MOTIVATION: Knowledge graphs (KG) are being adopted in industry, commerce, and academia. Biomedical KG present a challenge due to the complexity, size, and heterogeneity of the underlying information. RESULTS: In this work we present the Scalable Precision Medicine Open Knowledge Engine (SPOKE), a biomedical KG connecting millions of concepts via semantically meaningful relationships. SPOKE contains 27 million nodes of 21 different types and 53 million edges of 55 types downloaded from 41 databases. The graph is built on the framework of 11 ontologies that maintain its structure, enable mappings, and facilitate navigation. SPOKE is built weekly by python scripts which download each resource, check for integrity and completeness, and then create a "parent table" of nodes and edges. Graph queries are translated by a REST API and users can submit searches directly via an API or a graphical user interface. Conclusions/Significance: SPOKE enables the integration of seemingly disparate information to support precision medicine efforts. AVAILABILITY: The SPOKE neighborhood explorer is available at https://spoke.rbvi.ucsf.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Molecular dynamics (MD) simulations of cell membranes allow for a better understanding of complex processes such as changing membrane dynamics, lipid rafts and the incorporation/passing of macromolecules into/through membranes. To explore and understand cell membrane compositions, dynamics and processes, visual analytics can help to interpret MD simulation data. APL@Voro is a software for the interactive visualisation and analysis of cell membrane simulations. Here, we present the new APL@Voro, which has been continuously developed since its initial release in 2013. We discuss newly implemented algorithms, methodologies and features, such as the interactive comparison of related simulations and methods to assign lipids to either the upper or lower leaflet. AVAILABILITY AND IMPLEMENTATION: The current open-source version of APL@Voro can be downloaded from http://aplvoro.com.

MOTIVATION: A chronogram is a dated phylogenetic tree whose branch lengths have been scaled to represent time. Such chronograms are computed based on available date estimates (e.g., from dated fossils), which provide absolute time constraints for one or more nodes of an input undated phylogeny, coupled with an appropriate underlying model for evolutionary rates variation along the branches of the phylogeny. However, traditional methods for phylogenetic dating cannot take into account relative time constraints, such as those provided by inferred horizontal transfer events. In many cases, chronograms computed using only absolute time constraints are inconsistent with known relative time constraints. RESULTS: In this work, we introduce a new approach, DaTeR, for phylogenetic dating that can take into account both absolute and relative time constraints. The key idea is to use existing Bayesian approaches for phylogenetic dating to sample posterior chronograms satisfying desired absolute time constraints, minimally adjust or "error-correct" these sampled chronograms to satisfy all given relative time constraints, and aggregate across all error-corrected chronograms. DaTeR uses a constrained optimization framework for the error-correction step, finding minimal deviations from previously assigned dates or branch lengths. We applied DaTeR to a biological dataset of 170 Cyanobacterial taxa and a reliable set of 24 transfer-based relative constraints, under six different molecular dating models. Our extensive analysis of this dataset demonstrates that DaTeR is both highly effective and scalable and that its application can significantly improve estimated chronograms. AVAILABILITY: Freely available from https://compbio.engr.uconn.edu/software/dater/.

MOTIVATION: With the rapidly growing volume of knowledge and data in biomedical databases, improved methods for knowledge-graph-based computational reasoning are needed in order to answer translational questions. Previous efforts to solve such challenging computational reasoning problems have contributed tools and approaches, but progress has been hindered by the lack of an expressive analysis workflow language for translational reasoning and by the lack of a reasoning engine-supporting that language-that federates semantically integrated knowledge-bases. RESULTS: We introduce ARAX, a new reasoning system for translational biomedicine that provides a web browser user interface and an application programming interface. ARAX enables users to encode translational biomedical questions and to integrate knowledge across sources to answer the user's query and facilitate exploration of results. For ARAX, we developed new approaches to query planning, knowledge-gathering, reasoning, and result ranking and dynamically integrate knowledge providers for answering biomedical questions. To illustrate ARAX's application and utility in specific disease contexts, we present several use-case examples. AVAILABILITY AND IMPLEMENTATION: The source code and technical documentation for building the ARAX server-side software and its built-in knowledge database are freely available online (https://github.com/RTXteam/RTX). We provide a hosted ARAX service with a web browser interface at arax.rtx.ai and a web application programming interface (API) endpoint at arax.rtx.ai/api/arax/v1.3/ui/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Pairwise sequence alignment remains a fundamental problem in computational biology and bioinformatics. Recent advances in genomics and sequencing technologies demand faster and scalable algorithms that can cope with the ever-increasing sequence lengths. Classical pairwise alignment algorithms based on dynamic programming are strongly limited by quadratic requirements in time and memory. The recently proposed wavefront alignment algorithm (WFA) introduced an efficient algorithm to perform exact gap-affine alignment in O(ns) time, where s is the optimal score and n is the sequence length. Notwithstanding these bounds, WFA's O(s2) memory requirements become computationally impractical for genome-scale alignments, leading to a need for further improvement. RESULTS: In this paper, we present the bidirectional WFA algorithm (BiWFA), the first gap-affine algorithm capable of computing optimal alignments in O(s) memory while retaining WFA's time complexity of O(ns). As a result, this work improves the lowest known memory bound O(n) to compute gap-affine alignments. In practice, our implementation never requires more than a few hundred MBs aligning noisy Oxford Nanopore Technologies reads up to 1 Mbp long while maintaining competitive execution times. AVAILABILITY: All code is publicly available at https://github.com/smarco/BiWFA-paper.

