILITY AND IMPLEMENTATION: All scripts for predictions and analysis are available from https://github.com/ElofssonLab/bioinfo-toolbox/ and https://gitlab.com/ElofssonLab/benchmark5/. All models joined alignments, and evaluation results are available from the following figshare repository https://doi.org/10.6084/m9.figshare.14654886.v2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The MS2-MCP (MS2 coat protein) live imaging system allows for visualization of transcription dynamics through the introduction of hairpin stem-loop sequences into a gene. A fluorescent signal at the site of nascent transcription in the nucleus quantifies mRNA production. Computational modelling can be used to infer the promoter states along with the kinetic parameters governing transcription, such as promoter switching frequency and polymerase loading rate. However, modelling of the fluorescent trace presents a challenge due its persistence; the observed fluorescence at a given time point depends on both current and previous promoter states. A compound state Hidden Markov Model (cpHMM) was recently introduced to allow inference of promoter activity from MS2-MCP data. However, the computational time for inference scales exponentially with gene length and the cpHMM is therefore not currently practical for application to many eukaryotic genes. RESULTS: We present a scalable implementation of the cpHMM for fast inference of promoter activity and transcriptional kinetic parameters. This new method can model genes of arbitrary length through the use of a time-adaptive truncated compound state space. The truncated state space provides a good approximation to the full state space by retaining the most likely set of states at each time during the forward pass of the algorithm. Testing on MS2-MCP fluorescent data collected from early Drosophila melanogaster embryos indicates that the method provides accurate inference of kinetic parameters within a computationally feasible timeframe. The inferred promoter traces generated by the model can also be used to infer single-cell transcriptional parameters. AVAILABILITY AND IMPLEMENTATION: Python implementation is available at https://github.com/ManchesterBioinference/burstInfer, along with code to reproduce the examples presented here. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Accurate disease diagnosis and prognosis based on omics data rely on the effective identification of robust prognostic and diagnostic markers that reflect the states of the biological processes underlying the disease pathogenesis and progression. In this article, we present GCNCC, a Graph Convolutional Network-based approach for Clustering and Classification, that can identify highly effective and robust network-based disease markers. Based on a geometric deep learning framework, GCNCC learns deep network representations by integrating gene expression data with protein interaction data to identify highly reproducible markers with consistently accurate prediction performance across independent datasets possibly from different platforms. GCNCC identifies these markers by clustering the nodes in the protein interaction network based on latent similarity measures learned by the deep architecture of a graph convolutional network, followed by a supervised feature selection procedure that extracts clusters that are highly predictive of the disease state. RESULTS: By benchmarking GCNCC based on independent datasets from different diseases (psychiatric disorder and cancer) and different platforms (microarray and RNA-seq), we show that GCNCC outperforms other state-of-the-art methods in terms of accuracy and reproducibility. AVAILABILITY AND IMPLEMENTATION: https://github.com/omarmaddouri/GCNCC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A major task in genetic studies is to identify genes related to human diseases and traits to understand functional characteristics of genetic mutations and enhance patient diagnosis. Compared with marginal analyses of individual genes, identification of gene pathways, i.e. a set of genes with known interactions that collectively contribute to specific biological functions, can provide more biologically meaningful results. Such gene pathway analysis can be formulated into a high-dimensional two-sample testing problem. Given the typically limited sample size of gene expression datasets, most existing two-sample tests tend to have compromised powers because they ignore or only inefficiently incorporate the auxiliary pathway information on gene interactions. RESULTS: We propose T2-DAG, a Hotelling's T2-type test for detecting differentially expressed gene pathways, which efficiently leverages the auxiliary pathway information on gene interactions from existing pathway databases through a linear structural equation model. We further establish its asymptotic distribution under pertinent assumptions. Simulation studies under various scenarios show that T2-DAG outperforms several representative existing methods with well-controlled type-I error rates and substantially improved powers, even with incomplete or inaccurate pathway information or unadjusted confounding effects. We also illustrate the performance of T2-DAG in an application to detect differentially expressed KEGG pathways between different stages of lung cancer. AVAILABILITY AND IMPLEMENTATION: The R (R Development Core Team, 2021) package T2DAG which implements the proposed T2-DAG test is available on Github at https://github.com/Jin93/T2DAG. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Adverse outcome pathways (AOPs) are a conceptual framework developed to support the use of alternative toxicology approaches in the risk assessment. AOPs are structured linear organizations of existing knowledge illustrating causal pathways from the initial molecular perturbation triggered by various stressors, through key events (KEs) at different levels of biology, to the ultimate health or ecotoxicological adverse outcome. RESULTS: Artificial intelligence can be used to systematically explore available toxicological data that can be parsed in the scientific literature. Recently, a tool called AOP-helpFinder was developed to identify associations between stressors and KEs supporting thus documentation of AOPs. To facilitate the utilization of this advanced bioinformatics tool by the scientific and the regulatory community, a webserver was created. The proposed AOP-helpFinder webserver uses better performing version of the tool which reduces the need for manual curation of the obtained results. As an example, the server was successfully applied to explore relationships of a set of endocrine disruptors with metabolic-related events. The AOP-helpFinder webserver assists in a rapid evaluation of existing knowledge stored in the PubMed database, a global resource of scientific information, to build AOPs and Adverse Outcome Networks supporting the chemical risk assessment. AVAILABILITY AND IMPLEMENTATION: AOP-helpFinder is available at http://aop-helpfinder.u-paris-sciences.fr/index.php. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: With the advancement of sequencing technologies, genomic data sets are constantly being expanded by high volumes of different data types. One recently introduced data type in genomic science is genomic signals, which are usually short-read coverage measurements over the genome. To understand and evaluate the results of such studies, one needs to understand and analyze the characteristics of the input data. RESULTS: SigTools is an R-based genomic signals visualization package developed with two objectives: (i) to facilitate genomic signals exploration in order to uncover insights for later model training, refinement and development by including distribution and autocorrelation plots; (ii) to enable genomic signals interpretation by including correlation and aggregation plots. In addition, our corresponding web application, SigTools-Shiny, extends the accessibility scope of these modules to people who are more comfortable working with graphical user interfaces instead of command-line tools. AVAILABILITY AND IMPLEMENTATION: SigTools source code, installation guide and manual is freely available on http://github.com/shohre73.

