MOTIVATION: Data transformations are an important step in the analysis of RNA-seq data. Nonetheless, the impact of transformation on the outcome of unsupervised clustering procedures is still unclear. RESULTS: Here, we present an Asymmetric Winsorization per Sample Transformation (AWST), which is robust to data perturbations and removes the need for selecting the most informative genes prior to sample clustering. Our procedure leads to robust and biologically meaningful clusters both in bulk and in single-cell applications. AVAILABILITY: The AWST method is available at https://github.com/drisso/awst. The code to reproduce the analyses is available at https://github.com/drisso/awst\_analysis. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: SARS-CoV-2 is a novel coronavirus currently causing a pandemic. Here, we performed a combined in-silico and cell culture comparison of SARS-CoV-2 and the closely related SARS-CoV. RESULTS: Many amino acid positions are differentially conserved between SARS-CoV-2 and SARS-CoV, which reflects the discrepancies in virus behaviour, i.e. more effective human-to-human transmission of SARS-CoV-2 and higher mortality associated with SARS-CoV. Variations in the S protein (mediates virus entry) were associated with differences in its interaction with ACE2 (cellular S receptor) and sensitivity to TMPRSS2 (enables virus entry via S cleavage) inhibition. Anti-ACE2 antibodies more strongly inhibited SARS-CoV than SARS-CoV-2 infection, probably due to a stronger SARS-CoV-2 S-ACE2 affinity relative to SARS-CoV S. Moreover, SARS-CoV-2 and SARS-CoV displayed differences in cell tropism. Cellular ACE2 and TMPRSS2 levels did not indicate susceptibility to SARS-CoV-2. In conclusion, we identified genomic variation between SARS-CoV-2 and SARS-CoV that may reflect the differences in their clinical and biological behaviour. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The prediction performance of Cox proportional hazard model suffers when there are only few uncensored events in the training data. RESULTS: We propose a Sparse-Group regularized Cox regression method to improve the prediction performance of large-scale and high-dimensional survival data with few observed events. Our approach is applicable when there is one or more other survival responses that 1. has a large number of observed events; 2. share a common set of associated predictors with the rare event response. This scenario is common in the UK Biobank (Sudlow et al., 2015) dataset where records for a large number of common and less prevalent diseases of the same set of individuals are available. By analyzing these responses together, we hope to achieve higher prediction performance than when they are analyzed individually. To make this approach practical for large-scale data, we developed an accelerated proximal gradient optimization algorithm as well as a screening procedure inspired by Qian et al. (2020). AVAILABILITY: https://github.com/rivas-lab/multisnpnet-Cox. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Modern Bioinformatics is facing increasingly complex problems to solve, and we are indeed rapidly approaching an era in which the ability to seamlessly integrate heterogeneous sources of information will be crucial for the scientific progress. Here we present a novel non-linear data fusion framework that generalizes the conventional Matrix Factorization paradigm allowing inference over arbitrary Entity-Relation graphs, and we applied it to the prediction of Protein-Protein Interactions (PPIs). Improving our knowledge of Protein Protein Interaction (PPI) networks at the proteome scale is indeed crucial to understand protein function, physiological and disease states and cell life in general. RESULTS: We devised three data-fusion based models for the proteome-level prediction of PPIs, and we show that our method outperforms state of the art approaches on common benchmarks. Moreover, we investigate its predictions on newly published PPIs, showing that this new data has a clear shift in its underlying distributions and we thus train and test our models on this extended dataset. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Diverse disciplines in biology process and analyze multiple sequence alignments (MSAs) and phylogenetic trees to evaluate their information content, infer evolutionary events and processes, and predict gene function. However, automated processing of MSAs and trees remains a challenge due to the lack of a unified toolkit. To fill this gap, we introduce PhyKIT, a toolkit for the UNIX shell environment with 30 functions that process MSAs and trees, including but not limited to estimation of mutation rate, evaluation of sequence composition biases, calculation of the degree of violation of a molecular clock, and collapsing bipartitions (internal branches) with low support. RESULTS: To demonstrate the utility of PhyKIT, we detail three use cases: (1) summarizing information content in MSAs and phylogenetic trees for diagnosing potential biases in sequence or tree data; (2) evaluating gene-gene covariation of evolutionary rates to identify functional relationships, including novel ones, among genes; and (3) identify lack of resolution events or polytomies in phylogenetic trees, which are suggestive of rapid radiation events or lack of data. We anticipate PhyKIT will be useful for processing, examining, and deriving biological meaning from increasingly large phylogenomic datasets. AVAILABILITY: PhyKIT is freely available on GitHub (https://github.com/JLSteenwyk/PhyKIT), PyPi (https://pypi.org/project/phykit/), and the Anaconda Cloud (https://anaconda.org/JLSteenwyk/phykit) under the MIT license with extensive documentation and user tutorials (https://jlsteenwyk.com/PhyKIT). SUPPLEMENTARY INFORMATION: Supplementary data are available on figshare (doi: 10.6084/m9.figshare.13118600) and are available at Bioinformatics online.

