BACKGROUND: Except for bacteria, the taxonomic diversity of the human fecal metagenome has not been widely studied, despite the potential importance of viruses and eukaryotes. Widely used bioinformatic tools contain limited numbers of non-bacterial species in their databases compared to available genomic sequences and their methodologies do not favour classification of rare sequences which may represent only a small fraction of their parent genome. In seeking to optimise identification of non-bacterial species, we evaluated five widely-used metagenome classifier programs (BURST, Kraken2, Centrifuge, MetaPhlAn2 and CCMetagen) for their ability to correctly assign and count simulations of bacterial, viral and eukaryotic DNA sequence reads, including the effect of taxonomic order of analysis of bacteria, viruses and eukaryotes and the effect of sequencing depth. RESULTS: We found that the precision of metagenome classifiers varied significantly between programs and between taxonomic groups. When classifying viruses and eukaryotes, ordering the analysis such that bacteria were classified first significantly improved classification precision. Increasing sequencing depth decreased classification precision and did not improve recall of rare species. CONCLUSIONS: Choice of metagenome classifier program can have a marked effect on results with respect to precision of species assignment in different taxonomic groups. The order of taxonomic classification can markedly improve precision. Increasing sequencing depth can decrease classification precision and yields diminishing returns in probability of species detection.

BACKGROUND: Single-cell RNA sequencing (scRNA-Seq) experiments are gaining ground to study the molecular processes that drive normal development as well as the onset of different pathologies. Finding an effective and efficient low-dimensional representation of the data is one of the most important steps in the downstream analysis of scRNA-Seq data, as it could provide a better identification of known or putatively novel cell-types. Another step that still poses a challenge is the integration of different scRNA-Seq datasets. Though standard computational pipelines to gain knowledge from scRNA-Seq data exist, a further improvement could be achieved by means of machine learning approaches. RESULTS: Autoencoders (AEs) have been effectively used to capture the non-linearities among gene interactions of scRNA-Seq data, so that the deployment of AE-based tools might represent the way forward in this context. We introduce here scAEspy, a unifying tool that embodies: (1) four of the most advanced AEs, (2) two novel AEs that we developed on purpose, (3) different loss functions. We show that scAEspy can be coupled with various batch-effect removal tools to integrate data by different scRNA-Seq platforms, in order to better identify the cell-types. We benchmarked scAEspy against the most used batch-effect removal tools, showing that our AE-based strategies outperform the existing solutions. CONCLUSIONS: scAEspy is a user-friendly tool that enables using the most recent and promising AEs to analyse scRNA-Seq data by only setting up two user-defined parameters. Thanks to its modularity, scAEspy can be easily extended to accommodate new AEs to further improve the downstream analysis of scRNA-Seq data. Considering the relevant results we achieved, scAEspy can be considered as a starting point to build a more comprehensive toolkit designed to integrate multi single-cell omics.

BACKGROUND: Circular RNAs (circRNAs) are a class of single-stranded RNA molecules with a closed-loop structure. A growing body of research has shown that circRNAs are closely related to the development of diseases. Because biological experiments to verify circRNA-disease associations are time-consuming and wasteful of resources, it is necessary to propose a reliable computational method to predict the potential candidate circRNA-disease associations for biological experiments to make them more efficient. RESULTS: In this paper, we propose a double matrix completion method (DMCCDA) for predicting potential circRNA-disease associations. First, we constructed a similarity matrix of circRNA and disease according to circRNA sequence information and semantic disease information. We also built a Gauss interaction profile similarity matrix for circRNA and disease based on experimentally verified circRNA-disease associations. Then, the corresponding circRNA sequence similarity and semantic similarity of disease are used to update the association matrix from the perspective of circRNA and disease, respectively, by matrix multiplication. Finally, from the perspective of circRNA and disease, matrix completion is used to update the matrix block, which is formed by splicing the association matrix obtained in the previous step with the corresponding Gaussian similarity matrix. Compared with other approaches, the model of DMCCDA has a relatively good result in leave-one-out cross-validation and five-fold cross-validation. Additionally, the results of the case studies illustrate the effectiveness of the DMCCDA model. CONCLUSION: The results show that our method works well for recommending the potential circRNAs for a disease for biological experiments.

BACKGROUND: Even when microbial communities vary wildly in their taxonomic composition, their functional composition is often surprisingly stable. This suggests that a functional perspective could provide much deeper insight into the principles governing microbiome assembly. Much work to date analyzing the functional composition of microbial communities, however, relies heavily on inference from genomic features. Unfortunately, output from these methods can be hard to interpret and often suffers from relatively high error rates. RESULTS: We built and analyzed a domain-specific microbial trait database from known microbe-trait pairs recorded in the literature to better understand the functional composition of the human microbiome. Using a combination of phylogentically conscious machine learning tools and a network science approach, we were able to link particular traits to areas of the human body, discover traits that determine the range of body areas a microbe can inhabit, and uncover drivers of metabolic breadth. CONCLUSIONS: Domain-specific trait databases are an effective compromise between noisy methods to infer complex traits from genomic data and exhaustive, expensive attempts at database curation from the literature that do not focus on any one subset of taxa. They provide an accurate account of microbial traits and, by limiting the number of taxa considered, are feasible to build within a reasonable time-frame. We present a database specific for the human microbiome, in the hopes that this will prove useful for research into the functional composition of human-associated microbial communities.

