MOTIVATION: Single-cell RNA sequencing allows us to study cell heterogeneity at an unprecedented cell-level resolution and identify known and new cell populations. Current cell labeling pipeline uses unsupervised clustering and assigns labels to clusters by manual inspection. However, this pipeline does not utilize available gold-standard labels because there are usually too few of them to be useful to most computational methods. This article aims to facilitate cell labeling with a semi-supervised method in an alternative pipeline, in which a few gold-standard labels are first identified and then extended to the rest of the cells computationally. RESULTS: We built a semi-supervised dimensionality reduction method, a network-enhanced autoencoder (netAE). Tested on three public datasets, netAE outperforms various dimensionality reduction baselines and achieves satisfactory classification accuracy even when the labeled set is very small, without disrupting the similarity structure of the original space. AVAILABILITY AND IMPLEMENTATION: The code of netAE is available on GitHub: https://github.com/LeoZDong/netAE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Many software libraries for using Hidden Markov Models in bioinformatics focus on inference tasks, such as likelihood calculation, parameter-fitting and alignment. However, construction of the state machines can be a laborious task, automation of which would be time-saving and less error-prone. RESULTS: We present Machine Boss, a software tool implementing not just inference and parameter-fitting algorithms, but also a set of operations for manipulating and combining automata. The aim is to make prototyping of bioinformatics HMMs as quick and easy as the construction of regular expressions, with one-line 'recipes' for many common applications. We report data from several illustrative examples involving protein-to-DNA alignment, DNA data storage and nanopore sequence analysis. AVAILABILITY AND IMPLEMENTATION: Machine Boss is released under the BSD-3 open source license and is available from http://machineboss.org/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Correlating genetic loci with a disease phenotype is a common approach to improve our understanding of the genetics underlying complex diseases. Standard analyses mostly ignore two aspects, namely genetic heterogeneity and interactions between loci. Genetic heterogeneity, the phenomenon that genetic variants at different loci lead to the same phenotype, promises to increase statistical power by aggregating low-signal variants. Incorporating interactions between loci results in a computational and statistical bottleneck due to the vast amount of candidate interactions. RESULTS: We propose a novel method SiNIMin that addresses these two aspects by finding pairs of interacting genes that are, upon combination, associated with a phenotype of interest under a model of genetic heterogeneity. We guide the interaction search using biological prior knowledge in the form of protein-protein interaction networks. Our method controls type I error and outperforms state-of-the-art methods with respect to statistical power. Additionally, we find novel associations for multiple Arabidopsis thaliana phenotypes, and, with an adapted variant of SiNIMin, for a study of rare variants in migraine patients. AVAILABILITY AND IMPLEMENTATION: Code available at https://github.com/BorgwardtLab/SiNIMin. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Early cancer detection is significant for the patient mortality rate reduction. Although machine learning has been widely employed in that context, there are still deficiencies. In this work, we studied different machine learning algorithms for early cancer detection and proposed an Adaptive Support Vector Machine (ASVM) method by synergizing Shuffled Frog Leaping Algorithm (SFLA) and Support Vector Machine (SVM) in this paper. RESULTS: As ASVM regulates SVM for parameter adaption based on data characteristics, the experimental results demonstrated the robust generalization capability of ASVM on different datasets under different settings; for instance, ASVM can enhance the sensitivity by over 10% for early cancer detection compared with SVM. Besides, our proposed ASVM outperformed Grid Search + SVM and Random Search + SVM by significant margins in terms of the area under the ROC curve (AUC) (0.938 vs. 0.922 vs. 0.921). AVAILABILITY: The proposed algorithm and dataset are available at https://github.com/ElaineLIU-920/ASVM-for-Early-Cancer-Detection. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Curation is essential for any data platform to maintain the quality of the data it provides. Today, more effective curation tools are often vital to keep up with the rapid growth of existing, maintenance-requiring databases and the amount of newly published information that needs to be surveyed. However, curation interfaces are often complex and challenging to be further developed. Therefore, opportunities for experimentation with curation workflows may be lost due to a lack of development resources or a reluctance to change sensitive production systems. RESULTS: We propose a decoupled, modular and scriptable architecture to build new curation tools on top of existing platforms. Our architecture treats the existing platform as a black box. It therefore only relies on its public application programming interfaces (APIs) and web application instead of requiring any changes to the existing infrastructure. As a case study, we have implemented this architecture in cmd-iaso, a curation tool for the identifiers.org registry. With cmd-iaso, we also show that the proposed design's flexibility can be utilised to streamline and enhance the curator's workflow with the platform's existing web interface. AVAILABILITY: The cmd-iaso curation tool is implemented in Python 3.7+ and supports Linux, macOS and Windows. Its source code and documentation are freely available from https://github.com/identifiers-org/cmd-iaso. It is also published as a Docker container at https://hub.docker.com/r/identifiersorg/cmd-iaso. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome Architecture Mapping (GAM) was recently introduced as a digestion- and ligation-free method to detect chromatin conformation. Orthogonal to existing approaches based on chromatin conformation capture (3C), GAM's ability to capture both inter- and intra-chromosomal contacts from low amounts of input data makes it particularly well suited for allele-specific analyses in a clinical setting. Allele-specific analyses are powerful tools to investigate the effects of genetic variants on many cellular phenotypes including chromatin conformation, but require the haplotypes of the individuals under study to be known a-priori. So far however, no algorithm exists for haplotype reconstruction and phasing of genetic variants from GAM data, hindering the allele-specific analysis of chromatin contact points in non-model organisms or individuals with unknown haplotypes. RESULTS: We present GAMIBHEAR, a tool for accurate haplotype reconstruction from GAM data. GAMIBHEAR aggregates allelic co-observation frequencies from GAM data and employs a GAM-specific probabilistic model of haplotype capture to optimise phasing accuracy. Using a hybrid mouse embryonic stem cell line with known haplotype structure as a benchmark dataset, we assess correctness and completeness of the reconstructed haplotypes, and demonstrate the power of GAMIBHEAR to infer accurate genome-wide haplotypes from GAM data. AVAILABILITY: GAMIBHEAR is available as an R package under the open source GPL-2 license at https://bitbucket.org/schwarzlab/gamibhear. MAINTAINER: julia.markowski@mdc-berlin.de. SUPPLEMENTARY INFORMATION: Supplementary information is available at Bioinformatics online.

MOTIVATION: Identifying rare subpopulations of cells is a critical step in order to extract knowledge from single-cell expression data, especially when the available data is limited and rare subpopulations only contain a few cells. In this paper, we present a data mining method to identify small subpopulations of cells that present highly specific expression profiles. This objective is formalized as a constrained optimization problem that jointly identifies a small group of cells and a corresponding subset of specific genes. The proposed method extends the max-sum submatrix problem to yield genes that are, for instance, highly expressed inside a small number of cells, but have a low expression in the remaining ones. RESULTS: We show through controlled experiments on scRNA-seq data that the MicroCellClust method achieves a high F1 score to identify rare sub-populations of artificially planted human T cells. The effectiveness of MicroCellClust is confirmed as it reveals a subpopulation of CD4 T cells with a specific phenotype from breast cancer samples, and a subpopulation linked to a specific stage in the cell cycle from breast cancer samples as well. Finally, 3 rare subpopulations in mouse embryonic stem cells are also identified with MicroCellClust. These results illustrate the proposed method outperforms typical alternatives at identifying small subsets of cells with highly specific expression profiles. AVAILABILITY: The R and Scala implementation of MicroCellClust is freely available on GitHub, at https://github.com/agerniers/MicroCellClust/ The data underlying this article are available on Zenodo, at https://dx.doi.org/10.5281/zenodo.4580332. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Reliability assessment of automated pre-processing of liquid chromatography-high resolution mass spectrometry data presents a significant challenge. Here we present a tool named mzRAPP, which generates and validates a benchmark from user-supplied information and later utilises it for reliability assessment of data pre-processing. As a result, mzRAPP produces several performance metrics for different steps of the pre-processing workflow, supporting 5 of the most commonly used pre-processing tools. AVAILABILITY: mzRAPP is implemented in R and can be downloaded from GitHub under GNU GPL v.3.0 licence. Extensive documentation, background, and examples are available at (https://github.com/YasinEl/mzRAPP).