SUMMARY: As the FAIR (Findable, Accessible, Interoperable, Reusable) principles have become widely accepted in the proteomics field, under the guidance of ProteomeXchange (PX) and The Human Proteome Organization Proteomics Standards Initiative (HUPO-PSI), proteomics public databases have been providing Application Programming Interfaces (APIs) for programmatic access. Based on generating logic from proteomics data, we present Patpat, an extensible framework for searching public datasets, merging results from multiple databases to help researchers find their proteins of interest in the vast mass spectrometry. Patpat's two-dimensional strategy of combining results from multiple databases allows users to provide only protein identifiers to obtain metadata for relevant datasets, improving the "Findable" of proteomics data. AVAILABILITY AND IMPLEMENTATION: The Patpat framework is released under the Apache 2.0 license open source, and the source code is stored on GitHub (https://github.com/henry-leo/Patpat) and is freely available. SUPPLEMENTARY INFORMATION: Supplementary information.

SUMMARY: DeepPheWAS is an R package for phenome wide association studies that creates clinically-curated composite phenotypes, and integrates quantitative phenotypes from primary care data, longitudinal trajectories of quantitative measures, disease progression, and drug response phenotypes. Tools are provided for efficient analysis of association with any genetic input, under any genetic model, with optional sex-stratified analysis, and for developing novel phenotypes. AVAILABILITY AND IMPLEMENTATION: The DeepPheWAS R package is freely available under GNU general public licence v3.0 from at https://github.com/Richard-Packer/DeepPheWAS. SUPPLEMENTARY INFORMATION: Supplementary methods and results are available at Bioinformatics online.

MOTIVATION: Mass Spectrometry Imaging (MSI) analyzes complex biological samples such as tissues. It simultaneously characterizes the ions present in the tissue in the form of mass spectra, and the spatial distribution of the ions across the tissue in the form of ion images. Unsupervised clustering of ion images facilitates the interpretation in the spectral domain, by identifying groups of ions with similar spatial distributions. Unfortunately, many current methods for clustering ion images ignore the spatial features of the images, and are therefore unable to learn these features for clustering purposes. Alternative methods extract spatial features using deep neural networks pre-trained on natural image tasks; however, this is often inadequate since ion images are substantially noisier than natural images. RESULTS: We contribute a deep clustering approach for ion images that accounts for both spatial contextual features and noise. In evaluations on a simulated dataset and on four experimental datasets of different tissue types, the proposed method grouped ions from the same source into a same cluster more frequently than existing methods. We further demonstrated that using ion image clustering as a pre-processing step facilitated the interpretation of a subsequent spatial segmentation as compared to using either all the ions or one ion at a time. As a result, the proposed approach facilitated the interpretability of MSI data in both the spectral domain and the spatial domain. AVAILABILITY: The data and code are available at https://github.com/DanGuo1223/mzClustering. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The findings from genome-wide association studies (GWASs) have greatly helped us to understand the genetic basis of human complex traits and diseases. Despite the tremendous progress, much effects are still needed to address several major challenges arising in GWAS. First, most GWAS hits are located in the non-coding region of human genome, and thus their biological functions largely remain unknown. Second, due to the polygenicity of human complex traits and diseases, many genetic risk variants with weak or moderate effects have not been identified yet. RESULTS: To address the above challenges, we propose a powerful and adaptive latent model (PALM) to integrate cell-type/tissue specific functional annotations with GWAS summary statistics. Unlike existing methods which are mainly based on linear models, PALM leverages a tree ensemble to adaptively characterize nonlinear relationship between functional annotations and the association status of genetic variants. To make PALM scalable to millions of variants and hundreds of functional annotations, we develop a functional gradient-based expectation-maximization (EM) algorithm, to fit the tree-based nonlinear model in a stable manner. Through comprehensive simulation studies, we show that PALM not only controls false discovery rate well, but also improves statistical power of identifying risk variants. We also apply PALM to integrate summary statistics of 30 GWASs with 127 cell type/tissue-specific functional annotations. The results indicate that PALM can identify more risk variants as well as rank the importance of functional annotations, yielding better interpretation of GWAS results. AVAILABILITY: The source code is available at https://github.com/YangLabHKUST/PALM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We introduce mapache, a flexible, robust and scalable pipeline to map, quantify and impute ancient and present-day DNA in a reproducible way. Mapache is implemented in the workflow manager Snakemake and is optimized for low-space consumption, allowing to efficiently (re)map large datasets-such as reference panels and multiple extracts and libraries per sample - to one or several genomes. Mapache can easily be customized or combined with other Snakemake tools. AVAILABILITY AND IMPLEMENTATION: Mapache is freely available on GitHub (https://github.com/sneuensc/mapache). An extensive manual is provided at https://github.com/sneuensc/mapache/wiki. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: We face an increasing flood of genetic sequence data, from diverse sources, requiring rapid computational analysis. Rapid analysis can be achieved by sampling a subset of positions in each sequence. Previous sequence-sampling methods, such as minimizers, syncmers and minimally overlapping words, were developed by heuristic intuition, and are not optimal. RESULTS: We present a sequence-sampling approach that provably optimizes sensitivity for a whole class of sequence comparison methods, for randomly evolving sequences. It is likely near-optimal for a wide range of alignment-based and alignment-free analyses. For real biological DNA, it increases specificity by avoiding simple repeats. Our approach generalizes universal hitting sets (which guarantee to sample a sequence at least once) and polar sets (which guarantee to sample a sequence at most once). This helps us understand how to do rapid sequence analysis as accurately as possible. AVAILABILITY AND IMPLEMENTATION: Source code is freely available at https://gitlab.com/mcfrith/noverlap. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: PyGenePlexus is a Python package that enables a user to gain insight into any gene set of interest through a molecular interaction network informed supervised machine learning model. PyGenePlexus provides predictions of how associated every gene in the network is to the input gene set, offers interpretability by comparing the model trained on the input gene set to models trained on thousands of known gene sets, and returns the network connectivity of the top predicted genes. AVAILABILITY AND IMPLEMENTATION: https://pypi.org/project/geneplexus/ and https://github.com/krishnanlab/PyGenePlexus. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The emergence of drug-resistant bacteria makes the discovery of new antibiotics an urgent issue, but finding new molecules with the desired antibacterial activity is an extremely difficult task. To address this challenge, we established a framework, MDAGS (Molecular Design via Attribute-Guided Search), to optimize and generate potent antibiotic molecules. RESULTS: By designing the antibacterial activity latent space and guiding the optimization of functional compounds based on this space, the model MDAGS can generate novel compounds with desirable antibacterial activity without the need for extensive expensive and time-consuming evaluations. Compared with existing antibiotics, candidate antibacterial compounds generated by MDAGS always possessed significantly better antibacterial activity and ensured high similarity. Furthermore, although without explicit constraints on similarity to known antibiotics, these candidate antibacterial compounds all exhibited the highest structural similarity to antibiotics of expected function in the DrugBank database query. Overall, our approach provides a viable solution to the problem of bacterial drug resistance. AVAILABILITY AND IMPLEMENTATION: Code of the model and datasets can be downloaded from GitHub (https://github.com/LiangYu-Xidian/MDAGS). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The regulation of genes by cis-regulatory elements (CREs) is complex and differs between cell types. Visual analysis of large collections of chromatin profiles across diverse cell types, integrated with computational methods, can reveal meaningful biological insights. We developed Cistrome Explorer, a web-based interactive visual analytics tool for exploring thousands of chromatin profiles in diverse cell types. Integrated with the Cistrome Data Browser database which contains thousands of ChIP-seq, DNase-seq and ATAC-seq samples, Cistrome Explorer enables the discovery of patterns of CREs across cell types and the identification of transcription factor binding underlying these patterns. AVAILABILITY AND IMPLEMENTATION: Cistrome Explorer and its source code are available at http://cisvis.gehlenborglab.org/ and released under the MIT License. Documentation can be accessed via http://cisvis.gehlenborglab.org/docs/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Machine learning (ML) methods are motivated by the need to automate information extraction from large datasets in order to support human users in data-driven tasks. This is an attractive approach for integrative joint analysis of vast amounts of omics data produced in next generation sequencing and other -omics assays. A systematic assessment of the current literature can help to identify key trends and potential gaps in methodology and applications. We surveyed the literature on ML multi-omic data integration and quantitatively explored the goals, techniques and data involved in this field. We were particularly interested in examining how researchers use ML to deal with the volume and complexity of these datasets. RESULTS: Our main finding is that the methods used are those that address the challenges of datasets with few samples and many features. Dimensionality reduction methods are used to reduce the feature count alongside models that can also appropriately handle relatively few samples. Popular techniques include autoencoders, random forests and support vector machines. We also found that the field is heavily influenced by the use of The Cancer Genome Atlas dataset, which is accessible and contains many diverse experiments. AVAILABILITY AND IMPLEMENTATION: All data and processing scripts are available at this GitLab repository: https://gitlab.com/polavieja_lab/ml_multi-omics_review/ or in Zenodo: https://doi.org/10.5281/zenodo.7361807. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We recently introduced the Gut Microbiome Wellness Index (GMWI), a stool metagenome-based indicator for assessing health by determining the likelihood of disease given the state of one's gut microbiome. The calculation of our wellness index depends on the relative abundances of health-prevalent and health-scarce species. Encouragingly, GMWI has already been utilized in various studies focusing on differences in the gut microbiome between cases and controls. Herein, we introduce the GMWI-webtool, a user-friendly browser application that computes GMWI, health-prevalent/-scarce species' relative abundances, and α-diversities from stool shotgun metagenome taxonomic profiles. Users of our interactive online tool can visualize their results and compare them side-by-side with those from our pooled reference dataset of metagenomes, as well as export data in.csv format and high-resolution figures. AVAILABILITY AND IMPLEMENTATION: GMWI-webtool is freely available here: https://gmwi-webtool.github.io/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The human genome encodes over 500 distinct protein kinases which regulate nearly all cellular processes by the specific phosphorylation of protein substrates. While advances in mass spectrometry and proteomics studies have identified thousands of phosphorylation sites across species, information on the specific kinases that phosphorylate these sites is currently lacking for the vast majority of phosphosites. Recently, there has been a major focus on the development of computational models for predicting kinase-substrate associations. However, most current models only allow predictions on a subset of well-studied kinases. Furthermore, the utilization of hand-curated features and imbalances in training and testing datasets pose unique challenges in the development of accurate predictive models for kinase-specific phosphorylation prediction. Motivated by the recent development of universal protein language models which automatically generate context-aware features from primary sequence information, we sought to develop a unified framework for kinase-specific phosphosite prediction, allowing for greater investigative utility and enabling substrate predictions at the whole kinome level. RESULTS: We present a deep learning model for kinase-specific phosphosite prediction, termed Phosformer, which predicts the probability of phosphorylation given an arbitrary pair of unaligned kinase and substrate peptide sequences. We demonstrate that Phosformer implicitly learns evolutionary and functional features during training, removing the need for feature curation and engineering. Further analyses reveal that Phosformer also learns substrate specificity motifs and is able to distinguish between functionally distinct kinase families. Benchmarks indicate that Phosformer exhibits significant improvements compared to the state-of-the-art models, while also presenting a more generalized, unified, and interpretable predictive framework. AVAILABILITY AND IMPLEMENTATION: Code and data are available at https://github.com/esbgkannan/phosformer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recently, deep learning has become the mainstream methodology for drug-target binding affinity prediction. However, two deficiencies of the existing methods restrict their practical applications. On the one hand, most existing methods ignore the individual information of sequence elements, resulting in poor sequence feature representations. On the other hand, without prior biological knowledge, the prediction of drug-target binding regions based on attention weights of a deep neural network could be difficult to verify, which may bring adverse interference to biological researchers. RESULTS: We propose a novel Multi-Functional and Robust Drug-Target binding Affinity prediction (MFR-DTA) method to address the above issues. Specifically, we design a new biological sequence feature extraction block, namely BioMLP, that assists the model in extracting individual features of sequence elements. Then, we propose a new Elem-feature fusion block to refine the extracted features. After that, we construct a Mix-Decoder block that extracts drug-target interaction information and predicts their binding regions simultaneously. Last, we evaluate MFR-DTA on two benchmarks consistently with the existing methods and propose a new dataset, sc-PDB, to better measure the accuracy of binding region prediction. We also visualize some samples to demonstrate the locations of their binding sites and the predicted multi-scale interaction regions. The proposed method achieves excellent performance on these datasets, demonstrating its merits and superiority over the state-of-the-art methods. AVAILABILITY AND IMPLEMENTATION: https://github.com/JU-HuaY/MFR.

