MOTIVATION: Cells respond to environments by regulating gene expression to exploit resources optimally. Recent advances in technologies allow for measuring the abundances of RNA, proteins, lipids and metabolites. These highly complex datasets reflect the states of the different layers in a biological system. Multi-omics is the integration of these disparate methods and data to gain a clearer picture of the biological state. Multi-omic studies of the proteome and metabolome are becoming more common as mass spectrometry technology continues to be democratized. However, knowledge extraction through the integration of these data remains challenging. RESULTS: Connections between molecules in different omic layers were discovered through a combination of machine learning and model interpretation. Discovered connections reflected protein control (ProC) over metabolites. Proteins discovered to control citrate were mapped onto known genetic and metabolic networks, revealing that these protein regulators are novel. Further, clustering the magnitudes of ProC over all metabolites enabled the prediction of five gene functions, each of which was validated experimentally. Two uncharacterized genes, YJR120W and YDL157C, were accurately predicted to modulate mitochondrial translation. Functions for three incompletely characterized genes were also predicted and validated, including SDH9, ISC1 and FMP52. A website enables results exploration and also MIMaL analysis of user-supplied multi-omic data. AVAILABILITY AND IMPLEMENTATION: The website for MIMaL is at https://mimal.app. Code for the website is at https://github.com/qdickinson/mimal-website. Code to implement MIMaL is at https://github.com/jessegmeyerlab/MIMaL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The comprehensive analysis of the proteome and its modulation by post-translational modification (PTM) is increasingly used in biological and biomedical studies. As a result, proteomics data analysis is ever more carried out by scientists with limited expertise in this type of data. While excellent software solutions for comprehensive and rigorous analysis of quantitative proteomic data exist, most are complex and not well suited for non-proteomics scientists. Integrative analysis of multi-level proteomics data on protein and diverse PTMs, like phosphorylation or proteolytic processing, remains particularly challenging and inaccessible to most biologists. To fill this void, we developed SQuAPP, an R-Shiny web-based analysis pipeline for the quantitative analysis of proteomic data. SQuAPP uses a streamlined workflow model to guide expert and novice users through quality control, data pre-processing, statistical analysis and visualization steps. Processing the protein, peptide and PTM datasets in parallel and their quantitative integration enable rapid identification of protein-level-independent modulation of protein modifications and intuitive interpretation of dynamic dependencies between different protein modifications. AVAILABILITY AND IMPLEMENTATION: SQuAPP is available at http://squapp.langelab.org/. The source code and local setup instructions can be accessed from https://github.com/LangeLab/SQuAPP.

MOTIVATION: The capability to predict the potential drug binding affinity against a protein target has always been a fundamental challenge in silico drug discovery. The traditional experiments in vitro and in vivo are costly and time-consuming which need to search over large compound space. Recent years have witnessed significant success on deep learning-based models for drug-target binding affinity prediction task. RESULTS: Following the recent success of the Transformer model, we propose a multigranularity protein-ligand interaction (MGPLI) model, which adopts the Transformer encoders to represent the character-level features and fragment-level features, modeling the possible interaction between residues and atoms or their segments. In addition, we use the convolutional neural network to extract higher-level features based on transformer encoder outputs and a highway layer to fuse the protein and drug features. We evaluate MGPLI on different protein-ligand interaction datasets and show the improvement of prediction performance compared to state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: The model scripts are available at https://github.com/IILab-Resource/MGDTA.git.

SUMMARY: Due to the sparsity and high dimensionality, microbiome data are routinely summarized into pairwise distances capturing the compositional differences. Many biological insights can be gained by analyzing the distance matrix in relation to some covariates. A microbiome sampling method that characterizes the inter-sample relationship more reproducibly is expected to yield higher statistical power. Traditionally, the intraclass correlation coefficient (ICC) has been used to quantify the degree of reproducibility for a univariate measurement using technical replicates. In this work, we extend the traditional ICC to distance measures and propose a distance-based ICC (dICC). We derive the asymptotic distribution of the sample-based dICC to facilitate statistical inference. We illustrate dICC using a real dataset from a metagenomic reproducibility study. AVAILABILITY AND IMPLEMENTATION: dICC is implemented in the R CRAN package GUniFrac. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Analysis of cell types is recognized as a major task in current single-cell genotyping and phenotyping. In neuroscience, 3-D neuron morphologies are often reconstructed from multi-dimensional microscopic images. Recent studies indicate that neurons could form very complicated distributions in the feature space, and thus they can be explored using manifold analysis. We have developed manifold classification toolkit software to replace the conventional clustering analysis to discover cell subtypes from three state-of-the-art collections of single neurons' 3-D morphologies that reconstructed from images. We have gathered 9208 3-D spatially registered whole mouse brain neurons from three datasets with the highest quality to date generated by the single neuron morphology community. To explore manifold distribution, our method uses minimum spanning tree-based principal skeletons to approximate locally linear embeddings, to explore the morphological feature spaces, which correspond to dendritic arbors, axonal arbors or both categories of arborization patterns of neurons. We show manifold classification is a suitable approach for a majority of often referred cell types, each of which was also discovered to contain multiple subtypes. Our results show an initial effort to employ manifold classification but not traditional clustering analysis as an alternative framework for analyzing 3-D neuron morphologies reconstructed from 3-D microscopic images. AVAILABILITY AND IMPLEMENTATION: Freely available at https://github.com/Mr-strlen/Cell_Pattern_Analysis_Tool.

MOTIVATION: High-throughput fluorescent microscopy is a popular class of techniques for studying tissues and cells through automated imaging and feature extraction of hundreds to thousands of samples. Like other high-throughput assays, these approaches can suffer from unwanted noise and technical artifacts that obscure the biological signal. In this work, we consider how an experimental design incorporating multiple levels of replication enables the removal of technical artifacts from such image-based platforms. RESULTS: We develop a general approach to remove technical artifacts from high-throughput image data that leverages an experimental design with multiple levels of replication. To illustrate the methods, we consider microenvironment microarrays (MEMAs), a high-throughput platform designed to study cellular responses to microenvironmental perturbations. In application to MEMAs, our approach removes unwanted spatial artifacts and thereby enhances the biological signal. This approach has broad applicability to diverse biological assays. AVAILABILITY AND IMPLEMENTATION: Raw data are on synapse (syn2862345), analysis code is on github: gjhunt/mema_norm, a reproducible Docker image is available on dockerhub: gjhunt/mema_norm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: AEON.py is a Python library for the analysis of the long-term behaviour in very large asynchronous Boolean networks. It provides significant computational improvements over the state-of-the-art methods for attractor detection. Furthermore, it admits the analysis of partially specified Boolean networks with uncertain update functions. It also includes techniques for identifying viable source-target control strategies and the assessment of their robustness with respect to parameter perturbations. AVAILABILITY AND IMPLEMENTATION: All relevant results are available in Supplementary Materials. The tool is accessible through https://github.com/sybila/biodivine-aeon-py. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Species tree inference from multi-copy gene trees has long been a challenge in phylogenomics. The recent method ASTRAL-Pro has made strides by enabling multi-copy gene family trees as input and has been quickly adopted. Yet, its scalability, especially memory usage, needs to improve to accommodate the ever-growing dataset size. RESULTS: We present ASTRAL-Pro 2, an ultrafast and memory efficient version of ASTRAL-Pro that adopts a placement-based optimization algorithm for significantly better scalability without sacrificing accuracy. AVAILABILITY AND IMPLEMENTATION: The source code and binary files are publicly available at https://github.com/chaoszhang/ASTER; data are available at https://github.com/chaoszhang/A-Pro2_data. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: A collection of conformers that exist in a dynamical equilibrium defines the native state of a protein. The structural differences between them describe their conformational diversity, a defining characteristic of the protein with an essential role in multiple cellular processes. Since most proteins carry out their functions by assembling into complexes, we have developed CoDNaS-Q, the first online resource to explore conformational diversity in homooligomeric proteins. It features a curated collection of redundant protein structures with known quaternary structure. CoDNaS-Q integrates relevant annotations that allow researchers to identify and explore the extent and possible reasons of conformational diversity in homooligomeric protein complexes. AVAILABILITY AND IMPLEMENTATION: CoDNaS-Q is freely accessible at http://ufq.unq.edu.ar/codnasq/ or https://codnas-q.bioinformatica.org/home. The data can be retrieved from the website. The source code of the database can be downloaded from https://github.com/SfrRonaldo/codnas-q.