MOTIVATION: Routine infectious disease surveillance is increasingly based on large-scale whole genome sequencing databases. Real-time surveillance would benefit from immediate assignments of each genome assembly to hierarchical population structures. Here we present pHierCC, a pipeline that defines a scalable clustering scheme, HierCC, based on core genome multi-locus typing that allows incremental, static, multi-level cluster assignments of genomes. We also present HCCeval, which identifies optimal thresholds for assigning genomes to cohesive HierCC clusters. HierCC was implemented in EnteroBase in 2018, and has since genotyped >530,000 genomes from Salmonella, Escherichia/Shigella, Streptococcus, Clostridioides, Vibrio and Yersinia. AVAILABILITY: Implementation: https://enterobase.warwick.ac.uk/ and Source codes and instructions: https://github.com/zheminzhou/pHierCC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Exploring the relationship between human proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment of diseases. The human phenotype ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human diseases. However, the current HPO annotations of proteins are not complete. Thus, it is important to identify missing protein-phenotype associations. RESULTS: We propose HPOFiller, a graph convolutional network (GCN)-based approach, for predicting missing HPO annotations. HPOFiller has two key GCN components for capturing embeddings from complex network structures: 1) S-GCN for both protein-protein interaction (PPI) network and HPO semantic similarity network to utilize network weights; 2) Bi-GCN for the protein-phenotype bipartite graph to conduct message passing between proteins and phenotypes. The core idea of HPOFiller is to repeat run these two GCN modules consecutively over the three networks, to refine the embeddings. Empirical results of extremely stringent evaluation avoiding potential information leakage including cross-validation and temporal validation demonstrates that HPOFiller significantly outperforms all other state-of-the-art methods. In particular, the ablation study shows that batch normalization contributes the most to the performance. The further examination offers literature evidence for highly ranked predictions. Finally using known disease-HPO term associations, HPOFiller could suggest promising, unknown disease-gene associations, presenting possible genetic causes of human disorders. AVAILABILITY: https://github.com/liulizhi1996/HPOFiller. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The Gamma-Poisson distribution is a theoretically and empirically motivated model for the sampling variability of single cell RNA-sequencing counts and an essential building block for analysis approaches including differential expression analysis, principal component analysis and factor analysis. Existing implementations for inferring its parameters from data often struggle with the size of single cell datasets, which can comprise millions of cells; at the same time, they do not take full advantage of the fact that zero and other small numbers are frequent in the data. These limitations have hampered uptake of the model, leaving room for statistically inferior approaches such as logarithm(-like) transformation. RESULTS: We present a new R package for fitting the Gamma-Poisson distribution to data with the characteristics of modern single cell datasets more quickly and more accurately than existing methods. The software can work with data on disk without having to load them into RAM simultaneously. AVAILABILITYAND IMPLEMENTATION: The package glmGamPoi is available from Bioconductor for Windows, macOS and Linux, and source code is available on github.com/const-ae/glmGamPoi under a GPL-3 license. The scripts to reproduce the results of this paper are available on github.com/const-ae/glmGamPoi-Paper. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genetic linkage analysis has made a huge contribution to the genetic mapping of Mendelian diseases. However, most previously available linkage analysis methods have limited applicability. Since parametric linkage analysis requires predefined model of inheritance with a fixed set of parameters, it is inapplicable without fully structured pedigree information. Furthermore, the analytical results are dependent on the specification of model parameters. While non-parametric linkage analysis can avoid these problems, the runs of homozygosity (ROH) mapping, a widely used non-parametric linkage analysis method, can only deal with recessive inheritance. The implementation of non-parametric linkage analyses capable of dealing with both dominant and recessive inheritance has been required. RESULTS: We have developed the Obelisc (Observational linkage scan), a flexibly applicable user-friendly non-parametric linkage analysis tool, which also provides an intuitive visualization of the analytical results. Obelisc is based on the SNP streak approach, which does not require any predefined inheritance model with parameters. In contrast to the ROH mapping, the SNP streak approach is applicable to both dominant and recessive traits. To illustrate the performance of Obelisc, we generated a pseudo-pedigree from the publicly available BioBank Japan Project genome-wide genotype dataset (n > 180 000). By applying Obelisc to this pseudo-pedigree, we successfully identified the regions with inherited identical-by-descent haplotypes shared among the members of the pseudo-pedigree, which was validated by the population-based haplotype phasing approach. AVAILABILITY AND IMPLEMENTATION: Obelisc is feely available at https://github.com/qsonehara/Obelisc as a python package with example datasets. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A large variety of molecular interactions occurs between biomolecular components in cells. When a molecular interaction results in a regulatory effect, exerted by one component onto a downstream component, a so-called 'causal interaction' takes place. Causal interactions constitute the building blocks in our understanding of larger regulatory networks in cells. These causal interactions and the biological processes they enable (e.g. gene regulation) need to be described with a careful appreciation of the underlying molecular reactions. A proper description of this information enables archiving, sharing and reuse by humans and for automated computational processing. Various representations of causal relationships between biological components are currently used in a variety of resources. RESULTS: Here, we propose a checklist that accommodates current representations, called the Minimum Information about a Molecular Interaction CAusal STatement (MI2CAST). This checklist defines both the required core information, as well as a comprehensive set of other contextual details valuable to the end user and relevant for reusing and reproducing causal molecular interaction information. The MI2CAST checklist can be used as reporting guidelines when annotating and curating causal statements, while fostering uniformity and interoperability of the data across resources. AVAILABILITY AND IMPLEMENTATION: The checklist together with examples is accessible at https://github.com/MI2CAST/MI2CAST. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: ProDy, an integrated API developed for modelling and analysing protein dynamics, has significantly evolved in recent years in response to the growing data and needs of computational biology community. We present major developments that led to ProDy 2.0: (i) improved interfacing with databases and parsing new file formats, (ii) SignDy for signature dynamics of protein families, (iii) CryoDy for collective dynamics of supramolecular systems using cryo-EM density maps, and (v) essential site scanning analysis (ESSA) for identifying sites essential to modulating global dynamics. AVAILABILITY AND IMPLEMENTATION: ProDy is open-source and freely available under MIT License from https://github.com/prody/ProDy. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online, and tutorials at http://prody.csb.pitt.edu/.

MOTIVATION: The Severe Acute Respiratory Syndrome-Coronavirus 2 (SARS-CoV-2) has recently emerged as the responsible for the pandemic outbreak of the coronavirus disease 2019. This virus is closely related to coronaviruses infecting bats and Malayan pangolins, species suspected to be an intermediate host in the passage to humans. Several genomic mutations affecting viral proteins have been identified, contributing to the understanding of the recent animal-to-human transmission. However, the capacity of SARS-CoV-2 to encode functional putative microRNAs (miRNAs) remains largely unexplored. RESULTS: We have used deep learning to discover 12 candidate stem-loop structures hidden in the viral protein-coding genome. Among the precursors, the expression of eight mature miRNAs-like sequences was confirmed in small RNA-seq data from SARS-CoV-2 infected human cells. Predicted miRNAs are likely to target a subset of human genes of which 109 are transcriptionally deregulated upon infection. Remarkably, 28 of those genes potentially targeted by SARS-CoV-2 miRNAs are down-regulated in infected human cells. Interestingly, most of them have been related to respiratory diseases and viral infection, including several afflictions previously associated with SARS-CoV-1 and SARS-CoV-2. The comparison of SARS-CoV-2 pre-miRNA sequences with those from bat and pangolin coronaviruses suggests that single nucleotide mutations could have helped its progenitors jumping inter-species boundaries, allowing the gain of novel mature miRNAs targeting human mRNAs. Our results suggest that the recent acquisition of novel miRNAs-like sequences in the SARS-CoV-2 genome may have contributed to modulate the transcriptional reprograming of the new host upon infection. AVAILABILITY AND IMPLEMENTATION: https://github.com/sinc-lab/sarscov2-mirna-discovery. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Predicting early in treatment whether a tumor is likely to respond to treatment is one of the most difficult yet important tasks in providing personalized cancer care. Most oropharyngeal squamous cell carcinoma (OPSCC) patients receive standard cancer therapy. However, the treatment outcomes vary significantly and are difficult to predict. Multiple studies indicate that microRNAs (miRNAs) are promising cancer biomarkers for the prognosis of oropharyngeal cancer. The reliable and efficient use of miRNAs for patient stratification and treatment outcome prognosis is still a very challenging task, mainly due to the relatively high dimensionality of miRNAs compared to the small number of observation sets; the redundancy, irrelevancy and uncertainty in the large amount of miRNAs; and the imbalanced observation patient samples. RESULTS: In this study, a new machine learning-based prognosis model was proposed to stratify subsets of OPSCC patients with low and high risks for treatment failure. The model cascaded a two-stage prognostic biomarker selection method and an evidential K-nearest neighbors (EK-NN) classifier to address the challenges and improve the accuracy of patient stratification. The model has been evaluated on miRNA expression profiling of 150 oropharyngeal tumors by use of overall survival and disease-specific survival as the end points of disease treatment outcomes, respectively. The proposed method showed superior performance compared to other advanced machine-learning methods in terms of common performance quantification metrics. The proposed prognosis model can be employed as a supporting tool to identify patients who are likely to fail standard therapy and potentially benefit from alternative targeted treatments.