BACKGROUND: Early detection of bladder cancer remains challenging because patients with early-stage bladder cancer usually have no incentive to take cytology or cystoscopy tests if they are asymptomatic. Our goal is to find non-invasive marker candidates that may help us gain insight into the metabolism of early-stage bladder cancer and be examined in routine health checks. RESULTS: We acquired urine samples from 124 patients diagnosed with early-stage bladder cancer or hernia (63 cancer patients and 61 controls). In which 100 samples were included in our marker discovery cohort, and the remaining 24 samples were included in our independent test cohort. We obtained metabolic profiles of 922 compounds of the samples by gas chromatography-mass spectrometry. Based on the metabolic profiles of the marker discovery cohort, we selected marker candidates using Wilcoxon rank-sum test with Bonferroni correction and leave-one-out cross-validation; we further excluded compounds detected in less than 60% of the bladder cancer samples. We finally selected eight putative markers. The abundance of all the eight markers in bladder cancer samples was high but extremely low in hernia samples. Moreover, the up-regulation of these markers might be in association with sugars and polyols metabolism. CONCLUSIONS: In the present study, comparative urine metabolomics selected putative metabolite markers for the detection of early-stage bladder cancer. The suggested relations between early-stage bladder cancer and sugars and polyols metabolism may create opportunities for improving the detection of bladder cancer.

BACKGROUND: The detection of genome variants, including point mutations, indels and structural variants, is a fundamental and challenging computational problem. We address here the problem of variant detection between two deep-sequencing (DNA-seq) samples, such as two human samples from an individual patient, or two samples from distinct bacterial strains. The preferred strategy in such a case is to align each sample to a common reference genome, collect all variants and compare these variants between samples. Such mapping-based protocols have several limitations. DNA sequences with large indels, aggregated mutations and structural variants are hard to map to the reference. Furthermore, DNA sequences cannot be mapped reliably to genomic low complexity regions and repeats. RESULTS: We introduce 2-kupl, a k-mer based, mapping-free protocol to detect variants between two DNA-seq samples. On simulated and actual data, 2-kupl achieves higher accuracy than other mapping-free protocols. Applying 2-kupl to prostate cancer whole exome sequencing data, we identify a number of candidate variants in hard-to-map regions and propose potential novel recurrent variants in this disease. CONCLUSIONS: We developed a mapping-free protocol for variant calling between matched DNA-seq samples. Our protocol is suitable for variant detection in unmappable genome regions or in the absence of a reference genome.

BACKGROUND: Long-read sequencing is revolutionizing genome assembly: as PacBio and Nanopore technologies become more accessible in technicity and in cost, long-read assemblers flourish and are starting to deliver chromosome-level assemblies. However, these long reads are usually error-prone, making the generation of a haploid reference out of a diploid genome a difficult enterprise. Failure to properly collapse haplotypes results in fragmented and structurally incorrect assemblies and wreaks havoc on orthology inference pipelines, yet this serious issue is rarely acknowledged and dealt with in genomic projects, and an independent, comparative benchmark of the capacity of assemblers and post-processing tools to properly collapse or purge haplotypes is still lacking. RESULTS: We tested different assembly strategies on the genome of the rotifer Adineta vaga, a non-model organism for which high coverages of both PacBio and Nanopore reads were available. The assemblers we tested (Canu, Flye, NextDenovo, Ra, Raven, Shasta and wtdbg2) exhibited strikingly different behaviors when dealing with highly heterozygous regions, resulting in variable amounts of uncollapsed haplotypes. Filtering reads generally improved haploid assemblies, and we also benchmarked three post-processing tools aimed at detecting and purging uncollapsed haplotypes in long-read assemblies: HaploMerger2, purge_haplotigs and purge_dups. CONCLUSIONS: We provide a thorough evaluation of popular assemblers on a non-model eukaryote genome with variable levels of heterozygosity. Our study highlights several strategies using pre and post-processing approaches to generate haploid assemblies with high continuity and completeness. This benchmark will help users to improve haploid assemblies of non-model organisms, and evaluate the quality of their own assemblies.

BACKGROUND: Quantitative proteomics studies are often used to detect proteins that are differentially expressed across different experimental conditions. Functional enrichment analyses are then typically used to detect annotations, such as biological processes that are significantly enriched among such differentially expressed proteins to provide insights into the molecular impacts of the studied conditions. While common, this analytical pipeline often heavily relies on arbitrary thresholds of significance. However, a functional annotation may be dysregulated in a given experimental condition, while none, or very few of its proteins may be individually considered to be significantly differentially expressed. Such an annotation would therefore be missed by standard approaches. RESULTS: Herein, we propose a novel graph theory-based method, PIGNON, for the detection of differentially expressed functional annotations in different conditions. PIGNON does not assess the statistical significance of the differential expression of individual proteins, but rather maps protein differential expression levels onto a protein-protein interaction network and measures the clustering of proteins from a given functional annotation within the network. This process allows the detection of functional annotations for which the proteins are differentially expressed and grouped in the network. A Monte-Carlo sampling approach is used to assess the clustering significance of proteins in an expression-weighted network. When applied to a quantitative proteomics analysis of different molecular subtypes of breast cancer, PIGNON detects Gene Ontology terms that are both significantly clustered in a protein-protein interaction network and differentially expressed across different breast cancer subtypes. PIGNON identified functional annotations that are dysregulated and clustered within the network between the HER2+, triple negative and hormone receptor positive subtypes. We show that PIGNON's results are complementary to those of state-of-the-art functional enrichment analyses and that it highlights functional annotations missed by standard approaches. Furthermore, PIGNON detects functional annotations that have been previously associated with specific breast cancer subtypes. CONCLUSION: PIGNON provides an alternative to functional enrichment analyses and a more comprehensive characterization of quantitative datasets. Hence, it contributes to yielding a better understanding of dysregulated functions and processes in biological samples under different experimental conditions.