MOTIVATION: Biological processes are complex systems with distinct behaviour. Despite the growing amount of available data, knowledge is sparse and often insufficient to investigate the complex regulatory behaviour of these systems. Moreover, different cellular phenotypes are possible under varying conditions. Mathematical models attempt to unravel these mechanisms by investigating the dynamics of regulatory networks. Therefore, a major challenge is to combine regulations and phenotypical information as well as the underlying mechanisms. To predict regulatory links in these models, we established an approach called CANTATA to support the integration of information into regulatory networks and retrieve potential underlying regulations. This is achieved by optimizing both static and dynamic properties of these networks. RESULTS: Initial results show that the algorithm predicts missing interactions by recapitulating the known phenotypes while preserving the original topology and optimizing the robustness of the model. The resulting models allow for hypothesizing about the biological impact of certain regulatory dependencies. AVAILABILITY AND IMPLEMENTATION: Source code of the application, example files and results are available at https://github.com/sysbio-bioinf/Cantata. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: High-throughput chromosome conformation capture (Hi-C) is a widely used assay for studying the three-dimensional (3D) genome organization across the whole genome. Here, we present PHi-C2, a Python package supported by mathematical and biophysical polymer modeling that converts input Hi-C matrix data into the polymer model's dynamics, structural conformations and rheological features. The updated optimization algorithm for regenerating a highly similar Hi-C matrix provides a fast and accurate optimal solution compared to the previous version by eliminating the factors underlying the inefficiency of the optimization algorithm in the iterative optimization process. In addition, we have enabled a Google Colab workflow to run the algorithm, wherein users can easily change the parameters and check the results in the notebook. Overall, PHi-C2 represents a valuable tool for mining the dynamic 3D genome state embedded in Hi-C data. AVAILABILITY AND IMPLEMENTATION: PHi-C2 as the phic Python package is freely available under the GPL license and can be installed from the Python package index. The source code is available from GitHub at https://github.com/soyashinkai/PHi-C2. Moreover, users do not have to prepare a Python environment because PHi-C2 can run on Google Colab (https://bit.ly/3rlptGI). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: HMI-PRED 2.0 is a publicly available web service for the prediction of host-microbe protein-protein interaction by interface mimicry that is intended to be used without extensive computational experience. A microbial protein structure is screened against a database covering the entire available structural space of complexes of known human proteins. AVAILABILITY AND IMPLEMENTATION: HMI-PRED 2.0 provides user-friendly graphic interfaces for predicting, visualizing and analyzing host-microbe interactions. HMI-PRED 2.0 is available at https://hmipred.org/.

SUMMARY: Current pharmacophore-based virtual screening (VS) software has limited interactive capabilities and less intuitive screening processes. In this study, a novel tool named VRPharmer is proposed to perform the entire VS workflow in VR environments. VRPharmer enables users to interactively perceive computation processes and immersively observe molecular structures. Besides a typical screening mode (OPT mode), VRPharmer provides a unique interactive screening mode (SCORE mode) for freely exploring the optimal binding poses. Pharmacophore models are editable to study the impact of each feature and further refine the screening results. Moreover, molecular rendering algorithms are improved for precise representations. AVAILABILITY AND IMPLEMENTATION: VRPharmer is open-source software under the MIT license. The released version is available at https://github.com/VRPharmer/VRPharmer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We present Icolos, a workflow manager written in Python as a tool for automating complex structure-based workflows for drug design. Icolos can be used as a standalone tool, for example in virtual screening campaigns, or can be used in conjunction with deep learning-based molecular generation facilitated for example by REINVENT, a previously published molecular de novo design package. In this publication, we focus on the internal structure and general capabilities of Icolos, using molecular docking experiments as an illustrative example. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at https://github.com/MolecularAI/Icolos under the Apache 2.0 license. Tutorial notebooks containing minimal working examples can be found at https://github.com/MolecularAI/IcolosCommunity. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Various constraint-based optimization approaches have been developed for the computational analysis and design of metabolic networks. Herein, we present StrainDesign, a comprehensive Python package that builds upon the COBRApy toolbox and integrates the most popular metabolic design algorithms, including nested strain optimization methods such as OptKnock, RobustKnock and OptCouple as well as the more general minimal cut sets approach. The optimization approaches are embedded in individual modules, which can also be combined for setting up more elaborate strain design problems. Advanced features, such as the efficient integration of GPR rules and the possibility to consider gene and reaction additions or regulatory interventions, have been generalized and are available for all modules. The package uses state-of-the-art preprocessing methods, supports multiple solvers and provides a number of enhanced tools for analyzing computed intervention strategies including 2D and 3D plots of user-selected metabolic fluxes or yields. Furthermore, a user-friendly interface for the StrainDesign package has been implemented in the GUI-based metabolic modeling software CNApy. StrainDesign provides thus a unique and rich framework for computational strain design in Python, uniting many algorithmic developments in the field and allowing modular extension in the future. AVAILABILITY AND IMPLEMENTATION: The StrainDesign package can be retrieved from PyPi, Anaconda and GitHub (https://github.com/klamt-lab/straindesign) and is also part of the latest CNApy package.