MOTIVATION: A fundamental problem for disease treatment is that while antibiotics are a powerful counter to bacteria, they are ineffective against viruses. Often, bacterial and viral infections are confused due to their similar symptoms and lack of rapid diagnostics. With many clinicians relying primarily on symptoms for diagnosis, overuse and misuse of modern antibiotics are rife, contributing to the growing pool of antibiotic resistance. To ensure an individual receives optimal treatment given their disease state and to reduce over-prescription of antibiotics, the host response can in theory be measured quickly to distinguish between the two states. To establish a predictive biomarker panel of disease state (viral/bacterial/no-infection) we conducted a meta-analysis of human blood infection studies using Machine Learning (ML). RESULTS: We focused on publicly available gene expression data from two widely used platforms, Affymetrix and Illumina microarrays as they represented a significant proportion of the available data. We were able to develop multi-class models with high accuracies with our best model predicting 93% of bacterial and 89% viral samples correctly. To compare the selected features in each of the different technologies, we reverse engineered the underlying molecular regulatory network and explored the neighbourhood of the selected features. The networks highlighted that although on the gene-level the models differed, they contained genes from the same areas of the network. Specifically, this convergence was to pathways including the Type I interferon Signalling Pathway, Chemotaxis, Apoptotic Processes, and Inflammatory/Innate Response. AVAILABILITY: Data and code are available on the Gene Expression Omnibus and github. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Erratum in Bioinformatics. 2023 Jan 1;39(1):

MOTIVATION: Species delimitation, the process of deciding how to group a set of organisms into units called species, is one of the most challenging problems in evolutionary computational biology. While many methods exist for species delimitation, most based on the coalescent theory, few are scalable to very large datasets, and methods that scale tend to be not accurate. Species delimitation is closely related to species tree inference from discordant gene trees, a problem that has enjoyed rapid advances in recent years. RESULTS: In this paper, we build on the accuracy and scalability of recent quartet-based methods for species tree estimation and propose a new method called SODA for species delimitation. SODA relies heavily on a recently developed method for testing zero branch length in species trees. In extensive simulations, we show that SODA can easily scale to very large datasets while maintaining high accuracy. AVAILABILITY: The code and data presented here are available on https://github.com/maryamrabiee/SODA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: To better understand the molecular features of cancers, a comprehensive analysis using multiomics data has been conducted. Additionally, a pathway activity inference method has been developed to facilitate the integrative effects of multiple genes. In this respect, we have recently proposed a novel integrative pathway activity inference approach, iDRW, and demonstrated the effectiveness of the method with respect to dichotomizing two survival groups. However, there were several limitations, such as a lack of generality. In this study, we designed a directed gene-gene graph using pathway information by assigning interactions between genes in multiple layers of networks. RESULTS: : As a proof-of-concept study, it was evaluated using three genomic profiles of urologic cancer patients. The proposed integrative approach achieved improved outcome prediction performances compared with a single genomic profile alone and other existing pathway activity inference methods. The integrative approach also identified common/cancer-specific candidate driver pathways as predictive prognostic features in urologic cancers. Furthermore, it provides better biological insights into the prioritized pathways and genes in an integrated view using a multi-layered gene-gene network. Our framework is not specifically designed for urologic cancers and can be generally applicable for various datasets. AVAILABILITY: iDRW is implemented as the R software package. The source codes are available at https://github.com/sykim122/iDRW. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The majority of genome analysis tools and pipelines require data to be decrypted for access. This potentially leaves sensitive genetic data exposed, either because the unencrypted data is not removed after analysis, or because the data leaves traces on the permanent storage medium. RESULTS: We defined a file container specification enabling direct byte-level compatible random access to encrypted genetic data stored in community standards such as SAM/BAM/CRAM/VCF/BCF. By standardizing this format, we show how it can be added as a native file format to genomic libraries, enabling direct analysis of encrypted data without the need to create a decrypted copy. AVAILABILITY: The Crypt4GH specification can be found at: http://samtools.github.io/hts-specs/crypt4gh.pdf.

MOTIVATION: Deciphering the language of non-coding DNA is one of the fundamental problems in genome research. Gene regulatory code is highly complex due to the existence of polysemy and distant semantic relationship, which previous informatics methods often fail to capture especially in data-scarce scenarios. RESULTS: To address this challenge, we developed a novel pre-trained bidirectional encoder represen-tation, named DNABERT, to capture global and transferrable understanding of genomic DNA sequences based on up and downstream nucleotide contexts. We compared DNABERT to the most widely used programs for genome-wide regulatory elements prediction and demonstrate its ease of use, accuracy, and efficiency. We show that the single pre-trained transformers model can simultaneously achieve state-of-the-art performance on prediction of promoters, splice sites, and transcription factor binding sites, after easy fine-tuning using small task-specific labelled data. Further, DNABERT enables direct visualization of nucleotide-level importance and semantic relationship within input sequences for better interpretability and accurate identification of conserved sequence motifs and functional genetic variant candidates. Finally, we demonstrate that pre-trained DNABERT with human genome can even be readily applied to other organisms with exceptional performance. We anticipate that the pre-trained DNABERT model can be fined tuned to many other sequence analyses tasks. AVAILABILITY: The source code, pretrained and finetuned model for DNABERT are available at GitHub https://github.com/jerryji1993/DNABERT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Achieving a near complete understanding of how the genome of an individual affects the phenotypes of that individual requires deciphering the order of variations along homologous chromosomes in species with diploid genomes. However, true diploid assembly of long-range haplotypes remains challenging. RESULTS: To address this, we have developed Haplotype-resolved Assembly for Synthetic long reads using a Trio-binning strategy, or HAST, which uses parental information to classify reads into maternal or paternal. Once sorted, these reads are used to independently de novo assemble the parent-specific haplotypes. We applied HAST to co-barcoded second-generation sequencing data from an Asian individual, resulting in a haplotype assembly covering 94.7% of the reference genome with a scaffold N50 longer than 11 Mb. The high haplotyping precision (∼99.7%) and recall (∼95.9%) represents a substantial improvement over the commonly used tool for assembling co-barcoded reads (Supernova), and is comparable to a trio-binning-based third generation long-read based assembly method (TrioCanu) but with a significantly higher single-base accuracy (up to 99.99997% (Q65)). This makes HAST a superior tool for accurate haplotyping and future haplotype-based studies. AVAILABILITY: The code of the analysis is available at https://github.com/BGI-Qingdao/HAST. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Predicting the folding dynamics of RNAs is a computationally difficult problem, first and foremost due to the combinatorial explosion of alternative structures in the folding space. Abstractions are therefore needed to simplify downstream analyses, and thus make them computationally tractable. This can be achieved by various structure sampling algorithms. However, current sampling methods are still time consuming and frequently fail to represent key elements of the folding space. METHOD: We introduce RNAxplorer, a novel adaptive sampling method to efficiently explore the structure space of RNAs. RNAxplorer uses dynamic programming to perform an efficient Boltzmann sampling in the presence of guiding potentials, which are accumulated into pseudo-energy terms and reflect similarity to already well-sampled structures. This way, we effectively steer sampling towards underrepresented or unexplored regions of the structure space. RESULTS: We developed and applied different measures to benchmark our sampling methods against its competitors. Most of the measures show that RNAxplorer produces more diverse structure samples, yields rare conformations that may be inaccessible to other sampling methods and is better at finding the most relevant kinetic traps in the landscape. Thus, it produces a more representative coarse graining of the landscape, which is well suited to subsequently compute better approximations of RNA folding kinetics. AVAILABILITY: https://github.com/ViennaRNA/RNAxplorer/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: In mass spectrometry-based proteomics, accurate peptide masses improve identifications, alignment and quantitation. Getting the most out of any instrument therefore requires proper calibration. Here we present a new stand-alone software, mzRecal, for universal automatic recalibration of data from all common mass analyzers using standard open formats and based on physical principles. AVAILABILITY AND IMPLEMENTATION: mzRecal is implemented in Go and freely available on https://github.com/524D/mzRecal. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Detailed mechanistic models of biological processes can pose significant challenges for analysis and parameter estimations due to the large number of equations used to track the dynamics of all distinct configurations in which each involved biochemical species can be found. Model reduction can help tame such complexity by providing a lower-dimensional model in which each macro-variable can be directly related to the original variables. RESULTS: We present CLUE, an algorithm for exact model reduction of systems of polynomial differential equations by constrained linear lumping. It computes the smallest dimensional reduction as a linear mapping of the state space such that the reduced model preserves the dynamics of user-specified linear combinations of the original variables. Even though CLUE works with nonlinear differential equations, it is based on linear algebra tools, which makes it applicable to high-dimensional models. Using case studies from the literature, we show how CLUE can substantially lower model dimensionality and help extract biologically intelligible insights from the reduction. AVAILABILITY: An implementation of the algorithm and relevant resources to replicate the experiments herein reported are freely available for download at https://github.com/pogudingleb/CLUE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

With the advance of genomic sequencing techniques, chromatin accessible regions, transcription factor binding sites and epigenetic modifications can be identified at genome-wide scale. Conventional analyses focus on the gene regulation at proximal regions; however, distal regions are usually less focused, largely due to the lack of reliable tools to link these regions to coding genes. In this study, we introduce RAD (Region Associated Differentially expressed genes), a user-friendly web tool to identify both proximal and distal region associated differentially expressed genes (DEGs). With DEGs and genomic regions of interest (gROI) as input, RAD maps the up- and down-regulated genes associated with any gROI and helps researchers to infer the regulatory function of these regions based on the distance of gROI to differentially expressed genes. RAD includes visualization of the results and statistical inference for significance. AVAILABILITY: RAD is implemented with Python 3.7 and run on a Nginx server. RAD is freely available at http://labw.org/rad as online web service. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome-wide association studies (GWAS) have identified thousands of common trait-associated genetic variants but interpretation of their function remains challenging. These genetic variants can overlap the binding sites of transcription factors (TFs) and therefore could alter gene expression. However, we currently lack a systematic understanding on how this mechanism contributes to phenotype. RESULTS: We present Motif-Raptor, a TF-centric computational tool that integrates sequence-based predictive models, chromatin accessibility, gene expression datasets and GWAS summary statistics to systematically investigate how TF function is affected by genetic variants. Given trait associated non-coding variants, Motif-Raptor can recover relevant cell types and critical TFs to drive hypotheses regarding their mechanism of action. We tested Motif-Raptor on complex traits such as rheumatoid arthritis and red blood cell count and demonstrated its ability to prioritize relevant cell types, potential regulatory TFs and non-coding SNPs which have been previously characterized and validated. AVAILABILITY: Motif-Raptor is freely available as a Python package at: https://github.com/pinellolab/MotifRaptor. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Biomolecular structures come in multiple representations and diverse data formats. Their incompatibility with the requirements of data analysis programs significantly hinders the analytics and the creation of new structure-oriented bioinformatic tools. Therefore, the need for robust libraries of data processing functions is still growing. RESULTS: BioCommons is an open-source, Java library for structural bioinformatics. It contains many functions working with the 2D and 3D structures of biomolecules, with a particular emphasis on RNA. AVAILABILITY: The library is available in Maven Central Repository and its source code is hosted on GitHub: https://github.com/tzok/BioCommons. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Many tools can reconstruct viral sequences based on next generation sequencing reads. Although existing tools effectively recover local regions, their accuracy suffers when reconstructing the whole viral genomes (strains). Moreover, they consume significant memory when the sequencing coverage is high or when the genome size is large. We present WgLink to meet this challenge. WgLink takes local reconstructions produced by other tools as input and patches the resulting segments together into coherent whole-genome strains. We accomplish this using an L0+L1-regularized regression synthesizing variant allele frequency data with physical linkage between multiple variants spanning multiple regions simultaneously. WgLink achieves higher accuracy than existing tools both on simulated and real data sets while using significantly less memory (RAM) and fewer CPU hours. AVAILABILITY: Source code and binaries are freely available at https://github.com/theLongLab/wglink. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Compared with the second generation sequencing technologies, the third generation sequencing technologies allows us to obtain longer reads (average ∼10kbps, maximum 900kbps), but brings a higher error rate (∼15% error rate). Nanopolish is a variant and methylation detection tool based on Hidden Markov Model (HMM), which uses Oxford Nanopore sequencing data for signal-level analysis. Nanopolish can greatly improve the accuracy of assembly, whereas it is limited by long running time since most executive parts of Nanopolish is a serial and computationally expensive process. RESULTS: In this paper, we present an effective polishing tool, Multithreading Nanopolish (MultiNanopolish), which decomposes the whole process of iterative calculation in Nanopolish into small independent calculation tasks, making it possible to run this process in the parallel mode. Experimental results show that MultiNanopolish reduces running time by 50% with read-uncorrected assembler (Miniasm) and 20% with read-corrected assembler (Canu and Flye) based on 40 threads mode compared to the original Nanopolish. AVAILABILITY: MultiNanopolish is available at GitHub: https://github.com/BioinformaticsCSU/MultiNanopolish. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The retrieval of a single gene sequence and context from completely sequenced bacterial and archaeal genomes constitutes an intimidating task for the wet bench biologist. Existing web-based genome browsers are either too complex for routine use or only provide a subset of the available prokaryotic genomes. RESULTS: We have developed BAGET 2.0 (Bacterial and Archaeal Gene Exploration Tool), an updated web service granting access in just three mouse clicks to the sequence and synteny of any gene from completely sequenced bacteria and archaea. User-provided annotated genomes can be processed as well. BAGET 2.0 relies on a local database updated on a daily basis. AVAILABILITY AND IMPLEMENTATION: BAGET 2.0 befits all current browsers such as Chrome, Firefox, Edge, Opera and Safari. Internet Explorer 11 is supported. BAGET 2.0 is freely accessible at https://archaea.i2bc.paris-saclay.fr/baget/.

