MOTIVATION: Post-acquisition sample normalization is a critical step in comparative metabolomics to remove the variation introduced by sample amount or concentration difference. Previously reported approaches are either specific to one sample type or built on strong assumptions on data structure, which are limited to certain levels. This encouraged us to develop MAFFIN, an accurate and robust post-acquisition sample normalization workflow that works universally for metabolomics data collected on mass spectrometry (MS) platforms. RESULTS: MAFFIN calculates normalization factors using maximal density fold change (MDFC) computed by a kernel density-based approach. Using both simulated data and 20 metabolomics datasets, we showcased that MDFC outperforms four commonly used normalization methods in terms of reducing the intragroup variation among samples. Two essential steps, overlooked in conventional methods, were also examined and incorporated into MAFFIN. (i) MAFFIN uses multiple orthogonal criteria to select high-quality features for normalization factor calculation, which minimizes the bias caused by abiotic features or metabolites with poor quantitative performance. (ii) MAFFIN corrects the MS signal intensities of high-quality features using serial quality control samples, which guarantees the accuracy of fold change calculations. MAFFIN was applied to a human saliva metabolomics study and led to better data separation in principal component analysis and more confirmed significantly altered metabolites. AVAILABILITY AND IMPLEMENTATION: The MAFFIN algorithm was implemented in an R package named MAFFIN. Package installation, user instruction and demo data are available at https://github.com/HuanLab/MAFFIN. Other data in this work are available on request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein design has become increasingly important for medical and biotechnological applications. Because of the complex mechanisms underlying protein formation, the creation of a novel protein requires tedious and time-consuming computational or experimental protocols. At the same time, machine learning has enabled the solving of complex problems by leveraging large amounts of available data, more recently with great improvements on the domain of generative modeling. Yet, generative models have mainly been applied to specific sub-problems of protein design. RESULTS: Here, we approach the problem of general-purpose protein design conditioned on functional labels of the hierarchical Gene Ontology. Since a canonical way to evaluate generative models in this domain is missing, we devise an evaluation scheme of several biologically and statistically inspired metrics. We then develop the conditional generative adversarial network ProteoGAN and show that it outperforms several classic and more recent deep-learning baselines for protein sequence generation. We further give insights into the model by analyzing hyperparameters and ablation baselines. Lastly, we hypothesize that a functionally conditional model could generate proteins with novel functions by combining labels and provide first steps into this direction of research. AVAILABILITY AND IMPLEMENTATION: The code and data underlying this article are available on GitHub at https://github.com/timkucera/proteogan, and can be accessed with doi:10.5281/zenodo.6591379. SUPPLEMENTARY INFORMATION: Supplemental data are available at Bioinformatics online.

MOTIVATION: Chromatographic peak picking is among the first steps in data processing workflows of raw LC-HRMS datasets in untargeted metabolomics applications. Its performance is crucial for the holistic detection of all metabolic features as well as their relative quantification for statistical analysis and metabolite identification. Random noise, non-baseline separated compounds and unspecific background signals complicate this task. RESULTS: A machine-learning-based approach entitled PeakBot was developed for detecting chromatographic peaks in LC-HRMS profile-mode data. It first detects all local signal maxima in a chromatogram, which are then extracted as super-sampled standardized areas (retention-time versus m/z). These are subsequently inspected by a custom-trained convolutional neural network that forms the basis of PeakBot's architecture. The model reports if the respective local maximum is the apex of a chromatographic peak or not as well as its peak center and bounding box. In training and independent validation datasets used for development, PeakBot achieved a high performance with respect to discriminating between chromatographic peaks and background signals (accuracy of 0.99). For training the machine-learning model a minimum of 100 reference features are needed to learn their characteristics to achieve high-quality peak-picking results for detecting such chromatographic peaks in an untargeted fashion. PeakBot is implemented in python (3.8) and uses the TensorFlow (2.5.0) package for machine-learning related tasks. It has been tested on Linux and Windows OSs. AVAILABILITY AND IMPLEMENTATION: The package is available free of charge for non-commercial use (CC BY-NC-SA). It is available at https://github.com/christophuv/PeakBot. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Identifying the protein-peptide binding residues is fundamentally important to understand the mechanisms of protein functions and explore drug discovery. Although several computational methods have been developed, most of them highly rely on third-party tools or complex data preprocessing for feature design, easily resulting in low computational efficacy and suffering from low predictive performance. To address the limitations, we propose PepBCL, a novel BERT (Bidirectional Encoder Representation from Transformers) -based contrastive learning framework to predict the protein-peptide binding residues based on protein sequences only. PepBCL is an end-to-end predictive model that is independent of feature engineering. Specifically, we introduce a well pre-trained protein language model that can automatically extract and learn high-latent representations of protein sequences relevant for protein structures and functions. Further, we design a novel contrastive learning module to optimize the feature representations of binding residues underlying the imbalanced dataset. We demonstrate that our proposed method significantly outperforms the state-of-the-art methods under benchmarking comparison, and achieves more robust performance. Moreover, we found that we further improve the performance via the integration of traditional features and our learnt features. Interestingly, the interpretable analysis of our model highlights the flexibility and adaptability of deep learning-based protein language model to capture both conserved and non-conserved sequential characteristics of peptide-binding residues. Finally, to facilitate the use of our method, we establish an online predictive platform as the implementation of the proposed PepBCL, which is now available at http://server.wei-group.net/PepBCL/. AVAILABILITY AND IMPLEMENTATION: https://github.com/Ruheng-W/PepBCL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The extraction of k-mers is a fundamental component in many complex analyses of large next-generation sequencing datasets, including reads classification in genomics and the characterization of RNA-seq datasets. The extraction of all k-mers and their frequencies is extremely demanding in terms of running time and memory, owing to the size of the data and to the exponential number of k-mers to be considered. However, in several applications, only frequent k-mers, which are k-mers appearing in a relatively high proportion of the data, are required by the analysis. RESULTS: In this work, we present SPRISS, a new efficient algorithm to approximate frequent k-mers and their frequencies in next-generation sequencing data. SPRISS uses a simple yet powerful reads sampling scheme, which allows to extract a representative subset of the dataset that can be used, in combination with any k-mer counting algorithm, to perform downstream analyses in a fraction of the time required by the analysis of the whole data, while obtaining comparable answers. Our extensive experimental evaluation demonstrates the efficiency and accuracy of SPRISS in approximating frequent k-mers, and shows that it can be used in various scenarios, such as the comparison of metagenomic datasets, the identification of discriminative k-mers, and SNP (single nucleotide polymorphism) genotyping, to extract insights in a fraction of the time required by the analysis of the whole dataset. AVAILABILITY AND IMPLEMENTATION: SPRISS [a preliminary version (Santoro et al., 2021) of this work was presented at RECOMB 2021] is available at https://github.com/VandinLab/SPRISS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Bioinformatics software tools operate largely through the use of specialized genomics file formats. Often these formats lack formal specification, making it difficult or impossible for the creators of these tools to robustly test them for correct handling of input and output. This causes problems in interoperability between different tools that, at best, wastes time and frustrates users. At worst, interoperability issues could lead to undetected errors in scientific results. RESULTS: We developed a new verification system, Acidbio, which tests for correct behavior in bioinformatics software packages. We crafted tests to unify correct behavior when tools encounter various edge cases-potentially unexpected inputs that exemplify the limits of the format. To analyze the performance of existing software, we tested the input validation of 80 Bioconda packages that parsed the Browser Extensible Data (BED) format. We also used a fuzzing approach to automatically perform additional testing. Of 80 software packages examined, 75 achieved less than 70% correctness on our test suite. We categorized multiple root causes for the poor performance of different types of software. Fuzzing detected other errors that the manually designed test suite could not. We also created a badge system that developers can use to indicate more precisely which BED variants their software accepts and to advertise the software's performance on the test suite. AVAILABILITY AND IMPLEMENTATION: Acidbio is available at https://github.com/hoffmangroup/acidbio. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Although advances in untargeted metabolomics have made it possible to gather data on thousands of cellular metabolites in parallel, identification of novel metabolites from these datasets remains challenging. To address this need, Metabolic in silico Network Expansions (MINEs) were developed. A MINE is an expansion of known biochemistry which can be used as a list of potential structures for unannotated metabolomics peaks. Here, we present MINE 2.0, which utilizes a new set of biochemical transformation rules that covers 93% of MetaCyc reactions (compared to 25% in MINE 1.0). This results in a 17-fold increase in database size and a 40% increase in MINE database compounds matching unannotated peaks from an untargeted metabolomics dataset. MINE 2.0 is thus a significant improvement to this community resource. AVAILABILITY AND IMPLEMENTATION: The MINE 2.0 website can be accessed at https://minedatabase.ci.northwestern.edu. The MINE 2.0 web API documentation can be accessed at https://mine-api.readthedocs.io/en/latest/. The data and code underlying this article are available in the MINE-2.0-Paper repository at https://github.com/tyo-nu/MINE-2.0-Paper. MINE 2.0 source code can be accessed at https://github.com/tyo-nu/MINE-Database (MINE construction), https://github.com/tyo-nu/MINE-Server (backend web API) and https://github.com/tyo-nu/MINE-app (web app). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Automated molecule generation is a crucial step in in-silico drug discovery. Graph-based generation algorithms have seen significant progress over recent years. However, they are often complex to implement, hard to train and can under-perform when generating long-sequence molecules. The development of a simple and powerful alternative can help improve practicality of automated drug discovery method. RESULTS: We proposed a ConvNet-based sequential graph generation algorithm. The molecular graph generation problem is reformulated as a sequence of simple classification tasks. At each step, a convolutional neural network operates on a sub-graph that is generated at previous step, and predicts/classifies an atom/bond adding action to populate the input sub-graph. The proposed model is pretrained by learning to sequentially reconstruct existing molecules. The pretrained model is abbreviated as SEEM (structural encoder for engineering molecules). It is then fine-tuned with reinforcement learning to generate molecules with improved properties. The fine-tuned model is named SEED (structural encoder for engineering drug-like-molecules). The proposed models have demonstrated competitive performance comparing to 16 state-of-the-art baselines on three benchmark datasets. AVAILABILITY AND IMPLEMENTATION: Code is available at https://github.com/yuh8/SEEM and https://github.com/yuh8/SEED. QM9 dataset is availble at http://quantum-machine.org/datasets/, ZINC250k dataset is availble at https://raw.githubusercontent.com/aspuru-guzik-group/chemical_vae/master/models/zinc_properties/250k_rndm_zinc_drugs_clean_3.csv, and ChEMBL dataset is availble at https://www.ebi.ac.uk/chembl/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Clustered mutations are found in the human germline as well as in the genomes of cancer and normal somatic cells. Clustered events can be imprinted by a multitude of mutational processes, and they have been implicated in both cancer evolution and development disorders. Existing tools for identifying clustered mutations have been optimized for a particular subtype of clustered event and, in most cases, relied on a predefined inter-mutational distance (IMD) cutoff combined with a piecewise linear regression analysis. RESULTS: Here, we present SigProfilerClusters, an automated tool for detecting all types of clustered mutations by calculating a sample-dependent IMD threshold using a simulated background model that takes into account extended sequence context, transcriptional strand asymmetries and regional mutation densities. SigProfilerClusters disentangles all types of clustered events from non-clustered mutations and annotates each clustered event into an established subclass, including the widely used classes of doublet-base substitutions, multi-base substitutions, omikli and kataegis. SigProfilerClusters outputs non-clustered mutations and clustered events using standard data formats as well as provides multiple visualizations for exploring the distributions and patterns of clustered mutations across the genome. AVAILABILITY AND IMPLEMENTATION: SigProfilerClusters is supported across most operating systems and made freely available at https://github.com/AlexandrovLab/SigProfilerClusters with an extensive documentation located at https://osf.io/qpmzw/wiki/home/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The emergence of next-generation sequencing techniques opens up tremendous opportunities for researchers to uncover the basic mechanisms of disease at the molecular level. Recently, automatic machine learning (AutoML) frameworks have been employed for genomic and epigenomic data analysis. However, to analyze those high-dimensional data, existing AutoML frameworks suffer from the following issues: (i) they could not effectively filter out the redundant features from the original data, and (ii) they usually obey the rule of feature engineering first and algorithm hyper-parameter tuning later to build the machine learning pipeline, which could lead to sub-optimal outcomes. Thus, it is an urgent need to design a new AutoML framework for high-dimensional omics data analysis. RESULTS: We introduce a new method: AutoDC, a tailored AutoML framework, for different disease classification based on gene expression data. AutoDC designs two novel optimization strategies to improve the performance. One is that AutoDC designs a novel two-stage feature selection method to select the features with high gene contribution scores. The other is that AutoDC proposes a novel optimization method, based on a two-layer Multi-Armed Bandit framework, to jointly optimize the feature engineering, algorithm selection and algorithm hyper-parameter tuning. We apply our framework to two public gene expression datasets. Compared with three state-of-the-art AutoML frameworks, AutoDC could effectively classify diseases with higher predictive accuracy. AVAILABILITY AND IMPLEMENTATION: The data and codes of AutoDC are available at https://github.com/dingdian110/AutoDC. The data underlying this article are available in the article and in its online supplementary material. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein function prediction, based on the patterns of connection in a protein-protein interaction (or association) network, is perhaps the most studied of the classical, fundamental inference problems for biological networks. A highly successful set of recent approaches use random walk-based low-dimensional embeddings that tend to place functionally similar proteins into coherent spatial regions. However, these approaches lose valuable local graph structure from the network when considering only the embedding. We introduce GLIDER, a method that replaces a protein-protein interaction or association network with a new graph-based similarity network. GLIDER is based on a variant of our previous GLIDE method, which was designed to predict missing links in protein-protein association networks, capturing implicit local and global (i.e. embedding-based) graph properties. RESULTS: GLIDER outperforms competing methods on the task of predicting GO functional labels in cross-validation on a heterogeneous collection of four human protein-protein association networks derived from the 2016 DREAM Disease Module Identification Challenge, and also on three different protein-protein association networks built from the STRING database. We show that this is due to the strong functional enrichment that is present in the local GLIDER neighborhood in multiple different types of protein-protein association networks. Furthermore, we introduce the GLIDER graph neighborhood as a way for biologists to visualize the local neighborhood of a disease gene. As an application, we look at the local GLIDER neighborhoods of a set of known Parkinson's Disease GWAS genes, rediscover many genes which have known involvement in Parkinson's disease pathways, plus suggest some new genes to study. AVAILABILITY AND IMPLEMENTATION: All code is publicly available and can be accessed here: https://github.com/kap-devkota/GLIDER. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Rapid developments of single-cell RNA sequencing technologies allow study of responses to external perturbations at individual cell level. However, in many cases, it is hard to collect the perturbed cells, such as knowing the response of a cell type to the drug before actual medication to a patient. Prediction in silicon could alleviate the problem and save cost. Although several tools have been developed, their prediction accuracy leaves much room for improvement. RESULTS: In this article, we propose scPreGAN (Single-Cell data Prediction base on GAN), a deep generative model for predicting the response of single-cell expression to perturbation. ScPreGAN integrates autoencoder and generative adversarial network, the former is to extract common information of the unperturbed data and the perturbed data, the latter is to predict the perturbed data. Experiments on three real datasets show that scPreGAN outperforms three state-of-the-art methods, which can capture the complicated distribution of cell expression and generate the prediction data with the same expression abundance as the real data. AVAILABILITY AND IMPLEMENTATION: The implementation of scPreGAN is available via https://github.com/JaneJiayiDong/scPreGAN. To reproduce the results of this article, please visit https://github.com/JaneJiayiDong/scPreGAN-reproducibility. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: With continually improved instrumentation, Fourier transform infrared (FTIR) microspectroscopy can now be used to capture thousands of high-resolution spectra for chemical characterization of a sample. The spatially resolved nature of this method lends itself well to histological profiling of complex biological specimens. However, current software can make joint analysis of multiple samples challenging and, for large datasets, computationally infeasible. RESULTS: To overcome these limitations, we have developed Photizo-an open-source Python library enabling high-throughput spectral data pre-processing, visualization and downstream analysis, including principal component analysis, clustering, macromolecular quantification and mapping. Photizo can be used for analysis of data without a spatial component, as well as spatially resolved data, obtained e.g. by scanning mode IR microspectroscopy and IR imaging by focal plane array detector. AVAILABILITY AND IMPLEMENTATION: The code underlying this article is available at https://github.com/DendrouLab/Photizo with access to example data available at https://zenodo.org/record/6417982#.Yk2O9TfMI6A.

SUMMARY: Integrative analysis of single-cell RNA-sequencing (scRNA-seq) data with spatial data for the same species and organ would provide each cell sample with a predictive spatial location, which would facilitate biological study. However, publicly available spatial sequencing datasets for specific species and organs are rare and are often displayed in different formats. In this study, we introduce a new web-based scRNA-seq analysis tool, webSCST, that integrates well-organized spatial transcriptome sequencing datasets categorized by species and organs, provides a user-friendly interface for raw single-cell processing with popular integration methods and allows users to submit their raw scRNA-seq data once to obtain predicted spatial locations for each cell type. AVAILABILITY AND IMPLEMENTATION: webSCST implemented in shiny with all major browsers supported is available at http://www.webscst.com. webSCST is also freely available as an R package at https://github.com/swsoyee/webSCST.

MOTIVATION: Molecular phenotyping by gene expression profiling is central in contemporary cancer research and in molecular diagnostics but remains resource intense to implement. Changes in gene expression occurring in tumours cause morphological changes in tissue, which can be observed on the microscopic level. The relationship between morphological patterns and some of the molecular phenotypes can be exploited to predict molecular phenotypes from routine haematoxylin and eosin-stained whole slide images (WSIs) using convolutional neural networks (CNNs). In this study, we propose a new, computationally efficient approach to model relationships between morphology and gene expression. RESULTS: We conducted the first transcriptome-wide analysis in prostate cancer, using CNNs to predict bulk RNA-sequencing estimates from WSIs for 370 patients from the TCGA PRAD study. Out of 15 586 protein coding transcripts, 6618 had predicted expression significantly associated with RNA-seq estimates (FDR-adjusted P-value <1×10-4) in a cross-validation and 5419 (81.9%) of these associations were subsequently validated in a held-out test set. We furthermore predicted the prognostic cell-cycle progression score directly from WSIs. These findings suggest that contemporary computer vision models offer an inexpensive and scalable solution for prediction of gene expression phenotypes directly from WSIs, providing opportunity for cost-effective large-scale research studies and molecular diagnostics. AVAILABILITY AND IMPLEMENTATION: A self-contained example is available from http://github.com/phiwei/prostate_coexpression. Model predictions and metrics are available from doi.org/10.5281/zenodo.4739097. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Each gene has its own evolutionary history which can substantially differ from evolutionary histories of other genes. For example, some individual genes or operons can be affected by specific horizontal gene transfer or recombination events. Thus, the evolutionary history of each gene should be represented by its own phylogenetic tree which may display different evolutionary patterns from the species tree that accounts for the main patterns of vertical descent. However, the output of traditional consensus tree or supertree inference methods is a unique consensus tree or supertree. RESULTS: We present a new efficient method for inferring multiple alternative consensus trees and supertrees to best represent the most important evolutionary patterns of a given set of gene phylogenies. We show how an adapted version of the popular k-means clustering algorithm, based on some remarkable properties of the Robinson and Foulds distance, can be used to partition a given set of trees into one (for homogeneous data) or multiple (for heterogeneous data) cluster(s) of trees. Moreover, we adapt the popular Caliński-Harabasz, Silhouette, Ball and Hall, and Gap cluster validity indices to tree clustering with k-means. Special attention is given to the relevant but very challenging problem of inferring alternative supertrees. The use of the Euclidean property of the objective function of the method makes it faster than the existing tree clustering techniques, and thus better suited for analyzing large evolutionary datasets. AVAILABILITY AND IMPLEMENTATION: Our KMeansSuperTreeClustering program along with its C++ source code is available at: https://github.com/TahiriNadia/KMeansSuperTreeClustering. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Pangenome graphs provide a complete representation of the mutual alignment of collections of genomes. These models offer the opportunity to study the entire genomic diversity of a population, including structurally complex regions. Nevertheless, analyzing hundreds of gigabase-scale genomes using pangenome graphs is difficult as it is not well-supported by existing tools. Hence, fast and versatile software is required to ask advanced questions to such data in an efficient way. RESULTS: We wrote Optimized Dynamic Genome/Graph Implementation (ODGI), a novel suite of tools that implements scalable algorithms and has an efficient in-memory representation of DNA pangenome graphs in the form of variation graphs. ODGI supports pre-built graphs in the Graphical Fragment Assembly format. ODGI includes tools for detecting complex regions, extracting pangenomic loci, removing artifacts, exploratory analysis, manipulation, validation and visualization. Its fast parallel execution facilitates routine pangenomic tasks, as well as pipelines that can quickly answer complex biological questions of gigabase-scale pangenome graphs. AVAILABILITY AND IMPLEMENTATION: ODGI is published as free software under the MIT open source license. Source code can be downloaded from https://github.com/pangenome/odgi and documentation is available at https://odgi.readthedocs.io. ODGI can be installed via Bioconda https://bioconda.github.io/recipes/odgi/README.html or GNU Guix https://github.com/pangenome/odgi/blob/master/guix.scm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A dictionary of k-mers is a data structure that stores a set of n distinct k-mers and supports membership queries. This data structure is at the hearth of many important tasks in computational biology. High-throughput sequencing of DNA can produce very large k-mer sets, in the size of billions of strings-in such cases, the memory consumption and query efficiency of the data structure is a concrete challenge. RESULTS: To tackle this problem, we describe a compressed and associative dictionary for k-mers, that is: a data structure where strings are represented in compact form and each of them is associated to a unique integer identifier in the range [0,n). We show that some statistical properties of k-mer minimizers can be exploited by minimal perfect hashing to substantially improve the space/time trade-off of the dictionary compared to the best-known solutions. AVAILABILITY AND IMPLEMENTATION: https://github.com/jermp/sshash. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Molecular carcinogenicity is a preventable cause of cancer, but systematically identifying carcinogenic compounds, which involves performing experiments on animal models, is expensive, time consuming and low throughput. As a result, carcinogenicity information is limited and building data-driven models with good prediction accuracy remains a major challenge. RESULTS: In this work, we propose CONCERTO, a deep learning model that uses a graph transformer in conjunction with a molecular fingerprint representation for carcinogenicity prediction from molecular structure. Special efforts have been made to overcome the data size constraint, such as multi-round pre-training on related but lower quality mutagenicity data, and transfer learning from a large self-supervised model. Extensive experiments demonstrate that our model performs well and can generalize to external validation sets. CONCERTO could be useful for guiding future carcinogenicity experiments and provide insight into the molecular basis of carcinogenicity. AVAILABILITY AND IMPLEMENTATION: The code and data underlying this article are available on github at https://github.com/bowang-lab/CONCERTO.