MOTIVATION: Inference of identity-by-descent (IBD) sharing along the genome between pairs of individuals has important uses. But all existing inference methods are based on genotypes, which is not ideal for low-depth Next Generation Sequencing (NGS) data from which genotypes can only be called with high uncertainty. RESULTS: We present a new probabilistic software tool, LocalNgsRelate, for inferring IBD sharing along the genome between pairs of individuals from low-depth NGS data. Its inference is based on genotype likelihoods instead of genotypes, and thereby it takes the uncertainty of the genotype calling into account. Using real data from the 1000 Genomes project, we show that LocalNgsRelate provides more accurate IBD inference for low-depth NGS data than two state-of-the-art genotype-based methods, Albrechtsen et al. (2009) and hap-IBD. We also show that the method works well for NGS data down to a depth of 2×. AVAILABILITY AND IMPLEMENTATION: LocalNgsRelate is freely available at https://github.com/idamoltke/LocalNgsRelate. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Accurate prediction of protein structure relies heavily on exploiting multiple sequence alignment (MSA) for residue mutations and correlations as this information specifies protein tertiary structure. The widely used prediction approaches usually transform MSA into inter-mediate models, say position-specific scoring matrix or profile hidden Markov model. These inter-mediate models, however, cannot fully represent residue mutations and correlations carried by MSA; hence, an effective way to directly exploit MSAs is highly desirable. RESULTS: Here, we report a novel sequence set network (called Seq-SetNet) to directly and effectively exploit MSA for protein structure prediction. Seq-SetNet uses an 'encoding and aggregation' strategy that consists of two key elements: (i) an encoding module that takes a component homologue in MSA as input, and encodes residue mutations and correlations into context-specific features for each residue; and (ii) an aggregation module to aggregate the features extracted from all component homologues, which are further transformed into structural properties for residues of the query protein. As Seq-SetNet encodes each homologue protein individually, it could consider both insertions and deletions, as well as long-distance correlations among residues, thus representing more information than the inter-mediate models. Moreover, the encoding module automatically learns effective features and thus avoids manual feature engineering. Using symmetric aggregation functions, Seq-SetNet processes the homologue proteins as a sequence set, making its prediction results invariable to the order of these proteins. On popular benchmark sets, we demonstrated the successful application of Seq-SetNet to predict secondary structure and torsion angles of residues with improved accuracy and efficiency. AVAILABILITY AND IMPLEMENTATION: The code and datasets are available through https://github.com/fusong-ju/Seq-SetNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: We present a new software-tool allowing an easy visualization of fragment ions and thus a rapid evaluation of key experimental parameters on the sequence coverage obtained for the MS/MS (tandem mass spectrometry) analysis of intact proteins. Our tool can process data obtained from various deconvolution and fragment assignment software. RESULTS: We demonstrate that TDFragMapper can rapidly highlight the experimental fragmentation parameters that are critical to the characterization of intact proteins of various size using top-down proteomics. AVAILABILITY AND IMPLEMENTATION: TDFragMapper, a demonstration video and user tutorial are freely available for academic use at https://msbio.pasteur.fr/tdfragmapper; all data are thus available from the ProteomeXchange consortium (identifier PXD024643). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Identifying sample mix-ups in biobanks is essential to allow the repurposing of genetic data for clinical pharmacogenetics. Pharmacogenetic advice based on the genetic information of another individual is potentially harmful. Existing methods for identifying mix-ups are limited to datasets in which additional omics data (e.g. gene expression) is available. Cohorts lacking such data can only use sex, which can reveal only half of the mix-ups. Here, we describe Idéfix, a method for the identification of accidental sample mix-ups in biobanks using polygenic scores. RESULTS: In the Lifelines population-based biobank, we calculated polygenic scores (PGSs) for 25 traits for 32 786 participants. We then applied Idéfix to compare the actual phenotypes to PGSs, and to use the relative discordance that is expected for mix-ups, compared to correct samples. In a simulation, using induced mix-ups, Idéfix reaches an AUC of 0.90 using 25 polygenic scores and sex. This is a substantial improvement over using only sex, which has an AUC of 0.75. Subsequent simulations present Idéfix's potential in varying datasets with more powerful PGSs. This suggests its performance will likely improve when more highly powered GWASs for commonly measured traits will become available. Idéfix can be used to identify a set of high-quality participants for whom it is very unlikely that they reflect sample mix-ups, and for these participants we can use genetic data for clinical purposes, such as pharmacogenetic profiles. For instance, in Lifelines, we can select 34.4% of participants, reducing the sample mix-up rate from 0.15% to 0.01%. AVAILABILITYAND IMPLEMENTATION: Idéfix is freely available at https://github.com/molgenis/systemsgenetics/wiki/Idefix. The individual-level data that support the findings were obtained from the Lifelines biobank under project application number ov16_0365. Data is made available upon reasonable request submitted to the LifeLines Research office (research@lifelines.nl, https://www.lifelines.nl/researcher/how-to-apply/apply-here). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: CRISPR/Cas9-based technology allows for the functional analysis of genetic variants at single nucleotide resolution whilst maintaining genomic context. This approach, known as saturation genome editing (SGE), a form of deep mutational scanning, systematically alters each position in a target region to explore its function. SGE experiments require the design and synthesis of oligonucleotide variant libraries which are introduced into the genome. This technology is applicable to diverse fields such as disease variant identification, drug development, structure-function studies, synthetic biology, evolutionary genetics and host-pathogen interactions. Here, we present the Variant Library Annotation Tool (VaLiAnT) which can be used to generate variant libraries from user-defined genomic coordinates and standard input files. The software can accommodate user-specified species, reference sequences and transcript annotations. RESULTS: Coordinates for a genomic range are provided by the user to retrieve a corresponding oligonucleotide reference sequence. A user-specified range within this sequence is then subject to systematic, nucleotide and/or amino acid saturating mutator functions. VaLiAnT provides a novel way to retrieve, mutate and annotate genomic sequences for oligonucleotide library generation. Specific features for SGE library generation can be employed. In addition, VaLiAnT is configurable, allowing for cDNA and prime editing saturation library generation, with other diverse applications possible. AVAILABILITY AND IMPLEMENTATION: VaLiAnT is a command line tool written in Python. Source code, testing data, example input and output files and executables are available (https://github.com/cancerit/VaLiAnT) in addition to a detailed user manual (https://github.com/cancerit/VaLiAnT/wiki). VaLiAnT is licensed under AGPLv3. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Teratogenic drugs can cause severe fetal malformation and therefore have critical impact on the health of the fetus, yet the teratogenic risks are unknown for most approved drugs. This article proposes an explainable machine learning model for classifying pregnancy drug safety based on multimodal data and suggests an orthogonal ensemble for modeling multimodal data. To train the proposed model, we created a set of labeled drugs by processing over 100 000 textual responses collected by a large teratology information service. Structured textual information is incorporated into the model by applying clustering analysis to textual features. RESULTS: We report an area under the receiver operating characteristic curve (AUC) of 0.891 using cross-validation and an AUC of 0.904 for cross-expert validation. Our findings suggest the safety of two drugs during pregnancy, Varenicline and Mebeverine, and suggest that Meloxicam, an NSAID, is of higher risk; according to existing data, the safety of these three drugs during pregnancy is unknown. We also present a web-based application that enables physicians to examine a specific drug and its risk factors. AVAILABILITY AND IMPLEMENTATION: The code and data is available from https://github.com/goolig/drug_safety_pregnancy_prediction.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Erratum in Bioinformatics. 2022 Jan 12;38(3):881.