MOTIVATION: Many real-world biomedical interactions such as 'gene-disease', 'disease-symptom', and 'drug-target' are modeled as a bipartite network structure. Learning meaningful representations for such networks is a fundamental problem in the research area of Network Representation Learning (NRL). NRL approaches aim to translate the network structure into low-dimensional vector representations that are useful to a variety of biomedical applications. Despite significant advances, the existing approaches still have certain limitations. First, a majority of these approaches do not model the unique topological properties of bipartite networks. Consequently, their straightforward application to the bipartite graphs yields unsatisfactory results. Second, the existing approaches typically learn representations from static networks. This is limiting for the biomedical bipartite networks that evolve at a rapid pace, and thus necessitate the development of approaches that can update the representations in an online fashion. RESULTS: In this research, we propose a novel representation learning approach that accurately preserves the intricate bipartite structure, and efficiently updates the node representations. Specifically, we design a customized autoencoder that captures the proximity relationship between nodes participating in the bipartite bicliques (2 × 2 sub-graph), while preserving both the global and local structures. Moreover, the proposed structure-preserving technique is carefully interleaved with the central tenets of continual machine learning to design an incremental learning strategy that updates the node representations in an online manner. Taken together, the proposed approach produces meaningful representations with high fidelity and computational efficiency. Extensive experiments conducted on several biomedical bipartite networks validate the effectiveness and rationality of the proposed approach. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Hematopoietic stem cells (HSCs) give rise to all blood cells and play a vital role throughout the whole lifespan through their pluripotency and self-renewal properties. Accurately identifying the stages of early HSCs is extremely important, as it may open up new prospects for extracorporeal blood research. Existing experimental techniques for identifying the early stages of HSCs development are time-consuming and expensive. Machine learning has shown its excellence in massive single-cell data processing and it is desirable to develop related computational models as good complements to experimental techniques. RESULTS: In this study, we presented a novel predictor called eHSCPr specifically for predicting the early stages of HSCs development. To reveal the distinct genes at each developmental stage of HSCs, we compared F-score with three state-of-art differential gene selection methods (limma, DESeq2, edgeR) and evaluated their performance. F-score captured the more critical surface markers of endothelial cells and hematopoietic cells, and the area under receiver operating characteristic curve (ROC) value was 0.987. Based on SVM, the 10-fold cross-validation accuracy of eHSCpr in the independent dataset and the training dataset reached 94.84% and 94.19%, respectively. Importantly, we performed transcription analysis on the F-score gene set, which indeed further enriched the signal markers of HSCs development stages. eHSCPr can be a powerful tool for predicting early stages of HSCs development, facilitating hypothesis-driven experimental design and providing crucial clues for the in vitro blood regeneration studies. AVAILABILITY: http://bioinfor.imu.edu.cn/ehscpr. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Many recent advancements in single molecule localisation microscopy exploit the stochastic photo-switching of fluorophores to reveal complex cellular structures beyond the classical diffraction limit. However, this same stochasticity makes counting the number of molecules to high precision extremely challenging, preventing key insight into the cellular structures and processes under observation. RESULTS: Modelling the photo-switching behaviour of a fluorophore as an unobserved continuous time Markov process transitioning between a single fluorescent and multiple dark states, and fully mitigating for missed blinks and false positives, we present a method for computing the exact probability distribution for the number of observed localisations from a single photo-switching fluorophore. This is then extended to provide the probability distribution for the number of localisations in a dSTORM experiment involving an arbitrary number of molecules. We demonstrate that when training data is available to estimate photoswitching rates, the unknown number of molecules can be accurately recovered from the posterior mode of the number of molecules given the number of localisations. Finally, we demonstrate the method on experimental data by quantifying the number of adapter protein Linker for Activation of T cells (LAT) on the cell surface of the T cell immunological synapse. AVAILABILITY: Software available at https://github.com/lp1611/mol_count_dstorm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A global effort is underway to identify compounds for the treatment of COVID-19. Since de novo compound design is an extremely long, time-consuming, and expensive process, efforts are underway to discover existing compounds that can be repurposed for COVID-19 and new viral diseases. MODEL: We propose a machine learning representation framework that uses deep learning induced vector embeddings of compounds and viral proteins as features to predict compound-viral protein activity. The prediction model in-turn uses a consensus framework to rank approved compounds against viral proteins of interest. RESULTS: Our consensus framework achieves a highmean Pearson correlation of 0.916, mean R2 of 0.840 and a low mean squared error of 0.313 for the task of compound-viral protein activity prediction on an independent test set. As a use case, we identify a ranked list of 47 compounds common to three main proteins of SARS-COV-2 virus (PL-PRO, 3CL-PRO and Spike protein) as potential targets including 21 antivirals, 15 anticancer, 5 antibiotics and 6 other investigationalhuman compounds.We performadditional molecular docking simulations to demonstrate thatmajority of these compounds have low binding energies and thus high binding affinity with the potential to be effective against the SARS-COV-2 virus. AVAILABILITY: All the source code and data is available at: https://github.com/raghvendra5688/Drug-Repurposing and https://dx.doi.org/10.17632/8rrwnbcgmx.3. We also implemented a web-server at: https://machinelearning-protein.qcri.org/index.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Reliable predictive models of protein-ligand binding affinity are required in many areas of biomedical research. Accurate prediction based on current descriptors or molecular fingerprints remains a challenge. We develop novel interaction fingerprints (IFPs) to encode protein-ligand interactions and use them to improve the prediction. RESULTS: Proteo-chemometrics IFPs (PrtCmm IFPs) formed by combining extended connectivity fingerprints (ECFPs) with the proteo-chemometrics concept, were developed. Combining PrtCmm IFPs with machine-learning models led to efficient scoring models, which were validated on the PDBbind v2019 core set and CSAR-HiQ sets. The PrtCmm IFP Score outperformed several other models in predicting protein-ligand binding affinities. Besides, conventional ECFPs were simplified to generate new IFPs, which provided consistent but faster predictions. The relationship between the base atom properties of ECFPs and the accuracy of predictions was also investigated. AVAILABILITY: PrtCmm IFP has been implemented in the IFP Score Toolkit on github https://github.com/debbydanwang/IFPscore. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Long non-coding RNAs (lncRNAs) are generally expressed in a tissue-specific way, and subcellular localizations of lncRNAs depend on the tissues or cell lines that they are expressed. Previous computational methods for predicting subcellular localizations of lncRNAs do not take this characteristic into account, they train a unified machine learning model for pooled lncRNAs from all available cell lines. It is of importance to develop a cell-line-specific computational method to predict lncRNA locations in different cell lines. RESULTS: In this study, we present an updated cell-line-specific predictor lncLocator 2.0, which trains an end-to-end deep model per cell line, for predicting lncRNA subcellular localization from sequences.We first construct benchmark datasets of lncRNA subcellular localizations for 15 cell lines. Then we learn word embeddings using natural language models, and these learned embeddings are fed into convolutional neural network, long short-term memory and multilayer perceptron to classify subcellular localizations. lncLocator 2.0 achieves varying effectiveness for different cell lines and demonstrates the necessity of training cell-line-specific models. Furthermore, we adopt Integrated Gradients to explain the proposed model in lncLocator 2.0, and find some potential patterns that determine the subcellular localizations of lncRNAs, suggesting that the subcellular localization of lncRNAs is linked to some specific nucleotides. AVAILABILITY: The lncLocator 2.0 is available at www.csbio.sjtu.edu.cn/bioinf/lncLocator2 and the source code can be found at https://github.com/Yang-J-LIN/lncLocator2. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome data is a subject of study for both biology and computer science since the start of the Human Genome Project in 1990. Since then, genome sequencing for medical and social purposes becomes more and more available and affordable. Genome data can be shared on public websites or with service providers. However, this sharing compromises the privacy of donors even under partial sharing conditions. We mainly focus on the liability aspect ensued by the unauthorized sharing of these genome data. One of the techniques to address the liability issues in data sharing is the watermarking mechanism. RESULTS: To detect malicious correspondents and service providers (SPs) -whose aim is to share genome data without individuals' consent and undetected-, we propose a novel watermarking method on sequential genome data using belief propagation algorithm. In our method, we have two criteria to satisfy. (i) Embedding robust watermarks so that the malicious adversaries can not temper the watermark by modification and are identified with high probability (ii) Achieving ε-local differential privacy in all data sharings with SPs. For the preservation of system robustness against single SP and collusion attacks, we consider publicly available genomic information like Minor Allele Frequency, Linkage Disequilibrium, Phenotype Information and Familial Information. Our proposed scheme achieves 100% detection rate against the single SP attacks with only 3% watermark length. For the worst case scenario of collusion attacks (50% of SPs are malicious), 80% detection is achieved with 5% watermark length and 90% detection is achieved with 10% watermark length. For all cases, the impact of ε on precision remained negligible and high privacy is ensured. AVAILABILITY: https://github.com/acoksuz/PPRW_SGD_BPLDP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Gene-gene co-expression networks (GCN) are of biological interest for the useful information they provide for understanding gene-gene interactions. The advent of single cell RNA-sequencing allows us to examine more subtle gene co-expression occurring within a cell type. Many imputation and denoising methods have been developed to deal with the technical challenges observed in single cell data; meanwhile, several simulators have been developed for benchmarking and assessing these methods. Most of these simulators, however, either do not incorporate gene co-expression or generate co-expression in an inconvenient manner. RESULTS: Therefore, with the focus on gene co-expression, we propose a new simulator, ESCO, which adopts the idea of the copula to impose gene co-expression, while preserving the highlights of available simulators, which perform well for simulation of gene expression marginally. Using ESCO, we assess the performance of imputation methods on GCN recovery and find that imputation generally helps GCN recovery when the data are not too sparse, and the ensemble imputation method works best among leading methods. In contrast, imputation fails to help in the presence of an excessive fraction of zero counts, where simple data aggregating methods are a better choice. These findings are further verified with mouse and human brain cell data. AVAILABILITY: The ESCO implementation is available as R package ESCO. Users can either download the development version via github (https://github.com/JINJINT/ESCO) or the archived version via Zenodo (https://zenodo.org/record/4455890). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: We previously described the construction and characterization of generic and reusable blood transcriptional module repertoires. More recently we released a third iteration ("BloodGen3" module repertoire) that comprises 382 functionally annotated gene sets (modules) and encompasses 14,168 transcripts. Custom bioinformatic tools are needed to support downstream analysis, visualization and interpretation relying on such fixed module repertoires. RESULTS: We have developed and describe here a R package, BloodGen3Module. The functions of our package permit group comparison analyses to be performed at the module-level, and to display the results as annotated fingerprint grid plots. A parallel workflow for computing module repertoire changes for individual samples rather than groups of samples is also available; these results are displayed as fingerprint heatmaps. An illustrative case is used to demonstrate the steps involved in generating blood transcriptome repertoire fingerprints of septic patients. Taken together, this resource could facilitate the analysis and interpretation of changes in blood transcript abundance observed across a wide range of pathological and physiological states. AVAILABILITY: The BloodGen3Module package and documentation are freely available from Github: https://github.com/Drinchai/BloodGen3Module. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome-wide association studies have successfully identified multiple independent genetic loci that harbour variants associated with human traits and diseases, but the exact causal genes are largely unknown. Common genetic risk variants are enriched in non-protein-coding regions of the genome and often affect gene expression (expression quantitative trait loci, eQTL) in a tissue-specific manner. To address this challenge, we developed a methodological framework, E-MAGMA, which converts genome-wide association summary statistics into gene-level statistics by assigning risk variants to their putative genes based on tissue-specific eQTL information. RESULTS: We compared E-MAGMA to three eQTL informed gene-based approaches using simulated phenotype data. Phenotypes were simulated based on eQTL reference data using GCTA for all genes with at least one eQTL at chromosome 1. We performed 10 simulations per gene. The eQTL-h2 (i.e., the proportion of variation explained by the eQTLs) was set at 1%, 2%, and 5%. We found E-MAGMA outperforms other gene-based approaches across a range of simulated parameters (e.g. the number of identified causal genes). When applied to genome-wide association summary statistics for five neuropsychiatric disorders, E-MAGMA identified more putative candidate causal genes compared to other eQTL-based approaches. By integrating tissue-specific eQTL information, these results show E-MAGMA will help to identify novel candidate causal genes from genome-wide association summary statistics and thereby improve the understanding of the biological basis of complex disorders. AVAILABILITY: A tutorial and input files are made available in a github repository: https://github.com/eskederks/eMAGMA-tutorial. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In genomic studies, identifying biomarkers associated with a variable of interest is a major concern in biomedical research. Regularized approaches are classically used to perform variable selection in high-dimensional linear models. However, these methods can fail in highly correlated settings. RESULTS: We propose a novel variable selection approach called WLasso, taking these correlations into account. It consists in rewriting the initial high-dimensional linear model to remove the correlation between the biomarkers (predictors) and in applying the generalized Lasso criterion. The performance of WLasso is assessed using synthetic data in several scenarios and compared with recent alternative approaches. The results show that when the biomarkers are highly correlated, WLasso outperforms the other approaches in sparse high-dimensional frameworks. The method is also illustrated on publicly available gene expression data in breast cancer. AVAILABILITY: Our method is implemented in the WLasso R package which is available from the Comprehensive R Archive Network (CRAN). SUPPLEMENTARY INFORMATION: Supplementary material is available at Bioinformatics online.