MOTIVATION: Synthetic lethality (SL) is a form of genetic interaction that can selectively kill cancer cells without damaging normal cells. Exploiting this mechanism is gaining popularity in the field of targeted cancer therapy and anticancer drug development. Due to the limitations of identifying SL interactions from laboratory experiments, an increasing number of research groups are devising computational prediction methods to guide the discovery of potential SL pairs. Although existing methods have attempted to capture the underlying mechanisms of SL interactions, methods that have a deeper understanding of and attempt to explain SL mechanisms still need to be developed. RESULTS: In this work, we propose a novel SL prediction method, SLGNN. This method is based on the following assumption: SL interactions are caused by different molecular events or biological processes, which we define as SL-related factors that lead to SL interactions. SLGNN, apart from identifying SL interaction pairs, also models the preferences of genes for different SL-related factors, making the results more interpretable for biologists and clinicians. SLGNN consists of three steps: first, we model the combinations of relationships in the gene-related knowledge graph as the SL-related factors. Next, we derive initial embeddings of genes through an explicit message aggregation process of the knowledge graph. Finally, we derive the final gene embeddings through an SL graph, constructed using known SL gene pairs, utilizing factor-based message aggregation. At this stage, a supervised end-to-end training model is used for SL interaction prediction. Based on experimental results, the proposed SLGNN model outperforms all current state-of-the-art SL prediction methods and provides better interpretability. AVAILABILITY AND IMPLEMENTATION: SLGNN is freely available at https://github.com/zy972014452/SLGNN.

MOTIVATION: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for MHC Class I proteins, in vitro experiments have been conducted to screen peptides with high binding affinities to hundreds of given MHC Class I proteins. However, considering tens of thousands of known MHC Class I proteins, conducting in vitro experiments for extensive MHC proteins is infeasible, and thus a more efficient and scalable way to characterize binding motifs is needed. RESULTS: We presented a de novo generation framework, coined PepPPO, to characterize binding motif for any given MHC Class I proteins via generating repertoires of peptides presented by them. PepPPO leverages a reinforcement learning agent with a mutation policy to mutate random input peptides into positive presented ones. Using PepPPO, we characterized binding motifs for around 10 000 known human MHC Class I proteins with and without experimental data. These computed motifs demonstrated high similarities with those derived from experimental data. In addition, we found that the motifs could be used for the rapid screening of neoantigens at a much lower time cost than previous deep-learning methods. AVAILABILITY AND IMPLEMENTATION: The software can be found in https://github.com/minrq/pMHC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Despite the fact that antimicrobial resistance is an increasing health concern, the pace of production of new drugs is slow due to the high cost and uncertain success of the process. The development of high-throughput technologies has allowed the integration of biological data into detailed genome-scale models of multiple organisms. Such models can be exploited by means of computational methods to identify system vulnerabilities such as chokepoint reactions and essential reactions. These vulnerabilities are appealing drug targets that can lead to novel drug developments. However, the current approach to compute these vulnerabilities is only based on topological data and ignores the dynamic information of the model. This can lead to misidentified drug targets. RESULTS: This work computes flux constraints that are consistent with a certain growth rate of the modelled organism, and integrates the computed flux constraints into the model to improve the detection of vulnerabilities. By exploiting these flux constraints, we are able to obtain a directionality of the reactions of metabolism consistent with a given growth rate of the model, and consequently, a more realistic detection of vulnerabilities can be performed. Several sets of reactions that are system vulnerabilities are defined and the relationships among them are studied. The approach for the detection of these vulnerabilities has been implemented in the Python tool CONTRABASS. Such tool, for which an online web server has also been implemented, computes flux constraints and generates a report with the detected vulnerabilities. AVAILABILITY AND IMPLEMENTATION: CONTRABASS is available as an open source Python package at https://github.com/openCONTRABASS/CONTRABASS under GPL-3.0 License. An online web server is available at http://contrabass.unizar.es. SUPPLEMENTARY INFORMATION: A glossary of terms are available at Bioinformatics online.