MOTIVATION: A factory in a metabolic network specifies how to produce target molecules from source compounds through biochemical reactions, properly accounting for reaction stoichiometry to conserve or not deplete intermediate metabolites. While finding factories is a fundamental problem in systems biology, available methods do not consider the number of reactions used, nor address negative regulation. METHODS: We introduce the new problem of finding optimal factories that use the fewest reactions, for the first time incorporating both first- and second-order negative regulation. We model this problem with directed hypergraphs, prove it is NP-complete, solve it via mixed-integer linear programming, and accommodate second-order negative regulation by an iterative approach that generates next-best factories. RESULTS: This optimization-based approach is remarkably fast in practice, typically finding optimal factories in a few seconds, even for metabolic networks involving tens of thousands of reactions and metabolites, as demonstrated through comprehensive experiments across all instances from standard reaction databases. AVAILABILITY AND IMPLEMENTATION: Source code for an implementation of our new method for optimal factories with negative regulation in a new tool called Odinn, together with all datasets, is available free for non-commercial use at http://odinn.cs.arizona.edu.

MOTIVATION: Modern biological screens yield enormous numbers of measurements, and identifying and interpreting statistically significant associations among features are essential. In experiments featuring multiple high-dimensional datasets collected from the same set of samples, it is useful to identify groups of associated features between the datasets in a way that provides high statistical power and false discovery rate (FDR) control. RESULTS: Here, we present a novel hierarchical framework, HAllA (Hierarchical All-against-All association testing), for structured association discovery between paired high-dimensional datasets. HAllA efficiently integrates hierarchical hypothesis testing with FDR correction to reveal significant linear and non-linear block-wise relationships among continuous and/or categorical data. We optimized and evaluated HAllA using heterogeneous synthetic datasets of known association structure, where HAllA outperformed all-against-all and other block-testing approaches across a range of common similarity measures. We then applied HAllA to a series of real-world multiomics datasets, revealing new associations between gene expression and host immune activity, the microbiome and host transcriptome, metabolomic profiling and human health phenotypes. AVAILABILITY AND IMPLEMENTATION: An open-source implementation of HAllA is freely available at http://huttenhower.sph.harvard.edu/halla along with documentation, demo datasets and a user group. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Phage-host associations play important roles in microbial communities. But in natural communities, as opposed to culture-based lab studies where phages are discovered and characterized metagenomically, their hosts are generally not known. Several programs have been developed for predicting which phage infects which host based on various sequence similarity measures or machine learning approaches. These are often based on whole viral and host genomes, but in metagenomics-based studies, we rarely have whole genomes but rather must rely on contigs that are sometimes as short as hundreds of bp long. Therefore, we need programs that predict hosts of phage contigs on the basis of these short contigs. Although most existing programs can be applied to metagenomic datasets for these predictions, their accuracies are generally low. Here, we develop ContigNet, a convolutional neural network-based model capable of predicting phage-host matches based on relatively short contigs, and compare it to previously published VirHostMatcher (VHM) and WIsH. RESULTS: On the validation set, ContigNet achieves 72-85% area under the receiver operating characteristic curve (AUROC) scores, compared to the maximum of 68% by VHM or WIsH for contigs of lengths between 200 bps to 50 kbps. We also apply the model to the Metagenomic Gut Virus (MGV) catalogue, a dataset containing a wide range of draft genomes from metagenomic samples and achieve 60-70% AUROC scores compared to that of VHM and WIsH of 52%. Surprisingly, ContigNet can also be used to predict plasmid-host contig associations with high accuracy, indicating a similar genetic exchange between mobile genetic elements and their hosts. AVAILABILITY AND IMPLEMENTATION: The source code of ContigNet and related datasets can be downloaded from https://github.com/tianqitang1/ContigNet.

MOTIVATION: Alignments are correspondences between sequences. How reliable are alignments of amino acid sequences of proteins, and what inferences about protein relationships can be drawn? Using techniques not previously applied to these questions, by weighting every possible sequence alignment by its posterior probability we derive a formal mathematical expectation, and develop an efficient algorithm for computation of the distance between alternative alignments allowing quantitative comparisons of sequence-based alignments with corresponding reference structure alignments. RESULTS: By analyzing the sequences and structures of 1 million protein domain pairs, we report the variation of the expected distance between sequence-based and structure-based alignments, as a function of (Markov time of) sequence divergence. Our results clearly demarcate the 'daylight', 'twilight' and 'midnight' zones for interpreting residue-residue correspondences from sequence information alone. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Computational methods to predict protein-protein interaction (PPI) typically segregate into sequence-based 'bottom-up' methods that infer properties from the characteristics of the individual protein sequences, or global 'top-down' methods that infer properties from the pattern of already known PPIs in the species of interest. However, a way to incorporate top-down insights into sequence-based bottom-up PPI prediction methods has been elusive. We thus introduce Topsy-Turvy, a method that newly synthesizes both views in a sequence-based, multi-scale, deep-learning model for PPI prediction. While Topsy-Turvy makes predictions using only sequence data, during the training phase it takes a transfer-learning approach by incorporating patterns from both global and molecular-level views of protein interaction. In a cross-species context, we show it achieves state-of-the-art performance, offering the ability to perform genome-scale, interpretable PPI prediction for non-model organisms with no existing experimental PPI data. In species with available experimental PPI data, we further present a Topsy-Turvy hybrid (TT-Hybrid) model which integrates Topsy-Turvy with a purely network-based model for link prediction that provides information about species-specific network rewiring. TT-Hybrid makes accurate predictions for both well- and sparsely-characterized proteins, outperforming both its constituent components as well as other state-of-the-art PPI prediction methods. Furthermore, running Topsy-Turvy and TT-Hybrid screens is feasible for whole genomes, and thus these methods scale to settings where other methods (e.g. AlphaFold-Multimer) might be infeasible. The generalizability, accuracy and genome-level scalability of Topsy-Turvy and TT-Hybrid unlocks a more comprehensive map of protein interaction and organization in both model and non-model organisms. AVAILABILITY AND IMPLEMENTATION: https://topsyturvy.csail.mit.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) allows studying the development of cells in unprecedented detail. Given that many cellular differentiation processes are hierarchical, their scRNA-seq data are expected to be approximately tree-shaped in gene expression space. Inference and representation of this tree structure in two dimensions is highly desirable for biological interpretation and exploratory analysis. RESULTS: Our two contributions are an approach for identifying a meaningful tree structure from high-dimensional scRNA-seq data, and a visualization method respecting the tree structure. We extract the tree structure by means of a density-based maximum spanning tree on a vector quantization of the data and show that it captures biological information well. We then introduce density-tree biased autoencoder (DTAE), a tree-biased autoencoder that emphasizes the tree structure of the data in low dimensional space. We compare to other dimension reduction methods and demonstrate the success of our method both qualitatively and quantitatively on real and toy data. AVAILABILITY AND IMPLEMENTATION: Our implementation relying on PyTorch and Higra is available at github.com/hci-unihd/DTAE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Untargeted metabolomics experiments rely on spectral libraries for structure annotation, but these libraries are vastly incomplete; in silico methods search in structure databases, allowing us to overcome this limitation. The best-performing in silico methods use machine learning to predict a molecular fingerprint from tandem mass spectra, then use the predicted fingerprint to search in a molecular structure database. Predicted molecular fingerprints are also of great interest for compound class annotation, de novo structure elucidation, and other tasks. So far, kernel support vector machines are the best tool for fingerprint prediction. However, they cannot be trained on all publicly available reference spectra because their training time scales cubically with the number of training data. RESULTS: We use the Nyström approximation to transform the kernel into a linear feature map. We evaluate two methods that use this feature map as input: a linear support vector machine and a deep neural network (DNN). For evaluation, we use a cross-validated dataset of 156 017 compounds and three independent datasets with 1734 compounds. We show that the combination of kernel method and DNN outperforms the kernel support vector machine, which is the current gold standard, as well as a DNN on tandem mass spectra on all evaluation datasets. AVAILABILITY AND IMPLEMENTATION: The deep kernel learning method for fingerprint prediction is part of the SIRIUS software, available at https://bio.informatik.uni-jena.de/software/sirius.

MOTIVATION: Genome-wide association studies (GWAS), aiming to find genetic variants associated with a trait, have widely been used on bacteria to identify genetic determinants of drug resistance or hypervirulence. Recent bacterial GWAS methods usually rely on k-mers, whose presence in a genome can denote variants ranging from single-nucleotide polymorphisms to mobile genetic elements. This approach does not require a reference genome, making it easier to account for accessory genes. However, a same gene can exist in slightly different versions across different strains, leading to diluted effects. RESULTS: Here, we overcome this issue by testing covariates built from closed connected subgraphs (CCSs) of the de Bruijn graph defined over genomic k-mers. These covariates capture polymorphic genes as a single entity, improving k-mer-based GWAS both in terms of power and interpretability. However, a method naively testing all possible subgraphs would be powerless due to multiple testing corrections, and the mere exploration of these subgraphs would quickly become computationally intractable. The concept of testable hypothesis has successfully been used to address both problems in similar contexts. We leverage this concept to test all CCSs by proposing a novel enumeration scheme for these objects which fully exploits the pruning opportunity offered by testability, resulting in drastic improvements in computational efficiency. Our method integrates with existing visual tools to facilitate interpretation. AVAILABILITY AND IMPLEMENTATION: We provide an implementation of our method, as well as code to reproduce all results at https://github.com/HectorRDB/Caldera_ISMB. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Understanding the mechanisms underlying T cell receptor (TCR) binding is of fundamental importance to understanding adaptive immune responses. A better understanding of the biochemical rules governing TCR binding can be used, e.g. to guide the design of more powerful and safer T cell-based therapies. Advances in repertoire sequencing technologies have made available millions of TCR sequences. Data abundance has, in turn, fueled the development of many computational models to predict the binding properties of TCRs from their sequences. Unfortunately, while many of these works have made great strides toward predicting TCR specificity using machine learning, the black-box nature of these models has resulted in a limited understanding of the rules that govern the binding of a TCR and an epitope. RESULTS: We present an easy-to-use and customizable computational pipeline, DECODE, to extract the binding rules from any black-box model designed to predict the TCR-epitope binding. DECODE offers a range of analytical and visualization tools to guide the user in the extraction of such rules. We demonstrate our pipeline on a recently published TCR-binding prediction model, TITAN, and show how to use the provided metrics to assess the quality of the computed rules. In conclusion, DECODE can lead to a better understanding of the sequence motifs that underlie TCR binding. Our pipeline can facilitate the investigation of current immunotherapeutic challenges, such as cross-reactive events due to off-target TCR binding. AVAILABILITY AND IMPLEMENTATION: Code is available publicly at https://github.com/phineasng/DECODE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Identifying cell types and their abundances and how these evolve during tumor progression is critical to understanding the mechanisms of metastasis and identifying predictors of metastatic potential that can guide the development of new diagnostics or therapeutics. Single-cell RNA sequencing (scRNA-seq) has been especially promising in resolving heterogeneity of expression programs at the single-cell level, but is not always feasible, e.g. for large cohort studies or longitudinal analysis of archived samples. In such cases, clonal subpopulations may still be inferred via genomic deconvolution, but deconvolution methods have limited ability to resolve fine clonal structure and may require reference cell type profiles that are missing or imprecise. Prior methods can eliminate the need for reference profiles but show unstable performance when few bulk samples are available. RESULTS: In this work, we develop a new method using reference scRNA-seq to interpret sample collections for which only bulk RNA-seq is available for some samples, e.g. clonally resolving archived primary tissues using scRNA-seq from metastases. By integrating such information in a Quadratic Programming framework, our method can recover more accurate cell types and corresponding cell type abundances in bulk samples. Application to a breast tumor bone metastases dataset confirms the power of scRNA-seq data to improve cell type inference and quantification in same-patient bulk samples. AVAILABILITY AND IMPLEMENTATION: Source code is available on Github at https://github.com/CMUSchwartzLab/RADs.