MOTIVATION: Cell-cell communications regulate internal cellular states, e.g. gene expression and cell functions, and play pivotal roles in normal development and disease states. Furthermore, single-cell RNA sequencing methods have revealed cell-to-cell expression variability of highly variable genes (HVGs), which is also crucial. Nevertheless, the regulation of cell-to-cell expression variability of HVGs via cell-cell communications is still largely unexplored. The recent advent of spatial transcriptome methods has linked gene expression profiles to the spatial context of single cells, which has provided opportunities to reveal those regulations. The existing computational methods extract genes with expression levels influenced by neighboring cell types. However, limitations remain in the quantitativeness and interpretability: they neither focus on HVGs nor consider the effects of multiple neighboring cell types. RESULTS: Here, we propose CCPLS (Cell-Cell communications analysis by Partial Least Square regression modeling), which is a statistical framework for identifying cell-cell communications as the effects of multiple neighboring cell types on cell-to-cell expression variability of HVGs, based on the spatial transcriptome data. For each cell type, CCPLS performs PLS regression modeling and reports coefficients as the quantitative index of the cell-cell communications. Evaluation using simulated data showed our method accurately estimated the effects of multiple neighboring cell types on HVGs. Furthermore, applications to the two real datasets demonstrate that CCPLS can extract biologically interpretable insights from the inferred cell-cell communications. AVAILABILITY AND IMPLEMENTATION: The R package is available at https://github.com/bioinfo-tsukuba/CCPLS. The data are available at https://github.com/bioinfo-tsukuba/CCPLS_paper. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Poly-alanine (polyA) regions are protein stretches mostly composed of alanines. Despite their abundance in eukaryotic proteomes and their association to nine inherited human diseases, the structural and functional roles exerted by polyA stretches remain poorly understood. In this work we study how the amino acid context in which polyA regions are settled in proteins influences their structure and function. RESULTS: We identified glycine and proline as the most abundant amino acids within polyA and in the flanking regions of polyA tracts, in human proteins as well as in 17 additional eukaryotic species. Our analyses indicate that the non-structuring nature of these two amino acids influences the α-helical conformations predicted for polyA, suggesting a relevant role in reducing the inherent aggregation propensity of long polyA. Then, we show how polyA position in protein N-termini relates with their function as transit peptides. PolyA placed just after the initial methionine is often predicted as part of mitochondrial transit peptides, whereas when placed in downstream positions, polyA are part of signal peptides. A few examples from known structures suggest that short polyA can emerge by alanine substitutions in α-helices; but evolution by insertion is observed for longer polyA. Our results showcase the importance of studying the sequence context of homorepeats as a mechanism to shape their structure-function relationships. AVAILABILITY AND IMPLEMENTATION: The datasets used and/or analyzed during the current study are available from the corresponding author onreasonable request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In multi-cohort machine learning studies, it is critical to differentiate between effects that are reproducible across cohorts and those that are cohort-specific. Multi-task learning (MTL) is a machine learning approach that facilitates this differentiation through the simultaneous learning of prediction tasks across cohorts. Since multi-cohort data can often not be combined into a single storage solution, there would be the substantial utility of an MTL application for geographically distributed data sources. RESULTS: Here, we describe the development of 'dsMTL', a computational framework for privacy-preserving, distributed multi-task machine learning that includes three supervised and one unsupervised algorithms. First, we derive the theoretical properties of these methods and the relevant machine learning workflows to ensure the validity of the software implementation. Second, we implement dsMTL as a library for the R programming language, building on the DataSHIELD platform that supports the federated analysis of sensitive individual-level data. Third, we demonstrate the applicability of dsMTL for comorbidity modeling in distributed data. We show that comorbidity modeling using dsMTL outperformed conventional, federated machine learning, as well as the aggregation of multiple models built on the distributed datasets individually. The application of dsMTL was computationally efficient and highly scalable when applied to moderate-size (n < 500), real expression data given the actual network latency. AVAILABILITY AND IMPLEMENTATION: dsMTL is freely available at https://github.com/transbioZI/dsMTLBase (server-side package) and https://github.com/transbioZI/dsMTLClient (client-side package). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Unveiling the heterogeneity in the tissues is crucial to explore cell-cell interactions and cellular targets of human diseases. Spatial transcriptomics (ST) supplies spatial gene expression profile which has revolutionized our biological understanding, but variations in cell-type proportions of each spot with dozens of cells would confound downstream analysis. Therefore, deconvolution of ST has been an indispensable step and a technical challenge toward the higher-resolution panorama of tissues. RESULTS: Here, we propose a novel ST deconvolution method called SD2 integrating spatial information of ST data and embracing an important characteristic, dropout, which is traditionally considered as an obstruction in single-cell RNA sequencing data (scRNA-seq) analysis. First, we extract the dropout-based genes as informative features from ST and scRNA-seq data by fitting a Michaelis-Menten function. After synthesizing pseudo-ST spots by randomly composing cells from scRNA-seq data, auto-encoder is applied to discover low-dimensional and non-linear representation of the real- and pseudo-ST spots. Next, we create a graph containing embedded profiles as nodes, and edges determined by transcriptional similarity and spatial relationship. Given the graph, a graph convolutional neural network is used to predict the cell-type compositions for real-ST spots. We benchmark the performance of SD2 on the simulated seqFISH+ dataset with different resolutions and measurements which show superior performance compared with the state-of-the-art methods. SD2 is further validated on three real-world datasets with different ST technologies and demonstrates the capability to localize cell-type composition accurately with quantitative evidence. Finally, ablation study is conducted to verify the contribution of different modules proposed in SD2. AVAILABILITY AND IMPLEMENTATION: The SD2 is freely available in github (https://github.com/leihouyeung/SD2) and Zenodo (https://doi.org/10.5281/zenodo.7024684). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A common experimental output in biomedical science is a list of genes implicated in a given biological process or disease. The gene lists resulting from a group of studies answering the same, or similar, questions can be combined by ranking aggregation methods to find a consensus or a more reliable answer. Evaluating a ranking aggregation method on a specific type of data before using it is required to support the reliability since the property of a dataset can influence the performance of an algorithm. Such evaluation on gene lists is usually based on a simulated database because of the lack of a known truth for real data. However, simulated datasets tend to be too small compared to experimental data and neglect key features, including heterogeneity of quality, relevance and the inclusion of unranked lists. RESULTS: In this study, a group of existing methods and their variations that are suitable for meta-analysis of gene lists are compared using simulated and real data. Simulated data were used to explore the performance of the aggregation methods as a function of emulating the common scenarios of real genomic data, with various heterogeneity of quality, noise level and a mix of unranked and ranked data using 20 000 possible entities. In addition to the evaluation with simulated data, a comparison using real genomic data on the SARS-CoV-2 virus, cancer (non-small cell lung cancer) and bacteria (macrophage apoptosis) was performed. We summarize the results of our evaluation in a simple flowchart to select a ranking aggregation method, and in an automated implementation using the meta-analysis by information content algorithm to infer heterogeneity of data quality across input datasets. AVAILABILITY AND IMPLEMENTATION: The code for simulated data generation and running edited version of algorithms: https://github.com/baillielab/comparison_of_RA_methods. Code to perform an optimal selection of methods based on the results of this review, using the MAIC algorithm to infer the characteristics of an input dataset, can be downloaded here: https://github.com/baillielab/maic. An online service for running MAIC: https://baillielab.net/maic. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Drug repurposing is an approach used to discover new indications for existing drugs. Recently, several computational approaches have been developed for drug repurposing in cancer. Nevertheless, no approaches have reported a systematic analysis of pathway crosstalk. Pathway crosstalk, which refers to the phenomenon of interaction or cooperation between pathways, is a critical aspect of tumor pathways that allows cancer cells to survive and acquire resistance to drug therapy. Here, we innovatively developed a system biology R-based software package, DRviaSPCN, to repurpose drugs for cancer via a subpathway (SP) crosstalk network. This package provides a novel approach to prioritize cancer candidate drugs by considering drug-induced SPs and their crosstalk effects. The operation modes mainly include construction of the SP network and calculation of the centrality scores of SPs to reflect the influence of SP crosstalk, calculation of enrichment scores of drug- and disease-induced dysfunctional SPs and weighted them by the centrality scores of SPs, evaluation of the drug-disease reverse association at the weighted SP level, identification of cancer candidate drugs and visualization of the results. Its capabilities enable DRviaSPCN to find cancer candidate drugs, which will complement the recent tools which did not consider crosstalk among pathways/SPs. DRviaSPCN may help to facilitate the development of drug discovery. AVAILABILITY AND IMPLEMENTATION: The package is implemented in R and available under GPL-2 license from the CRAN website (https://CRAN.R-project.org/package=DRviaSPCN). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recognition of protein subcellular distribution patterns and identification of location biomarker proteins in cancer tissues are important for understanding protein functions and related diseases. Immunohistochemical (IHC) images enable visualizing the distribution of proteins at the tissue level, providing an important resource for the protein localization studies. In the past decades, several image-based protein subcellular location prediction methods have been developed, but the prediction accuracies still have much space to improve due to the complexity of protein patterns resulting from multi-label proteins and the variation of location patterns across cell types or states. RESULTS: Here, we propose a multi-label multi-instance model based on deep graph convolutional neural networks, GraphLoc, to recognize protein subcellular location patterns. GraphLoc builds a graph of multiple IHC images for one protein, learns protein-level representations by graph convolutions and predicts multi-label information by a dynamic threshold method. Our results show that GraphLoc is a promising model for image-based protein subcellular location prediction with model interpretability. Furthermore, we apply GraphLoc to the identification of candidate location biomarkers and potential members for protein networks. A large portion of the predicted results have supporting evidence from the existing literatures and the new candidates also provide guidance for further experimental screening. AVAILABILITY AND IMPLEMENTATION: The dataset and code are available at: www.csbio.sjtu.edu.cn/bioinf/GraphLoc. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) has been widely used to decompose complex tissues into functionally distinct cell types. The first and usually the most important step of scRNA-seq data analysis is to accurately annotate the cell labels. In recent years, many supervised annotation methods have been developed and shown to be more convenient and accurate than unsupervised cell clustering. One challenge faced by all the supervised annotation methods is the identification of the novel cell type, which is defined as the cell type that is not present in the training data, only exists in the testing data. Existing methods usually label the cells simply based on the correlation coefficients or confidence scores, which sometimes results in an excessive number of unlabeled cells. RESULTS: We developed a straightforward yet effective method combining autoencoder with iterative feature selection to automatically identify novel cells from scRNA-seq data. Our method trains an autoencoder with the labeled training data and applies the autoencoder to the testing data to obtain reconstruction errors. By iteratively selecting features that demonstrate a bi-modal pattern and reclustering the cells using the selected feature, our method can accurately identify novel cells that are not present in the training data. We further combined this approach with a support vector machine to provide a complete solution for annotating the full range of cell types. Extensive numerical experiments using five real scRNA-seq datasets demonstrated favorable performance of the proposed method over existing methods serving similar purposes. AVAILABILITY AND IMPLEMENTATION: Our R software package CAMLU is publicly available through the Zenodo repository (https://doi.org/10.5281/zenodo.7054422) or GitHub repository (https://github.com/ziyili20/CAMLU). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Identifying genes that play a causal role in cancer evolution remains one of the biggest challenges in cancer biology. With the accumulation of high-throughput multi-omics data over decades, it becomes a great challenge to effectively integrate these data into the identification of cancer driver genes. RESULTS: Here, we propose MODIG, a graph attention network (GAT)-based framework to identify cancer driver genes by combining multi-omics pan-cancer data (mutations, copy number variants, gene expression and methylation levels) with multi-dimensional gene networks. First, we established diverse types of gene relationship maps based on protein-protein interactions, gene sequence similarity, KEGG pathway co-occurrence, gene co-expression patterns and gene ontology. Then, we constructed a multi-dimensional gene network consisting of approximately 20 000 genes as nodes and five types of gene associations as multiplex edges. We applied a GAT to model within-dimension interactions to generate a gene representation for each dimension based on this graph. Moreover, we introduced a joint learning module to fuse multiple dimension-specific representations to generate general gene representations. Finally, we used the obtained gene representation to perform a semi-supervised driver gene identification task. The experiment results show that MODIG outperforms the baseline models in terms of area under precision-recall curves and area under the receiver operating characteristic curves. AVAILABILITY AND IMPLEMENTATION: The MODIG program is available at https://github.com/zjupgx/modig. The code and data underlying this article are also available on Zenodo, at https://doi.org/10.5281/zenodo.7057241. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Electronic health record (EHR) data linked to DNA biobanks are a valuable resource for understanding the phenotypic effects of human genetic variation. We previously developed the phenotype risk score (PheRS) as an approach to quantify the extent to which a patient's clinical features resemble a given Mendelian disease. Using PheRS, we have uncovered novel associations between Mendelian disease-like phenotypes and rare genetic variants, and identified patients who may have undiagnosed Mendelian disease. Although the PheRS approach is conceptually simple, it involves multiple mapping steps and was previously only available as custom scripts, limiting the approach's usability. Thus, we developed the phers R package, a complete and user-friendly set of functions and maps for performing a PheRS-based analysis on linked clinical and genetic data. The package includes up-to-date maps between EHR-based phenotypes (i.e. ICD codes and phecodes), human phenotype ontology terms and Mendelian diseases. Starting with occurrences of ICD codes, the package enables the user to calculate PheRSs, validate the scores using case-control analyses, and perform genetic association analyses. By increasing PheRS's transparency and usability, the phers R package will help improve our understanding of the relationships between rare genetic variants and clinically meaningful human phenotypes. AVAILABILITY AND IMPLEMENTATION: The phers R package is free and open-source and available on CRAN and at https://phers.hugheylab.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Exitron splicing is a type of alternative splicing where coding sequences are spliced out. Recently, exitron splicing has been shown to increase proteome plasticity and play a role in cancer. Long-read RNA-seq is well suited for quantification and discovery of alternative splicing events; however, there are currently no tools available for the detection and annotation of exitrons in long-read RNA-seq data. Here, we present ScanExitronLR, an application for the characterization and quantification of exitron splicing events in long-reads. From a BAM alignment file, reference genome and reference gene annotation, ScanExitronLR outputs exitron events at the individual transcript level. Outputs of ScanExitronLR can be used in downstream analyses of differential exitron splicing. In addition, ScanExitronLR optionally reports exitron annotations such as truncation or frameshift type, nonsense-mediated decay status and Pfam domain interruptions. We demonstrate that ScanExitronLR performs better on noisy long-reads than currently published exitron detection algorithms designed for short-read data. AVAILABILITY AND IMPLEMENTATION: ScanExitronLR is freely available at https://github.com/ylab-hi/ScanExitronLR and distributed as a pip package on the Python Package Index. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Reliable and integrated data are prerequisites for effective research on the recent coronavirus disease 2019 (COVID-19) pandemic. The CovidGraph project integrates and connects heterogeneous COVID-19 data in a knowledge graph, referred to as 'CovidGraph'. It provides easy access to multiple data sources through a single point of entry and enables flexible data exploration. AVAILABILITY AND IMPLEMENTATION: More information on CovidGraph is available from the project website: https://healthecco.org/covidgraph/. Source code and documentation are provided on GitHub: https://github.com/covidgraph. SUPPLEMENTARY INFORMATION: Supplementary data is available at Bioinformatics online.

SUMMARY: Shotgun metagenomic sequencing provides the capacity to understand microbial community structure and function at unprecedented resolution; however, the current analytical methods are constrained by a focus on taxonomic classifications that may obfuscate functional relationships. Here, we present expam, a tree-based, taxonomy agnostic tool for the identification of biologically relevant clades from shotgun metagenomic sequencing. AVAILABILITY AND IMPLEMENTATION: expam is an open-source Python application released under the GNU General Public Licence v3.0. expam installation instructions, source code and tutorials can be found at https://github.com/seansolari/expam. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Spaced seeds are robust alternatives to k-mers in analyzing nucleotide sequences with high base mismatch rates. Hashing is also crucial for efficiently storing abundant sequence data. Here, we introduce ntHash2, a fast algorithm for spaced seed hashing that can be integrated into various bioinformatics tools for efficient sequence analysis with applications in genome research. RESULTS: ntHash2 is up to 2.1× faster at hashing various spaced seeds than the previous version and 3.8× faster than conventional hashing algorithms with naïve adaptation. Additionally, we reduced the collision rate of ntHash for longer k-mer lengths and improved the uniformity of the hash distribution by modifying the canonical hashing mechanism. AVAILABILITY AND IMPLEMENTATION: ntHash2 is freely available online at github.com/bcgsc/ntHash under an MIT license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Building calibrated and discriminating predictive models can be developed through the direct optimization of model performance metrics with combinatorial search algorithms. Often, predictive algorithms are desired in clinical settings to identify patients that may be high and low risk. However, due to the large combinatorial search space, these algorithms are slow and do not guarantee the global optimality of their selection. RESULTS: Here, we present a novel and quick maximum likelihood-based feature selection algorithm, named GameRank. The method is implemented into an R package composed of additional functions to build calibrated and discriminative predictive models. AVAILABILITY AND IMPLEMENTATION: GameRank is available at https://github.com/Genentech/GameRank and released under the MIT License.