BACKGROUND: Accurate prognosis and identification of cancer subtypes at molecular level are important steps towards effective and personalised treatments of breast cancer. To this end, many computational methods have been developed to use gene (mRNA) expression data for breast cancer subtyping and prognosis. Meanwhile, microRNAs (miRNAs) and long non-coding RNAs (lncRNAs) have been extensively studied in the last 2 decades and their associations with breast cancer subtypes and prognosis have been evidenced. However, it is not clear whether using miRNA and/or lncRNA expression data helps improve the performance of gene expression based subtyping and prognosis methods, and this raises challenges as to how and when to use these data and methods in practice. RESULTS: In this paper, we conduct a comparative study of 35 methods, including 12 breast cancer subtyping methods and 23 breast cancer prognosis methods, on a collection of 19 independent breast cancer datasets. We aim to uncover the roles of miRNAs and lncRNAs in breast cancer subtyping and prognosis from the systematic comparison. In addition, we created an R package, CancerSubtypesPrognosis, including all the 35 methods to facilitate the reproducibility of the methods and streamline the evaluation. CONCLUSIONS: The experimental results show that integrating miRNA expression data helps improve the performance of the mRNA-based cancer subtyping methods. However, miRNA signatures are not as good as mRNA signatures for breast cancer prognosis. In general, lncRNA expression data does not help improve the mRNA-based methods in both cancer subtyping and cancer prognosis. These results suggest that the prognostic roles of miRNA/lncRNA signatures in the improvement of breast cancer prognosis needs to be further verified.

BACKGROUND: Network models are well-established as very useful computational-statistical tools in cell biology. However, a genomic network model based only on gene expression data can, by definition, only infer gene co-expression networks. Hence, in order to infer gene regulatory patterns, it is necessary to also include data related to binding of regulatory factors to DNA. RESULTS: We propose a new dynamic genomic network model, for inferring patterns of genomic regulatory influence in dynamic processes such as development. Our model fuses experiment-specific gene expression data with publicly available DNA-binding data. The method we propose is computationally efficient, and can be applied to genome-wide data with tens of thousands of transcripts. Thus, our method is well suited for use as an exploratory tool for genome-wide data. We apply our method to data from human fetal cortical development, and our findings confirm genomic regulatory patterns which are recognised as being fundamental to neuronal development. CONCLUSIONS: Our method provides a mathematical/computational toolbox which, when coupled with targeted experiments, will reveal and confirm important new functional genomic regulatory processes in mammalian development.

BACKGROUND: An increasing number of studies have shown that lncRNAs are crucial for the control of hormones and the regulation of various physiological processes in the human body, and deletion mutations in RNA are related to many human diseases. LncRNA- disease association prediction is very useful for understanding pathogenesis, diagnosis, and prevention of diseases, and is helpful for labelling relevant biological information. RESULTS: In this manuscript, we propose a computational model named bidirectional generative adversarial network (BiGAN), which consists of an encoder, a generator, and a discriminator to predict new lncRNA-disease associations. We construct features between lncRNA and disease pairs by utilizing the disease semantic similarity, lncRNA sequence similarity, and Gaussian interaction profile kernel similarities of lncRNAs and diseases. The BiGAN maps the latent features of similarity features to predict unverified association between lncRNAs and diseases. The computational results have proved that the BiGAN performs significantly better than other state-of-the-art approaches in cross-validation. We employed the proposed model to predict candidate lncRNAs for renal cancer and colon cancer. The results are promising. Case studies show that almost 70% of lncRNAs in the top 10 prediction lists are verified by recent biological research. CONCLUSION: The experimental results indicated that our proposed model had an accurate predictive ability for the association of lncRNA-disease pairs.

BACKGROUND: Feature extraction of protein sequences is widely used in various research areas related to protein analysis, such as protein similarity analysis and prediction of protein functions or interactions. RESULTS: In this study, we introduce FEGS (Feature Extraction based on Graphical and Statistical features), a novel feature extraction model of protein sequences, by developing a new technique for graphical representation of protein sequences based on the physicochemical properties of amino acids and effectively employing the statistical features of protein sequences. By fusing the graphical and statistical features, FEGS transforms a protein sequence into a 578-dimensional numerical vector. When FEGS is applied to phylogenetic analysis on five protein sequence data sets, its performance is notably better than all of the other compared methods. CONCLUSION: The FEGS method is carefully designed, which is practically powerful for extracting features of protein sequences. The current version of FEGS is developed to be user-friendly and is expected to play a crucial role in the related studies of protein sequence analyses.

BACKGROUND: RNA-Seq is a well-established technology extensively used for transcriptome profiling, allowing the analysis of coding and non-coding RNA molecules. However, this technology produces a vast amount of data requiring sophisticated computational approaches for their analysis than other traditional technologies such as Real-Time PCR or microarrays, strongly discouraging non-expert users. For this reason, dozens of pipelines have been deployed for the analysis of RNA-Seq data. Although interesting, these present several limitations and their usage require a technical background, which may be uncommon in small research laboratories. Therefore, the application of these technologies in such contexts is still limited and causes a clear bottleneck in knowledge advancement. RESULTS: Motivated by these considerations, we have developed RNAdetector, a new free cross-platform and user-friendly RNA-Seq data analysis software that can be used locally or in cloud environments through an easy-to-use Graphical User Interface allowing the analysis of coding and non-coding RNAs from RNA-Seq datasets of any sequenced biological species. CONCLUSIONS: RNAdetector is a new software that fills an essential gap between the needs of biomedical and research labs to process RNA-Seq data and their common lack of technical background in performing such analysis, which usually relies on outsourcing such steps to third party bioinformatics facilities or using expensive commercial software.