MOTIVATION: Intermediately methylated regions occupy a significant fraction of the human genome and are closely associated with epigenetic regulations or cell-type deconvolution of bulk data. However, these regions show distinct methylation patterns, corresponding to different biological mechanisms. Although there have been some metrics developed for investigating these regions, the high noise sensitivity limits the utility for distinguishing distinct methylation patterns. RESULTS: We proposed a method named MeConcord to measure local methylation concordance across reads and CpG sites, respectively. MeConcord showed the most stable performance in distinguishing distinct methylation patterns ('identical', 'uniform' and 'disordered') compared with other metrics. Applying MeConcord to the whole genome data across 25 cell lines or primary cells or tissues, we found that distinct methylation patterns were associated with different genomic characteristics, such as CTCF binding or imprinted genes. Further, we showed the differences of CpG island hypermethylation patterns between senescence and tumorigenesis by using MeConcord. MeConcord is a powerful method to study local read-level methylation patterns for both the whole genome and specific regions of interest. AVAILABILITY AND IMPLEMENTATION: MeConcord is available at https://github.com/WangLabTHU/MeConcord. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: CRISPR/Cas9 technology has been revolutionizing the field of gene editing in recent years. Guide RNAs (gRNAs) enable Cas9 proteins to target specific genomic loci for editing. However, editing efficiency varies between gRNAs. Thus, computational methods were developed to predict editing efficiency for any gRNA of interest. High-throughput datasets of Cas9 editing efficiencies were produced to train machine-learning models to predict editing efficiency. However, these high-throughput datasets have low correlation with functional and endogenous editing. Another difficulty arises from the fact that functional and endogenous editing efficiency is more difficult to measure, and as a result, functional and endogenous datasets are too small to train accurate machine-learning models on. RESULTS: We developed DeepCRISTL, a deep-learning model to predict the on-target efficiency given a gRNA sequence. DeepCRISTL takes advantage of high-throughput datasets to learn general patterns of gRNA on-target editing efficiency, and then uses transfer learning (TL) to fine-tune the model and fit it to the functional and endogenous prediction task. We pre-trained the DeepCRISTL model on more than 150 000 gRNAs, produced through the DeepHF study as a high-throughput dataset of three Cas9 enzymes. We improved the DeepHF model by multi-task and ensemble techniques and achieved state-of-the-art results over each of the three enzymes: up to 0.89 in Spearman correlation between predicted and measured on-target efficiencies. To fine-tune model weights to predict on-target efficiency of functional or endogenous datasets, we tested several TL approaches, with gradual learning being the overall best performer, both when pre-trained on DeepHF and when pre-trained on CRISPROn, another high-throughput dataset. DeepCRISTL outperformed state-of-the-art methods on all functional and endogenous datasets. Using saliency maps, we identified and compared the important features learned by the model in each dataset. We believe DeepCRISTL will improve prediction performance in many other CRISPR/Cas9 editing contexts by leveraging TL to utilize both high-throughput datasets, and smaller and more biologically relevant datasets, such as functional and endogenous datasets. AVAILABILITY AND IMPLEMENTATION: DeepCRISTL is available via github.com/OrensteinLab/DeepCRISTL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Computationally predicting major histocompatibility complex (MHC)-peptide binding affinity is an important problem in immunological bioinformatics. Recent cutting-edge deep learning-based methods for this problem are unable to achieve satisfactory performance for MHC class II molecules. This is because such methods generate the input by simply concatenating the two given sequences: (the estimated binding core of) a peptide and (the pseudo sequence of) an MHC class II molecule, ignoring biological knowledge behind the interactions of the two molecules. We thus propose a binding core-aware deep learning-based model, DeepMHCII, with a binding interaction convolution layer, which allows to integrate all potential binding cores (in a given peptide) with the MHC pseudo (binding) sequence, through modeling the interaction with multiple convolutional kernels. RESULTS: Extensive empirical experiments with four large-scale datasets demonstrate that DeepMHCII significantly outperformed four state-of-the-art methods under numerous settings, such as 5-fold cross-validation, leave one molecule out, validation with independent testing sets and binding core prediction. All these results and visualization of the predicted binding cores indicate the effectiveness of our model, DeepMHCII, and the importance of properly modeling biological facts in deep learning for high predictive performance and efficient knowledge discovery. AVAILABILITY AND IMPLEMENTATION: DeepMHCII is publicly available at https://github.com/yourh/DeepMHCII. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Intra-sample heterogeneity describes the phenomenon where a genomic sample contains a diverse set of genomic sequences. In practice, the true string sets in a sample are often unknown due to limitations in sequencing technology. In order to compare heterogeneous samples, genome graphs can be used to represent such sets of strings. However, a genome graph is generally able to represent a string set universe that contains multiple sets of strings in addition to the true string set. This difference between genome graphs and string sets is not well characterized. As a result, a distance metric between genome graphs may not match the distance between true string sets. RESULTS: We extend a genome graph distance metric, Graph Traversal Edit Distance (GTED) proposed by Ebrahimpour Boroojeny et al., to FGTED to model the distance between heterogeneous string sets and show that GTED and FGTED always underestimate the Earth Mover's Edit Distance (EMED) between string sets. We introduce the notion of string set universe diameter of a genome graph. Using the diameter, we are able to upper-bound the deviation of FGTED from EMED and to improve FGTED so that it reduces the average error in empirically estimating the similarity between true string sets. On simulated T-cell receptor sequences and actual Hepatitis B virus genomes, we show that the diameter-corrected FGTED reduces the average deviation of the estimated distance from the true string set distances by more than 250%. AVAILABILITY AND IMPLEMENTATION: Data and source code for reproducing the experiments are available at: https://github.com/Kingsford-Group/gtedemedtest/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Breast cancer is a type of cancer that develops in breast tissues, and, after skin cancer, it is the most commonly diagnosed cancer in women in the United States. Given that an early diagnosis is imperative to prevent breast cancer progression, many machine learning models have been developed in recent years to automate the histopathological classification of the different types of carcinomas. However, many of them are not scalable to large-scale datasets. RESULTS: In this study, we propose the novel Primal-Dual Multi-Instance Support Vector Machine to determine which tissue segments in an image exhibit an indication of an abnormality. We derive an efficient optimization algorithm for the proposed objective by bypassing the quadratic programming and least-squares problems, which are commonly employed to optimize Support Vector Machine models. The proposed method is computationally efficient, thereby it is scalable to large-scale datasets. We applied our method to the public BreaKHis dataset and achieved promising prediction performance and scalability for histopathological classification. AVAILABILITY AND IMPLEMENTATION: Software is publicly available at: https://1drv.ms/u/s!AiFpD21bgf2wgRLbQq08ixD0SgRD?e=OpqEmY. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Dataset sizes in computational biology have been increased drastically with the help of improved data collection tools and increasing size of patient cohorts. Previous kernel-based machine learning algorithms proposed for increased interpretability started to fail with large sample sizes, owing to their lack of scalability. To overcome this problem, we proposed a fast and efficient multiple kernel learning (MKL) algorithm to be particularly used with large-scale data that integrates kernel approximation and group Lasso formulations into a conjoint model. Our method extracts significant and meaningful information from the genomic data while conjointly learning a model for out-of-sample prediction. It is scalable with increasing sample size by approximating instead of calculating distinct kernel matrices. RESULTS: To test our computational framework, namely, Multiple Approximate Kernel Learning (MAKL), we demonstrated our experiments on three cancer datasets and showed that MAKL is capable to outperform the baseline algorithm while using only a small fraction of the input features. We also reported selection frequencies of approximated kernel matrices associated with feature subsets (i.e. gene sets/pathways), which helps to see their relevance for the given classification task. Our fast and interpretable MKL algorithm producing sparse solutions is promising for computational biology applications considering its scalability and highly correlated structure of genomic datasets, and it can be used to discover new biomarkers and new therapeutic guidelines. AVAILABILITY AND IMPLEMENTATION: MAKL is available at https://github.com/begumbektas/makl together with the scripts that replicate the reported experiments. MAKL is also available as an R package at https://cran.r-project.org/web/packages/MAKL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein functions are often described using the Gene Ontology (GO) which is an ontology consisting of over 50 000 classes and a large set of formal axioms. Predicting the functions of proteins is one of the key challenges in computational biology and a variety of machine learning methods have been developed for this purpose. However, these methods usually require a significant amount of training data and cannot make predictions for GO classes that have only few or no experimental annotations. RESULTS: We developed DeepGOZero, a machine learning model which improves predictions for functions with no or only a small number of annotations. To achieve this goal, we rely on a model-theoretic approach for learning ontology embeddings and combine it with neural networks for protein function prediction. DeepGOZero can exploit formal axioms in the GO to make zero-shot predictions, i.e., predict protein functions even if not a single protein in the training phase was associated with that function. Furthermore, the zero-shot prediction method employed by DeepGOZero is generic and can be applied whenever associations with ontology classes need to be predicted. AVAILABILITY AND IMPLEMENTATION: http://github.com/bio-ontology-research-group/deepgozero. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Wikipedia is one of the most important channels for the public communication of science and is frequently accessed as an educational resource in computational biology. Joint efforts between the International Society for Computational Biology (ISCB) and the Computational Biology taskforce of WikiProject Molecular Biology (a group of expert Wikipedia editors) have considerably improved computational biology representation on Wikipedia in recent years. However, there is still an urgent need for further improvement in quality, especially when compared to related scientific fields such as genetics and medicine. Facilitating involvement of members from ISCB Communities of Special Interest (COSIs) would improve a vital open education resource in computational biology, additionally allowing COSIs to provide a quality educational resource highly specific to their subfield. RESULTS: We generate a list of around 1500 English Wikipedia articles relating to computational biology and describe the development of a binary COSI-Article matrix, linking COSIs to relevant articles and thereby defining domain-specific open educational resources. Our analysis of the COSI-Article matrix data provides a quantitative assessment of computational biology representation on Wikipedia against other fields and at a COSI-specific level. Furthermore, we conducted similarity analysis and subsequent clustering of COSI-Article data to provide insight into potential relationships between COSIs. Finally, based on our analysis, we suggest courses of action to improve the quality of computational biology representation on Wikipedia.