SUMMARY: Mian is a web application to interactively visualize, run statistical tools and train machine learning models on operational taxonomic unit (OTU) or amplicon sequence variant (ASV) datasets to identify key taxonomic groups, diversity trends or taxonomic composition shifts in the context of provided categorical or numerical sample metadata. Tools, including Fisher's exact test, Boruta feature selection, alpha and beta diversity, and random forest and deep neural network classifiers, facilitate open-ended data exploration and hypothesis generation on microbial datasets. AVAILABILITY: Mian is freely available at: miandata.org. Mian is an open-source platform licensed under the MIT license with source code available at github.com/tbj128/mian. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Alignment-free (AF) distance/similarity functions are a key tool for sequence analysis. Experimental studies on real datasets abound and, to some extent, there are also studies regarding their control of false positive rate (Type I error). However, assessment of their power, i.e. their ability to identify true similarity, has been limited to some members of the D2 family. The corresponding experimental studies have concentrated on short sequences, a scenario no longer adequate for current applications, where sequence lengths may vary considerably. Such a State of the Art is methodologically problematic, since information regarding a key feature such as power is either missing or limited. RESULTS: By concentrating on a representative set of word-frequency-based AF functions, we perform the first coherent and uniform evaluation of the power, involving also Type I error for completeness. Two alternative models of important genomic features (CIS Regulatory Modules and Horizontal Gene Transfer), a wide range of sequence lengths from a few thousand to millions, and different values of k have been used. As a result, we provide a characterization of those AF functions that is novel and informative. Indeed, we identify weak and strong points of each function considered, which may be used as a guide to choose one for analysis tasks. Remarkably, of the 15 functions that we have considered, only four stand out, with small differences between small and short sequence length scenarios. Finally, to encourage the use of our methodology for validation of future AF functions, the Big Data platform supporting it is public. AVAILABILITY AND IMPLEMENTATION: The software is available at: https://github.com/pipp8/power_statistics. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recent advancements in fluorescence in situ hybridization (FISH) techniques enable them to concurrently obtain information on the location and gene expression of single cells. A key question in the initial analysis of such spatial transcriptomics data is the assignment of cell types. To date, most studies used methods that only rely on the expression levels of the genes in each cell for such assignments. To fully utilize the data and to improve the ability to identify novel sub-types, we developed a new method, FICT, which combines both expression and neighborhood information when assigning cell types. RESULTS: FICT optimizes a probabilistic function that we formalize and for which we provide learning and inference algorithms. We used FICT to analyze both simulated and several real spatial transcriptomics data. As we show, FICT can accurately identify cell types and sub-types, improving on expression only methods and other methods proposed for clustering spatial transcriptomics data. Some of the spatial sub-types identified by FICT provide novel hypotheses about the new functions for excitatory and inhibitory neurons. AVAILABILITY AND IMPLEMENTATION: FICT is available at: https://github.com/haotianteng/FICT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The adoption of current single-cell DNA methylation sequencing protocols is hindered by incomplete coverage, outlining the need for effective imputation techniques. The task of imputing single-cell (methylation) data requires models to build an understanding of underlying biological processes. RESULTS: We adapt the transformer neural network architecture to operate on methylation matrices through combining axial attention with sliding window self-attention. The obtained CpG Transformer displays state-of-the-art performances on a wide range of scBS-seq and scRRBS-seq datasets. Furthermore, we demonstrate the interpretability of CpG Transformer and illustrate its rapid transfer learning properties, allowing practitioners to train models on new datasets with a limited computational and time budget. AVAILABILITY AND IMPLEMENTATION: CpG Transformer is freely available at https://github.com/gdewael/cpg-transformer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The objective is to diagnose dynamics perturbations caused by amino-acid mutations as prerequisite to assess protein functional health or drug failure, simply using network models of protein X-ray structures. RESULTS: We find that the differences in the allocation of the atomic interactions of each amino acid to 1D, 2D, 3D, 4D structural levels between variants structurally robust, recover experimental dynamic perturbations. The allocation measure validated on two B-pentamers variants of AB5 toxins having 17 mutations, also distinguishes dynamic perturbations of pathogenic and non-pathogenic Transthyretin single-mutants. Finally, the main proteases of the coronaviruses SARS-CoV and SARS-CoV-2 exhibit changes in the allocation measure, raising the possibility of drug failure despite the main proteases structural similarity. AVAILABILITY AND IMPLEMENTATION: The Python code used for the production of the results is available at github.com/lorpac/protein_partitioning_atomic_contacts. The authors will run the analysis on any PDB structures of protein variants upon request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Knowledge of subcellular locations of proteins is of great significance for understanding their functions. The multi-label proteins that simultaneously reside in or move between more than one subcellular structure usually involve with complex cellular processes. Currently, the subcellular location annotations of proteins in most studies and databases are descriptive terms, which fail to capture the protein amount or fractions across different locations. This highly limits the understanding of complex spatial distribution and functional mechanism of multi-label proteins. Thus, quantitatively analyzing the multiplex location patterns of proteins is an urgent and challenging task. RESULTS: In this study, we developed a deep-learning-based pattern unmixing pipeline for protein subcellular localization (DULoc) to quantitatively estimate the fractions of proteins localizing in different subcellular compartments from immunofluorescence images. This model used a deep convolutional neural network to construct feature representations, and combined multiple nonlinear decomposing algorithms as the pattern unmixing method. Our experimental results showed that the DULoc can achieve over 0.93 correlation between estimated and true fractions on both real and synthetic datasets. In addition, we applied the DULoc method on the images in the human protein atlas database on a large scale, and showed that 70.52% of proteins can achieve consistent location orders with the database annotations. AVAILABILITY AND IMPLEMENTATION: The datasets and code are available at: https://github.com/PRBioimages/DULoc. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Clustering is a fundamental task in the analysis of nucleotide sequences. Despite the exponential increase in the size of sequence databases of homologous genes, few methods exist to cluster divergent sequences. Traditional clustering methods have mostly focused on optimizing high speed clustering of highly similar sequences. We develop a phylogenetic clustering method which infers ancestral sequences for a set of initial clusters and then uses a greedy algorithm to cluster sequences. RESULTS: We describe a clustering program AncestralClust, which is developed for clustering divergent sequences. We compare this method with other state-of-the-art clustering methods using datasets of homologous sequences from different species. We show that, in divergent datasets, AncestralClust has higher accuracy and more even cluster sizes than current popular methods. AVAILABILITY AND IMPLEMENTATION: AncestralClust is an Open Source program available at https://github.com/lpipes/ancestralclust. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: As one of the most important post-translational modifications (PTMs), protein lysine crotonylation (Kcr) has attracted wide attention, which involves in important physiological activities, such as cell differentiation and metabolism. However, experimental methods are expensive and time-consuming for Kcr identification. Instead, computational methods can predict Kcr sites in silico with high efficiency and low cost. RESULTS: In this study, we proposed a novel predictor, BERT-Kcr, for protein Kcr sites prediction, which was developed by using a transfer learning method with pre-trained bidirectional encoder representations from transformers (BERT) models. These models were originally used for natural language processing (NLP) tasks, such as sentence classification. Here, we transferred each amino acid into a word as the input information to the pre-trained BERT model. The features encoded by BERT were extracted and then fed to a BiLSTM network to build our final model. Compared with the models built by other machine learning and deep learning classifiers, BERT-Kcr achieved the best performance with AUROC of 0.983 for 10-fold cross validation. Further evaluation on the independent test set indicates that BERT-Kcr outperforms the state-of-the-art model Deep-Kcr with an improvement of about 5% for AUROC. The results of our experiment indicate that the direct use of sequence information and advanced pre-trained models of NLP could be an effective way for identifying PTM sites of proteins. AVAILABILITY AND IMPLEMENTATION: The BERT-Kcr model is publicly available on http://zhulab.org.cn/BERT-Kcr_models/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome-wide association study (GWAS) requires a researcher to perform a multitude of different actions during analysis. From editing and formatting genotype and phenotype information to running the analysis software to summarizing and visualizing the results. A typical GWAS workflow poses a significant challenge of utilizing the command-line, manual text-editing and requiring knowledge of one or more programming/scripting languages, especially for newcomers. RESULTS: vcf2gwas is a package that provides a convenient pipeline to perform all of the steps of a traditional GWAS workflow by reducing it to a single command-line input of a Variant Call Format file and a phenotype data file. In addition, all the required software is installed with the package. vcf2gwas also implements several useful features enhancing the reproducibility of GWAS analysis. AVAILABILITY AND IMPLEMENTATION: The source code of vcf2gwas is available under the GNU General Public License. The package can be easily installed using conda. Installation instructions and a manual including tutorials can be accessed on the package website at https://github.com/frankvogt/vcf2gwas. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Immune cells are important components of the immune system and are crucial for disease initiation, progression, prognosis and survival. Although several computational methods have been designed for predicting the abundance of immune cells, very few tools are applicable to mouse. Given that, mouse is the most widely used animal model in biomedical research, there is an urgent need to develop a precise algorithm for predicting mouse immune cells. RESULTS: We developed a tool named Immune Cell Abundance Identifier for mouse (ImmuCellAI-mouse), for estimating the abundance of 36 immune cell (sub)types from gene expression data in a hierarchical strategy of three layers. Reference expression profiles and robust marker gene sets of immune cell types were curated. The abundance of cells in three layers was predicted separately by calculating the ssGSEA enrichment score of the expression deviation profile per cell type. Benchmark results showed high accuracy of ImmuCellAI-mouse in predicting most immune cell types, with correlation coefficients between predicted value and real cell proportion of most cell types being larger than 0.8. We applied ImmuCellAI-mouse to a mouse breast tumor dataset and revealed the dynamic change of immune cell infiltration during treatment, which is consistent with the findings of the original study but with more details. We also constructed an online server for ImmuCellAI-mouse, on which users can upload expression matrices for analysis. ImmuCellAI-mouse will be a useful tool for studying the immune microenvironment, cancer immunology and immunotherapy in mouse models, providing an indispensable supplement for human disease studies. AVAILABILITY AND IMPLEMENTATION: Software is available at http://bioinfo.life.hust.edu.cn/ImmuCellAI-mouse/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Integrating experimental information across proteomic datasets with the wealth of publicly available sequence annotations is a crucial part in many proteomic studies that currently lacks an automated analysis platform. Here, we present AlphaMap, a Python package that facilitates the visual exploration of peptide-level proteomics data. Identified peptides and post-translational modifications in proteomic datasets are mapped to their corresponding protein sequence and visualized together with prior knowledge from UniProt and with expected proteolytic cleavage sites. The functionality of AlphaMap can be accessed via an intuitive graphical user interface or-more flexibly-as a Python package that allows its integration into common analysis workflows for data visualization. AlphaMap produces publication-quality illustrations and can easily be customized to address a given research question. AVAILABILITY AND IMPLEMENTATION: AlphaMap is implemented in Python and released under an Apache license. The source code and one-click installers are freely available at https://github.com/MannLabs/alphamap. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Nutrient and contaminant behavior in the subsurface are governed by multiple coupled hydrobiogeochemical processes which occur across different temporal and spatial scales. Accurate description of macroscopic system behavior requires accounting for the effects of microscopic and especially microbial processes. Microbial processes mediate precipitation and dissolution and change aqueous geochemistry, all of which impacts macroscopic system behavior. As 'omics data describing microbial processes is increasingly affordable and available, novel methods for using this data quickly and effectively for improved ecosystem models are needed. RESULTS: We propose a workflow ('Omics to Reactive Transport-ORT) for utilizing metagenomic and environmental data to describe the effect of microbiological processes in macroscopic reactive transport models. This workflow utilizes and couples two open-source software packages: KBase (a software platform for systems biology) and PFLOTRAN (a reactive transport modeling code). We describe the architecture of ORT and demonstrate an implementation using metagenomic and geochemical data from a river system. Our demonstration uses microbiological drivers of nitrification and denitrification to predict nitrogen cycling patterns which agree with those provided with generalized stoichiometries. While our example uses data from a single measurement, our workflow can be applied to spatiotemporal metagenomic datasets to allow for iterative coupling between KBase and PFLOTRAN. AVAILABILITY AND IMPLEMENTATION: Interactive models available at https://pflotranmodeling.paf.subsurfaceinsights.com/pflotran-simple-model/. Microbiological data available at NCBI via BioProject ID PRJNA576070. ORT Python code available at https://github.com/subsurfaceinsights/ort-kbase-to-pflotran. KBase narrative available at https://narrative.kbase.us/narrative/71260 or static narrative (no login required) at https://kbase.us/n/71260/258. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Differential network inference is a fundamental and challenging problem to reveal gene interactions and regulation relationships under different conditions. Many algorithms have been developed for this problem; however, they do not consider the differences between the importance of genes, which may not fit the real-world situation. Different genes have different mutation probabilities, and the vital genes associated with basic life activities have less fault tolerance to mutation. Equally treating all genes may bias the results of differential network inference. Thus, it is necessary to consider the importance of genes in the models of differential network inference. RESULTS: Based on the Gaussian graphical model with adaptive gene importance regularization, we develop a novel Importance-Penalized Joint Graphical Lasso method (IPJGL) for differential network inference. The presented method is validated by the simulation experiments as well as the real datasets. Furthermore, to precisely evaluate the results of differential network inference, we propose a new metric named APC2 for the differential levels of gene pairs. We apply IPJGL to analyze the TCGA colorectal and breast cancer datasets and find some candidate cancer genes with significant survival analysis results, including SOST for colorectal cancer and RBBP8 for breast cancer. We also conduct further analysis based on the interactions in the Reactome database and confirm the utility of our method. AVAILABILITY AND IMPLEMENTATION: R source code of Importance-Penalized Joint Graphical Lasso is freely available at https://github.com/Wu-Lab/IPJGL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The hourglass model is a popular evo-devo model depicting that the developmental constraints in the middle of a developmental process are higher, and hence the phenotypes are evolutionarily more conserved, than those that occur in early and late ontogeny stages. Although this model has been supported by studies analyzing developmental gene expression data, the evolutionary explanation and molecular mechanism behind this phenomenon are not fully understood yet. To approach this problem, Raff proposed a hypothesis and claimed that higher interconnectivity among elements in an organism during organogenesis resulted in the larger constraints at the mid-developmental stage. By employing stochastic network analysis and gene-set pathway analysis, we aim to demonstrate such changes of interconnectivity claimed in Raff's hypothesis. RESULTS: We first compared the changes of network randomness among developmental processes in different species by measuring the stochasticity within the biological network in each developmental stage. By tracking the network entropy along each developmental process, we found that the network stochasticity follows an anti-hourglass trajectory, and such a pattern supports Raff's hypothesis in dynamic changes of interconnections among biological modules during development. To understand which biological functions change during the transition of network stochasticity, we sketched out the pathway dynamics along the developmental stages and found that species may activate similar groups of biological processes across different stages. Moreover, higher interspecies correlations are found at the mid-developmental stages. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: MicroRNAs (miRNAs) play pivotal roles in gene expression regulation by binding to target sites of messenger RNAs (mRNAs). While identifying functional targets of miRNAs is of utmost importance, their prediction remains a great challenge. Previous computational algorithms have major limitations. They use conservative candidate target site (CTS) selection criteria mainly focusing on canonical site types, rely on laborious and time-consuming manual feature extraction, and do not fully capitalize on the information underlying miRNA-CTS interactions. RESULTS: In this article, we introduce TargetNet, a novel deep learning-based algorithm for functional miRNA target prediction. To address the limitations of previous approaches, TargetNet has three key components: (i) relaxed CTS selection criteria accommodating irregularities in the seed region, (ii) a novel miRNA-CTS sequence encoding scheme incorporating extended seed region alignments and (iii) a deep residual network-based prediction model. The proposed model was trained with miRNA-CTS pair datasets and evaluated with miRNA-mRNA pair datasets. TargetNet advances the previous state-of-the-art algorithms used in functional miRNA target classification. Furthermore, it demonstrates great potential for distinguishing high-functional miRNA targets. AVAILABILITY AND IMPLEMENTATION: The codes and pre-trained models are available at https://github.com/mswzeus/TargetNet.

SUMMARY: TARDiS is a novel phylogenetic tool for optimal genetic subsampling. It optimizes both genetic diversity and temporal distribution through a genetic algorithm. AVAILABILITY AND IMPLEMENTATION: TARDiS, along with example datasets and a user manual, is available at https://github.com/smarini/tardis-phylogenetics.