MOTIVATION: Marker genes, defined as genes that are expressed primarily in a single cell type, can be identified from the single cell transcriptome; however, such data are not always available for the many uses of marker genes, such as deconvolution of bulk tissue. Marker genes for a cell type, however, are highly correlated in bulk data, because their expression levels depend primarily on the proportion of that cell type in the samples. Therefore, when many tissue samples are analyzed, it is possible to identify these marker genes from the correlation pattern. RESULTS: To capitalize on this pattern, we develop a new algorithm to detect marker genes by combining published information about likely marker genes with bulk transcriptome data in the form of a semi-supervised algorithm. The algorithm then exploits the correlation structure of the bulk data to refine the published marker genes by adding or removing genes from the list. AVAILABILITY AND IMPLEMENTATION: We implement this method as an R package markerpen, hosted on CRAN (https://CRAN.R-project.org/package=markerpen). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Biclustering is a generalization of clustering used to identify simultaneous grouping patterns in observations (rows) and features (columns) of a data matrix. Recently, the biclustering task has been formulated as a convex optimization problem. While this convex recasting of the problem has attractive properties, existing algorithms do not scale well. To address this problem and make convex biclustering a practical tool for analyzing larger data, we propose an implementation of fast convex biclustering called COBRAC to reduce the computing time by iteratively compressing problem size along the solution path. We apply COBRAC to several gene expression datasets to demonstrate its effectiveness and efficiency. Besides the standalone version for COBRAC, we also developed a related online web server for online calculation and visualization of the downloadable interactive results. AVAILABILITY: The source code and test data are available at https://github.com/haidyi/cvxbiclustr or https://zenodo.org/record/4620218. The web server is available at https://cvxbiclustr.ericchi.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In DNA storage systems, there are tradeoffs between writing and reading costs. Increasing the code rate of error-correcting codes may save writing cost, but it will need more sequence reads for data retrieval. There is potentially a way to improve sequencing and decoding processes in such a way that the reading cost induced by this tradeoff is reduced without increasing the writing cost. In past researches, clustering, alignment, and decoding processes were considered as separate stages but we believe that using the information from all these processes together may improve decoding performance. Actual experiments of DNA synthesis and sequencing should be performed because simulations cannot be relied on to cover all error possibilities in practical circumstances. RESULTS: For DNA storage systems using fountain code and Reed-Solomon (RS) code, we introduce several techniques to improve the decoding performance. We designed the decoding process focusing on the cooperation of key components: Hamming-distance based clustering, discarding of abnormal sequence reads, RS error correction as well as detection, and quality score-based ordering of sequences. We synthesized 513.6KB data into DNA oligo pools and sequenced this data successfully with Illumina MiSeq instrument. Compared to Erlich's research, the proposed decoding method additionally incorporates sequence reads with minor errors which had been discarded before, and thuswas able to make use of 10.6-11.9% more sequence reads from the same sequencing environment, this resulted in 6.5-8.9% reduction in the reading cost. Channel characteristics including sequence coverage and read-length distributions are provided as well. AVAILABILITY: The raw data files and the source codes of our experiments are available at: https://github.com/jhjeong0702/dna-storage.

SUMMARY: The heterogeneous cell types of the tumor-immune microenvironment (TIME) play key roles in determining cancer progression, metastasis, and response to treatment. We report the development of TIMEx, a novel tumor-immune microenvironment deconvolution method emphasizing on estimating infiltrating immune cells for bulk transcriptomics using pan-cancer single-cell RNA-seq signatures. We also implemented a comprehensive, user-friendly web-portal for users to evaluate TIMEx and other deconvolution methods with bulk transcriptomic profiles. AVAILABILITY: TIMEx web portal is freely accessible at http://timex.moffitt.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The crucial role of protein interactions and the difficulty in characterising them experimentally strongly motivates the development of computational approaches for structural prediction. Even when protein-protein docking samples correct models, current scoring functions struggle to discriminate them from incorrect decoys. The previous incorporation of conservation and coevolution information has shown promise for improving protein-protein scoring. Here, we present a novel strategy to integrate atomic-level evolutionary information into different types of scoring functions to improve their docking discrimination. RESULTS: : We applied this general strategy to our residue-level statistical potential from InterEvScore and to two atomic-level scores, SOAP-PP and Rosetta interface score (ISC). Including evolutionary information from as few as ten homologous sequences improves the top 10 success rates of individual atomic-level scores SOAP-PP and Rosetta ISC by respectively 6 and 13.5 percentage points, on a large benchmark of 752 docking cases. The best individual homology-enriched score reaches a top 10 success rate of 34.4%. A consensus approach based on the complementarity between different homology-enriched scores further increases the top 10 success rate to 40%. AVAILABILITY: All data used for benchmarking and scoring results, as well as a Singularity container of the pipeline, are available at http://biodev.cea.fr/interevol/interevdata/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Duplication and recombination of protein fragments have led to the highly diverse protein space that we observe today. By mimicking this natural process, the design of protein chimeras via fragment recombination has proven experimentally successful and has opened a new era for the design of customizable proteins. The in-silico building of structural models for these chimeric proteins, however, remains a manual task that requires a considerable degree of expertise and is not amenable for high-throughput studies. Energetic and structural analysis of the designed proteins often require the use of several tools, each with their unique technical difficulties and available in different programming languages or web servers. RESULTS: We implemented a Python package that enables automated, high-throughput design of chimeras and their structural analysis. First, it fetches evolutionarily conserved fragments from a built-in database (also available at fuzzle.uni-bayreuth.de). These relationships can then be represented via networks or further selected for chimera construction via recombination. Designed chimeras or natural proteins are then scored and minimised with the Charmm and Amber forcefields and their diverse structural features can be analysed at ease. Here, we showcase Protlego's pipeline by exploring the relationships between the P-loop and Rossmann superfolds, building and characterising their offspring chimeras. We believe that Protlego provides a powerful new tool for the protein design community. AVAILABILITY AND IMPLEMENTATION: Protlego runs on the Linux platform and is freely available at (https://hoecker-lab.github.io/protlego/) with tutorials and documentation and runs on Linux OS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Typical RNA sequencing (RNA-Seq) analyses are performed either at the gene level by summing all reads from the same locus, assuming that all transcripts from a gene make a protein or at the transcript level, assuming that each transcript displays unique function. However, these assumptions are flawed, as a gene can code for different types of transcripts and different transcripts are capable of synthesizing similar, different or no protein. As a consequence, functional changes are not well illustrated by either gene or transcript analyses. We propose to improve RNA-Seq analyses by grouping the transcripts based on their similar functions. We developed FuSe to predict functional similarities using the primary and secondary structure of proteins. To estimate the likelihood of proteins with similar functions, FuSe computes two confidence scores: knowledge (KS) and discovery (DS) for protein pairs. Overlapping protein pairs exhibiting high confidence are grouped to form 'similar function protein groups' and expression is calculated for each functional group. The impact of using FuSe is demonstrated on in vitro cells exposed to paracetamol, which highlight genes responsible for cell adhesion and glycogen regulation which were earlier shown to be not differentially expressed with traditional analysis methods. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/rajinder4489/FuSe. Data for APAP exposure are available in the BioStudies database (http://www.ebi.ac.uk/biostudies) under accession numbers S-HECA143, S-HECA(158) and S-HECA139. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Proteins are ubiquitous molecules whose function in biological processes is determined by their 3D structure. Experimental identification of a protein's structure can be time-consuming, prohibitively expensive and not always possible. Alternatively, protein folding can be modeled using computational methods, which however are not guaranteed to always produce optimal results. GraphQA is a graph-based method to estimate the quality of protein models, that possesses favorable properties such as representation learning, explicit modeling of both sequential and 3D structure, geometric invariance and computational efficiency. RESULTS: GraphQA performs similarly to state-of-the-art methods despite using a relatively low number of input features. In addition, the graph network structure provides an improvement over the architecture used in ProQ4 operating on the same input features. Finally, the individual contributions of GraphQA components are carefully evaluated. AVAILABILITY AND IMPLEMENTATION: PyTorch implementation, datasets, experiments and link to an evaluation server are available through this GitHub repository: github.com/baldassarreFe/graphqa. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Zoonosis, the natural transmission of infections from animals to humans, is a far-reaching global problem. The recent outbreaks of Zikavirus, Ebolavirus and Coronavirus are examples of viral zoonosis, which occur more frequently due to globalization. In case of a virus outbreak, it is helpful to know which host organism was the original carrier of the virus to prevent further spreading of viral infection. Recent approaches aim to predict a viral host based on the viral genome, often in combination with the potential host genome and arbitrarily selected features. These methods are limited in the number of different hosts they can predict or the accuracy of the prediction. RESULTS: Here, we present a fast and accurate deep learning approach for viral host prediction, which is based on the viral genome sequence only. We tested our deep neural network (DNN) on three different virus species (influenza A virus, rabies lyssavirus and rotavirus A). We achieved for each virus species an AUC between 0.93 and 0.98, allowing highly accurate predictions while using only fractions (100-400 bp) of the viral genome sequences. We show that deep neural networks are suitable to predict the host of a virus, even with a limited amount of sequences and highly unbalanced available data. The trained DNNs are the core of our virus-host prediction tool VIrus Deep learning HOst Prediction (VIDHOP). VIDHOP also allows the user to train and use models for other viruses. AVAILABILITY AND IMPLEMENTATION: VIDHOP is freely available under https://github.com/flomock/vidhop. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Networks are used to relate topological structure to system dynamics and function, particularly in ecology systems biology. Network analysis is often guided or complemented by data-driven visualization. Hive one of many network visualizations, distinguish themselves as providing a general, consistent and coherent rule-based representation to motivate hypothesis development and testing. RESULTS: Here, we present HyPE, Hive Panel Explorer, a software application that creates a panel of interactive hive plots. HyPE enables network exploration based on user-driven layout rules and parameter combinations for simultaneous of multiple network views. We demonstrate HyPE's features by exploring a microbial co-occurrence network constructed from forest soil microbiomes. AVAILABILITY AND IMPLEMENTATION: HyPE is available under the GNU license: https://github.com/hallamlab/HivePanelExplorer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Rtpca is an R package implementing methods for inferring protein-protein interactions (PPIs) based on thermal proteome profiling experiments of a single condition or in a differential setting via an approach called thermal proximity coaggregation. It offers user-friendly tools to explore datasets for their PPI predictive performance and easily integrates with available R packages. AVAILABILITY AND IMPLEMENTATION: Rtpca is available from Bioconductor (https://bioconductor.org/packages/Rtpca). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: RNA-sequencing (RNA-Seq) is the current method of choice for studying bacterial transcriptomes. To date, many computational pipelines have been developed to predict differentially expressed genes from RNA-Seq data, but no gold-standard has been widely accepted. We present the Snakemake-based tool Smart Consensus Of RNA Expression (SCORE) which uses a consensus approach founded on a selection of well-established tools for differential gene expression analysis. This allows SCORE to increase the overall prediction accuracy and to merge varying results into a single, human-readable output. SCORE performs all steps for the analysis of bacterial RNA-Seq data, from read preprocessing to the overrepresentation analysis of significantly associated ontologies. Development of consensus approaches like SCORE will help to streamline future RNA-Seq workflows and will fundamentally contribute to the creation of new gold-standards for the analysis of these types of data. AVAILABILITY AND IMPLEMENTATION: https://github.com/SiWolf/SCORE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Analysis of biological data often involves the simultaneous testing of thousands of genes. This requires two key steps: the ranking of genes and the selection of important genes based on a significance threshold. One such testing procedure, called the optimal discovery procedure (ODP), leverages information across different tests to provide an optimal ranking of genes. This approach can lead to substantial improvements in statistical power compared to other methods. However, current applications of the ODP have only been established for simple study designs using microarray technology. Here, we extend this work to the analysis of complex study designs and RNA-sequencing studies. RESULTS: We apply our extended framework to a static RNA-sequencing study, a longitudinal study, an independent sampling time-series study,and an independent sampling dose-response study. Our method shows improved performance compared to other testing procedures, finding more differentially expressed genes and increasing power for enrichment analysis. Thus, the extended ODP enables a favorable significance analysis of genome-wide gene expression studies. AVAILABILITY AND IMPLEMENTATION: The algorithm is implemented in our freely available R package called edge and can be downloaded at https://www.bioconductor.org/packages/release/bioc/html/edge.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Natural Language Processing techniques are constantly being advanced to accommodate the influx of data as well as to provide exhaustive and structured knowledge dissemination. Within the biomedical domain, relation detection between bio-entities known as the Bio-Entity Relation Extraction (BRE) task has a critical function in knowledge structuring. Although recent advances in deep learning-based biomedical domain embedding have improved BRE predictive analytics, these works are often task selective or use external knowledge-based pre-/post-processing. In addition, deep learning-based models do not account for local syntactic contexts, which have improved data representation in many kernel classifier-based models. In this study, we propose a universal BRE model, i.e. LBERT, which is a Lexically aware Transformer-based Bidirectional Encoder Representation model, and which explores both local and global contexts representations for sentence-level classification tasks. RESULTS: This article presents one of the most exhaustive BRE studies ever conducted over five different bio-entity relation types. Our model outperforms state-of-the-art deep learning models in protein-protein interaction (PPI), drug-drug interaction and protein-bio-entity relation classification tasks by 0.02%, 11.2% and 41.4%, respectively. LBERT representations show a statistically significant improvement over BioBERT in detecting true bio-entity relation for large corpora like PPI. Our ablation studies clearly indicate the contribution of the lexical features and distance-adjusted attention in improving prediction performance by learning additional local semantic context along with bi-directionally learned global context. AVAILABILITY AND IMPLEMENTATION: Github. https://github.com/warikoone/LBERT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Copy number variation plays important roles in human complex diseases. The detection of copy number variants (CNVs) is identifying mean shift in genetic intensities to locate chromosomal breakpoints, the step of which is referred to as chromosomal segmentation. Many segmentation algorithms have been developed with a strong assumption of independent observations in the genetic loci, and they assume each locus has an equal chance to be a breakpoint (i.e. boundary of CNVs). However, this assumption is violated in the genetics perspective due to the existence of correlation among genomic positions, such as linkage disequilibrium (LD). Our study showed that the LD structure is related to the location distribution of CNVs, which indeed presents a non-random pattern on the genome. To generate more accurate CNVs, we proposed a novel algorithm, LDcnv, that models the CNV data with its biological characteristics relating to genetic dependence structure (i.e. LD). RESULTS: We theoretically demonstrated the correlation structure of CNV data in SNP array, which further supports the necessity of integrating biological structure in statistical methods for CNV detection. Therefore, we developed the LDcnv that integrated the genomic correlation structure with a local search strategy into statistical modeling of the CNV intensities. To evaluate the performance of LDcnv, we conducted extensive simulations and analyzed large-scale HapMap datasets. We showed that LDcnv presented high accuracy, stability and robustness in CNV detection and higher precision in detecting short CNVs compared to existing methods. This new segmentation algorithm has a wide scope of potential application with data from various high-throughput technology platforms. AVAILABILITY AND IMPLEMENTATION: https://github.com/FeifeiXiaoUSC/LDcnv. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: With the advance of next-generation sequencing technologies and reductions in the costs of these techniques, bulked segregant analysis (BSA) has become not only a powerful tool for mapping quantitative trait loci but also a useful way to identify causal gene mutations underlying phenotypes of interest. However, due to the presence of background mutations and errors in sequencing, genotyping, and reference assembly, it is often difficult to distinguish true causal mutations from background mutations. In this study, we developed the BSAseq workflow, which includes an automated bioinformatics analysis pipeline with a probabilistic model for estimating the linked region (the region linked to the causal mutation) and an interactive Shiny web application for visualizing the results. We deeply sequenced a sorghum male-sterile parental line (ms8) to capture the majority of background mutations in our bulked F2 data. We applied the workflow to 11 bulked sorghum F2 populations and 1 rice F2 population and identified the true causal mutation in each population. The workflow is intuitive and straightforward, facilitating its adoption by users without bioinformatics analysis skills. We anticipate that the BSAseq workflow will be broadly applicable to the identification of causal mutations for many phenotypes of interest. AVAILABILITY AND IMPLEMENTATION: BSAseq is freely available on https://www.sciapps.org/page/bsa. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Generating publication ready plots to display multiple genomic tracks can pose a serious challenge. Making desirable and accurate figures requires considerable effort. This is usually done by hand or using a vector graphic software. RESULTS: pyGenomeTracks (PGT) is a modular plotting tool that easily combines multiple tracks. It enables a reproducible and standardized generation of highly customizable and publication ready images. AVAILABILITY AND IMPLEMENTATION: PGT is available through a graphical interface on https://usegalaxy.eu and through the command line. It is provided on conda via the bioconda channel, on pip and it is openly developed on github: https://github.com/deeptools/pyGenomeTracks. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: The searching of user-defined 3D queries in molecular interfaces is a computationally challenging problem that is not satisfactorily solved so far. Most of the few existing tools focused on that purpose are desktop based and not openly available. Besides that, they show a lack of query versatility, search efficiency and user-friendliness. We address this issue with GeoMine, a publicly available web application that provides textual, numerical and geometrical search functionality for protein-ligand binding sites derived from structural data contained in the Protein Data Bank (PDB). The query generation is supported by a 3D representation of a start structure that provides interactively selectable elements like atoms, bonds and interactions. GeoMine gives full control over geometric variability in the query while performing a deterministic, precise search. Reasonably selective queries are processed on the entire set of protein-ligand complexes in the PDB within a few minutes. GeoMine offers an interactive and iterative search process of successive result analyses and query adaptations. From the numerous potential applications, we picked two from the field of side-effect analyze showcasing the usefulness of GeoMine. AVAILABILITY AND IMPLEMENTATION: GeoMine is part of the ProteinsPlus web application suite and freely available at https://proteins.plus. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Fine-mapping human leukocyte antigen (HLA) genes involved in disease susceptibility to individual alleles or amino acid residues has been challenging. Using information regarding HLA alleles obtained from HLA typing, HLA imputation or HLA inference, our software expands the alleles to amino acid sequences using the most recent IMGT/HLA database and prepares a dataset suitable for fine-mapping analysis. Our software also provides useful functionalities, such as various association tests, visualization tools and nomenclature conversion. AVAILABILITY AND IMPLEMENTATION: https://github.com/WansonChoi/HATK.