MOTIVATION: Inter-organ/inter-tissue communication is central to multi-cellular organisms including humans, and mapping inter-tissue interactions can advance system-level whole-body modeling efforts. Large volumes of biomedical literature have fostered studies that map within-tissue or tissue-agnostic interactions, but literature-mining studies that infer inter-tissue relations, such as between hormones and genes are solely missing. RESULTS: We present a first study to predict from biomedical literature the hormone-gene associations mediating inter-tissue signaling in the human body. Our BioEmbedS* models use neural network-based Biomedical word Embeddings with a Support Vector Machine classifier to predict if a hormone-gene pair is associated or not, and whether an associated gene is involved in the hormone's production or response. Model training relies on our unified dataset Hormone-Gene version 1 of ground-truth associations between genes and endocrine hormones, which we compiled and carefully balanced in the embedded space to handle data disparities, such as between poorly- versus well-studied hormones. Our BioEmbedS model recapitulates known gene mediators of tissue-tissue signaling with 70.4% accuracy; predicts novel inter-tissue communication genes in humans, which are enriched for hormone-related disorders; and generalizes well to mouse, thereby holding promise for its extension to other multi-cellular organisms as well. AVAILABILITY AND IMPLEMENTATION: Freely available at https://cross-tissue-signaling.herokuapp.com are our model predictions & datasets; https://github.com/BIRDSgroup/BioEmbedS has all relevant code. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Transcriptome-based gene co-expression analysis has become a standard procedure for structured and contextualized understanding and comparison of different conditions and phenotypes. Since large study designs with a broad variety of conditions are costly and laborious, extensive comparisons are hindered when utilizing only a single dataset. Thus, there is an increased need for tools that allow the integration of multiple transcriptomic datasets with subsequent joint analysis, which can provide a more systematic understanding of gene co-expression and co-functionality within and across conditions. To make such an integrative analysis accessible to a wide spectrum of users with differing levels of programming expertise it is essential to provide user-friendliness and customizability as well as thorough documentation. RESULTS: This article introduces horizontal CoCena (hCoCena: horizontal construction of co-expression networks and analysis), an R-package for network-based co-expression analysis that allows the analysis of a single transcriptomic dataset as well as the joint analysis of multiple datasets. With hCoCena, we provide a freely available, user-friendly and adaptable tool for integrative multi-study or single-study transcriptomics analyses alongside extensive comparisons to other existing tools. AVAILABILITY AND IMPLEMENTATION: The hCoCena R-package is provided together with R Markdowns that implement an exemplary analysis workflow including extensive documentation and detailed descriptions of data structures and objects. Such efforts not only make the tool easy to use but also enable the seamless integration of user-written scripts and functions into the workflow, creating a tool that provides a clear design while remaining flexible and highly customizable. The package and additional information including an extensive Wiki are freely available on GitHub: https://github.com/MarieOestreich/hCoCena. The version at the time of writing has been added to Zenodo under the following link: https://doi.org/10.5281/zenodo.6911782. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A wide range of computational packages has been developed for regional DNA methylation analyses of Illumina's Infinium array data. Aclust, one of the first unsupervised algorithms, was originally designed to analyze regional methylation of Infinium's 27K and 450K arrays by clustering neighboring methylation sites prior to downstream analyses. However, Aclust relied on outdated packages that rendered it largely non-operational especially with the newer Infinium EPIC and mouse arrays. RESULTS: We have created Aclust2.0, a streamlined pipeline that involves five steps for the analyses of human (450K and EPIC) and mouse array data. Aclust2.0 provides a user-friendly pipeline and versatile for regional DNA methylation analyses for molecular epidemiological and mouse studies. AVAILABILITY AND IMPLEMENTATION: Aclust2.0 is freely available on Github (https://github.com/OluwayioseOA/Alcust2.0.git).

In biomedical natural language processing, named entity recognition (NER) and named entity normalization (NEN) are key tasks that enable the automatic extraction of biomedical entities (e.g. diseases and drugs) from the ever-growing biomedical literature. In this article, we present BERN2 (Advanced Biomedical Entity Recognition and Normalization), a tool that improves the previous neural network-based NER tool by employing a multi-task NER model and neural network-based NEN models to achieve much faster and more accurate inference. We hope that our tool can help annotate large-scale biomedical texts for various tasks such as biomedical knowledge graph construction. AVAILABILITY AND IMPLEMENTATION: Web service of BERN2 is publicly available at http://bern2.korea.ac.kr. We also provide local installation of BERN2 at https://github.com/dmis-lab/BERN2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome-scale metabolic reconstructions have been assembled for thousands of organisms using a wide range of tools. However, metabolite annotations, required to compare and link metabolites between reconstructions, remain incomplete. Here, we aim to further extend metabolite annotation coverage using various databases and chemoinformatic approaches. RESULTS: We developed a COBRA toolbox extension, deemed MetaboAnnotator, which facilitates the comprehensive annotation of metabolites with database independent and dependent identifiers, obtains molecular structure files, and calculates metabolite formula and charge at pH 7.2. The resulting metabolite annotations allow for subsequent cross-mapping between reconstructions and mapping of, e.g., metabolomic data. AVAILABILITY AND IMPLEMENTATION: MetaboAnnotator and tutorials are freely available at https://github.com/opencobra. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We developed grenepipe, an all-in-one Snakemake workflow to streamline the data processing from raw high-throughput sequencing data of individuals or populations to genotype variant calls. Our pipeline offers a range of popular software tools within a single configuration file, automatically installs software dependencies, is highly optimized for scalability in cluster environments and runs with a single command. AVAILABILITY AND IMPLEMENTATION: grenepipe is published under the GPLv3 and freely available at github.com/moiexpositoalonsolab/grenepipe.

MOTIVATION: The medical data are complex in nature as terms that appear in records usually appear in different contexts. Through this article, we investigate various bio model's embeddings (BioBERT, BioELECTRA and PubMedBERT) on their understanding of 'negation and speculation context' wherein we found that these models were unable to differentiate 'negated context' versus 'non-negated context'. To measure the understanding of models, we used cosine similarity scores of negated sentence embeddings versus non-negated sentence embeddings pairs. For improving these models, we introduce a generic super tuning approach to enhance the embeddings on 'negation and speculation context' by utilizing a synthesized dataset. RESULTS: After super-tuning the models, we can see that the model's embeddings are now understanding negative and speculative contexts much better. Furthermore, we fine-tuned the super-tuned models on various tasks and we found that the model has outperformed the previous models and achieved state-of-the-art on negation, speculation cue and scope detection tasks on BioScope abstracts and Sherlock dataset. We also confirmed that our approach had a very minimal trade-off in the performance of the model in other tasks like natural language inference after super-tuning. AVAILABILITY AND IMPLEMENTATION: The source code, data and the models are available at: https://github.com/comprehend/engg-ai-research/tree/uncertainty-super-tuning.

MOTIVATION: Gene-centric bioinformatics studies frequently involve the calculation or the extraction of various features of genes such as splice sites, promoters, independent introns and untranslated regions (UTRs) through manipulation of gene models. Gene models are often annotated in gene transfer format (GTF) files. The features are essential for subsequent analysis such as intron retention detection, DNA-binding site identification and computing splicing strength of splice sites. Some features such as independent introns and splice sites are not provided in existing resources including the commonly used BioMart database. A package that implements and integrates functions to analyze various features of genes will greatly ease routine analysis for related bioinformatics studies. However, to the best of our knowledge, such a package is not available yet. RESULTS: We introduce GTFtools, a stand-alone command-line software that provides a set of functions to calculate various gene features, including splice sites, independent introns, transcription start sites (TSS)-flanking regions, UTRs, isoform coordination and length, different types of gene lengths, etc. It takes the ENSEMBL or GENCODE GTF files as input and can be applied to both human and non-human gene models like the lab mouse. We compare the utilities of GTFtools with those of two related tools: Bedtools and BioMart. GTFtools is implemented in Python and not dependent on any third-party software, making it very easy to install and use. AVAILABILITY AND IMPLEMENTATION: GTFtools is freely available at www.genemine.org/gtftools.php as well as pyPI and Bioconda.