MOTIVATION: One of the standard methods of high-throughput RNA sequencing analysis is differential expression. However, it does not detect changes in molecular regulation. In contrast to the standard differential expression analysis, differential co-expression one aims to detect pairs or clusters whose mutual expression changes between two conditions. RESULTS: We developed Differential Co-expression Network Analysis (DCoNA)-an open-source statistical tool that allows one to identify pair interactions, which correlation significantly changes between two conditions. Comparing DCoNA with the state-of-the-art analog, we showed that DCoNA is a faster, more accurate and less memory-consuming tool. We applied DCoNA to prostate mRNA/miRNA-seq data collected from The Cancer Genome Atlas (TCGA) and compared predicted regulatory interactions of miRNA isoforms (isomiRs) and their target mRNAs between normal and cancer samples. As a result, almost all highly expressed isomiRs lost negative correlation with their targets in prostate cancer samples compared to ones without the pathology. One exception to this trend was the canonical isomiR of hsa-miR-93-5p acquiring cancer-specific targets. Further analysis showed that cancer aggressiveness simultaneously increased with the expression level of this isomiR in both TCGA primary tumor samples and 153 blood plasma samples of P. Hertsen Moscow Oncology Research Institute patients' cohort analyzed by miRNA microarrays. AVAILABILITY AND IMPLEMENTATION: Source code and documentation of DCoNA are available at https://github.com/zhiyanov/DCoNA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein-protein interaction (PPI) networks and transcriptional regulatory networks are critical in regulating cells and their signaling. A thorough understanding of PPIs can provide more insights into cellular physiology at normal and disease states. Although numerous methods have been proposed to predict PPIs, it is still challenging for interaction prediction between unknown proteins. In this study, a novel neural network named AFTGAN was constructed to predict multi-type PPIs. Regarding feature input, ESM-1b embedding containing much biological information for proteins was added as a protein sequence feature besides amino acid co-occurrence similarity and one-hot coding. An ensemble network was also constructed based on a transformer encoder containing an AFT module (performing the weight operation on vital protein sequence feature information) and graph attention network (extracting the relational features of protein pairs) for the part of the network framework. RESULTS: The experimental results showed that the Micro-F1 of the AFTGAN based on three partitioning schemes (BFS, DFS and the random mode) on the SHS27K and SHS148K datasets was 0.685, 0.711 and 0.867, as well as 0.745, 0.819 and 0.920, respectively, all higher than that of other popular methods. In addition, the experimental comparisons confirmed the performance superiority of the proposed model for predicting PPIs of unknown proteins on the STRING dataset. AVAILABILITY AND IMPLEMENTATION: The source code is publicly available at https://github.com/1075793472/AFTGAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Small insertion and deletion (sindel) of human genome has an important implication for human disease. One important mechanism for non-coding sindel (nc-sindel) to have an impact on human diseases and phenotypes is through the regulation of gene expression. Nevertheless, current sequencing experiments may lack statistical power and resolution to pinpoint the functional sindel due to lower minor allele frequency or small effect size. As an alternative strategy, a supervised machine learning method can identify the otherwise masked functional sindels by predicting their regulatory potential directly. However, computational methods for annotating and predicting the regulatory sindels, especially in the non-coding regions, are underdeveloped. RESULTS: By leveraging labeled nc-sindels identified by cis-expression quantitative trait loci analyses across 44 tissues in Genotype-Tissue Expression (GTEx), and a compilation of both generic functional annotations and large-scale epigenomic profiles, we develop TIssue-specific Variant Annotation for Non-coding indel (TIVAN-indel), which is a supervised computational framework for predicting non-coding regulatory sindels. As a result, we demonstrate that TIVAN-indel achieves the best prediction performance in both with-tissue prediction and cross-tissue prediction. As an independent evaluation, we train TIVAN-indel from the 'Whole Blood' tissue in GTEx and test the model using 15 immune cell types from an independent study named Database of Immune Cell Expression. Lastly, we perform an enrichment analysis for both true and predicted sindels in key regulatory regions such as chromatin interactions, open chromatin regions and histone modification sites, and find biologically meaningful enrichment patterns. AVAILABILITY AND IMPLEMENTATION: https://github.com/lichen-lab/TIVAN-indel. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Sparse regularized regression methods are now widely used in genome-wide association studies (GWAS) to address the multiple testing burden that limits discovery of potentially important predictors. Linear mixed models (LMMs) have become an attractive alternative to principal components (PCs) adjustment to account for population structure and relatedness in high-dimensional penalized models. However, their use in binary trait GWAS rely on the invalid assumption that the residual variance does not depend on the estimated regression coefficients. Moreover, LMMs use a single spectral decomposition of the covariance matrix of the responses, which is no longer possible in generalized linear mixed models (GLMMs). RESULTS: We introduce a new method called pglmm, a penalized GLMM that allows to simultaneously select genetic markers and estimate their effects, accounting for between-individual correlations and binary nature of the trait. We develop a computationally efficient algorithm based on penalized quasi-likelihood estimation that allows to scale regularized mixed models on high-dimensional binary trait GWAS. We show through simulations that when the dimensionality of the relatedness matrix is high, penalized LMM and logistic regression with PC adjustment fail to select important predictors, and have inferior prediction accuracy compared to pglmm. Further, we demonstrate through the analysis of two polygenic binary traits in a subset of 6731 related individuals from the UK Biobank data with 320K SNPs that our method can achieve higher predictive performance, while also selecting fewer predictors than a sparse regularized logistic lasso with PC adjustment. AVAILABILITY AND IMPLEMENTATION: Our Julia package PenalizedGLMM.jl is publicly available on github: https://github.com/julstpierre/PenalizedGLMM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Accurate and rapid prediction of protein-ligand binding