SUMMARY: Dysfunctional regulations of gene expression programs relevant to fundamental cell processes can drive carcinogenesis. Therefore, systematically identifying dysregulation events is an effective path for understanding carcinogenesis and provides insightful clues to build predictive signatures with mechanistic interpretability for cancer precision medicine. Here, we implemented a machine learning-based gene dysregulation analysis framework in an R package, DysRegSig, which is capable of exploring gene dysregulations from high-dimensional data and building mechanistic signature based on gene dysregulations. DysRegSig can serve as an easy-to-use tool to facilitate gene dysregulation analysis and follow-up analysis. AVAILABILITY AND IMPLEMENTATION: The source code and user's guide of DysRegSig are freely available at Github: https://github.com/SCBIT-YYLab/DysRegSig. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In recent years, the well-known Infinite Sites Assumption has been a fundamental feature of computational methods devised for reconstructing tumor phylogenies and inferring cancer progressions. However, recent studies leveraging single-cell sequencing (SCS) techniques have shown evidence of the widespread recurrence and, especially, loss of mutations in several tumor samples. While there exist established computational methods that infer phylogenies with mutation losses, there remain some advancements to be made. RESULTS: We present Simulated Annealing Single-Cell inference (SASC): a new and robust approach based on simulated annealing for the inference of cancer progression from SCS datasets. In particular, we introduce an extension of the model of evolution where mutations are only accumulated, by allowing also a limited amount of mutation loss in the evolutionary history of the tumor: the Dollo-k model. We demonstrate that SASC achieves high levels of accuracy when tested on both simulated and real datasets and in comparison with some other available methods. AVAILABILITY AND IMPLEMENTATION: The SASC tool is open source and available at https://github.com/sciccolella/sasc. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: High-resolution microbial strain typing is essential for various clinical purposes, including disease outbreak investigation, tracking of microbial transmission events and epidemiological surveillance of bacterial infections. The widely used approach for multilocus sequence typing (MLST) that is based on the core genome, cgMLST, has the advantage of a high level of typeability and maximal discriminatory power. Yet, the transition from a seven loci-based scheme to cgMLST involves several challenges, that include the need by some users to maintain backward compatibility, growing difficulties in the day-to-day communication within the microbiology community with respect to nomenclature and ontology, issues with typeability, especially if a more stringent approach to loci presence is used, and computational requirements concerning laboratory data management and sharing with end-users. Hence, methods for optimizing cgMLST schemes through careful reduction of the number of loci are expected to be beneficial for practical needs in different settings. RESULTS: We present a new machine learning-based methodology, minMLST, for minimizing the number of genes in cgMLST schemes by identifying subsets of informative genes and analyzing the trade-off between gene reduction and typing performance. The results achieved with minMLST over eight bacterial species show that despite the reduction in the number of genes up to a factor of 10, the typing performance remains very high and significant with an Adjusted Rand Index that ranges between 0.4 and 0.93 in different species and a P-value < 10-3. The identification of such optimized MLST schemes for bacterial strain typing is expected to improve the implementation of cgMLST by improving interlaboratory agreement and communication. AVAILABILITY AND IMPLEMENTATION: The python package minMLST is available at https://PyPi.org/project/minmlst/PyPI and supported on Linux and Windows. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Methods to assess the quality of protein structure models are needed for user applications. To aid with the selection of structure models and further inform the development of structure prediction techniques, we describe the ResiRole method for the assessment of the quality of structure models. RESULTS: Structure prediction techniques are ranked according to the results of round-robin, head-to-head comparisons using difference scores. Each difference score was defined as the absolute value of the cumulative probability for a functional site prediction made with the FEATURE program for the reference structure minus that for the structure model. Overall, the difference scores correlate well with other model quality metrics; and based on benchmarking studies with NaïveBLAST, they are found to detect additional local structural similarities between the structure models and reference structures. AVAILABILITYAND IMPLEMENTATION: Automated analyses of models addressed in CAMEO are available via the ResiRole server, URL http://protein.som.geisinger.edu/ResiRole/. Interactive analyses with user-provided models and reference structures are also enabled. Code is available at github.com/wamclaughlin/ResiRole. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Quantitative structure-activity relationship (QSAR) methods are increasingly used in assisting the process of preclinical, small molecule drug discovery. Regression models are trained on data consisting of a finite-dimensional representation of molecular structures and their corresponding target-specific activities. These supervised learning models can then be used to predict the activity of previously unmeasured novel compounds. RESULTS: This work provides methods that solve three problems in QSAR modelling: (i) a method for comparing the information content between finite-dimensional representations of molecular structures (fingerprints) with respect to the target of interest, (ii) a method that quantifies how the accuracy of the model prediction degrades as a function of the distance between the testing and training data and (iii) a method to adjust for screening dependent selection bias inherent in many training datasets. For example, in the most extreme cases, only compounds which pass an activity-dependent screening threshold are reported. A semi-supervised learning framework combines (ii) and (iii) and can make predictions, which take into account the similarity of the testing compounds to those in the training data and adjust for the reporting selection bias. We illustrate the three methods using publicly available structure-activity data for a large set of compounds reported by GlaxoSmithKline (the Tres Cantos AntiMalarial Set, TCAMS) to inhibit asexual in vitro Plasmodium falciparum growth. AVAILABILITYAND IMPLEMENTATION: https://github.com/owatson/PenalizedPrediction. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single protein residue mutations may reshape the binding affinity of protein-protein interactions. Therefore, predicting its effects is of great interest in biotechnology and biomedicine. Unfortunately, the availability of experimental data on binding affinity changes upon mutation is limited, which hampers the development of new and more precise algorithms. Here, we propose UEP, a classifier for predicting beneficial and detrimental mutations in protein-protein complexes trained on interactome data. RESULTS: Regardless of the simplicity of the UEP algorithm, which is based on a simple three-body contact potential derived from interactome data, we report competitive results with the gold standard methods in this field with the advantage of being faster in terms of computational time. Moreover, we propose a consensus selection procedure by involving the combination of three predictors that showed higher classification accuracy in our benchmark: UEP, pyDock and EvoEF1/FoldX. Overall, we demonstrate that the analysis of interactome data allows predicting the impact of protein-protein mutations using UEP, a fast and reliable open-source code. AVAILABILITY AND IMPLEMENTATION: UEP algorithm can be found at: https://github.com/pepamengual/UEP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: As sequencing technologies and analysis pipelines evolve, de novo mutations(DNMs) calling tools must be adapted. Therefore, a flexible approach is needed that can accurately identify de novo mutations from genome or exome sequences from a variety of datasets and variant calling pipelines. RESULTS: Here, we describe SynthDNM, a random-forest based classifier that can be readily adapted to new sequencing or variant-calling pipelines by applying a flexible approach to constructing simulated training examples from real data. The optimized SynthDNM classifiers predict de novo SNPs and indels with robust accuracy across multiple methods of variant calling. AVAILABILITY: SynthDNM is freely available on Github (https://github.com/james-guevara/synthdnm). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Ordinary differential equation models facilitate the understanding of cellular signal transduction and other biological processes. However, for large and comprehensive models, the computational cost of simulating or calibrating can be limiting. AMICI is a modular toolbox implemented in C ++/Python/MATLAB that provides efficient simulation and sensitivity analysis routines tailored for scalable, gradient-based parameter estimation and uncertainty quantification. AVAILABILITY: AMICI is published under the permissive BSD-3-Clause license with source code publicly available on https://github.com/AMICI-dev/AMICI. Citeable releases are archived on Zenodo. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Rapid developments in sequencing technologies have boosted generating high volumes of sequence data. To archive and analyze those data, one primary step is sequence comparison. Alignment-free sequence comparison based on k-mer frequencies offers a computationally efficient solution, yet in practice, the k-mer frequency vectors for large k of practical interest lead to excessive memory and storage consumption. RESULTS: We report CRAFT, a general genomic/metagenomic search engine to learn compact representations of sequences and perform fast comparison between DNA sequences. Specifically, given genome or high throughput sequencing data as input, CRAFT maps the data into a much smaller embedding space and locates the best matching genome in the archived massive sequence repositories. With 102-104-fold reduction of storage space, CRAFT performs fast query for gigabytes of data within seconds or minutes, achieving comparable performance as six state-of-the-art alignment-free measures. AVAILABILITY AND IMPLEMENTATION: CRAFT offers a user-friendly graphical user interface with one-click installation on Windows and Linux operating systems, freely available at https://github.com/jiaxingbai/CRAFT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The latest advances in cancer sequencing, and the availability of a wide range of methods to infer the evolutionary history of tumors, have made it important to evaluate, reconcile and cluster different tumor phylogenies. Recently, several notions of distance or similarities have been proposed in the literature, but none of them has emerged as the golden standard. Moreover, none of the known similarity measures is able to manage mutations occurring multiple times in the tree, a circumstance often occurring in real cases. RESULTS: To overcome these limitations, in this article, we propose MP3, the first similarity measure for tumor phylogenies able to effectively manage cases where multiple mutations can occur at the same time and mutations can occur multiple times. Moreover, a comparison of MP3 with other measures shows that it is able to classify correctly similar and dissimilar trees, both on simulated and on real data. AVAILABILITY AND IMPLEMENTATION: An open source implementation of MP3 is publicly available at https://github.com/AlgoLab/mp3treesim. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein function prediction is a difficult bioinformatics problem. Many recent methods use deep neural networks to learn complex sequence representations and predict function from these. Deep supervised models require a lot of labeled training data which are not available for this task. However, a very large amount of protein sequences without functional labels is available. RESULTS: We applied an existing deep sequence model that had been pretrained in an unsupervised setting on the supervised task of protein molecular function prediction. We found that this complex feature representation is effective for this task, outperforming hand-crafted features such as one-hot encoding of amino acids, k-mer counts, secondary structure and backbone angles. Also, it partly negates the need for complex prediction models, as a two-layer perceptron was enough to achieve competitive performance in the third Critical Assessment of Functional Annotation benchmark. We also show that combining this sequence representation with protein 3D structure information does not lead to performance improvement, hinting that 3D structure is also potentially learned during the unsupervised pretraining. AVAILABILITY AND IMPLEMENTATION: Implementations of all used models can be found at https://github.com/stamakro/GCN-for-Structure-and-Function. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Protein phosphorylation is a ubiquitous mechanism of post-translational modification that plays a central role in cellular signaling. Phosphorylation is particularly important in the context of cancer, as downregulation of tumor suppressors and upregulation of oncogenes by the dysregulation of associated kinase and phosphatase networks are shown to have key roles in tumor growth and progression. Despite recent advances that enable large-scale monitoring of protein phosphorylation, these data are not fully incorporated into such computational tasks as phenotyping and subtyping of cancers. RESULTS: We develop a network-based algorithm, CoPPNet, to enable unsupervised subtyping of cancers using phosphorylation data. For this purpose, we integrate prior knowledge on evolutionary, structural and functional association of phosphosites, kinase-substrate associations and protein-protein interactions with the correlation of phosphorylation of phosphosites across different tumor samples (a.k.a co-phosphorylation) to construct a context-specific-weighted network of phosphosites. We then mine these networks to identify subnetworks with correlated phosphorylation patterns. We apply the proposed framework to two mass-spectrometry-based phosphorylation datasets for breast cancer (BC), and observe that (i) the phosphorylation pattern of the identified subnetworks are highly correlated with clinically identified subtypes, and (ii) the identified subnetworks are highly reproducible across datasets that are derived from different studies. Our results show that integration of quantitative phosphorylation data with network frameworks can provide mechanistic insights into the differences between the signaling mechanisms that drive BC subtypes. Furthermore, the reproducibility of the identified subnetworks suggests that phosphorylation can provide robust classification of disease response and markers. AVAILABILITY AND IMPLEMENTATION: CoPPNet is available at http://compbio.case.edu/coppnet/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Recent technological advances produce a wealth of high-dimensional descriptions of biological processes, yet extracting meaningful insight and mechanistic understanding from these data remains challenging. For example, in developmental biology, the dynamics of differentiation can now be mapped quantitatively using single-cell RNA sequencing, yet it is difficult to infer molecular regulators of developmental transitions. Here, we show that discovering informative features in the data is crucial for statistical analysis as well as making experimental predictions. RESULTS: We identify features based on their ability to discriminate between clusters of the data points. We define a class of problems in which linear separability of clusters is hidden in a low-dimensional space. We propose an unsupervised method to identify the subset of features that define a low-dimensional subspace in which clustering can be conducted. This is achieved by averaging over discriminators trained on an ensemble of proposed cluster configurations. We then apply our method to single-cell RNA-seq data from mouse gastrulation, and identify 27 key transcription factors (out of 409 total), 18 of which are known to define cell states through their expression levels. In this inferred subspace, we find clear signatures of known cell types that eluded classification prior to discovery of the correct low-dimensional subspace. AVAILABILITY AND IMPLEMENTATION: https://github.com/smelton/SMD. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Discrete stochastic models of gene regulatory networks are fundamental tools for in silico study of stochastic gene regulatory networks. Likelihood-free inference and model exploration are critical applications to study a system using such models. However, the massive computational cost of complex, high-dimensional and stochastic modelling currently limits systematic investigation to relatively simple systems. Recently, machine-learning-assisted methods have shown great promise to handle larger, more complex models. To support both ease-of-use of this new class of methods, as well as their further development, we have developed the scalable inference, optimization and parameter exploration (Sciope) toolbox. Sciope is designed to support new algorithms for machine-learning-assisted model exploration and likelihood-free inference. Moreover, it is built ground up to easily leverage distributed and heterogeneous computational resources for convenient parallelism across platforms from workstations to clouds. AVAILABILITY AND IMPLEMENTATION: The Sciope Python3 toolbox is freely available on https://github.com/Sciope/Sciope, and has been tested on Linux, Windows and macOS platforms. SUPPLEMENTARY INFORMATION: Supplementary information is available at Bioinformatics online.

SUMMARY: treeheatr is an R package for creating interpretable decision tree visualizations with the data represented as a heatmap at the tree's leaf nodes. The integrated presentation of the tree structure along with an overview of the data efficiently illustrates how the tree nodes split up the feature space and how well the tree model performs. This visualization can also be examined in depth to uncover the correlation structure in the data and importance of each feature in predicting the outcome. Implemented in an easily installed package with a detailed vignette, treeheatr can be a useful teaching tool to enhance students' understanding of a simple decision tree model before diving into more complex tree-based machine learning methods. AVAILABILITY AND IMPLEMENTATION: The treeheatr package is freely available under the permissive MIT license at https://trang1618.github.io/treeheatr and https://cran.r-project.org/package=treeheatr. It comes with a detailed vignette that is automatically built with GitHub Actions continuous integration.