BACKGROUND: Osteoarthritis (OA) is a multifactorial joint degenerative disease with low-grade inflammation. The gut microbiome has recently emerged as an pathogenic factor of OA, and prebiotics supplementation could alleviate OA symptoms in animal models. However, the relationship between the gut microbiome and OA in the older female adults is hitherto not clear. RESULTS: Here we studied the gut microbiome of 57 OA patients and their healthy controls by metagenome-wide association study based on previously published data. A significant reduction in the richness and diversity of gut microbiome were observed in OA patients. Bifidobacterium longum and Faecalibacterium prausnitzii were decreased while Clostridium spp. was increased in the OA group. The functional modules, particularly the energetic metabolism and acetate production were also decreased in the OA patients. To evaluate the diagnostic value of identified species for elderly patients with OA, we constructed a set of random forest disease classifiers based on species differences between the two groups. Among them, 9 species reached the lowest classification error in the random forest cross validation, and the area under ROC of the model was 0.81. CONCLUSIONS: Significant alterations in the gut microbial composition and function were observed between the older patients with OA and their controls, and a random forest classifier model for OA were constructed based on the differences in our study. Our study have identified several potential gut microbial targets in the elderly females with OA, which will facilitate the treatment of OA based on gut microbiota, is of great value in alleviating pain and improving the quality of life for them.

BACKGROUND: Phylogenies are a key part of research in many areas of biology. Tools that automate some parts of the process of phylogenetic reconstruction, mainly molecular character matrix assembly, have been developed for the advantage of both specialists in the field of phylogenetics and non-specialists. However, interpretation of results, comparison with previously available phylogenetic hypotheses, and selection of one phylogeny for downstream analyses and discussion still impose difficulties to one that is not a specialist either on phylogenetic methods or on a particular group of study. RESULTS: Physcraper is a command-line Python program that automates the update of published phylogenies by adding public DNA sequences to underlying alignments of previously published phylogenies. It also provides a framework for straightforward comparison of published phylogenies with their updated versions, by leveraging upon tools from the Open Tree of Life project to link taxonomic information across databases. The program can be used by the nonspecialist, as a tool to generate phylogenetic hypotheses based on publicly available expert phylogenetic knowledge. Phylogeneticists and taxonomic group specialists will find it useful as a tool to facilitate molecular dataset gathering and comparison of alternative phylogenetic hypotheses (topologies). CONCLUSION: The Physcraper workflow showcases the benefits of doing open science for phylogenetics, encouraging researchers to strive for better scientific sharing practices. Physcraper can be used with any OS and is released under an open-source license. Detailed instructions for installation and usage are available at https://physcraper.readthedocs.io.

BACKGROUND: The Raffinose synthetase (RAFS) genes superfamily is critical for the synthesis of raffinose, which accumulates in plant leaves under abiotic stress. However, it remains unclear whether RAFS contributes to resistance to abiotic stress in plants, specifically in the Gossypium species. RESULTS: In this study, we identified 74 RAFS genes from G. hirsutum, G. barbadense, G. arboreum and G. raimondii by using a series of bioinformatic methods. Phylogenetic analysis showed that the RAFS gene family in the four Gossypium species could be divided into four major clades; the relatively uniform distribution of the gene number in each species ranged from 12 to 25 based on species ploidy, most likely resulting from an ancient whole-genome polyploidization. Gene motif analysis showed that the RAFS gene structure was relatively conservative. Promoter analysis for cis-regulatory elements showed that some RAFS genes might be regulated by gibberellins and abscisic acid, which might influence their expression levels. Moreover, we further examined the functions of RAFS under cold, heat, salt and drought stress conditions, based on the expression profile and co-expression network of RAFS genes in Gossypium species. Transcriptome analysis suggested that RAFS genes in clade III are highly expressed in organs such as seed, root, cotyledon, ovule and fiber, and under abiotic stress in particular, indicating the involvement of genes belonging to clade III in resistance to abiotic stress. Gene co-expressed network analysis showed that GhRFS2A-GhRFS6A, GhRFS6D, GhRFS7D and GhRFS8A-GhRFS11A were key genes, with high expression levels under salt, drought, cold and heat stress. CONCLUSION: The findings may provide insights into the evolutionary relationships and expression patterns of RAFS genes in Gossypium species and a theoretical basis for the identification of stress resistance materials in cotton.

BACKGROUND: StrongestPath is a Cytoscape 3 application that enables the analysis of interactions between two proteins or groups of proteins in a collection of protein-protein interaction (PPI) network or signaling network databases. When there are different levels of confidence over the interactions, the application is able to process them and identify the cascade of interactions with the highest total confidence score. Given a set of proteins, StrongestPath can extract a set of possible interactions between the input proteins, and expand the network by adding new proteins that have the most interactions with highest total confidence to the current network of proteins. The application can also identify any activating or inhibitory regulatory paths between two distinct sets of transcription factors and target genes. This application can be used on the built-in human and mouse PPI or signaling databases, or any user-provided database for some organism. RESULTS: Our results on 12 signaling pathways from the NetPath database demonstrate that the application can be used for indicating proteins which may play significant roles in a pathway by finding the strongest path(s) in the PPI or signaling network. CONCLUSION: Easy access to multiple public large databases, generating output in a short time, addressing some key challenges in one platform, and providing a user-friendly graphical interface make StrongestPath an extremely useful application.