Comment in Bioinformatics. 2022 Oct 14;38(20):4848-4849.

MOTIVATION: Tumours evolve as heterogeneous populations of cells, which may be distinguished by different genomic aberrations. The resulting intra-tumour heterogeneity plays an important role in cancer patient relapse and treatment failure, so that obtaining a clear understanding of each patient's tumour composition and evolutionary history is key for personalized therapies. Single-cell sequencing (SCS) now provides the possibility to resolve tumour heterogeneity at the highest resolution of individual tumour cells, but brings with it challenges related to the particular noise profiles of the sequencing protocols as well as the complexity of the underlying evolutionary process. RESULTS: By modelling the noise processes and allowing mutations to be lost or to reoccur during tumour evolution, we present a method to jointly call mutations in each cell, reconstruct the phylogenetic relationship between cells, and determine the locations of mutational losses and recurrences. Our Bayesian approach allows us to accurately call mutations as well as to quantify our certainty in such predictions. We show the advantages of allowing mutational loss or recurrence with simulated data and present its application to tumour SCS data. AVAILABILITY AND IMPLEMENTATION: SCIΦN is available at https://github.com/cbg-ethz/SCIPhIN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: RNA epigenetics is an emerging field to study the post-transcriptional gene regulation. The dynamics of RNA epigenetic modification have been reported to associate with many human diseases. Recently developed high-throughput technology named Methylated RNA Immunoprecipitation Sequencing (MeRIP-seq) enables the transcriptome-wide profiling of N6-methyladenosine (m6A) modification and comparison of RNA epigenetic modifications. There are a few computational methods for the comparison of mRNA modifications under different conditions but they all suffer from serious limitations. RESULTS: In this work, we develop a novel statistical method to detect differentially methylated mRNA regions from MeRIP-seq data. We model the sequence count data by a hierarchical negative binomial model that accounts for various sources of variations and derive parameter estimation and statistical testing procedures for flexible statistical inferences under general experimental designs. Extensive benchmark evaluations in simulation and real data analyses demonstrate that our method is more accurate, robust and flexible compared to existing methods. AVAILABILITY AND IMPLEMENTATION: Our method TRESS is implemented as an R/Bioconductor package and is available at https://bioconductor.org/packages/devel/TRESS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Somatic copy-number alterations (SCNAs) play an important role in cancer development. Systematic noise in sequencing and array data present a significant challenge to the inference of SCNAs for cancer genome analyses. As part of The Cancer Genome Atlas, the Broad Institute Genome Characterization Center developed the Tangent normalization method to generate copy-number profiles using data from single-nucleotide polymorphism (SNP) arrays and whole-exome sequencing (WES) technologies for over 10 000 pairs of tumors and matched normal samples. Here, we describe the Tangent method, which uses a unique linear combination of normal samples as a reference for each tumor sample, to subtract systematic errors that vary across samples. We also describe a modification of Tangent, called Pseudo-Tangent, which enables denoising through comparisons between tumor profiles when few normal samples are available. RESULTS: Tangent normalization substantially increases signal-to-noise ratios (SNRs) compared to conventional normalization methods in both SNP array and WES analyses. Tangent and Pseudo-Tangent normalizations improve the SNR by reducing noise with minimal effect on signal and exceed the contribution of other steps in the analysis such as choice of segmentation algorithm. Tangent and Pseudo-Tangent are broadly applicable and enable more accurate inference of SCNAs from DNA sequencing and array data. AVAILABILITY AND IMPLEMENTATION: Tangent is available at https://github.com/broadinstitute/tangent and as a Docker image (https://hub.docker.com/r/broadinstitute/tangent). Tangent is also the normalization method for the copy-number pipeline in Genome Analysis Toolkit 4 (GATK4). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Drug combinations have exhibited promise in treating cancers with less toxicity and fewer adverse reactions. However, in vitro screening of synergistic drug combinations is time-consuming and labor-intensive because of the combinatorial explosion. Although a number of computational methods have been developed for predicting synergistic drug combinations, the multi-way relations between drug combinations and cell lines existing in drug synergy data have not been well exploited. RESULTS: We propose a multi-way relation-enhanced hypergraph representation learning method to predict anti-cancer drug synergy, named HypergraphSynergy. HypergraphSynergy formulates synergistic drug combinations over cancer cell lines as a hypergraph, in which drugs and cell lines are represented by nodes and synergistic drug-drug-cell line triplets are represented by hyperedges, and leverages the biochemical features of drugs and cell lines as node attributes. Then, a hypergraph neural network is designed to learn the embeddings of drugs and cell lines from the hypergraph and predict drug synergy. Moreover, the auxiliary task of reconstructing the similarity networks of drugs and cell lines is considered to enhance the generalization ability of the model. In the computational experiments, HypergraphSynergy outperforms other state-of-the-art synergy prediction methods on two benchmark datasets for both classification and regression tasks and is applicable to unseen drug combinations or cell lines. The studies revealed that the hypergraph formulation allows us to capture and explain complex multi-way relations of drug combinations and cell lines, and also provides a flexible framework to make the best use of diverse information. AVAILABILITY AND IMPLEMENTATION: The source data and codes of HypergraphSynergy can be freely downloaded from https://github.com/liuxuan666/HypergraphSynergy. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Computational systems biology analyses typically make use of multiple software and their dependencies, which are often run across heterogeneous compute environments. This can introduce differences in performance and reproducibility. Capturing metadata (e.g. package versions, GPU model) currently requires repetitious code and is difficult to store centrally for analysis. Even where virtual environments and containers are used, updates over time mean that versioning metadata should still be captured within analysis pipelines to guarantee reproducibility. RESULTS: Microbench is a simple and extensible Python package to automate metadata capture to a file or Redis database. Captured metadata can include execution time, software package versions, environment variables, hardware information, Python version and more, with plugins. We present three case studies demonstrating Microbench usage to benchmark code execution and examine environment metadata for reproducibility purposes. AVAILABILITY AND IMPLEMENTATION: Install from the Python Package Index using pip install microbench. Source code is available from https://github.com/alubbock/microbench. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: With the recent surge of large-cohort scale single cell research, it is of critical importance that analytical methods can fully utilize the comprehensive characterization of cellular systems that single cell technologies produce to provide insights into samples from individuals. Currently, there is little consensus on the best ways to compress information from the complex data structures of these technologies to summary statistics that represent each sample (e.g. individuals). RESULTS: Here, we present scFeatures, an approach that creates interpretable cellular and molecular representations of single-cell and spatial data at the sample level. We demonstrate that summarizing a broad collection of features at the sample level is both important for understanding underlying disease mechanisms in different experimental studies and for accurately classifying disease status of individuals. AVAILABILITY AND IMPLEMENTATION: scFeatures is publicly available as an R package at https://github.com/SydneyBioX/scFeatures. All data used in this study are publicly available with accession ID reported in the Section 2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Metagenomics is the study of microbiomes using DNA sequencing. A microbiome consists of an assemblage of microbes that is associated with a 'theater of activity' (ToA). An important question is, to what degree does the taxonomic and functional content of the former depend on the (details of the) latter? Here, we investigate a related technical question: Given a taxonomic and/or functional profile estimated from metagenomic sequencing data, how to predict the associated ToA? We present a deep-learning approach to this question. We use both taxonomic and functional profiles as input. We apply node2vec to embed hierarchical taxonomic profiles into numerical vectors. We then perform dimension reduction using clustering, to address the sparseness of the taxonomic data and thus make the problem more amenable to deep-learning algorithms. Functional features are combined with textual descriptions of protein families or domains. We present an ensemble deep-learning framework DeepToA for predicting the ToA of amicrobial community, based on taxonomic and functional profiles. We use SHAP (SHapley Additive exPlanations) values to determine which taxonomic and functional features are important for the prediction. RESULTS: Based on 7560 metagenomic profiles downloaded from MGnify, classified into 10 different theaters of activity, we demonstrate that DeepToA has an accuracy of 98.30%. We show that adding textual information to functional features increases the accuracy. AVAILABILITY AND IMPLEMENTATION: Our approach is available at http://ab.inf.uni-tuebingen.de/software/deeptoa. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: With the advent of high-throughput sequencing in molecular biology and medicine, the need for scalable statistical solutions for modeling complex biological systems has become of critical importance. The increasing number of platforms and possible experimental scenarios raised the problem of integrating large amounts of new heterogeneous data and current knowledge, to test novel hypotheses and improve our comprehension of physiological processes and diseases. RESULTS: Combining network analysis and causal inference within the framework of structural equation modeling (SEM), we developed the R package SEMgraph. It provides a fully automated toolkit, managing complex biological systems as multivariate networks, ensuring robustness and reproducibility through data-driven evaluation of model architecture and perturbation, which is readily interpretable in terms of causal effects among system components. AVAILABILITY AND IMPLEMENTATION: SEMgraph package is available at https://cran.r-project.org/web/packages/SEMgraph. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The joint analysis of multiple phenotypes is important in many biological studies, such as plant and animal breeding. The heritability estimation for a linear combination of phenotypes is designed to account for correlation information. Existing methods for estimating heritability mainly focus on single phenotypes under random-effect models. These methods also require some stringent conditions, which calls for a more flexible and interpretable method for estimating heritability. Fixed-effect models emerge as a useful alternative. RESULTS: In this article, we propose a novel heritability estimator based on multivariate ridge regression for linear combinations of phenotypes, yielding accurate estimates in both sparse and dense cases. Under mild conditions in the high-dimensional setting, the proposed estimator appears to be consistent and asymptotically normally distributed. Simulation studies show that the proposed estimator is promising under different scenarios. Compared with independently combined heritability estimates in the case of multiple phenotypes, the proposed method significantly improves the performance by considering correlations among those phenotypes. We further demonstrate its application in heritability estimation and correlation analysis for the Oryza sativa rice dataset. AVAILABILITY AND IMPLEMENTATION: An R package implementing the proposed method is available at https://github.com/xg-SUFE1/MultiRidgeVar, where covariance estimates are also given together with heritability estimates. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Computational methods that track single cells and quantify fluorescent biosensors in time-lapse microscopy images have revolutionized our approach in studying the molecular control of cellular decisions. One barrier that limits the adoption of single-cell analysis in biomedical research is the lack of efficient methods to robustly track single cells over cell division events. Here, we developed an application that automatically tracks and assigns mother-daughter relationships of single cells. By incorporating cell cycle information from a well-established fluorescent cell cycle reporter, we associate mitosis relationships enabling high fidelity long-term single-cell tracking. This was achieved by integrating a deep-learning-based fluorescent proliferative cell nuclear antigen signal instance segmentation module with a cell tracking and cell cycle resolving pipeline. The application offers a user-friendly interface and extensible APIs for customized cell cycle analysis and manual correction for various imaging configurations. AVAILABILITY AND IMPLEMENTATION: pcnaDeep is an open-source Python application under the Apache 2.0 licence. The source code, documentation and tutorials are available at https://github.com/chan-labsite/PCNAdeep. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Flow cytometry (FCM) and transcription profiling are the two widely used assays in translational immunology research. However, there is no data integration pipeline for analyzing these two types of assays together with experiment variables for biomarker inference. Current FCM data analysis mainly relies on subjective manual gating analysis, which is difficult to be directly integrated with other automated computational methods. Existing deconvolutional analysis of bulk transcriptomics relies on predefined marker genes in the transcriptomics data, which are unavailable for novel cell types and does not utilize the FCM data that provide canonical phenotypic definitions of the cell types. RESULTS: We developed a novel analytics pipeline-FastMix-for computational immunology, which integrates flow cytometry, bulk transcriptomics and clinical covariates for identifying cell type-specific gene expression signatures and biomarker genes. FastMix addresses the 'large p, small n' problem in the gene expression and flow cytometry integration analysis via a linear mixed effects model (LMER) for both cross-sectional and longitudinal studies. Its novel moment-based estimator not only reduces bias in parameter estimation but also is more efficient than iterative optimization. The FastMix pipeline also includes a cutting-edge flow cytometry data analysis method-DAFi-for identifying cell populations of interest and their characteristics. Simulation studies showed that FastMix produced smaller type I/II errors than competing methods. Validation using real data of two vaccine studies showed that FastMix identified a consistent set of signature genes as in independent single-cell RNA-seq analysis, producing additional interesting findings. AVAILABILITY AND IMPLEMENTATION: Source code of FastMix is publicly available at https://github.com/terrysun0302/FastMix. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Analysis of whole-genome sequencing (WGS) for genetics is still a challenge due to the lack of accurate functional annotation of non-coding variants, especially the rare ones. As eQTLs have been extensively implicated in the genetics of human diseases, we hypothesize that rare non-coding variants discovered in WGS play a regulatory role in predisposing disease risk. RESULTS: With thousands of tissue- and cell-type-specific epigenomic features, we propose TVAR. This multi-label learning-based deep neural network predicts the functionality of non-coding variants in the genome based on eQTLs across 49 human tissues in the GTEx project. TVAR learns the relationships between high-dimensional epigenomics and eQTLs across tissues, taking the correlation among tissues into account to understand shared and tissue-specific eQTL effects. As a result, TVAR outputs tissue-specific annotations, with an average AUROC of 0.77 across these tissues. We evaluate TVAR's performance on four complex diseases (coronary artery disease, breast cancer, Type 2 diabetes and Schizophrenia), using TVAR's tissue-specific annotations, and observe its superior performance in predicting functional variants for both common and rare variants, compared with five existing state-of-the-art tools. We further evaluate TVAR's G-score, a scoring scheme across all tissues, on ClinVar, fine-mapped GWAS loci, Massive Parallel Reporter Assay (MPRA) validated variants and observe the consistently better performance of TVAR compared with other competing tools. AVAILABILITY AND IMPLEMENTATION: The TVAR source code and its scores on the ClinVar catalog, fine mapped GWAS Loci, high confidence eQTLs from GTEx dataset, and MPRA validated functional variants are available at https://github.com/haiyang1986/TVAR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: DNA metabarcoding is an emerging approach to assess and monitor biodiversity worldwide and consequently the number and size of data sets increases exponentially. To date, no published DNA metabarcoding data processing pipeline exists that is (i) platform independent, (ii) easy to use [incl. graphical user interface (GUI)], (iii) fast (does scale well with dataset size) and (iv) complies with data protection regulations of e.g. environmental agencies. The presented pipeline APSCALE meets these requirements and handles the most common tasks of sequence data processing, such as paired-end merging, primer trimming, quality filtering, clustering and denoising of any popular metabarcoding marker, such as internal transcribed spacer, 16S or cytochrome c oxidase subunit I. APSCALE comes in a command line and a GUI version. The latter provides the user with additional summary statistics options and links to GUI-based downstream applications. AVAILABILITY AND IMPLEMENTATION: APSCALE is written in Python, a platform-independent language, and integrates functions of the open-source tools, VSEARCH (Rognes et al., 2016), cutadapt (Martin, 2011) and LULU (Frøslev et al., 2017). All modules support multithreading to allow fast processing of larger DNA metabarcoding datasets. Further information and troubleshooting are provided on the respective GitHub pages for the command-line version (https://github.com/DominikBuchner/apscale) and the GUI-based version (https://github.com/TillMacher/apscale_gui), including a detailed tutorial. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single cell RNA-Sequencing (scRNA-seq) has rapidly gained popularity over the last few years for profiling the transcriptomes of thousands to millions of single cells. This technology is now being used to analyse experiments with complex designs including biological replication. One question that can be asked from single cell experiments, which has been difficult to directly address with bulk RNA-seq data, is whether the cell type proportions are different between two or more experimental conditions. As well as gene expression changes, the relative depletion or enrichment of a particular cell type can be the functional consequence of disease or treatment. However, cell type proportion estimates from scRNA-seq data are variable and statistical methods that can correctly account for different sources of variability are needed to confidently identify statistically significant shifts in cell type composition between experimental conditions. RESULTS: We have developed propeller, a robust and flexible method that leverages biological replication to find statistically significant differences in cell type proportions between groups. Using simulated cell type proportions data, we show that propeller performs well under a variety of scenarios. We applied propeller to test for significant changes in cell type proportions related to human heart development, ageing and COVID-19 disease severity. AVAILABILITY AND IMPLEMENTATION: The propeller method is publicly available in the open source speckle R package (https://github.com/phipsonlab/speckle). All the analysis code for the article is available at the associated analysis website: https://phipsonlab.github.io/propeller-paper-analysis/. The speckle package, analysis scripts and datasets have been deposited at https://doi.org/10.5281/zenodo.7009042. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: LipidMS was initially envisioned to use fragmentation rules and data-independent acquisition (DIA) for lipid annotation. However, data-dependent acquisition (DDA) remains the most widespread acquisition mode for untargeted LC-MS/MS-based lipidomics. Here, we present LipidMS 3.0, an R package that not only adds DDA and new lipid classes to its pipeline but also the required functionalities to cover the whole data analysis workflow from pre-processing (i.e. peak-peaking, alignment and grouping) to lipid annotation. RESULTS: We applied the new workflow in the data analysis of a commercial human serum pool spiked with 68 representative lipid standards acquired in full scan, DDA and DIA modes. When focusing on the detected lipid standard features and total identified lipids, LipidMS 3.0 data pre-processing performance is similar to XCMS, whereas it complements the annotations returned by MS-DIAL, providing a higher level of structural information and a lower number of incorrect annotations. To extend and facilitate LipidMS 3.0 usage among less experienced R-programming users, the workflow is also implemented as a web-based application. AVAILABILITY AND IMPLEMENTATION: The LipidMS R-package is freely available at https://CRAN.R-project.org/package=LipidMS and as a website at http://www.lipidms.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Current advances in omics technologies are paving the diagnosis of rare diseases proposing a complementary assay to identify the responsible gene. The use of transcriptomic data to identify aberrant gene expression (AGE) has demonstrated to yield potential pathogenic events. However, popular approaches for AGE identification are limited by the use of statistical tests that imply the choice of arbitrary cut-off for significance assessment and the availability of several replicates not always possible in clinical contexts. RESULTS: Hence, we developed ABerrant Expression Identification empLoying machine LEarning from sequencing data (ABEILLE) a variational autoencoder (VAE)-based method for the identification of AGEs from the analysis of RNA-seq data without the need for replicates or a control group. ABEILLE combines the use of a VAE, able to model any data without specific assumptions on their distribution, and a decision tree to classify genes as AGE or non-AGE. An anomaly score is associated with each gene in order to stratify AGE by the severity of aberration. We tested ABEILLE on a semi-synthetic and an experimental dataset demonstrating the importance of the flexibility of the VAE configuration to identify potential pathogenic candidates. AVAILABILITY AND IMPLEMENTATION: ABEILLE source code is freely available at: https://github.com/UCA-MSI/ABEILLE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Machine learning models for predicting cell-type-specific transcription factor (TF) binding sites have become increasingly more accurate thanks to the increased availability of next-generation sequencing data and more standardized model evaluation criteria. However, knowledge transfer from data-rich to data-limited TFs and cell types remains crucial for improving TF binding prediction models because available binding labels are highly skewed towards a small collection of TFs and cell types. Transfer prediction of TF binding sites can potentially benefit from a multitask learning approach; however, existing methods typically use shallow single-task models to generate low-resolution predictions. Here, we propose NetTIME, a multitask learning framework for predicting cell-type-specific TF binding sites with base-pair resolution. RESULTS: We show that the multitask learning strategy for TF binding prediction is more efficient than the single-task approach due to the increased data availability. NetTIME trains high-dimensional embedding vectors to distinguish TF and cell-type identities. We show that this approach is critical for the success of the multitask learning strategy and allows our model to make accurate transfer predictions within and beyond the training panels of TFs and cell types. We additionally train a linear-chain conditional random field (CRF) to classify binding predictions and show that this CRF eliminates the need for setting a probability threshold and reduces classification noise. We compare our method's predictive performance with two state-of-the-art methods, Catchitt and Leopard, and show that our method outperforms previous methods under both supervised and transfer learning settings. AVAILABILITY AND IMPLEMENTATION: NetTIME is freely available at https://github.com/ryi06/NetTIME and the code is also archived at https://doi.org/10.5281/zenodo.6994897. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Serial-section electron microscopy (ssEM) is a powerful technique for cellular visualization, especially for large-scale specimens. Limited by the field of view, a megapixel image of whole-specimen is regularly captured by stitching several overlapping images. However, suffering from distortion by manual operations, lens distortion or electron impact, simple rigid transformations are not adequate for perfect mosaic generation. Non-linear deformation usually causes 'ghosting' phenomenon, especially with high magnification. To date, existing microscope image processing tools provide mature rigid stitching methods but have no idea with local distortion correction. RESULTS: In this article, following the development of unsupervised deep learning, we present a multi-scale network to predict the dense deformation fields of image pairs in ssEM and blend these images into a clear and seamless montage. The model is composed of two pyramidal backbones, sharing parameters and interacting with a set of registration modules, in which the pyramidal architecture could effectively capture large deformation according to multi-scale decomposition. A novel 'intermediate-space solving' paradigm is adopted in our model to treat inputted images equally and ensure nearly perfect stitching of the overlapping regions. Combining with the existing rigid transformation method, our model further improves the accuracy of sequential image stitching. Extensive experimental results well demonstrate the superiority of our method over the other traditional methods. AVAILABILITY AND IMPLEMENTATION: The code is available at https://github.com/HeracleBT/ssEM_stitching. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The i2b2 platform is used at major academic health institutions and research consortia for querying for electronic health data. However, a major obstacle for wider utilization of the platform is the complexity of data loading that entails a steep curve of learning the platform's complex data schemas. To address this problem, we have developed the i2b2-etl package that simplifies the data loading process, which will facilitate wider deployment and utilization of the platform. RESULTS: We have implemented i2b2-etl as a Python application that imports ontology and patient data using simplified input file schemas and provides inbuilt record number de-identification and data validation. We describe a real-world deployment of i2b2-etl for a population-management initiative at MassGeneral Brigham. AVAILABILITY AND IMPLEMENTATION: i2b2-etl is a free, open-source application implemented in Python available under the Mozilla 2 license. The application can be downloaded as compiled docker images. A live demo is available at https://i2b2clinical.org/demo-i2b2etl/ (username: demo, password: Etl@2021). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.