MOTIVATION: Cancer is one of the most prevalent diseases in theworld. Tumors arise due to important genes changing their activity, e.g., when inhibited or over-expressed. But these gene perturbations are difficult to observe directly. Molecular profiles of tumors can provide indirect evidence of gene perturbations. However, inferring perturbation profiles from molecular alterations is challenging due to error-prone molecular measurements and incomplete coverage of all possible molecular causes of gene perturbations. RESULTS: We have developed a novel mathematical method to analyze cancer driver genes and their patient-specific perturbation profiles. We combine genetic aberrations with gene expression data in a causal network derived across patients to infer unobserved perturbations. We show that our method can predict perturbations in simulations, CRISPR perturbation screens, and breast cancer samples from The Cancer Genome Atlas. AVAILABILITY: The method is available as the R-package nempi at https://github.com/cbg-ethz/nempi and http://bioconductor.org/packages/nempi. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Synthetic Lethality (SL) plays an increasingly critical role in the targeted anticancer therapeutics. In addition, identifying SL interactions can create opportunities to selectively kill cancer cells without harming normal cells. Given the high cost of wet-lab experiments, in silico prediction of SL interactions as an alternative can be a rapid and cost-effective way to guide the experimental screening of candidate SL pairs. Several matrix factorization-based methods have recently been proposed for human SL prediction. However, they are limited in capturing the dependencies of neighbors. In addition, it is also highly challenging to make accurate predictions for new genes without any known SL partners. RESULTS: In this work, we propose a novel graph contextualized attention network named GCATSL to learn gene representations for SL prediction. First, we leverage different data sources to construct multiple feature graphs for genes, which serve as the feature inputs for our GCATSL method. Second, for each feature graph, we design node-level attention mechanism to effectively capture the importance of local and global neighbors and learn local and global representations for the nodes, respectively. We further exploit multi-layer perceptron (MLP) to aggregate the original features with the local and global representations and then derive the feature-specific representations. Third, to derive the final representations, we design feature-level attention to integrate feature-specific representations by taking the importance of different feature graphs into account. Extensive experimental results on three datasets under different settings demonstrated that our GCATSL model outperforms 14 state-of-the-art methods consistently. In addition, case studies further validated the effectiveness of our proposed model in identifying novel SL pairs. AVAILABILITY: Python codes and dataset are freely available on GitHub (https://github.com/longyahui/GCATSL) and Zenodo (https://zenodo.org/record/4522679) under the MIT license.

MOTIVATION: Cross-(multi)platform normalization of gene-expression microarray data remains an unresolved issue. Despite the existence of several algorithms, they are either constrained by the need to normalize all samples of all platforms together, compromising scalability and reuse, by adherence to the platforms of a specific provider, or simply by poor performance. In addition, many of the methods presented in the literature have not been specifically tested against multi-platform data and/or other methods applicable in this context. Thus, we set out to develop a normalization algorithm appropriate for gene-expression studies based on multiple, potentially large microarray sets collected along multiple platforms and at different times, applicable in systematic studies aimed at extracting knowledge from the wealth of microarray data available in public repositories; for example, for the extraction of Real-World Data to complement data from Randomized Controlled Trials. Our main focus or criterion for performance was on the capacity of the algorithm to properly separate samples from different biological groups. RESULTS: We present CuBlock, an algorithm addressing this objective, together with a strategy to validate cross-platform normalization methods. To validate the algorithm and benchmark it against existing methods, we used two distinct data sets, one specifically generated for testing and standardization purposes and one from an actual experimental study. Using these data sets, we benchmarked CuBlock against ComBat (Johnson et al., 2007), UPC (Piccolo et al., 2013), YuGene (Lê Cao et al., 2014), DBNorm (Meng et al., 2017), Shambhala (Borisov et al., 2019) and a simple log2 transform as reference. We note that many other popular normalization methods are not applicable in this context. CuBlock was the only algorithm in this group that could always and clearly differentiate the underlying biological groups after mixing the data, from up to six different platforms in this study. AVAILABILITY: CuBlock can be downloaded from https://www.mathworks.com/matlabcentral/fileexchange/77882-cublock. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Off-target predictions are crucial in gene editing research. Recently, significant progress has been made in the field of prediction of off-target mutations, particularly with CRISPR-Cas9 data, thanks to the use of deep learning. CRISPR-Cas9 is a gene editing technique which allows manipulation of DNA fragments. The sgRNA-DNA (single guide RNA-DNA) sequence encoding for deep neural networks, however, has a strong impact on the prediction accuracy. We propose a novel encoding of sgRNA-DNA sequences that aggregates sequence data with no loss of information. RESULTS: In our experiments, we compare the proposed sgRNA-DNA sequence encoding applied in a deep learning prediction framework with state-of-the-art encoding and prediction methods. We demonstrate the superior accuracy of our approach in a simulation study involving Feedforward Neural Networks (FNNs), Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) as well as the traditional Random Forest (RF), Naive Bayes (NB) and Logistic Regression (LR) classifiers.We highlight the quality of our results by building several FNNs, CNNs and RNNs with various layer depths and performing predictions on two popular CRISPOR and GUIDE-seq gene editing data sets. In all our experiments, the new encoding led to more accurate off-target prediction results, providing an improvement of the area under the Receiver Operating Characteristic (ROC) curve up to 35%. AVAILABILITY: The code and data used in this study are available at: https://github.com/dagrate/dl-offtarget.