BACKGROUND: Fragment libraries play a key role in fragment-assembly based protein structure prediction, where protein fragments are assembled to form a complete three-dimensional structure. Rich and accurate structural information embedded in fragment libraries has not been systematically extracted and used beyond fragment assembly. METHODS: To better leverage the valuable structural information for protein structure prediction, we extracted seven types of structural information from fragment libraries. We broadened the usage of such structural information by transforming fragment libraries into protein-specific potentials for gradient-descent based protein folding and encoding fragment libraries as structural features for protein property prediction. RESULTS: Fragment libraires improved the accuracy of protein folding and outperformed state-of-the-art algorithms with respect to predicted properties, such as torsion angles and inter-residue distances. CONCLUSION: Our work implies that the rich structural information extracted from fragment libraries can complement sequence-derived features to help protein structure prediction.

BACKGROUND: An individual's genetics play a role in how RNA transcripts are generated from DNA and consequently in their translation into protein. Transcriptional and translational profiling of patients furnishes the information that a specific marker is present; however, it fails to provide evidence whether the marker correlates with response to a therapeutic agent. A comparative analysis of the frequency of genetic variants, such as single nucleotide polymorphisms (SNPs), in diseased and general populations can identify pathogenic variants in individual patients. This is in part because SNPs have considerable effects on protein function and gene expression when they occur in coding regions and regulatory sequences, respectively. Therefore, a tool that can help users to obtain the allele frequency for a corresponding transcript is the need of the day. Several annotation tools such as SNPnexus and VariED are publicly available; however, none of them can use transcript IDs as input and provide the corresponding genomic positions of variants. RESULTS: In this study, we developed an R package, called transcript annotation tool (TransAT), that provides (i) SNP ID and genomic position for a user-provided transcript ID from patients, and (ii) allele frequencies for the SNPs from publicly available global populations. All data elements are extracted, collected, and displayed in an easily downloadable format in two simple command lines. TransAT is available on Windows/Linux/MacOS and is operative for R version 4.0.4 or later. It is available at https://github.com/ShihChingYu/TransAT and can be downloaded and installed using devtools::install_github("ShihChingYu/TransAT", force=T) on the R execution page. Thereafter, all functions can be executed by loading the package into R with library(TransAT). CONCLUSIONS: TransAT is a novel tool that seamlessly provides genetic annotations for queried transcripts. Such easily obtainable information would be greatly advantageous for physicians, assisting them to make individualized decisions about specific drug treatments. Moreover, allele frequencies from user-chosen global ethnic populations will highlight the importance of ethnicity and its effect on patient pathogenicity.

BACKGROUND: Plasmids are mobile genetic elements that often carry accessory genes, and are vectors for horizontal transfer between bacterial genomes. Plasmid detection in large genomic datasets is crucial to analyze their spread and quantify their role in bacteria adaptation and particularly in antibiotic resistance propagation. Bioinformatics methods have been developed to detect plasmids. However, they suffer from low sensitivity (i.e., most plasmids remain undetected) or low precision (i.e., these methods identify chromosomes as plasmids), and are overall not adapted to identify plasmids in whole genomes that are not fully assembled (contigs and scaffolds). RESULTS: We developed PlasForest, a homology-based random forest classifier identifying bacterial plasmid sequences in partially assembled genomes. Without knowing the taxonomical origin of the samples, PlasForest identifies contigs as plasmids or chromosomes with a F1 score of 0.950. Notably, it can detect 77.4% of plasmid contigs below 1 kb with 2.8% of false positives and 99.9% of plasmid contigs over 50 kb with 2.2% of false positives. CONCLUSIONS: PlasForest outperforms other currently available tools on genomic datasets by being both sensitive and precise. The performance of PlasForest on metagenomic assemblies are currently well below those of other k-mer-based methods, and we discuss how homology-based approaches could improve plasmid detection in such datasets.

BACKGROUND: Recent advances in 3D imaging technologies provide novel insights to researchers and reveal finer and more detail of examined specimen, especially in the biomedical domain, but also impose huge challenges regarding scalability for automated analysis algorithms due to rapidly increasing dataset sizes. In particular, existing research towards automated vessel network analysis does not always consider memory requirements of proposed algorithms and often generates a large number of spurious branches for structures consisting of many voxels. Additionally, very often these algorithms have further restrictions such as the limitation to tree topologies or relying on the properties of specific image modalities. RESULTS: We propose a scalable iterative pipeline (in terms of computational cost, required main memory and robustness) that extracts an annotated abstract graph representation from the foreground segmentation of vessel networks of arbitrary topology and vessel shape. The novel iterative refinement process is controlled by a single, dimensionless, a-priori determinable parameter. CONCLUSIONS: We are able to, for the first time, analyze the topology of volumes of roughly 1 TB on commodity hardware, using the proposed pipeline. We demonstrate improved robustness in terms of surface noise, vessel shape deviation and anisotropic resolution compared to the state of the art. An implementation of the presented pipeline is publicly available in version 5.1 of the volume rendering and processing engine Voreen.

BACKGROUND: Low-depth sequencing allows researchers to increase sample size at the expense of lower accuracy. To incorporate uncertainties while maintaining statistical power, we introduce MCPCA_PopGen to analyze population structure of low-depth sequencing data. RESULTS: The method optimizes the choice of nonlinear transformations of dosages to maximize the Ky Fan norm of the covariance matrix. The transformation incorporates the uncertainty in calling between heterozygotes and the common homozygotes for loci having a rare allele and is more linear when both variants are common. CONCLUSIONS: We apply MCPCA_PopGen to samples from two indigenous Siberian populations and reveal hidden population structure accurately using only a single chromosome. The MCPCA_PopGen package is available on https://github.com/yiwenstat/MCPCA_PopGen .