MOTIVATION: Influenza viruses are a cause of large outbreaks and pandemics with high death tolls. A key obstacle is that flu vaccines have inconsistent performance, in the best cases up to 60% effectiveness, but it can be as low as 10%. Uncovering the hidden pathways of how antibodies (Abs) induced by one influenza strain are effective against another, cross-reaction, is a central vexation for the design of universal flu vaccines. RESULTS: We conceive a stochastic model that successfully represents the antibody cross-reactive data from mice infected with H3N2 influenza strains and further validation with cross-reaction data of H1N1 strains. Using a High-Performance Computing cluster, several aspects and parameters in the model were tested. Computational simulations highlight that changes in time of infection and the B-cells population are relevant, however, the affinity threshold of B-cells between consecutive infections is a necessary condition for the successful Abs cross-reaction. Our results suggest a 3-D reformulation of the current influenza antibody landscape for the representation and modeling of cross-reactive data. AVAILABILITY AND IMPLEMENTATION: The full code as a testing/simulation platform is freely available here: https://github.com/systemsmedicine/Antibody_cross-reaction_dynamics. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The automatic extraction of published relationships between molecular entities has important applications in many biomedical fields, ranging from Systems Biology to Personalized Medicine. Existing works focused on extracting relationships described in single articles or in single sentences. However, a single record is rarely sufficient to judge upon the biological correctness of a relation, as experimental evidence might be weak or only valid in a certain context. Furthermore, statements may be more speculative than confirmative, and different articles often contradict each other. Experts therefore always take the complete literature into account to take a reliable decision upon a relationship. It is an open research question how to do this effectively in an automatic manner. RESULTS: We propose two novel relation extraction approaches which use recent representation learning techniques to create comprehensive models of biomedical entities or entity-pairs, respectively. These representations are learned by considering all publications from PubMed mentioning an entity or a pair. They are used as input for a neural network for classifying relations globally, i.e. the derived predictions are corpus-based, not sentence- or article based as in prior art. Experiments on the extraction of mutation-disease, drug-disease and drug-drug relationships show that the learned embeddings indeed capture semantic information of the entities under study and outperform traditional methods by 4-29% regarding F1 score. AVAILABILITY AND IMPLEMENTATION: Source codes are available at: https://github.com/mariosaenger/bio-re-with-entity-embeddings. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Drugs and diseases play a central role in many areas of biomedical research and healthcare. Aggregating knowledge about these entities across a broader range of domains and languages is critical for information extraction (IE) applications. To facilitate text mining methods for analysis and comparison of patient's health conditions and adverse drug reactions reported on the Internet with traditional sources such as drug labels, we present a new corpus of Russian language health reviews. RESULTS: The Russian Drug Reaction Corpus (RuDReC) is a new partially annotated corpus of consumer reviews in Russian about pharmaceutical products for the detection of health-related named entities and the effectiveness of pharmaceutical products. The corpus itself consists of two parts, the raw one and the labeled one. The raw part includes 1.4 million health-related user-generated texts collected from various Internet sources, including social media. The labeled part contains 500 consumer reviews about drug therapy with drug- and disease-related information. Labels for sentences include health-related issues or their absence. The sentences with one are additionally labeled at the expression level for identification of fine-grained subtypes such as drug classes and drug forms, drug indications and drug reactions. Further, we present a baseline model for named entity recognition (NER) and multilabel sentence classification tasks on this corpus. The macro F1 score of 74.85% in the NER task was achieved by our RuDR-BERT model. For the sentence classification task, our model achieves the macro F1 score of 68.82% gaining 7.47% over the score of BERT model trained on Russian data. AVAILABILITY AND IMPLEMENTATION: We make the RuDReC corpus and pretrained weights of domain-specific BERT models freely available at https://github.com/cimm-kzn/RuDReC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Tumours are composed of distinct cancer cell populations (clones), which continuously adapt to their local micro-environment. Standard methods for clonal deconvolution seek to identify groups of mutations and estimate the prevalence of each group in the tumour, while considering its purity and copy number profile. These methods have been applied on cross-sectional data and on longitudinal data after discarding information on the timing of sample collection. Two key questions are how can we incorporate such information in our analyses and is there any benefit in doing so? RESULTS: We developed a clonal deconvolution method, which incorporates explicitly the temporal spacing of longitudinally sampled tumours. By merging a Dirichlet Process Mixture Model with Gaussian Process priors and using as input a sequence of several sparsely collected samples, our method can reconstruct the temporal profile of the abundance of any mutation cluster supported by the data as a continuous function of time. We benchmarked our method on whole genome, whole exome and targeted sequencing data from patients with chronic lymphocytic leukaemia, on liquid biopsy data from a patient with melanoma and on synthetic data and we found that incorporating information on the timing of tissue collection improves model performance, as long as data of sufficient volume and complexity are available for estimating free model parameters. Thus, our approach is particularly useful when collecting a relatively long sequence of tumour samples is feasible, as in liquid cancers (e.g. leukaemia) and liquid biopsies. AVAILABILITY AND IMPLEMENTATION: The statistical methodology presented in this paper is freely available at github.com/dvav/clonosGP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Hydrogen deuterium exchange mass spectrometry (HDX-MS) is becoming increasing routine for monitoring changes in the structural dynamics of proteins. Differential HDX-MS allows comparison of protein states, such as in the absence or presence of a ligand. This can be used to attribute changes in conformation to binding events, allowing the mapping of entire conformational networks. As such, the number of necessary cross-state comparisons quickly increases as additional states are introduced to the system of study. There are currently very few software packages available that offer quick and informative comparison of HDX-MS datasets and even fewer which offer statistical analysis and advanced visualization. Following the feedback from our original software Deuteros, we present Deuteros 2.0 which has been redesigned from the ground up to fulfill a greater role in the HDX-MS analysis pipeline. Deuteros 2.0 features a repertoire of facilities for back exchange correction, data summarization, peptide-level statistical analysis and advanced data plotting features. AVAILABILITY AND IMPLEMENTATION: Deuteros 2.0 can be downloaded for both Windows and MacOS from https://github.com/andymlau/Deuteros_2.0 under the Apache 2.0 license.

MOTIVATION: Cryoelectron tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at submolecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However, often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domain may perform poorly in predicting subtomogram classes in the target domain. RESULTS: In this article, we adapt a few shot domain adaptation method for deep learning-based cross-domain subtomogram classification. The essential idea of our method consists of two parts: (i) take full advantage of the distribution of plentiful unlabeled target domain data, and (ii) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods. AVAILABILITY AND IMPLEMENTATION: Software is available online https://github.com/xulabs/aitom. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Visualization is a vital task in phylogenetics and yet there is a deficit in programs which visualize the multispecies coalescent (MSC) model. UglyTrees (UT) is an easy-to-use program for visualizing multiple gene trees embedded within a single species trees. The mapping between gene and species nodes is automatically detected allowing for ready access to the program. UT can scrape the contents of a website for MSC analyses, enabling the sharing of interactive MSC figures through optional parameters in the URL. If a posterior distribution is uploaded, the transitions between MSC states are animated allowing the visual tracking of trees throughout the sequence. AVAILABILITY AND IMPLEMENTATION: UT runs in all major web browsers including mobile devices, and is hosted at www.uglytrees.nz. The MIT-licensed code is available at https://github.com/UglyTrees/uglytrees.github.io.

SUMMARY: Sequence Processing and Data Extraction (SPDE) has eight modules comprising 100 basic functions ranging from sequence extraction, format conversion to data reorganization and mining, and all of these functions can be completed by point-and-click icons. SPDE also incorporates eight public analyses tools; thus, SPDE is a comprehensive bioinformatics platform for big biological data analysis. AVAILABILITY AND IMPLEMENTATION: SPDE built by Python can run on 32-bit, 64-bit Windows and MacOS systems. It can be downloaded from https://github.com/simon19891216/SPDEv1.2.git. SUPPLEMENTARY INFORMATION: The test data and video tutorials can be downloaded from https://github.com/simon19891216/SPDEv1.2.git.