affinity is a great challenge currently encountered in drug discovery. Recent advances have manifested a promising alternative in applying deep learning-based computational approaches for accurately quantifying binding affinity. The structure complementarity between protein-binding pocket and ligand has a great effect on the binding strength between a protein and a ligand, but most of existing deep learning approaches usually extracted the features of pocket and ligand by these two detached modules. RESULTS: In this work, a new deep learning approach based on the cross-attention mechanism named CAPLA was developed for improved prediction of protein-ligand binding affinity by learning features from sequence-level information of both protein and ligand. Specifically, CAPLA employs the cross-attention mechanism to capture the mutual effect of protein-binding pocket and ligand. We evaluated the performance of our proposed CAPLA on comprehensive benchmarking experiments on binding affinity prediction, demonstrating the superior performance of CAPLA over state-of-the-art baseline approaches. Moreover, we provided the interpretability for CAPLA to uncover critical functional residues that contribute most to the binding affinity through the analysis of the attention scores generated by the cross-attention mechanism. Consequently, these results indicate that CAPLA is an effective approach for binding affinity prediction and may contribute to useful help for further consequent applications. AVAILABILITY AND IMPLEMENTATION: The source code of the method along with trained models is freely available at https://github.com/lennylv/CAPLA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: We present NMRtist, an online platform that combines deep learning, large-scale optimization and cloud computing to automate protein NMR spectra analysis. Our website provides virtual storage for NMR spectra deposition together with a set of applications designed for automated peak picking, chemical shift assignment and protein structure determination. The system can be used by non-experts and allows protein assignments and structures to be determined within hours after the measurements, strictly without any human intervention. AVAILABILITY AND IMPLEMENTATION: NMRtist is freely available to non-commercial users at https://nmrtist.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Many methods have been proposed for mapping the targets of transcription factors (TFs) from gene expression data. It is known that combining outputs from multiple methods can improve performance. To date, outputs have been combined by using either simplistic formulae, such as geometric mean, or carefully hand-tuned formulae that may not generalize well to new inputs. Finally, the evaluation of accuracy has been challenging due to the lack of genome-scale, ground-truth networks. RESULTS: We developed NetProphet3, which combines scores from multiple analyses automatically, using a tree boosting algorithm trained on TF binding location data. We also developed three independent, genome-scale evaluation metrics. By these metrics, NetProphet3 is more accurate than other commonly used packages, including NetProphet 2.0, when gene expression data from direct TF perturbations are available. Furthermore, its integration mode can forge a consensus network from gene expression data and TF binding location data. AVAILABILITY AND IMPLEMENTATION: All data and code are available at https://zenodo.org/record/7504131#.Y7Wu3i-B2x8. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Interpretation of newly acquired mass spectrometry data can be improved by identifying, from an online repository, previous mass spectrometry runs that resemble the new data. However, this retrieval task requires computing the similarity between an arbitrary pair of mass spectrometry runs. This is particularly challenging for runs acquired using different experimental protocols. RESULTS: We propose a method, MS1Connect, that calculates the similarity between a pair of runs by examining only the intact peptide (MS1) scans, and we show evidence that the MS1Connect score is accurate. Specifically, we show that MS1Connect outperforms several baseline methods on the task of predicting the species from which a given proteomics sample originated. In addition, we show that MS1Connect scores are highly correlated with similarities computed from fragment (MS2) scans, even though these data are not used by MS1Connect. AVAILABILITY AND IMPLEMENTATION: The MS1Connect software is available at https://github.com/bmx8177/MS1Connect. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Gene-disease associations are fundamental for understanding disease etiology and developing effective interventions and treatments. Identifying genes not yet associated with a disease due to a lack of studies is a challenging task in which prioritization based on prior knowledge is an important element. The computational search for new candidate disease genes may be eased by positive-unlabeled learning, the machine learning setting in which only a subset of instances are labeled as positive while the rest of the data set is unlabeled. In this work, we propose a set of effective network-based features to be used in a novel Markov diffusion-based multi-class labeling strategy for putative disease gene discovery. RESULTS: The performances of the new labeling algorithm and the effectiveness of the proposed features have been tested on ten different disease data sets using three machine learning algorithms. The new features have been compared against classical topological and functional/ontological features and a set of network- and biological-derived features already used in gene discovery tasks. The predictive power of the integrated methodology in searching for new disease genes has been found to be competitive against state-of-the-art algorithms. AVAILABILITY AND IMPLEMENTATION: The source code of NIAPU can be accessed at https://github.com/AndMastro/NIAPU. The source data used in this study are available online on the respective websites. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The author argues that the field of Literature-Based Discovery (LBD) is built on sand, due to a lack of appropriate evaluation method. The field is considered mature and a healthy number of papers are published every year. Although the evaluation issue is known for twenty years, so far it did not cause any impetus to solve or alleviate it. It does not stop novel contributions to be accepted in reputable journals, despite their often poor evaluation methodology. In fact, the evaluation issue seems to have been admitted as an idiosyncrasy of the field, something the LBD community has learned to live with. After briefly presenting the issue, the author advocates for the LBD community to seriously address it: not only by making it a scientific priority, but also by designing an editorial policy in journals such as Bioinformatics to counter the systemic biases which hinder progress on this issue.