We present Genozip, a universal and fully featured compression software for genomic data. Genozip is designed to be a general-purpose software and a development framework for genomic compression by providing five core capabilities - universality (support for all common genomic file formats), high compression ratios, speed, feature-richness, and extensibility. Genozip delivers high-performance compression for widely-used genomic data formats in genomics research, namely FASTQ, SAM/BAM/CRAM, VCF, GVF, FASTA, PHYLIP, and 23andMe formats. Our test results show that Genozip is fast and achieves greatly improved compression ratios, even when the files are already compressed. Further, Genozip is architected with a separation of the Genozip Framework from file-format-specific Segmenters and data-type-specific Codecs. With this, we intend for Genozip to be a general-purpose compression platform where researchers can implement compression for additional file formats, as well as new codecs for data types or fields within files, in the future. We anticipate that this will ultimately increase the visibility and adoption of these algorithms by the user community, thereby accelerating further innovation in this space. Availability: Genozip is written in C. The code is open-source and available on GitHub (https://github.com/divonlan/genozip). The package is free for non-commercial use. It is distributed as a Docker container on DockerHub and through the conda package manager. Genozip is tested on Linux, Mac, and Windows. Supplementary information: Supplementary data are available at Bioinformatics online.

MOTIVATION: Linking microbial community members to their ecological functions is a central goal of environmental microbiology. When assigned taxonomy, amplicon sequences of metabolic marker genes can suggest such links, thereby offering an overview of the phylogenetic structure underpinning particular ecosystem functions. However, inferring microbial taxonomy from metabolic marker gene sequences remains a challenge, particularly for the frequently sequenced nitrogen fixation marker gene, nitrogenase reductase (nifH). Horizontal gene transfer in recent nifH evolutionary history can confound taxonomic inferences drawn from the pairwise identity methods used in existing software. Other methods for inferring taxonomy are not standardized and require manual inspection that is difficult to scale. RESULTS: We present Phylogenetic Placement for Inferring Taxonomy (PPIT), an R package that infers microbial taxonomy from nifH amplicons using both phylogenetic and sequence identity approaches. After users place query sequences on a reference nifH gene tree provided by PPIT (n = 6317 full-length nifH sequences), PPIT searches the phylogenetic neighborhood of each query sequence and attempts to infer microbial taxonomy. An inference is drawn only if references in the phylogenetic neighborhood are: (1) taxonomically consistent and (2) share sufficient pairwise identity with the query, thereby avoiding erroneous inferences due to known horizontal gene transfer events. We find that PPIT returns a higher proportion of correct taxonomic inferences than BLAST-based approaches at the cost of fewer total inferences. We demonstrate PPIT on deep-sea sediment and find that Deltaproteobacteria are the most abundant potential diazotrophs. Using this dataset we show that emending PPIT inferences based on visual inspection of query sequence placement can achieve taxonomic inferences for nearly all sequences in a query set. We additionally discuss how users can apply PPIT to the analysis of other marker genes. AVAILABILITY: PPIT is freely available to non-commercial users at https://github.com/bkapili/ppit. Installation includes a vignette that demonstrates package use and reproduces the nifH amplicon analysis discussed here. The raw nifH amplicon sequence data have been deposited in the GenBank, EMBL, and DDBJ databases under BioProject number PRJEB37167. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Transferring knowledge between species is challenging: different species contain distinct proteomes and cellular architectures, which cause their proteins to carry out different functions via different interaction networks. Many approaches to protein functional annotation use sequence similarity to transfer knowledge between species. These approaches cannot produce accurate predictions for proteins without homologues of known function, as many functions require cellular context for meaningful prediction. To supply this context, network-based methods use protein-protein interaction (PPI) networks as a source of information for inferring protein function and have demonstrated promising results in function prediction. However, most of these methods are tied to a network for a single species, and many species lack biological networks. RESULTS: In this work, we integrate sequence and network information across multiple species by computing IsoRank similarity scores to create a meta-network profile of the proteins of multiple species. We use this integrated multispecies meta-network as input to train a maxout neural network with Gene Ontology terms as target labels. Our multispecies approach takes advantage of more training examples, and consequently leads to significant improvements in function prediction performance compared to two network-based methods, a deep learning sequence-based method, and the BLAST annotation method used in the Critial Assessment of Functional Annotation. We are able to demonstrate that our approach performs well even in cases where a species has no network information available: when an organism's PPI network is left out we can use our multi-species method to make predictions for the left-out organism with good performance. AVAILABILITY: The code is freely available at https://github.com/nowittynamesleft/NetQuilt. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Inferring gene regulatory networks (GRNs) from high-throughput data is an important and challenging problem in systems biology. Although numerous GRN methods have been developed, most have focused on the verification of the specific data set. However, it is difficult to establish directed topological networks that are both suitable for time-series and non-time-series datasets due to the complexity and diversity of biological networks. RESULTS: Here, we proposed a novel method, GNIPLR (Gene networks inference based on projection and lagged regression) to infer GRNs from time-series or non-time-series gene expression data. GNIPLR projected gene data twice using the LASSO projection (LSP) algorithm and the linear projection (LP) approximation to produce a linear and monotonous pseudo-time series, and then determined the direction of regulation in combination with lagged regression analyses. The proposed algorithm was validated using simulated and real biological data. Moreover, we also applied the GNIPLR algorithm to the liver hepatocellular carcinoma (LIHC) and bladder urothelial carcinoma (BLCA) cancer expression datasets. These analyses revealed significantly higher accuracy and AUC values than other popular methods. AVAILABILITY: The GNIPLR tool is freely available at https://github.com/zyllluck/GNIPLR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The gut microbiota is the human body's largest population of microorganisms that interact with human intestinal cells. They use ingested nutrients for fundamental biological processes and have important impacts on human physiology, immunity, and metabolome in the gastrointestinal tract. RESULTS: Here, we present M2R, a Python add-on to cobrapy that allows incorporating information about the gut microbiota metabolism models to human genome-scale metabolic models (GEMs) like RECON3D. The idea behind the software is to modify the lower bounds of the exchange reactions in the model using aggregated in- and out-fluxes from selected microbes. M2R enables users to quickly and easily modify the pool of the metabolites that enter and leave the GEM, which is particularly important for those looking into an analysis of the metabolic interaction between the gut microbiota and human cells and its dysregulation. AVAILABILITY AND IMPLEMENTATION: M2R is freely available under an MIT License at https://github.com/e-weglarz-tomczak/m2r. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Hi-C matrices are cornerstones for qualitative and quantitative studies of genome folding, from its territorial organization to compartments and topological domains. The high dynamic range of genomic distances probed in Hi-C assays reflects in an inherent stochastic background of the interactions matrices, which inevitably convolve the features of interest with largely non-specific ones. RESULTS: Here we introduce and discuss essHi-C, a method to isolate the specific, or essential component of Hi-C matrices from the non-specific portion of the spectrum that is compatible with random matrices. Systematic comparisons show that essHi-C improves the clarity of the interaction patterns, enhances the robustness against sequencing depth of topologically associating domains identification, allows the unsupervised clustering of experiments in different cell lines and recovers the cell-cycle phasing of single-cells based on Hi-C data. Thus, essHi-C provides means for isolating significant biological and physical features from Hi-C matrices. AVAILABILITY: The essHi-C software package is available at: https://github.com/stefanofranzini/essHIC . SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: As machine learning has become increasingly popular over the last few decades, so too has the number of machine learning interfaces for implementing these models. Whilst many R libraries exist for machine learning, very few offer extended support for survival analysis. This is problematic considering its importance in fields like medicine, bioinformatics, economics, engineering, and more. mlr3proba provides a comprehensive machine learning interface for survival analysis and connects with mlr3's general model tuning and benchmarking facilities to provide a systematic infrastructure for survival modeling and evaluation. AVAILABILITY: mlr3proba is available under an LGPL-3 license on CRAN and at https://github.com/mlr-org/mlr3proba, with further documentation at https://mlr3book.mlr-org.com/survival.html.