SUMMARY: Single-cell DNA template strand sequencing (Strand-seq) enables chromosome length haplotype phasing, construction of phased assemblies, mapping sister-chromatid exchange events and structural variant discovery. The initial quality control of potentially thousands of single-cell libraries is still done manually by domain experts. ASHLEYS automates this tedious task, delivers near-expert performance and labels even large data sets in seconds. AVAILABILITY AND IMPLEMENTATION: github.com/friendsofstrandseq/ashleys-qc, MIT license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Variant Call Format (VCF), the prevailing representation for germline genotypes in population sequencing, suffers rapid size growth as larger cohorts are sequenced and more rare variants are discovered. We present Sparse Project VCF (spVCF), an evolution of VCF with judicious entropy reduction and run-length encoding, delivering >10× size reduction for modern studies with practically minimal information loss. spVCF interoperates with VCF efficiently, including tabix-based random access. We demonstrate its effectiveness with the DiscovEHR and UK Biobank whole-exome sequencing cohorts. AVAILABILITY AND IMPLEMENTATION: Apache-licensed reference implementation: github.com/mlin/spVCF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Quantitative structure-activity relationship (QSAR) analysis is commonly used in drug discovery. Collaborations among pharmaceutical institutions can lead to a better performance in QSAR prediction, however, intellectual property and related financial interests remain substantially hindering inter-institutional collaborations in QSAR modeling for drug discovery. RESULTS: For the first time, we verified the feasibility of applying the horizontal federated learning (HFL), which is a recently developed collaborative and privacy-preserving learning framework to perform QSAR analysis. A prototype platform of federated-learning-based QSAR modeling for collaborative drug discovery, i.e. FL-QSAR, is presented accordingly. We first compared the HFL framework with a classic privacy-preserving computation framework, i.e. secure multiparty computation to indicate its difference from various perspective. Then we compared FL-QSAR with the public collaboration in terms of QSAR modeling. Our extensive experiments demonstrated that (i) collaboration by FL-QSAR outperforms a single client using only its private data, and (ii) collaboration by FL-QSAR achieves almost the same performance as that of collaboration via cleartext learning algorithms using all shared information. Taking together, our results indicate that FL-QSAR under the HFL framework provides an efficient solution to break the barriers between pharmaceutical institutions in QSAR modeling, therefore promote the development of collaborative and privacy-preserving drug discovery with extendable ability to other privacy-related biomedical areas. AVAILABILITY AND IMPLEMENTATION: The source codes of FL-QSAR are available on the GitHub: https://github.com/bm2-lab/FL-QSAR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Polymerase chain reaction (PCR) has been a revolutionary biomedical advancement. However, for PCR to be appropriately used, one must spend a significant amount of effort on PCR primer design. Carefully designed PCR primers not only increase sensitivity and specificity, but also decrease effort spent on experimental optimization. Computer software removes the human element by performing and automating the complex and rigorous calculations required in PCR primer design. Classification and review of the available software options and their capabilities should be a valuable resource for any PCR application. RESULTS: This article focuses on currently available free PCR primer design software and their major functions (https://pcrprimerdesign.github.io/). The software are classified according to their PCR applications, such as Sanger sequencing, reverse transcription quantitative PCR, single nucleotide polymorphism detection, splicing variant detection, methylation detection, microsatellite detection, multiplex PCR and targeted next generation sequencing, and conserved/degenerate primers to clone orthologous genes from related species, new gene family members in the same species, or to detect a group of related pathogens. Each software is summarized to provide a technical review of their capabilities and utilities.

MOTIVATION: Single-cell gene expression distributions measured by single-cell RNA-sequencing (scRNA-seq) often display complex differences between samples. These differences are biologically meaningful but cannot be identified using standard methods for differential expression. RESULTS: Here, we derive and implement a flexible and fast differential distribution testing procedure based on the 2-Wasserstein distance. Our method is able to detect any type of difference in distribution between conditions. To interpret distributional differences, we decompose the 2-Wasserstein distance into terms that capture the relative contribution of changes in mean, variance and shape to the overall difference. Finally, we derive mathematical generalisations that allow our method to be used in a broad range of disciplines other than scRNA-seq or bioinformatics. AVAILABILITY: Our methods are implemented in the R/Bioconductor package waddR, which is freely available at https://github.com/goncalves-lab/waddR, along with documentation and examples. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: When rare missense variants are clinically interpreted as to their pathogenicity, most are classified as variants of uncertain significance (VUS). Although functional assays can provide strong evidence for variant classification, such results are generally unavailable. Multiplexed assays of variant effect can generate experimental 'variant effect maps' that score nearly all possible missense variants in selected protein targets for their impact on protein function. However, these efforts have not always prioritized proteins for which variant effect maps would have the greatest impact on clinical variant interpretation. RESULTS: Here, we mined databases of clinically interpreted variants and applied three strategies, each building on the previous, to prioritize genes for systematic functional testing of missense variation. The strategies ranked genes (i) by the number of unique missense VUS that had been reported to ClinVar; (ii) by movability- and reappearance-weighted impact scores, to give extra weight to reappearing, movable VUS and (iii) by difficulty-adjusted impact scores, to account for the more resource-intensive nature of generating variant effect maps for longer genes. Our results could be used to guide systematic functional testing of missense variation toward greater impact on clinical variant interpretation. AVAILABILITY AND IMPLEMENTATION: Source code available at: https://github.com/rothlab/mave-gene-prioritization. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Permutation tests offer a straightforward framework to assess the significance of differences in sample statistics. A significant advantage of permutation tests are the relatively few assumptions about the distribution of the test statistic are needed, as they rely on the assumption of exchangeability of the group labels. They have great value, as they allow a sensitivity analysis to determine the extent to which the assumed broad sample distribution of the test statistic applies. However, in this situation, permutation tests are rarely applied because the running time of naïve implementations is too slow and grows exponentially with the sample size. Nevertheless, continued development in the 1980s introduced dynamic programming algorithms that compute exact permutation tests in polynomial time. Albeit this significant running time reduction, the exact test has not yet become one of the predominant statistical tests for medium sample size. Here, we propose a computational parallelization of one such dynamic programming-based permutation test, the Green algorithm, which makes the permutation test more attractive. RESULTS: Parallelization of the Green algorithm was found possible by non-trivial rearrangement of the structure of the algorithm. A speed-up-by orders of magnitude-is achievable by executing the parallelized algorithm on a GPU. We demonstrate that the execution time essentially becomes a non-issue for sample sizes, even as high as hundreds of samples. This improvement makes our method an attractive alternative to, e.g. the widely used asymptotic Mann-Whitney U-test. AVAILABILITYAND IMPLEMENTATION: In Python 3 code from the GitHub repository https://github.com/statisticalbiotechnology/parallelPermutationTest under an Apache 2.0 license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Accurate prediction of drug-target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use DL library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. AVAILABILITY AND IMPLEMENTATION: https://github.com/kexinhuang12345/DeepPurpose. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Integrative genomic analysis is a powerful tool used to study the biological mechanisms underlying a complex disease or trait across multiplatform high-dimensional data, such as DNA methylation, copy number variation and gene expression. It is common to perform large-scale genome-wide association analysis of an outcome for each data type separately and combine the results ad hoc, leading to loss of statistical power and uncontrolled overall false discovery rate (FDR). RESULTS: We propose a multivariate mixture model (IMIX) framework that integrates multiple types of genomic data and allows modeling of inter-data-type correlations. We investigated the across-data-type FDR control in IMIX and demonstrated lower misclassification rates at controlled overall FDR than established individual data type analysis strategies, such as the Benjamini-Hochberg FDR control, the q-value and the local FDR control by extensive simulations. IMIX features statistically principled model selection, FDR control and computational efficiency. Applications to The Cancer Genome Atlas data provided novel multi-omics insights into the genes and mechanisms associated with the luminal and basal subtypes of bladder cancer and the prognosis of pancreatic cancer. AVAILABILITYAND IMPLEMENTATION: We have implemented our method in R package 'IMIX' available at https://github.com/ziqiaow/IMIX, as well as CRAN soon. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Metagenomics refers to the study of complex samples containing of genetic contents of multiple individual organisms and, thus, has been used to elucidate the microbiome and resistome of a complex sample. The microbiome refers to all microbial organisms in a sample, and the resistome refers to all of the antimicrobial resistance (AMR) genes in pathogenic and non-pathogenic bacteria. Single-nucleotide polymorphisms (SNPs) can be effectively used to 'fingerprint' specific organisms and genes within the microbiome and resistome and trace their movement across various samples. However, to effectively use these SNPs for this traceability, a scalable and accurate metagenomics SNP caller is needed. Moreover, such an SNP caller should not be reliant on reference genomes since 95% of microbial species is unculturable, making the determination of a reference genome extremely challenging. In this article, we address this need. RESULTS: We present LueVari, a reference-free SNP caller based on the read-colored de Bruijn graph, an extension of the traditional de Bruijn graph that allows repeated regions longer than the k-mer length and shorter than the read length to be identified unambiguously. LueVari is able to identify SNPs in both AMR genes and chromosomal DNA from shotgun metagenomics data with reliable sensitivity (between 91% and 99%) and precision (between 71% and 99%) as the performance of competing methods varies widely. Furthermore, we show that LueVari constructs sequences containing the variation, which span up to 97.8% of genes in datasets, which can be helpful in detecting distinct AMR genes in large metagenomic datasets. AVAILABILITY AND IMPLEMENTATION: Code and datasets are publicly available at https://github.com/baharpan/cosmo/tree/LueVari. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.