MOTIVATION: Advances in bioimaging now permit in situ proteomic characterization of cell-cell interactions in complex tissues, with important applications across a spectrum of biological problems from development to disease. These methods depend on selection of antibodies targeting proteins that are expressed specifically in particular cell types. Candidate marker proteins are often identified from single-cell transcriptomic data, with variable rates of success, in part due to divergence between expression levels of proteins and the genes that encode them. In principle, marker identification could be improved by using existing databases of immunohistochemistry for thousands of antibodies in human tissue, such as the Human Protein Atlas. However, these data lack detailed annotations of the types of cells in each image. RESULTS: We develop a method to predict cell type specificity of protein markers from unlabeled images. We train a convolutional neural network with a self-supervised objective to generate embeddings of the images. Using non-linear dimensionality reduction, we observe that the model clusters images according to cell types and anatomical regions for which the stained proteins are specific. We then use estimates of cell type specificity derived from an independent single-cell transcriptomics dataset to train an image classifier, without requiring any human labelling of images. Our scheme demonstrates superior classification of known proteomic markers in kidney compared to selection via single-cell transcriptomics. AVAILABILITY AND IMPLEMENTATION: Code and trained model are available at www.github.com/murphy17/HPA-SimCLR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The increasing prevalence and importance of machine learning in biological research have created a need for machine learning training resources tailored towards biological researchers. However, existing resources are often inaccessible, infeasible or inappropriate for biologists because they require significant computational and mathematical knowledge, demand an unrealistic time-investment or teach skills primarily for computational researchers. We created the Machine Learning for Biologists (ML4Bio) workshop, a short, intensive workshop that empowers biological researchers to comprehend machine learning applications and pursue machine learning collaborations in their own research. The ML4Bio workshop focuses on classification and was designed around three principles: (i) emphasizing preparedness over fluency or expertise, (ii) necessitating minimal coding and mathematical background and (iii) requiring low time investment. It incorporates active learning methods and custom open-source software that allows participants to explore machine learning workflows. After multiple sessions to improve workshop design, we performed a study on three workshop sessions. Despite some confusion around identifying subtle methodological flaws in machine learning workflows, participants generally reported that the workshop met their goals, provided them with valuable skills and knowledge and greatly increased their beliefs that they could engage in research that uses machine learning. ML4Bio is an educational tool for biological researchers, and its creation and evaluation provide valuable insight into tailoring educational resources for active researchers in different domains. AVAILABILITY AND IMPLEMENTATION: Workshop materials are available at https://github.com/carpentries-incubator/ml4bio-workshop and the ml4bio software is available at https://github.com/gitter-lab/ml4bio. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Estimating the effects of interventions on patient outcome is one of the key aspects of personalized medicine. Their inference is often challenged by the fact that the training data comprises only the outcome for the administered treatment, and not for alternative treatments (the so-called counterfactual outcomes). Several methods were suggested for this scenario based on observational data, i.e. data where the intervention was not applied randomly, for both continuous and binary outcome variables. However, patient outcome is often recorded in terms of time-to-event data, comprising right-censored event times if an event does not occur within the observation period. Albeit their enormous importance, time-to-event data are rarely used for treatment optimization. We suggest an approach named BITES (Balanced Individual Treatment Effect for Survival data), which combines a treatment-specific semi-parametric Cox loss with a treatment-balanced deep neural network; i.e. we regularize differences between treated and non-treated patients using Integral Probability Metrics (IPM). RESULTS: We show in simulation studies that this approach outperforms the state of the art. Furthermore, we demonstrate in an application to a cohort of breast cancer patients that hormone treatment can be optimized based on six routine parameters. We successfully validated this finding in an independent cohort. AVAILABILITY AND IMPLEMENTATION: We provide BITES as an easy-to-use python implementation including scheduled hyper-parameter optimization (https://github.com/sschrod/BITES). The data underlying this article are available in the CRAN repository at https://rdrr.io/cran/survival/man/gbsg.html and https://rdrr.io/cran/survival/man/rotterdam.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Sketching is now widely used in bioinformatics to reduce data size and increase data processing speed. Sketching approaches entice with improved scalability but also carry the danger of decreased accuracy and added bias. In this article, we investigate the minimizer sketch and its use to estimate the Jaccard similarity between two sequences. RESULTS: We show that the minimizer Jaccard estimator is biased and inconsistent, which means that the expected difference (i.e. the bias) between the estimator and the true value is not zero, even in the limit as the lengths of the sequences grow. We derive an analytical formula for the bias as a function of how the shared k-mers are laid out along the sequences. We show both theoretically and empirically that there are families of sequences where the bias can be substantial (e.g. the true Jaccard can be more than double the estimate). Finally, we demonstrate that this bias affects the accuracy of the widely used mashmap read mapping tool. AVAILABILITY AND IMPLEMENTATION: Scripts to reproduce our experiments are available at https://github.com/medvedevgroup/minimizer-jaccard-estimator/tree/main/reproduce. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Nanopore sequencers allow targeted sequencing of interesting nucleotide sequences by rejecting other sequences from individual pores. This feature facilitates the enrichment of low-abundant sequences by depleting overrepresented ones in-silico. Existing tools for adaptive sampling either apply signal alignment, which cannot handle human-sized reference sequences, or apply read mapping in sequence space relying on fast graphical processing units (GPU) base callers for real-time read rejection. Using nanopore long-read mapping tools is also not optimal when mapping shorter reads as usually analyzed in adaptive sampling applications. RESULTS: Here, we present a new approach for nanopore adaptive sampling that combines fast CPU and GPU base calling with read classification based on Interleaved Bloom Filters. ReadBouncer improves the potential enrichment of low abundance sequences by its high read classification sensitivity and specificity, outperforming existing tools in the field. It robustly removes even reads belonging to large reference sequences while running on commodity hardware without GPUs, making adaptive sampling accessible for in-field researchers. Readbouncer also provides a user-friendly interface and installer files for end-users without a bioinformatics background. AVAILABILITY AND IMPLEMENTATION: The C++ source code is available at https://gitlab.com/dacs-hpi/readbouncer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Pleiotropic SNPs are associated with multiple traits. Such SNPs can help pinpoint biological processes with an effect on multiple traits or point to a shared etiology between traits. We present PolarMorphism, a new method for the identification of pleiotropic SNPs from genome-wide association studies (GWAS) summary statistics. PolarMorphism can be readily applied to more than two traits or whole trait domains. PolarMorphism makes use of the fact that trait-specific SNP effect sizes can be seen as Cartesian coordinates and can thus be converted to polar coordinates r (distance from the origin) and theta (angle with the Cartesian x-axis, in the case of two traits). r describes the overall effect of a SNP, while theta describes the extent to which a SNP is shared. r and theta are used to determine the significance of SNP sharedness, resulting in a P-value per SNP that can be used for further analysis. RESULTS: We apply PolarMorphism to a large collection of publicly available GWAS summary statistics enabling the construction of a pleiotropy network that shows the extent to which traits share SNPs. We show how PolarMorphism can be used to gain insight into relationships between traits and trait domains and contrast it with genetic correlation. Furthermore, pathway analysis of the newly discovered pleiotropic SNPs demonstrates that analysis of more than two traits simultaneously yields more biologically relevant results than the combined results of pairwise analysis of the same traits. Finally, we show that PolarMorphism is more efficient and more powerful than previously published methods. AVAILABILITY AND IMPLEMENTATION: code: https://github.com/UMCUGenetics/PolarMorphism, results: 10.5281/zenodo.5844193. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome annotations are a common way to represent genomic features such as genes, regulatory elements or epigenetic modifications. The amount of overlap between two annotations is often used to ascertain if there is an underlying biological connection between them. In order to distinguish between true biological association and overlap by pure chance, a robust measure of significance is required. One common way to do this is to determine if the number of intervals in the reference annotation that intersect the query annotation is statistically significant. However, currently employed statistical frameworks are often either inefficient or inaccurate when computing P-values on the scale of the whole human genome. RESULTS: We show that finding the P-values under the typically used 'gold' null hypothesis is NP-hard. This motivates us to reformulate the null hypothesis using Markov chains. To be able to measure the fidelity of our Markovian null hypothesis, we develop a fast direct sampling algorithm to estimate the P-value under the gold null hypothesis. We then present an open-source software tool MCDP that computes the P-values under the Markovian null hypothesis in O(m2+n) time and O(m) memory, where m and n are the numbers of intervals in the reference and query annotations, respectively. Notably, MCDP runtime and memory usage are independent from the genome length, allowing it to outperform previous approaches in runtime and memory usage by orders of magnitude on human genome annotations, while maintaining the same level of accuracy. AVAILABILITY AND IMPLEMENTATION: The software is available at https://github.com/fmfi-compbio/mc-overlaps. All data for reproducibility are available at https://github.com/fmfi-compbio/mc-overlaps-reproducibility. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Phylogenomics faces a dilemma: on the one hand, most accurate species and gene tree estimation methods are those that co-estimate them; on the other hand, these co-estimation methods do not scale to moderately large numbers of species. The summary-based methods, which first infer gene trees independently and then combine them, are much more scalable but are prone to gene tree estimation error, which is inevitable when inferring trees from limited-length data. Gene tree estimation error is not just random noise and can create biases such as long-branch attraction. RESULTS: We introduce a scalable likelihood-based approach to co-estimation under the multi-species coalescent model. The method, called quartet co-estimation (QuCo), takes as input independently inferred distributions over gene trees and computes the most likely species tree topology and internal branch length for each quartet, marginalizing over gene tree topologies and ignoring branch lengths by making several simplifying assumptions. It then updates the gene tree posterior probabilities based on the species tree. The focus on gene tree topologies and the heuristic division to quartets enables fast likelihood calculations. We benchmark our method with extensive simulations for quartet trees in zones known to produce biased species trees and further with larger trees. We also run QuCo on a biological dataset of bees. Our results show better accuracy than the summary-based approach ASTRAL run on estimated gene trees. AVAILABILITY AND IMPLEMENTATION: QuCo is available on https://github.com/maryamrabiee/quco. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Estimating causal queries, such as changes in protein abundance in response to a perturbation, is a fundamental task in the analysis of biomolecular pathways. The estimation requires experimental measurements on the pathway components. However, in practice many pathway components are left unobserved (latent) because they are either unknown, or difficult to measure. Latent variable models (LVMs) are well-suited for such estimation. Unfortunately, LVM-based estimation of causal queries can be inaccurate when parameters of the latent variables are not uniquely identified, or when the number of latent variables is misspecified. This has limited the use of LVMs for causal inference in biomolecular pathways. RESULTS: In this article, we propose a general and practical approach for LVM-based estimation of causal queries. We prove that, despite the challenges above, LVM-based estimators of causal queries are accurate if the queries are identifiable according to Pearl's do-calculus and describe an algorithm for its estimation. We illustrate the breadth and the practical utility of this approach for estimating causal queries in four synthetic and two experimental case studies, where structures of biomolecular pathways challenge the existing methods for causal query estimation. AVAILABILITY AND IMPLEMENTATION: The code and the data documenting all the case studies are available at https://github.com/srtaheri/LVMwithDoCalculus. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: In biology, graph layout algorithms can reveal comprehensive biological contexts by visually positioning graph nodes in their relevant neighborhoods. A layout software algorithm/engine commonly takes a set of nodes and edges and produces layout coordinates of nodes according to edge constraints. However, current layout engines normally do not consider node, edge or node-set properties during layout and only curate these properties after the layout is created. Here, we propose a new layout algorithm, distance-bounded energy-field minimization algorithm (DEMA), to natively consider various biological factors, i.e., the strength of gene-to-gene association, the gene's relative contribution weight and the functional groups of genes, to enhance the interpretation of complex network graphs. In DEMA, we introduce a parameterized energy model where nodes are repelled by the network topology and attracted by a few biological factors, i.e., interaction coefficient, effect coefficient and fold change of gene expression. We generalize these factors as gene weights, protein-protein interaction weights, gene-to-gene correlations and the gene set annotations-four parameterized functional properties used in DEMA. Moreover, DEMA considers further attraction/repulsion/grouping coefficient to enable different preferences in generating network views. Applying DEMA, we performed two case studies using genetic data in autism spectrum disorder and Alzheimer's disease, respectively, for gene candidate discovery. Furthermore, we implement our algorithm as a plugin to Cytoscape, an open-source software platform for visualizing networks; hence, it is convenient. Our software and demo can be freely accessed at http://discovery.informatics.uab.edu/dema. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Sequences of proteins evolve by accumulating substitutions together with insertions and deletions (indels) of amino acids. However, it remains a common practice to disconnect substitutions and indels, and infer approximate models for each of them separately, to quantify sequence relationships. Although this approach brings with it computational convenience (which remains its primary motivation), there is a dearth of attempts to unify and model them systematically and together. To overcome this gap, this article demonstrates how a complete statistical model quantifying the evolution of pairs of aligned proteins can be constructed using a time-parameterized substitution matrix and a time-parameterized alignment state machine. Methods to derive all parameters of such a model from any benchmark collection of aligned protein sequences are described here. This has not only allowed us to generate a unified statistical model for each of the nine widely used substitution matrices (PAM, JTT, BLOSUM, JO, WAG, VTML, LG, MIQS and PFASUM), but also resulted in a new unified model, MMLSUM. Our underlying methodology measures the Shannon information content using each model to explain losslessly any given collection of alignments, which has allowed us to quantify the performance of all the above models on six comprehensive alignment benchmarks. Our results show that MMLSUM results in a new and clear overall best performance, followed by PFASUM, VTML, BLOSUM and MIQS, respectively, amongst the top five. We further analyze the statistical properties of MMLSUM model and contrast it with others. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Rooted species trees are a basic model with multiple applications throughout biology, including understanding adaptation, biodiversity, phylogeography and co-evolution. Because most species tree estimation methods produce unrooted trees, methods for rooting these trees have been developed. However, most rooting methods either rely on prior biological knowledge or assume that evolution is close to clock-like, which is not usually the case. Furthermore, most prior rooting methods do not account for biological processes that create discordance between gene trees and species trees. RESULTS: We present Quintet Rooting (QR), a method for rooting species trees based on a proof of identifiability of the rooted species tree under the multi-species coalescent model established by Allman, Degnan and Rhodes (J. Math. Biol., 2011). We show that QR is generally more accurate than other rooting methods, except under extreme levels of gene tree estimation error. AVAILABILITY AND IMPLEMENTATION: Quintet Rooting is available in open source form at https://github.com/ytabatabaee/Quintet-Rooting. The simulated datasets used in this study are from a prior study and are available at https://www.ideals.illinois.edu/handle/2142/55319. The biological dataset used in this study is also from a prior study and is available at http://gigadb.org/dataset/101041. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The presence of tumor cell clusters in pleural effusion may be a signal of cancer metastasis. The instance segmentation of single cell from cell clusters plays a pivotal role in cluster cell analysis. However, current cell segmentation methods perform poorly for cluster cells due to the overlapping/touching characters of clusters, multiple instance properties of cells, and the poor generalization ability of the models. RESULTS: In this article, we propose a contour constraint instance segmentation framework (CC framework) for cluster cells based on a cluster cell combination enhancement module. The framework can accurately locate each instance from cluster cells and realize high-precision contour segmentation under a few samples. Specifically, we propose the contour attention constraint module to alleviate over- and under-segmentation among individual cell-instance boundaries. In addition, to evaluate the framework, we construct a pleural effusion cluster cell dataset including 197 high-quality samples. The quantitative results show that the numeric result of APmask is > 90%, a more than 10% increase compared with state-of-the-art semantic segmentation algorithms. From the qualitative results, we can observe that our method rarely has segmentation errors.

MOTIVATION: K-mer-based methods are used ubiquitously in the field of computational biology. However, determining the optimal value of k for a specific application often remains heuristic. Simply reconstructing a new k-mer set with another k-mer size is computationally expensive, especially in metagenomic analysis where datasets are large. Here, we introduce a hashing-based technique that leverages a kind of bottom-m sketch as well as a k-mer ternary search tree (KTST) to obtain k-mer-based similarity estimates for a range of k values. By truncating k-mers stored in a pre-built KTST with a large k=kmax value, we can simultaneously obtain k-mer-based estimates for all k values up to kmax. This truncation approach circumvents the reconstruction of new k-mer sets when changing k values, making analysis more time and space-efficient. RESULTS: We derived the theoretical expression of the bias factor due to truncation. And we showed that the biases are negligible in practice: when using a KTST to estimate the containment index between a RefSeq-based microbial reference database and simulated metagenome data for 10 values of k, the running time was close to 10× faster compared to a classic MinHash approach while using less than one-fifth the space to store the data structure. AVAILABILITY AND IMPLEMENTATION: A python implementation of this method, CMash, is available at https://github.com/dkoslicki/CMash. The reproduction of all experiments presented herein can be accessed via https://github.com/KoslickiLab/CMASH-reproducibles. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Literature-based gene ontology annotations (GOA) are biological database records that use controlled vocabulary to uniformly represent gene function information that is described in the primary literature. Assurance of the quality of GOA is crucial for supporting biological research. However, a range of different kinds of inconsistencies in between literature as evidence and annotated GO terms can be identified; these have not been systematically studied at record level. The existing manual-curation approach to GOA consistency assurance is inefficient and is unable to keep pace with the rate of updates to gene function knowledge. Automatic tools are therefore needed to assist with GOA consistency assurance. This article presents an exploration of different GOA inconsistencies and an early feasibility study of automatic inconsistency detection. RESULTS: We have created a reliable synthetic dataset to simulate four realistic types of GOA inconsistency in biological databases. Three automatic approaches are proposed. They provide reasonable performance on the task of distinguishing the four types of inconsistency and are directly applicable to detect inconsistencies in real-world GOA database records. Major challenges resulting from such inconsistencies in the context of several specific application settings are reported. This is the first study to introduce automatic approaches that are designed to address the challenges in current GOA quality assurance workflows. The data underlying this article are available in Github at https://github.com/jiyuc/AutoGOAConsistency.

MOTIVATION: A critical element of drug development is the identification of therapeutic targets for diseases. However, the depletion of therapeutic targets is a serious problem. RESULTS: In this study, we propose the novel concept of target repositioning, an extension of the concept of drug repositioning, to predict new therapeutic targets for various diseases. Predictions were performed by a trans-disease analysis which integrated genetically perturbed transcriptomic signatures (knockdown of 4345 genes and overexpression of 3114 genes) and disease-specific gene transcriptomic signatures of 79 diseases. The trans-disease method, which takes into account similarities among diseases, enabled us to distinguish the inhibitory from activatory targets and to predict the therapeutic targetability of not only proteins with known target-disease associations but also orphan proteins without known associations. Our proposed method is expected to be useful for understanding the commonality of mechanisms among diseases and for therapeutic target identification in drug discovery. AVAILABILITY AND IMPLEMENTATION: Supplemental information and software are available at the following website [http://labo.bio.kyutech.ac.jp/~yamani/target_repositioning/]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In recent years, full-genome sequences have become increasingly available and as a result many modern phylogenetic analyses are based on very long sequences, often with over 100 000 sites. Phylogenetic reconstructions of large-scale alignments are challenging for likelihood-based phylogenetic inference programs and usually require using a powerful computer cluster. Current tools for alignment trimming prior to phylogenetic analysis do not promise a significant reduction in the alignment size and are claimed to have a negative effect on the accuracy of the obtained tree. RESULTS: Here, we propose an artificial-intelligence-based approach, which provides means to select the optimal subset of sites and a formula by which one can compute the log-likelihood of the entire data based on this subset. Our approach is based on training a regularized Lasso-regression model that optimizes the log-likelihood prediction accuracy while putting a constraint on the number of sites used for the approximation. We show that computing the likelihood based on 5% of the sites already provides accurate approximation of the tree likelihood based on the entire data. Furthermore, we show that using this Lasso-based approximation during a tree search decreased running-time substantially while retaining the same tree-search performance. AVAILABILITY AND IMPLEMENTATION: The code was implemented in Python version 3.8 and is available through GitHub (https://github.com/noaeker/lasso_positions_sampling). The datasets used in this paper were retrieved from Zhou et al. (2018) as described in section 3. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Author information: (1)Department of Biosystems Science and Engineering, ETH Zurich, Basel 4058, Switzerland. (2)SIB Swiss Institute of Bioinformatics, Lausanne 1015, Switzerland. (3)Division of Critical Care, Ann and Robert H. Lurie Children's Hospital of Chicago, Chicago, IL, USA. (4)Department of Pediatrics, Inselspital, Bern University Hospital University of Bern, Bern 3010, Switzerland. (5)Department of Intensive Care and Neonatology, and Children's Research Center, University Children's Hospital Zurich, Zurich 8032, Switzerland. (6)Paediatric Intensive Care Unit, Child Health Research Center, Queensland Children's Hospital, The University of Queensland, Brisbane, Australia.