MOTIVATION: Data generated from high-throughput technologies such as sequencing, microarray and bead-chip technologies are unavoidably affected by batch effects. Large effort has been put into developing methods for correcting these effects. Often, batch effect correction and hypothesis testing cannot be done with one single model, but are done successively with separate models in data analysis pipelines. This potentially leads to biased p-values or false discovery rates due to the influence of batch effect correction on the data. RESULTS: We present a novel approach for estimating null distributions of test statistics in data analysis pipelines where batch effect correction is followed by linear model analysis. The approach is based on generating simulated datasets by random rotation and thereby retains the dependence structure of genes adequately. This allows estimating null distributions of dependent test statistics and thus the calculation of resampling based p-values and false discovery rates following batch effect correction while maintaining the alpha level. AVAILABILITY: The described methods are implemented as randRotation package on Bioconductor: https://bioconductor.org/packages/randRotation/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Even within well studied organisms, many genes lack useful functional annotations. One way to generate such functional information is to infer biological relationships between genes/proteins, using a network of gene coexpression data that includes functional annotations. However, the lack of trustworthy functional annotations can impede the validation of such networks. Hence, there is a need for a principled method to construct gene coexpression networks that capture biological information and are structurally stable even in the absence of functional information. RESULTS: We introduce the concept of signed distance correlation as a measure of dependency between two variables, and apply it to generate gene coexpression networks. Distance correlation offers a more intuitive approach to network construction than commonly used methods such as Pearson correlation and mutual information. We propose a framework to generate self-consistent networks using signed distance correlation purely from gene expression data, with no additional information. We analyse data from three different organisms to illustrate how networks generated with our method are more stable and capture more biological information compared to networks obtained from Pearson correlation or mutual information. SUPPLEMENTARY INFORMATION: Supplementary Information and code are available at Bioinformatics and https://github.com/javier-pardodiaz/sdcorGCN online.

MOTIVATION: Cancer cell heterogeneity can manifest genetically and phenotypically. Bioinformatics methods have been used to analyze complex genomics and transcriptomics data, but have not been well-established for analyzing biophysical data of phenotypically heterogeneous tumor cells. Here, we take an informatics approach to analyze the biophysical data of MDA-MB-231 cells, a widely used breast cancer cell line, during their spontaneous migration through confined environments. Experimentally, we vary the constriction microchannel geometries (wide channel, short constriction, and long constriction) and apply drug treatments. We find that cells in the short constriction are similar in morphology to the cells in the wide channel. However, their fluorescence profiles are comparable to those in the long constriction. We demonstrate that the cell migratory phenotype is correlated more to mitochondria in a non-confined environment and more to actin in a confined environment. We demonstrate that the cells' migratory phenotypes are altered by ciliobrevin D, a dynein inhibitor, in both confined and non-confined environments. Overall, our approach elucidates phenotypic heterogeneity in cancer cells under confined microenvironments at single-cell resolution. RESULTS: Here, we apply a bioinformatics approach to a single cell invasion assay. We demonstrate that this method can determine distinctions in morphology, cytoskeletal activities, and mitochondrial activities under various geometric constraints and for cells of different speeds. Our approach can be readily adapted to various heterogeneity studies for different types of input biophysical data. In addition, this approach can be applied to studies related to biophysical changes due to differences in external stimuli, such as treatment effects on cellular and subcellular activities, at single-cell resolution. Finally, as similar bioinformatics methods have been widely applied in studies of genetic heterogeneity, biophysical information extracted using this approach can be analyzed together with the genetic data to relate genetic and phenotypic heterogeneity. AVAILABILITY: The data that support the findings of this study are available from the corresponding author upon reasonable request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The principle of Breiman's random forest (RF) is to build and assemble complementary classification trees in a way that maximizes their variability. We propose a new type of random forest that disobeys Breiman's principles and involves building trees with no classification errors in very large quantities. We used a new type of decision tree that uses a neuron at each node as well as an in-innovative half Christmas tree structure. With these new RFs, we developed a score, based on a family of ten new statistical information criteria, called Nguyen information criteria (NICs), to evaluate the predictive qualities of features in three dimensions. RESULTS: The first NIC allowed the Akaike information criterion to be minimized more quickly than data obtained with the Gini index when the features were introduced in a logistic regression model. The selected features based on the NICScore showed a slight advantage compared to the support vector machines-recursive feature elimination (SVM-RFE) method. We demonstrate that the inclusion of artificial neurons in tree nodes allows a large number of classifiers in the same node to be taken into account simultaneously and results in perfect trees without classification errors. AVAILABILITY AND IMPLEMENTATION: The methods used to build the perfect trees in this article were implemented in the "ROP" R package, archived at https://cran.r-project.org/web/packages/ROP/index.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.