MOTIVATION: Deciphering the relationship between human genes/proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment against diseases. The Human Phenotype Ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human disorders. However, the current HPO annotations are still incomplete. Thus, it is necessary to computationally predict human protein-phenotype associations. In terms of current, cutting-edge computational methods for annotating proteins (such as functional annotation), three important features are (i) multiple network input, (ii) semi-supervised learning and (iii) deep graph convolutional network (GCN), whereas there are no methods with all these features for predicting HPO annotations of human protein. RESULTS: We develop HPODNets with all above three features for predicting human protein-phenotype associations. HPODNets adopts a deep GCN with eight layers which allows to capture high-order topological information from multiple interaction networks. Empirical results with both cross-validation and temporal validation demonstrate that HPODNets outperforms seven competing state-of-the-art methods for protein function prediction. HPODNets with the architecture of deep GCNs is confirmed to be effective for predicting HPO annotations of human protein and, more generally, node label ranking problem with multiple biomolecular networks input in bioinformatics. AVAILABILITY AND IMPLEMENTATION: https://github.com/liulizhi1996/HPODNets. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Whole genome assembly (WGA) of bacterial genomes with short reads is a quite common task as DNA sequencing has become cheaper with the advances of its technology. The process of assembling a genome has no absolute golden standard and it requires to perform a sequence of steps each of which can involve combinations of many different tools. However, the quality of the final assembly is always strongly related to the quality of the input data. With this in mind we built WGA-LP, a package that connects state-of-the-art programs for microbial analysis and novel scripts to check and improve the quality of both samples and resulting assemblies. WGA-LP, with its conservative decontamination approach, has shown to be capable of creating high quality assemblies even in the case of contaminated reads. AVAILABILITY AND IMPLEMENTATION: WGA-LP is available on GitHub (https://github.com/redsnic/WGA-LP) and Docker Hub (https://hub.docker.com/r/redsnic/wgalp). The web app for node visualization is hosted by shinyapps.io (https://redsnic.shinyapps.io/ContigCoverageVisualizer/). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Medical image fusion has developed into an important technology, which can effectively merge the significant information of multiple source images into one image. Fused images with abundant and complementary information are desirable, which contributes to clinical diagnosis and surgical planning. RESULTS: In this article, the concept of the skewness of pixel intensity (SPI) and a novel adaptive co-occurrence filter (ACOF)-based image decomposition optimization model are proposed to improve the quality of fused images. Experimental results demonstrate that the proposed method outperforms 22 state-of-the-art medical image fusion methods in terms of five objective indices and subjective evaluation, and it has higher computational efficiency. AVAILABILITY AND IMPLEMENTATION: First, the concept of SPI is applied to the co-occurrence filter to design ACOF. The initial base layers of source images are obtained using ACOF, which relies on the contents of images rather than fixed scale. Then, the widely used iterative filter framework is replaced with an optimization model to ensure that the base layer and detail layer are sufficiently separated and the image decomposition has higher computational efficiency. The optimization function is constructed based on the characteristics of the ideal base layer. Finally, the fused images are generated by designed fusion rules and linear addition. The code and data can be downloaded at https://github.com/zhunui/acof. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Reverse engineering of gene regulatory networks (GRNs) has long been an attractive research topic in system biology. Computational prediction of gene regulatory interactions has remained a challenging problem due to the complexity of gene expression and scarce information resources. The high-throughput spatial gene expression data, like in situ hybridization images that exhibit temporal and spatial expression patterns, has provided abundant and reliable information for the inference of GRNs. However, computational tools for analyzing the spatial gene expression data are highly underdeveloped. RESULTS: In this study, we develop a new method for identifying gene regulatory interactions from gene expression images, called ConGRI. The method is featured by a contrastive learning scheme and deep Siamese convolutional neural network architecture, which automatically learns high-level feature embeddings for the expression images and then feeds the embeddings to an artificial neural network to determine whether or not the interaction exists. We apply the method to a Drosophila embryogenesis dataset and identify GRNs of eye development and mesoderm development. Experimental results show that ConGRI outperforms previous traditional and deep learning methods by a large margin, which achieves accuracies of 76.7% and 68.7% for the GRNs of early eye development and mesoderm development, respectively. It also reveals some master regulators for Drosophila eye development. AVAILABILITYAND IMPLEMENTATION: https://github.com/lugimzheng/ConGRI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The growing availability of genomewide polymorphism data has fueled interest in detecting diverse selective processes affecting population diversity. However, no model-based approaches exist to jointly detect and distinguish the two complementary processes of balancing and positive selection. We extend the BalLeRMix  B-statistic framework described in Cheng and DeGiorgio (2020) for detecting balancing selection and present BalLeRMix+, which implements five B statistic extensions based on mixture models to robustly identify both types of selection. BalLeRMix+ is implemented in Python and computes the composite likelihood ratios and associated model parameters for each genomic test position. AVAILABILITY AND IMPLEMENTATION: BalLeRMix+ is freely available at https://github.com/bioXiaoheng/BallerMixPlus. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: 3D neuron segmentation is a key step for the neuron digital reconstruction, which is essential for exploring brain circuits and understanding brain functions. However, the fine line-shaped nerve fibers of neuron could spread in a large region, which brings great computational cost to the neuron segmentation. Meanwhile, the strong noises and disconnected nerve fibers bring great challenges to the task. RESULTS: In this article, we propose a 3D wavelet and deep learning-based 3D neuron segmentation method. The neuronal image is first partitioned into neuronal cubes to simplify the segmentation task. Then, we design 3D WaveUNet, the first 3D wavelet integrated encoder-decoder network, to segment the nerve fibers in the cubes; the wavelets could assist the deep networks in suppressing data noises and connecting the broken fibers. We also produce a Neuronal Cube Dataset (NeuCuDa) using the biggest available annotated neuronal image dataset, BigNeuron, to train 3D WaveUNet. Finally, the nerve fibers segmented in cubes are assembled to generate the complete neuron, which is digitally reconstructed using an available automatic tracing algorithm. The experimental results show that our neuron segmentation method could completely extract the target neuron in noisy neuronal images. The integrated 3D wavelets can efficiently improve the performance of 3D neuron segmentation and reconstruction. AVAILABILITYAND IMPLEMENTATION: The data and codes for this work are available at https://github.com/LiQiufu/3D-WaveUNet. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Driver (epi)genomic alterations underlie the positive selection of cancer subpopulations, which promotes drug resistance and relapse. Even though substantial heterogeneity is witnessed in most cancer types, mutation accumulation patterns can be regularly found and can be exploited to reconstruct predictive models of cancer evolution. Yet, available methods can not infer logical formulas connecting events to represent alternative evolutionary routes or convergent evolution. RESULTS: We introduce PMCE, an expressive framework that leverages mutational profiles from cross-sectional sequencing data to infer probabilistic graphical models of cancer evolution including arbitrary logical formulas, and which outperforms the state-of-the-art in terms of accuracy and robustness to noise, on simulations. The application of PMCE to 7866 samples from the TCGA database allows us to identify a highly significant correlation between the predicted evolutionary paths and the overall survival in 7 tumor types, proving that our approach can effectively stratify cancer patients in reliable risk groups. AVAILABILITY AND IMPLEMENTATION: PMCE is freely available at https://github.com/BIMIB-DISCo/PMCE, in addition to the code to replicate all the analyses presented in the manuscript. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The acid dissociation constant (pKa) is a critical parameter to reflect the ionization ability of chemical compounds and is widely applied in a variety of industries. However, the experimental determination of pKa is intricate and time-consuming, especially for the exact determination of micro-pKa information at the atomic level. Hence, a fast and accurate prediction of pKa values of chemical compounds is of broad interest. RESULTS: Here, we compiled a large-scale pKa dataset containing 16 595 compounds with 17 489 pKa values. Based on this dataset, a novel pKa prediction model, named Graph-pKa, was established using graph neural networks. Graph-pKa performed well on the prediction of macro-pKa values, with a mean absolute error around 0.55 and a coefficient of determination around 0.92 on the test dataset. Furthermore, combining multi-instance learning, Graph-pKa was also able to automatically deconvolute the predicted macro-pKa into discrete micro-pKa values. AVAILABILITY AND IMPLEMENTATION: The Graph-pKa model is now freely accessible via a web-based interface (https://pka.simm.ac.cn/). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Liquid-chromatography mass-spectrometry (LC-MS) is the established standard for analyzing the proteome in biological samples by identification and quantification of thousands of proteins. Machine learning (ML) promises to considerably improve the analysis of the resulting data, however, there is yet to be any tool that mediates the path from raw data to modern ML applications. More specifically, ML applications are currently hampered by three major limitations: (i) absence of balanced training data with large sample size; (ii) unclear definition of sufficiently information-rich data representations for e.g. peptide identification; (iii) lack of benchmarking of ML methods on specific LC-MS problems. RESULTS: We created the MS2AI pipeline that automates the process of gathering vast quantities of MS data for large-scale ML applications. The software retrieves raw data from either in-house sources or from the proteomics identifications database, PRIDE. Subsequently, the raw data are stored in a standardized format amenable for ML, encompassing MS1/MS2 spectra and peptide identifications. This tool bridges the gap between MS and AI, and to this effect we also present an ML application in the form of a convolutional neural network for the identification of oxidized peptides. AVAILABILITY AND IMPLEMENTATION: An open-source implementation of the software can be found at https://gitlab.com/roettgerlab/ms2ai. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA-seq (scRNA-seq) has been widely used to resolve cellular heterogeneity. After collecting scRNA-seq data, the natural next step is to integrate the accumulated data to achieve a common ontology of cell types and states. Thus, an effective and efficient cell-type identification method is urgently needed. Meanwhile, high-quality reference data remain a necessity for precise annotation. However, such tailored reference data are always lacking in practice. To address this, we aggregated multiple datasets into a meta-dataset on which annotation is conducted. Existing supervised or semi-supervised annotation methods suffer from batch effects caused by different sequencing platforms, the effect of which increases in severity with multiple reference datasets. RESULTS: Herein, a robust deep learning-based single-cell Multiple Reference Annotator (scMRA) is introduced. In scMRA, a knowledge graph is constructed to represent the characteristics of cell types in different datasets, and a graphic convolutional network serves as a discriminator based on this graph. scMRA keeps intra-cell-type closeness and the relative position of cell types across datasets. scMRA is remarkably powerful at transferring knowledge from multiple reference datasets, to the unlabeled target domain, thereby gaining an advantage over other state-of-the-art annotation methods in multi-reference data experiments. Furthermore, scMRA can remove batch effects. To the best of our knowledge, this is the first attempt to use multiple insufficient reference datasets to annotate target data, and it is, comparatively, the best annotation method for multiple scRNA-seq datasets. AVAILABILITY AND IMPLEMENTATION: An implementation of scMRA is available from https://github.com/ddb-qiwang/scMRA-torch. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Large-scale cancer genome projects have generated genomic, transcriptomic, epigenomic and clinicopathological data from thousands of samples in almost every human tumor site. Although most omics data and their associated resources are publicly available, its full integration and interpretation to dissect the sources of gene expression modulation require specialized knowledge and software. RESULTS: We present Multiomix, an interactive cloud-based platform that allows biologists to identify genetic and epigenetic events associated with the transcriptional modulation of cancer-related genes through the analysis of multi-omics data available on public functional genomic databases or user-uploaded datasets. Multiomix consists of an integrated set of functions, pipelines and a graphical user interface that allows retrieval, aggregation, analysis and visualization of different omics data sources. After the user provides the data to be analyzed, Multiomix identifies all significant correlations between mRNAs and non-mRNA genomics features (e.g. miRNA, DNA methylation and CNV) across the genome, the predicted sequence-based interactions (e.g. miRNA-mRNA) and their associated prognostic values. AVAILABILITY AND IMPLEMENTATION: Multiomix is available at https://www.multiomix.org. The source code is freely available at https://github.com/omics-datascience/multiomix. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Chromosome conformation capture technologies (Hi-C) revealed extensive DNA folding into discrete 3D domains, such as Topologically Associating Domains and chromatin loops. The correct binding of CTCF and cohesin at domain boundaries is integral in maintaining the proper structure and function of these 3D domains. 3D domains have been mapped at the resolutions of 1 kilobase and above. However, it has not been possible to define their boundaries at the resolution of boundary-forming proteins. RESULTS: To predict domain boundaries at base-pair resolution, we developed preciseTAD, an optimized transfer learning framework trained on high-resolution genome annotation data. In contrast to current TAD/loop callers, preciseTAD-predicted boundaries are strongly supported by experimental evidence. Importantly, this approach can accurately delineate boundaries in cells without Hi-C data. preciseTAD provides a powerful framework to improve our understanding of how genomic regulators are shaping the 3D structure of the genome at base-pair resolution. AVAILABILITY AND IMPLEMENTATION: preciseTAD is an R/Bioconductor package available at https://bioconductor.org/packages/preciseTAD/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Coiled-coil is composed of two or more helices that are wound around each other. It widely exists in proteins and has been discovered to play a variety of critical roles in biology processes. Generally, there are three types of structural features in coiled-coil: coiled-coil domain (CCD), oligomeric state and register. However, most of the existing computational tools only focus on one of them. RESULTS: Here, we describe a new deep learning model, CoCoPRED, which is based on convolutional layers, bidirectional long short-term memory, and attention mechanism. It has three networks, i.e. CCD network, oligomeric state network, and register network, corresponding to the three types of structural features in coiled-coil. This means CoCoPRED has the ability of fulfilling comprehensive prediction for coiled-coil proteins. Through the 5-fold cross-validation experiment, we demonstrate that CoCoPRED can achieve better performance than the state-of-the-art models on both CCD prediction and oligomeric state prediction. Further analysis suggests the CCD prediction may be a performance indicator of the oligomeric state prediction in CoCoPRED. The attention heads in CoCoPRED indicate that registers a, b and e are more crucial for the oligomeric state prediction. AVAILABILITY AND IMPLEMENTATION: CoCoPRED is available at http://www.csbio.sjtu.edu.cn/bioinf/CoCoPRED. The datasets used in this research can also be downloaded from the website. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: By detecting homology among RNAs, the probabilistic consideration of RNA structural alignments has improved the prediction accuracy of significant RNA prediction problems. Predicting an RNA consensus secondary structure from an RNA sequence alignment is a fundamental research objective because in the detection of conserved base-pairings among RNA homologs, predicting an RNA consensus secondary structure is more convenient than predicting an RNA structural alignment. RESULTS: We developed and implemented ConsAlifold, a dynamic programming-based method that predicts the consensus secondary structure of an RNA sequence alignment. ConsAlifold considers RNA structural alignments. ConsAlifold achieves moderate running time and the best prediction accuracy of RNA consensus secondary structures among available prediction methods. AVAILABILITY AND IMPLEMENTATION: ConsAlifold, data and Python scripts for generating both figures and tables are freely available at https://github.com/heartsh/consalifold. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein-protein interaction (PPI), as a relative property, is determined by two binding proteins, which brings a great challenge to design an expert model with an unbiased learning architecture and a superior generalization performance. Additionally, few efforts have been made to allow PPI predictors to discriminate between relative properties and intrinsic properties. RESULTS: We present a sequence-based approach, DeepTrio, for PPI prediction using mask multiple parallel convolutional neural networks. Experimental evaluations show that DeepTrio achieves a better performance over several state-of-the-art methods in terms of various quality metrics. Besides, DeepTrio is extended to provide additional insights into the contribution of each input neuron to the prediction results. AVAILABILITY AND IMPLEMENTATION: We provide an online application at http://bis.zju.edu.cn/deeptrio. The DeepTrio models and training data are deposited at https://github.com/huxiaoti/deeptrio.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Eukaryotic gene expression requires coordination among hundreds of transcriptional regulators. To characterize a specific transcriptional regulator, identifying how it shares genomic-binding sites with other regulators can generate important insights into its action. As genomic data such as chromatin immunoprecipitation assays with sequencing (ChIP-Seq) are being continously generated from individual labs, there is a demand for timely integration and analysis of these new data. We have developed an R package, GPSmatch (Genomic-binding Profile Similarity match), for calculating the Jaccard index to compare the ChIP-Seq peaks from one experiment to other experiments stored in a user-supplied customizable database. GPSmatch also evaluates the statistical significance of the calculated Jaccard index using a nonparametric Monte Carlo procedure. We show that GPSmatch is suitable for identifying and ranking transcriptional regulators with shared genomic-binding profiles, which may unravel potential mechanistic actions of gene regulation. AVAILABILITY AND IMPLEMENTATION: The software is freely available at https://github.com/Bao-Lab/GPSmatch. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: RNA-binding proteins are fundamental to many cellular processes. Double-stranded RNA-binding proteins (dsRBPs) in particular are crucial for RNA interference, mRNA elongation, A-to-I editing, host defense, splicing and a multitude of other important mechanisms. Since dsRBPs require double-stranded RNA to bind, their binding affinity depends on the competition among all possible secondary structures of the target RNA molecule. Here, we introduce a quantitative model that allows calculation of the effective affinity of dsRBPs to any RNA given a principal affinity and the sequence of the RNA, while fully taking into account the entire secondary structure ensemble of the RNA. RESULTS: We implement our model within the ViennaRNA folding package while maintaining its O(N3) time complexity. We validate our quantitative model by comparing with experimentally determined binding affinities and stoichiometries for transactivation response element RNA-binding protein (TRBP). We also find that the change in dsRBP binding affinity purely due to the presence of alternative RNA structures can be many orders of magnitude and that the predicted affinity of TRBP for pre-miRNA-like constructs correlates with experimentally measured processing rates. AVAILABILITY AND IMPLEMENTATION: Our modified version of the ViennaRNA package is available for download at http://bioserv.mps.ohio-state.edu/dsRBPBind, is free to use for research and educational purposes, and utilizes simple get/set methods for footprint size, concentration, cooperativity, principal dissociation constant and overlap.

MOTIVATION: Metagenomes offer a glimpse into the total genomic diversity contained within a sample. Currently, however, there is no straightforward way to obtain a non-redundant list of all putative homologs of a set of reference sequences present in a metagenome. RESULTS: To address this problem, we developed a novel clustering approach called 'metagenomic clustering by reference library' (MCRL), where a reference library containing a set of reference genes is clustered with respect to an assembled metagenome. According to our proposed approach, reference genes homologous to similar sets of metagenomic sequences, termed 'signatures', are iteratively clustered in a greedy fashion, retaining at each step the reference genes yielding the lowest E values, and terminating when signatures of remaining reference genes have a minimal overlap. The outcome of this computation is a non-redundant list of reference genes homologous to minimally overlapping sets of contigs, representing potential candidates for gene families present in the metagenome. Unlike metagenomic clustering methods, there is no need for contigs to overlap to be associated with a cluster, enabling MCRL to draw on more information encoded in the metagenome when computing tentative gene families. We demonstrate how MCRL can be used to extract candidate viral gene families from an oral metagenome and an oral virome that otherwise could not be determined using standard approaches. We evaluate the sensitivity, accuracy and robustness of our proposed method for the viral case study and compare it with existing analysis approaches. AVAILABILITY AND IMPLEMENTATION: https://github.com/a-tadmor/MCRL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Studying biological systems generally relies on computational modeling and simulation, e.g., model-driven discovery and hypothesis testing. Progress in standardization efforts led to the development of interrelated file formats to exchange and reuse models in systems biology, such as SBML, the Simulation Experiment Description Markup Language (SED-ML) or the Open Modeling EXchange format. Conducting simulation experiments based on these formats requires efficient and reusable implementations to make them accessible to the broader scientific community and to ensure the reproducibility of the results. The Systems Biology Simulation Core Library (SBSCL) provides interpreters and solvers for these standards as a versatile open-source API in JavaTM. The library simulates even complex bio-models and supports deterministic Ordinary Differential Equations; Stochastic Differential Equations; constraint-based analyses; recent SBML and SED-ML versions; exchange of results, and visualization of in silico experiments; open modeling exchange formats (COMBINE archives); hierarchically structured models; and compatibility with standard testing systems, including the Systems Biology Test Suite and published models from the BioModels and BiGG databases. AVAILABILITY AND IMPLEMENTATION: SBSCL is freely available at https://draeger-lab.github.io/SBSCL/ and via Maven Central. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.