BACKGROUND: Computational tools analyzing RNA-sequencing data have boosted alternative splicing research by identifying and assessing differentially spliced genes. However, common alternative splicing analysis tools differ substantially in their statistical analyses and general performance. This report compares the computational performance (CPU utilization and RAM usage) of three event-level splicing tools; rMATS, MISO, and SUPPA2. Additionally, concordance between tool outputs was investigated. RESULTS: Log-linear relations were found between job times and dataset size in all splicing tools and all virtual machine (VM) configurations. MISO had the highest job times for all analyses, irrespective of VM size, while MISO analyses also exceeded maximum CPU utilization on all VM sizes. rMATS and SUPPA2 load averages were relatively low in both size and replicate comparisons, not nearing maximum CPU utilization in the VM simulating the lowest computational power (D2 VM). RAM usage in rMATS and SUPPA2 did not exceed 20% of maximum RAM in both size and replicate comparisons while MISO reached maximum RAM usage in D2 VM analyses for input size. Correlation coefficients of differential splicing analyses showed high correlation (β > 80%) between different tool outputs with the exception of comparisons of retained intron (RI) events between rMATS/MISO and rMATS/SUPPA2 (β < 60%). CONCLUSIONS: Prior to RNA-seq analyses, users should consider job time, amount of replicates and splice event type of interest to determine the optimal alternative splicing tool. In general, rMATS is superior to both MISO and SUPPA2 in computational performance. Analysis outputs show high concordance between tools, with the exception of RI events.

BACKGROUND: Autoimmune diseases are heterogeneous pathologies with difficult diagnosis and few therapeutic options. In the last decade, several omics studies have provided significant insights into the molecular mechanisms of these diseases. Nevertheless, data from different cohorts and pathologies are stored independently in public repositories and a unified resource is imperative to assist researchers in this field. RESULTS: Here, we present Autoimmune Diseases Explorer ( https://adex.genyo.es ), a database that integrates 82 curated transcriptomics and methylation studies covering 5609 samples for some of the most common autoimmune diseases. The database provides, in an easy-to-use environment, advanced data analysis and statistical methods for exploring omics datasets, including meta-analysis, differential expression or pathway analysis. CONCLUSIONS: This is the first omics database focused on autoimmune diseases. This resource incorporates homogeneously processed data to facilitate integrative analyses among studies.

BACKGROUND: Localization of messenger RNAs (mRNAs) plays a crucial role in the growth and development of cells. Particularly, it plays a major role in regulating spatio-temporal gene expression. The in situ hybridization is a promising experimental technique used to determine the localization of mRNAs but it is costly and laborious. It is also a known fact that a single mRNA can be present in more than one location, whereas the existing computational tools are capable of predicting only a single location for such mRNAs. Thus, the development of high-end computational tool is required for reliable and timely prediction of multiple subcellular locations of mRNAs. Hence, we develop the present computational model to predict the multiple localizations of mRNAs. RESULTS: The mRNA sequences from 9 different localizations were considered. Each sequence was first transformed to a numeric feature vector of size 5460, based on the k-mer features of sizes 1-6. Out of 5460 k-mer features, 1812 important features were selected by the Elastic Net statistical model. The Random Forest supervised learning algorithm was then employed for predicting the localizations with the selected features. Five-fold cross-validation accuracies of 70.87, 68.32, 68.36, 68.79, 96.46, 73.44, 70.94, 97.42 and 71.77% were obtained for the cytoplasm, cytosol, endoplasmic reticulum, exosome, mitochondrion, nucleus, pseudopodium, posterior and ribosome respectively. With an independent test set, accuracies of 65.33, 73.37, 75.86, 72.99, 94.26, 70.91, 65.53, 93.60 and 73.45% were obtained for the respective localizations. The developed approach also achieved higher accuracies than the existing localization prediction tools. CONCLUSIONS: This study presents a novel computational tool for predicting the multiple localization of mRNAs. Based on the proposed approach, an online prediction server "mLoc-mRNA" is accessible at http://cabgrid.res.in:8080/mlocmrna/ . The developed approach is believed to supplement the existing tools and techniques for the localization prediction of mRNAs.

BACKGROUND: VISPR is an interactive visualization and analysis framework for CRISPR screening experiments. However, it only supports the output of MAGeCK, and requires installation and manual configuration. Furthermore, VISPR is designed to run on a single computer, and data sharing between collaborators is challenging. RESULTS: To make the tool easily accessible to the community, we present VISPR-online, a web-based general application allowing users to visualize, explore, and share CRISPR screening data online with a few simple steps. VISPR-online provides an exploration of screening results and visualization of read count changes. Apart from MAGeCK, VISPR-online supports two more popular CRISPR screening analysis tools: BAGEL and JACKS. It provides an interactive environment for exploring gene essentiality, viewing guide RNA (gRNA) locations, and allowing users to resume and share screening results. CONCLUSIONS: VISPR-online allows users to visualize, explore and share CRISPR screening data online. It is freely available at http://vispr-online.weililab.org , while the source code is available at https://github.com/lemoncyb/VISPR-online .