MOTIVATION: Improvements in single-cell RNA-seq technologies mean that studies measuring multiple experimental conditions, such as time series, have become more common. At present, few computational methods exist to infer time series-specific transcriptome changes, and such studies have therefore typically used unsupervised pseudotime methods. While these methods identify cell subpopulations and the transitions between them, they are not appropriate for identifying the genes that vary coherently along the time series. In addition, the orderings they estimate are based only on the major sources of variation in the data, which may not correspond to the processes related to the time labels. RESULTS: We introduce psupertime, a supervised pseudotime approach based on a regression model, which explicitly uses time-series labels as input. It identifies genes that vary coherently along a time series, in addition to pseudotime values for individual cells, and a classifier that can be used to estimate labels for new data with unknown or differing labels. We show that psupertime outperforms benchmark classifiers in terms of identifying time-varying genes and provides better individual cell orderings than popular unsupervised pseudotime techniques. psupertime is applicable to any single-cell RNA-seq dataset with sequential labels (e.g. principally time series but also drug dosage and disease progression), derived from either experimental design and provides a fast, interpretable tool for targeted identification of genes varying along with specific biological processes. AVAILABILITY AND IMPLEMENTATION: R package available at github.com/wmacnair/psupertime and code for results reproduction at github.com/wmacnair/psupplementary. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Cancer develops through a process of clonal evolution in which an initially healthy cell gives rise to progeny gradually differentiating through the accumulation of genetic and epigenetic mutations. These mutations can take various forms, including single-nucleotide variants (SNVs), copy number alterations (CNAs) or structural variations (SVs), with each variant type providing complementary insights into tumor evolution as well as offering distinct challenges to phylogenetic inference. RESULTS: In this work, we develop a tumor phylogeny method, TUSV-ext, which incorporates SNVs, CNAs and SVs into a single inference framework. We demonstrate on simulated data that the method produces accurate tree inferences in the presence of all three variant types. We further demonstrate the method through application to real prostate tumor data, showing how our approach to coordinated phylogeny inference and clonal construction with all three variant types can reveal a more complicated clonal structure than is suggested by prior work, consistent with extensive polyclonal seeding or migration. AVAILABILITY AND IMPLEMENTATION: https://github.com/CMUSchwartzLab/TUSV-ext. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Bait enrichment is a protocol that is becoming increasingly ubiquitous as it has been shown to successfully amplify regions of interest in metagenomic samples. In this method, a set of synthetic probes ('baits') are designed, manufactured and applied to fragmented metagenomic DNA. The probes bind to the fragmented DNA and any unbound DNA is rinsed away, leaving the bound fragments to be amplified for sequencing. Metsky et al. demonstrated that bait-enrichment is capable of detecting a large number of human viral pathogens within metagenomic samples. RESULTS: We formalize the problem of designing baits by defining the Minimum Bait Cover problem, show that the problem is NP-hard even under very restrictive assumptions, and design an efficient heuristic that takes advantage of succinct data structures. We refer to our method as Syotti. The running time of Syotti shows linear scaling in practice, running at least an order of magnitude faster than state-of-the-art methods, including the method of Metsky et al. At the same time, our method produces bait sets that are smaller than the ones produced by the competing methods, while also leaving fewer positions uncovered. Lastly, we show that Syotti requires only 25 min to design baits for a dataset comprised of 3 billion nucleotides from 1000 related bacterial substrains, whereas the method of Metsky et al. shows clearly super-linear running time and fails to process even a subset of 17% of the data in 72 h. AVAILABILITY AND IMPLEMENTATION: https://github.com/jnalanko/syotti. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Simulation is an essential technique for generating biomolecular data with a 'known' history for use in validating phylogenetic inference and other evolutionary methods. On longer time scales, simulation supports investigations of equilibrium behavior and provides a formal framework for testing competing evolutionary hypotheses. Twenty years of molecular evolution research have produced a rich repertoire of simulation methods. However, current models do not capture the stringent constraints acting on the domain insertions, duplications, and deletions by which multidomain architectures evolve. Although these processes have the potential to generate any combination of domains, only a tiny fraction of possible domain combinations are observed in nature. Modeling these stringent constraints on domain order and co-occurrence is a fundamental challenge in domain architecture simulation that does not arise with sequence and gene family simulation. RESULTS: Here, we introduce a stochastic model of domain architecture evolution to simulate evolutionary trajectories that reflect the constraints on domain order and co-occurrence observed in nature. This framework is implemented in a novel domain architecture simulator, DomArchov, using the Metropolis-Hastings algorithm with data-driven transition probabilities. The use of a data-driven event module enables quick and easy redeployment of the simulator for use in different taxonomic and protein function contexts. Using empirical evaluation with metazoan datasets, we demonstrate that domain architectures simulated by DomArchov recapitulate properties of genuine domain architectures that reflect the constraints on domain order and adjacency seen in nature. This work expands the realm of evolutionary processes that are amenable to simulation. AVAILABILITY AND IMPLEMENTATION: DomArchov is written in Python 3 and is available at http://www.cs.cmu.edu/~durand/DomArchov. The data underlying this article are available via the same link. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-nucleotide variants (SNVs) are the most common variations in the human genome. Recently developed methods for SNV detection from single-cell DNA sequencing data, such as SCIΦ and scVILP, leverage the evolutionary history of the cells to overcome the technical errors associated with single-cell sequencing protocols. Despite being accurate, these methods are not scalable to the extensive genomic breadth of single-cell whole-genome (scWGS) and whole-exome sequencing (scWES) data. RESULTS: Here, we report on a new scalable method, Phylovar, which extends the phylogeny-guided variant calling approach to sequencing datasets containing millions of loci. Through benchmarking on simulated datasets under different settings, we show that, Phylovar outperforms SCIΦ in terms of running time while being more accurate than Monovar (which is not phylogeny-aware) in terms of SNV detection. Furthermore, we applied Phylovar to two real biological datasets: an scWES triple-negative breast cancer data consisting of 32 cells and 3375 loci as well as an scWGS data of neuron cells from a normal human brain containing 16 cells and approximately 2.5 million loci. For the cancer data, Phylovar detected somatic SNVs with high or moderate functional impact that were also supported by bulk sequencing dataset and for the neuron dataset, Phylovar identified 5745 SNVs with non-synonymous effects some of which were associated with neurodegenerative diseases. AVAILABILITY AND IMPLEMENTATION: Phylovar is implemented in Python and is publicly available at https://github.com/NakhlehLab/Phylovar.

MOTIVATION: Food-derived bioactive peptides (FBPs) have demonstrated their significance in pharmaceuticals, diets and nutraceuticals, benefiting public health and global ecology. While significant efforts have been made to discover FBPs and to elucidate the underlying bioactivity mechanisms, there is lack of a systemic study of sequence-structure-activity relationship of FBPs in a large dataset. RESULTS: Here, we construct a database of food-derived bioactive peptides (DFBP), containing a total of 6276 peptide entries in 31 types from different sources. Further, we develop a series of analysis tools for function discovery/repurposing, traceability, multifunctional bioactive exploration and physiochemical property assessment of peptides. Finally, we apply this database and data-mining techniques to discover new FBPs as potential drugs for cardiovascular diseases. The DFBP serves as a useful platform for not only the fundamental understanding of sequence-structure-activity of FBPs but also the design, discovery, and repurposing of peptide-based drugs, vaccines, materials and food ingredients. AVAILABILITY AND IMPLEMENTATION: DFBP service can be accessed freely via http://www.cqudfbp.net/. All data are incorporated into the article and its online supplementary material. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Mapping positional features from one-dimensional (1D) sequences onto three-dimensional (3D) structures of biological macromolecules is a powerful tool to show geometric patterns of biochemical annotations and provide a better understanding of the mechanisms underpinning protein and nucleic acid function at the atomic level. RESULTS: We present a new library designed to display fully customizable interactive views between 1D positional features of protein and/or nucleic acid sequences and their 3D structures as isolated chains or components of macromolecular assemblies. AVAILABILITY AND IMPLEMENTATION: https://github.com/rcsb/rcsb-saguaro-3d. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Expanding our knowledge of small molecules beyond what is known in nature or designed in wet laboratories promises to significantly advance cheminformatics, drug discovery, biotechnology and material science. In silico molecular design remains challenging, primarily due to the complexity of the chemical space and the non-trivial relationship between chemical structures and biological properties. Deep generative models that learn directly from data are intriguing, but they have yet to demonstrate interpretability in the learned representation, so we can learn more about the relationship between the chemical and biological space. In this article, we advance research on disentangled representation learning for small molecule generation. We build on recent work by us and others on deep graph generative frameworks, which capture atomic interactions via a graph-based representation of a small molecule. The methodological novelty is how we leverage the concept of disentanglement in the graph variational autoencoder framework both to generate biologically relevant small molecules and to enhance model interpretability. RESULTS: Extensive qualitative and quantitative experimental evaluation in comparison with state-of-the-art models demonstrate the superiority of our disentanglement framework. We believe this work is an important step to address key challenges in small molecule generation with deep generative frameworks. AVAILABILITY AND IMPLEMENTATION: Training and generated data are made available at https://ieee-dataport.org/documents/dataset-disentangled-representation-learning-interpretable-molecule-generation. All code is made available at https://anonymous.4open.science/r/D-MolVAE-2799/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) technologies have been testified revolutionary for their promotion on the profiling of single-cell transcriptomes at single-cell resolution. Excess zeros due to various technical noises, called dropouts, will mislead downstream analyses. Therefore, it is crucial to have accurate imputation methods to address the dropout problem. RESULTS: In this article, we develop a new dropout imputation method for scRNA-seq data based on multi-objective optimization. Our method is different from existing ones, which assume that the underlying data has a preconceived structure and impute the dropouts according to the information learned from such structure. We assume that the data combines three types of latent structures, including the horizontal structure (genes are similar to each other), the vertical structure (cells are similar to each other) and the low-rank structure. The combination weights and latent structures are learned using multi-objective optimization. And, the weighted average of the observed data and the imputation results learned from the three types of structures are considered as the final result. Comprehensive downstream experiments show the superiority of our method in terms of recovery of true gene expression profiles, differential expression analysis, cell clustering and cell trajectory inference. AVAILABILITY AND IMPLEMENTATION: The R package is available at https://github.com/Zhangxf-ccnu/scMOO and https://zenodo.org/record/5785195. The codes to reproduce the downstream analyses in this article can be found at https://github.com/Zhangxf-ccnu/scMOO_experiments_codes and https://zenodo.org/record/5786211. The detailed list of data sets used in the present study is represented in Supplementary Table S1 in the Supplementary materials. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Next-Generation Sequencing is widely used as a tool for identifying and quantifying microorganisms pooled together in either natural or designed samples. However, a prominent obstacle is achieving correct quantification when the pooled microbes are genetically related. In such cases, the outcome mostly depends on the method used for assigning reads to the individual targets. To address this challenge, we have developed Exodus-a reference-based Python algorithm for quantification of genomes, including those that are highly similar, when they are sequenced together in a single mix. To test Exodus' performance, we generated both empirical and in silico next-generation sequencing data of mixed genomes. When applying Exodus to these data, we observed median error rates varying between 0% and 0.21% as a function of the complexity of the mix. Importantly, no false negatives were recorded, demonstrating that Exodus' likelihood of missing an existing genome is very low, even if the genome's relative abundance is low and similar genomes are present in the same mix. Taken together, these data position Exodus as a reliable tool for identifying and quantifying genomes in mixed samples. Exodus is open source and free to use at: https://github.com/ilyavs/exodus. AVAILABILITY AND IMPLEMENTATION: Exodus is implemented in Python within a Snakemake framework. It is available on GitHub alongside a docker containing the required dependencies: https://github.com/ilyavs/exodus. The data underlying this article will be shared on reasonable request to the corresponding author. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The BioExcel Building Blocks (BioBB) library offers a broad collection of wrappers on top of common biomolecular simulation and bioinformatics tools. The possibility to access the library remotely and programmatically increases its usability, allowing individual and sporadic executions and enabling remote workflows. RESULTS: BioBB REST API extends and complements the BioBB library offering programmatic access to the collection of biomolecular simulation tools included in the BioExcel Building Blocks library. Molecular Dynamics setup, docking, structure modeling, free energy simulations and flexibility analyses are examples of functionalities included in the endpoints collection. All functionalities are accessible through standard REST API calls, voiding the need for tool installation. AVAILABILITY AND IMPLEMENTATION: All the information related to the BioBB REST API endpoints is accessible from https://mmb.irbbarcelona.org/biobb-api/. Links to extended documentation, including OpenAPI endpoints specification and examples, Read-The-Docs documentation and a complete workflow tutorial can be found in the Supplementary Table S1. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The existence of quasispecies in the viral population causes difficulties for disease prevention and treatment. High-throughput sequencing provides opportunity to determine rare quasispecies and long sequencing reads covering full genomes reduce quasispecies determination to a clustering problem. The challenge is high similarity of quasispecies and high error rate of long sequencing reads. RESULTS: We developed QuasiSeq using a novel signature-based self-tuning clustering method, SigClust, to profile viral mixtures with high accuracy and sensitivity. QuasiSeq can correctly identify quasispecies even using low-quality sequencing reads (accuracy <80%) and produce quasispecies sequences with high accuracy (≥99.55%). Using high-quality circular consensus sequencing reads, QuasiSeq can produce quasispecies sequences with 100% accuracy. QuasiSeq has higher sensitivity and specificity than similar published software. Moreover, the requirement of the computational resource can be controlled by the size of the signature, which makes it possible to handle big sequencing data for rare quasispecies discovery. Furthermore, parallel computation is implemented to process the clusters and further reduce the runtime. Finally, we developed a web interface for the QuasiSeq workflow with simple parameter settings based on the quality of sequencing data, making it easy to use for users without advanced data science skills. AVAILABILITY AND IMPLEMENTATION: QuasiSeq is open source and freely available at https://github.com/LHRI-Bioinformatics/QuasiSeq. The current release (v1.0.0) is archived and available at https://zenodo.org/badge/latestdoi/340494542. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The analysis of cancer genomes provides fundamental information about its etiology, the processes driving cell transformation or potential treatments. While researchers and clinicians are often only interested in the identification of oncogenic mutations, actionable variants or mutational signatures, the first crucial step in the analysis of any tumor genome is the identification of somatic variants in cancer cells (i.e. those that have been acquired during their evolution). For that purpose, a wide range of computational tools have been developed in recent years to detect somatic mutations in sequencing data from tumor samples. While there have been some efforts to benchmark somatic variant calling tools and strategies, the extent to which variant calling decisions impact the results of downstream analyses of tumor genomes remains unknown. RESULTS: Here, we quantify the impact of variant calling decisions by comparing the results obtained in three important analyses of cancer genomics data (identification of cancer driver genes, quantification of mutational signatures and detection of clinically actionable variants) when changing the somatic variant caller (MuSE, MuTect2, SomaticSniper and VarScan2) or the strategy to combine them (Consensus of two, Consensus of three and Union) across all 33 cancer types from The Cancer Genome Atlas. Our results show that variant calling decisions have a significant impact on these analyses, creating important differences that could even impact treatment decisions for some patients. Moreover, the Consensus of three calling strategy to combine the output of multiple variant calling tools, a very widely used strategy by the research community, can lead to the loss of some cancer driver genes and actionable mutations. Overall, our results highlight the limitations of widespread practices within the cancer genomics community and point to important differences in critical analyses of tumor sequencing data depending on variant calling, affecting even the identification of clinically actionable variants. AVAILABILITY AND IMPLEMENTATION: Code is available at https://github.com/carlosgarciaprieto/VariantCallingClinicalBenchmark. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Multiomics cancer profiles provide essential signals for predicting cancer survival. It is challenging to reveal the complex patterns from multiple types of data and link them to survival outcomes. We aim to develop a new deep learning-based algorithm to integrate three types of high-dimensional omics data measured on the same individuals to improve cancer survival outcome prediction. RESULTS: We built a three-dimension tensor to integrate multi-omics cancer data and factorized it into two-dimension matrices of latent factors, which were fed into neural networks-based survival networks. The new algorithm and other multi-omics-based algorithms, as well as individual genomic-based survival analysis algorithms, were applied to the breast cancer data colon and rectal cancer data from The Cancer Genome Atlas (TCGA) program. We evaluated the goodness-of-fit using the concordance index (C-index) and Integrated Brier Score (IBS). We demonstrated that the proposed tight integration framework has better survival prediction performance than the models using individual genomic data and other conventional data integration methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/jasperzyzhang/DeepTensorSurvival. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Though genome-wide association studies have identified tens of thousands of variants associated with complex traits and most of them fall within the non-coding regions, they may not be the causal ones. The development of high-throughput functional assays leads to the discovery of experimental validated non-coding functional variants. However, these validated variants are rare due to technical difficulty and financial cost. The small sample size of validated variants makes it less reliable to develop a supervised machine learning model for achieving a whole genome-wide prediction of non-coding causal variants. RESULTS: We will exploit a deep transfer learning model, which is based on convolutional neural network, to improve the prediction for functional non-coding variants (NCVs). To address the challenge of small sample size, the transfer learning model leverages both large-scale generic functional NCVs to improve the learning of low-level features and context-specific functional NCVs to learn high-level features toward the context-specific prediction task. By evaluating the deep transfer learning model on three MPRA datasets and 16 GWAS datasets, we demonstrate that the proposed model outperforms deep learning models without pretraining or retraining. In addition, the deep transfer learning model outperforms 18 existing computational methods in both MPRA and GWAS datasets. AVAILABILITY AND IMPLEMENTATION: https://github.com/lichen-lab/TLVar. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: High-quality visualization of biological networks often requires both manual curation for proper alignment and programming to map external data to the graphical components. Nezzle is a network visualization software written in Python, which provides programmable and interactive interfaces for facilitating both manual and automatic curation of the graphical components of networks to create high-quality figures. AVAILABILITY AND IMPLEMENTATION: Nezzle is an open-source project under MIT license and is available from https://github.com/dwgoon/nezzle. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The RNA splicing efficiency is of high interest for both understanding the regulatory machinery of gene expression and estimating the RNA velocity in single cells. However, its genomic regulation and stochasticity across contexts remain poorly understood. RESULTS: Here, by leveraging the recent RNA velocity tool, we estimated the relative splicing efficiency across a variety of single-cell RNA-Seq data sets. We further extracted large sets of genomic features and 120 RNA-binding protein features and found they are highly predictive to relative RNA splicing efficiency across multiple tissues and organs on human and mouse. This predictive power brings promise to reveal the complexity of RNA processing and to enhance the analysis of single-cell transcription activities. AVAILABILITY AND IMPLEMENTATION: In order to ensure reproducibility, all preprocessed datasets and scripts used for the prediction and figure generation are publicly available at https://doi.org/10.5281/zenodo.6513669. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Digitization of pathology laboratories through digital slide scanners and advances in deep learning approaches for objective histological assessment have resulted in rapid progress in the field of computational pathology (CPath) with wide-ranging applications in medical and pharmaceutical research as well as clinical workflows. However, the estimation of robustness of CPath models to variations in input images is an open problem with a significant impact on the downstream practical applicability, deployment and acceptability of these approaches. Furthermore, development of domain-specific strategies for enhancement of robustness of such models is of prime importance as well. RESULTS: In this work, we propose the first domain-specific Robustness Evaluation and Enhancement Toolbox (REET) for computational pathology applications. It provides a suite of algorithmic strategies for enabling robustness assessment of predictive models with respect to specialized image transformations such as staining, compression, focusing, blurring, changes in spatial resolution, brightness variations, geometric changes as well as pixel-level adversarial perturbations. Furthermore, REET also enables efficient and robust training of deep learning pipelines in computational pathology. Python implementation of REET is available at https://github.com/alexjfoote/reetoolbox. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Understanding whether and which microbes played a mediating role between an exposure and a disease outcome are essential for researchers to develop clinical interventions to treat the disease by modulating the microbes. Existing methods for mediation analysis of the microbiome are often limited to a global test of community-level mediation or selection of mediating microbes without control of the false discovery rate (FDR). Further, while the null hypothesis of no mediation at each microbe is a composite null that consists of three types of null, most existing methods treat the microbes as if they were all under the same type of null, leading to excessive false positive results. RESULTS: We propose a new approach based on inverse regression that regresses the microbiome data at each taxon on the exposure and the exposure-adjusted outcome. Then, the P-values for testing the coefficients are used to test mediation at both the community and individual taxon levels. This approach fits nicely into our Linear Decomposition Model (LDM) framework, so our new method LDM-med, implemented in the LDM framework, enjoys all the features of the LDM, e.g. allowing an arbitrary number of taxa to be tested simultaneously, supporting continuous, discrete, or multivariate exposures and outcomes (including survival outcomes), and so on. Using extensive simulations, we showed that LDM-med always preserved the FDR of testing individual taxa and had adequate sensitivity; LDM-med always controlled the type I error of the global test and had compelling power over existing methods. The flexibility of LDM-med for a variety of mediation analyses is illustrated by an application to a murine microbiome dataset, which identified several plausible mediating taxa. AVAILABILITY AND IMPLEMENTATION: Our new method has been added to our R package LDM, which is available on GitHub at https://github.com/yijuanhu/LDM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The field of natural language processing (NLP) has recently seen a large change toward using pre-trained language models for solving almost any task. Despite showing great improvements in benchmark datasets for various tasks, these models often perform sub-optimal in non-standard domains like the clinical domain where a large gap between pre-training documents and target documents is observed. In this article, we aim at closing this gap with domain-specific training of the language model and we investigate its effect on a diverse set of downstream tasks and settings. RESULTS: We introduce the pre-trained CLIN-X (Clinical XLM-R) language models and show how CLIN-X outperforms other pre-trained transformer models by a large margin for 10 clinical concept extraction tasks from two languages. In addition, we demonstrate how the transformer model can be further improved with our proposed task- and language-agnostic model architecture based on ensembles over random splits and cross-sentence context. Our studies in low-resource and transfer settings reveal stable model performance despite a lack of annotated data with improvements of up to 47 F1 points when only 250 labeled sentences are available. Our results highlight the importance of specialized language models, such as CLIN-X, for concept extraction in non-standard domains, but also show that our task-agnostic model architecture is robust across the tested tasks and languages so that domain- or task-specific adaptations are not required. AVAILABILITY AND IMPLEMENTATION: The CLIN-X language models and source code for fine-tuning and transferring the model are publicly available at https://github.com/boschresearch/clin_x/ and the huggingface model hub.