MOTIVATION: Plasma ionization is rapidly gaining popularity for MS based studies of volatiles and aerosols. However, data from plasma ionization is delicate to interpret as competing ionization pathways in the plasma create numerous ion species. There is no tool for detection of adducts and in-source fragments from plasma ionization data yet, which makes data evaluation ambiguous. SUMMARY: We developed DBDIpy, a Python library for processing and formal analysis of untargeted, time-sensitive plasma ionization MS datasets. Its core functionality lies in the identification of in-source fragments and identification of rivaling ionization pathways of the same analytes in time-sensitive datasets. It further contains elementary functions for processing of untargeted metabolomics data and interfaces to an established ecosystem for analysis of MS data in Python. AVAILABILITY AND IMPLEMENTATION: DBDIpy is implemented in Python (Version ≥ 3.7) and can be downloaded from PyPI the Python package repository (https://pypi.org/project/DBDIpy) or from GitHub (https://github.com/leopold-weidner/DBDIpy).

MOTIVATION: Mammalian cells can be transcriptionally reprogramed to other cellular phenotypes. Controllability of such complex transitions in transcriptional networks underlying cellular phenotypes is an inherent biological characteristic. This network controllability can be interpreted by operating a few key regulators to guide the transcriptional program from one state to another. Finding the key regulators in the transcriptional program can provide key insights into the network state transition underlying cellular phenotypes. RESULTS: To address this challenge, here, we proposed to identify the key regulators in the transcriptional co-expression network as a minimum dominating set (MDS) of driver nodes that can fully control the network state transition. Based on the theory of structural controllability, we developed a weighted MDS network model (WMDS.net) to find the driver nodes of differential gene co-expression networks. The weight of WMDS.net integrates the degree of nodes in the network and the significance of gene co-expression difference between two physiological states into the measurement of node controllability of the transcriptional network. To confirm its validity, we applied WMDS.net to the discovery of cancer driver genes in RNA-seq datasets from The Cancer Genome Atlas. WMDS.net is powerful among various cancer datasets and outperformed the other top-tier tools with a better balance between precision and recall. AVAILABILITY AND IMPLEMENTATION: https://github.com/chaofen123/WMDS.net. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell RNA sequencing (scRNA-seq) is an increasingly popular technique for transcriptomic analysis of gene expression at the single-cell level. Cell-type clustering is the first crucial task in the analysis of scRNA-seq data that facilitates accurate identification of cell types and the study of the characteristics of their transcripts. Recently, several computational models based on a deep autoencoder and the ensemble clustering have been developed to analyze scRNA-seq data. However, current deep autoencoders are not sufficient to learn the latent representations of scRNA-seq data, and obtaining consensus partitions from these feature representations remains under-explored. RESULTS: To address this challenge, we propose a single-cell deep clustering model via a dual denoising autoencoder with bipartite graph ensemble clustering called scBGEDA, to identify specific cell populations in single-cell transcriptome profiles. First, a single-cell dual denoising autoencoder network is proposed to project the data into a compressed low-dimensional space and that can learn feature representation via explicit modeling of synergistic optimization of the zero-inflated negative binomial reconstruction loss and denoising reconstruction loss. Then, a bipartite graph ensemble clustering algorithm is designed to exploit the relationships between cells and the learned latent embedded space by means of a graph-based consensus function. Multiple comparison experiments were conducted on 20 scRNA-seq datasets from different sequencing platforms using a variety of clustering metrics. The experimental results indicated that scBGEDA outperforms other state-of-the-art methods on these datasets, and also demonstrated its scalability to large-scale scRNA-seq datasets. Moreover, scBGEDA was able to identify cell-type specific marker genes and provide functional genomic analysis by quantifying the influence of genes on cell clusters, bringing new insights into identifying cell types and characterizing the scRNA-seq data from different perspectives. AVAILABILITY AND IMPLEMENTATION: The source code of scBGEDA is available at https://github.com/wangyh082/scBGEDA. The software and the supporting data can be downloaded from https://figshare.com/articles/software/scBGEDA/19657911. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.