BACKGROUND: Antifreeze proteins (AFPs) are a group of proteins that inhibit body fluids from growing to ice crystals and thus improve biological antifreeze ability. It is vital to the survival of living organisms in extremely cold environments. However, little research is performed on sequences feature extraction and selection for antifreeze proteins classification in the structure and function prediction, which is of great significance. RESULTS: In this paper, to predict the antifreeze proteins, a feature representation of weighted generalized dipeptide composition (W-GDipC) and an ensemble feature selection based on two-stage and multi-regression method (LRMR-Ri) are proposed. Specifically, four feature selection algorithms: Lasso regression, Ridge regression, Maximal information coefficient and Relief are used to select the feature sets, respectively, which is the first stage of LRMR-Ri method. If there exists a common feature subset among the above four sets, it is the optimal subset; otherwise we use Ridge regression to select the optimal subset from the public set pooled by the four sets, which is the second stage of LRMR-Ri. The LRMR-Ri method combined with W-GDipC was performed both on the antifreeze proteins dataset (binary classification), and on the membrane protein dataset (multiple classification). Experimental results show that this method has good performance in support vector machine (SVM), decision tree (DT) and stochastic gradient descent (SGD). The values of ACC, RE and MCC of LRMR-Ri and W-GDipC with antifreeze proteins dataset and SVM classifier have reached as high as 95.56%, 97.06% and 0.9105, respectively, much higher than those of each single method: Lasso, Ridge, Mic and Relief, nearly 13% higher than single Lasso for ACC. CONCLUSION: The experimental results show that the proposed LRMR-Ri and W-GDipC method can significantly improve the accuracy of antifreeze proteins prediction compared with other similar single feature methods. In addition, our method has also achieved good results in the classification and prediction of membrane proteins, which verifies its widely reliability to a certain extent.

BACKGROUND: Epigenetic modifications, including CG methylation (a major form of DNA methylation) and histone modifications, interact with each other to shape their genomic distribution patterns. However, the entire picture of the epigenetic crosstalk regulating the CG methylation pattern is unknown especially in cells that are available only in a limited number, such as mammalian oocytes. Most machine learning approaches developed so far aim at finding DNA sequences responsible for the CG methylation patterns and were not tailored for studying the epigenetic crosstalk. RESULTS: We built a machine learning model named epiNet to predict CG methylation patterns based on other epigenetic features, such as histone modifications, but not DNA sequence. Using epiNet, we identified biologically relevant epigenetic crosstalk between histone H3K36me3, H3K4me3, and CG methylation in mouse oocytes. This model also predicted the altered CG methylation pattern of mutant oocytes having perturbed histone modification, was applicable to cross-species prediction of the CG methylation pattern of human oocytes, and identified the epigenetic crosstalk potentially important in other cell types. CONCLUSIONS: Our findings provide insight into the epigenetic crosstalk regulating the CG methylation pattern in mammalian oocytes and other cells. The use of epiNet should help to design or complement biological experiments in epigenetics studies.

BACKGROUND: Approximate Bayesian Computation (ABC) has become a key tool for calibrating the parameters of discrete stochastic biochemical models. For higher dimensional models and data, its performance is strongly dependent on having a representative set of summary statistics. While regression-based methods have been demonstrated to allow for the automatic construction of effective summary statistics, their reliance on first simulating a large training set creates a significant overhead when applying these methods to discrete stochastic models for which simulation is relatively expensive. In this τ work, we present a method to reduce this computational burden by leveraging approximate simulators of these systems, such as ordinary differential equations and τ-Leaping approximations. RESULTS: We have developed an algorithm to accelerate the construction of regression-based summary statistics for Approximate Bayesian Computation by selectively using the faster approximate algorithms for simulations. By posing the problem as one of ratio estimation, we use state-of-the-art methods in machine learning to show that, in many cases, our algorithm can significantly reduce the number of simulations from the full resolution model at a minimal cost to accuracy and little additional tuning from the user. We demonstrate the usefulness and robustness of our method with four different experiments. CONCLUSIONS: We provide a novel algorithm for accelerating the construction of summary statistics for stochastic biochemical systems. Compared to the standard practice of exclusively training from exact simulator samples, our method is able to dramatically reduce the number of required calls to the stochastic simulator at a minimal loss in accuracy. This can immediately be implemented to increase the overall speed of the ABC workflow for estimating parameters in complex systems.

BACKGROUND: Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach that partially automates lead optimization workflow in silico, providing suggestions for modification hot spots. RESULTS: The initial data collection is achieved with physics-based molecular dynamics simulation. Contact matrices are calculated as the preliminary features extracted from the simulations. To take advantage of the temporal information from the simulations, we enhanced contact matrices data with temporal dynamism representation, which are then modeled with unsupervised convolutional variational autoencoder (CVAE). Finally, conventional and CVAE-based clustering methods are compared with metrics to rank the submolecular structures and propose potential candidates for lead optimization. CONCLUSION: With no need for extensive structure-activity data, our method provides new hints for drug modification hotspots which can be used to improve drug potency and reduce the lead optimization time. It can potentially become a valuable tool for medicinal chemists.

BACKGROUND: Brain wave signal recognition has gained increased attention in neuro-rehabilitation applications. This has driven the development of brain-computer interface (BCI) systems. Brain wave signals are acquired using electroencephalography (EEG) sensors, processed and decoded to identify the category to which the signal belongs. Once the signal category is determined, it can be used to control external devices. However, the success of such a system essentially relies on significant feature extraction and classification algorithms. One of the commonly used feature extraction technique for BCI systems is common spatial pattern (CSP). RESULTS: The performance of the proposed spatial-frequency-temporal feature extraction (SPECTRA) predictor is analysed using three public benchmark datasets. Our proposed predictor outperformed other competing methods achieving lowest average error rates of 8.55%, 17.90% and 20.26%, and highest average kappa coefficient values of 0.829, 0.643 and 0.595 for BCI Competition III dataset IVa, BCI Competition IV dataset I and BCI Competition IV dataset IIb, respectively. CONCLUSIONS: Our proposed SPECTRA predictor effectively finds features that are more separable and shows improvement in brain wave signal recognition that can be instrumental in developing improved real-time BCI systems that are computationally efficient.

BACKGROUND: Taxonomic assignment is a key step in the identification of human viral pathogens. Current tools for taxonomic assignment from sequencing reads based on alignment or alignment-free k-mer approaches may not perform optimally in cases where the sequences diverge significantly from the reference sequences. Furthermore, many tools may not incorporate the genomic coverage of assigned reads as part of overall likelihood of a correct taxonomic assignment for a sample. RESULTS: In this paper, we describe the development of a pipeline that incorporates a multi-task learning model based on convolutional neural network (MT-CNN) and a Bayesian ranking approach to identify and rank the most likely human virus from sequence reads. For taxonomic assignment of reads, the MT-CNN model outperformed Kraken 2, Centrifuge, and Bowtie 2 on reads generated from simulated divergent HIV-1 genomes and was more sensitive in identifying SARS as the closest relation in four RNA sequencing datasets for SARS-CoV-2 virus. For genomic region assignment of assigned reads, the MT-CNN model performed competitively compared with Bowtie 2 and the region assignments were used for estimation of genomic coverage that was incorporated into a naïve Bayesian network together with the proportion of taxonomic assignments to rank the likelihood of candidate human viruses from sequence data. CONCLUSIONS: We have developed a pipeline that combines a novel MT-CNN model that is able to identify viruses with divergent sequences together with assignment of the genomic region, with a Bayesian approach to ranking of taxonomic assignments by taking into account both the number of assigned reads and genomic coverage. The pipeline is available at GitHub via https://github.com/MaHaoran627/CNN_Virus .

BACKGROUND: Recent advances in simultaneous measurement of RNA and protein abundances at single-cell level provide a unique opportunity to predict protein abundance from scRNA-seq data using machine learning models. However, existing machine learning methods have not considered relationship among the proteins sufficiently. RESULTS: We formulate this task in a multi-label prediction framework where multiple proteins are linked to each other at the single-cell level. Then, we propose a novel method for single-cell RNA to protein prediction named PIKE-R2P, which incorporates protein-protein interactions (PPI) and prior knowledge embedding into a graph neural network. Compared with existing methods, PIKE-R2P could significantly improve prediction performance in terms of smaller errors and higher correlations with the gold standard measurements. CONCLUSION: The superior performance of PIKE-R2P indicates that adding the prior knowledge of PPI to graph neural networks can be a powerful strategy for cross-modality prediction of protein abundances at the single-cell level.

BACKGROUND: The rapid development of single-cell RNA sequencing (scRNA-seq) enables the exploration of cell heterogeneity, which is usually done by scRNA-seq data clustering. The essence of scRNA-seq data clustering is to group cells by measuring the similarities among genes/transcripts of cells. And the selection of features for cell similarity evaluation is of great importance, which will significantly impact clustering effectiveness and efficiency. RESULTS: In this paper, we propose a novel method called CaFew to select genes based on cluster-aware feature weighting. By optimizing the clustering objective function, CaFew obtains a feature weight matrix, which is further used for feature selection. The genes have large weights in at least one cluster or the genes whose weights vary greatly in different clusters are selected. Experiments on 8 real scRNA-seq datasets show that CaFew can obviously improve the clustering performance of existing scRNA-seq data clustering methods. Particularly, the combination of CaFew with SC3 achieves the state-of-art performance. Furthermore, CaFew also benefits the visualization of scRNA-seq data. CONCLUSION: CaFew is an effective scRNA-seq data clustering method due to its gene selection mechanism based on cluster-aware feature weighting, and it is a useful tool for scRNA-seq data analysis.

BACKGROUND: Genomic reads from sequencing platforms contain random errors. Global correction algorithms have been developed, aiming to rectify all possible errors in the reads using generic genome-wide patterns. However, the non-uniform sequencing depths hinder the global approach to conduct effective error removal. As some genes may get under-corrected or over-corrected by the global approach, we conduct instance-based error correction for short reads of disease-associated genes or pathways. The paramount requirement is to ensure the relevant reads, instead of the whole genome, are error-free to provide significant benefits for single-nucleotide polymorphism (SNP) or variant calling studies on the specific genes. RESULTS: To rectify possible errors in the short reads of disease-associated genes, our novel idea is to exploit local sequence features and statistics directly related to these genes. Extensive experiments are conducted in comparison with state-of-the-art methods on both simulated and real datasets of lung cancer associated genes (including single-end and paired-end reads). The results demonstrated the superiority of our method with the best performance on precision, recall and gain rate, as well as on sequence assembly results (e.g., N50, the length of contig and contig quality). CONCLUSION: Instance-based strategy makes it possible to explore fine-grained patterns focusing on specific genes, providing high precision error correction and convincing gene sequence assembly. SNP case studies show that errors occurring at some traditional SNP areas can be accurately corrected, providing high precision and sensitivity for investigations on disease-causing point mutations.

BACKGROUND: Biomedical named entity recognition is one of the most essential tasks in biomedical information extraction. Previous studies suffer from inadequate annotated datasets, especially the limited knowledge contained in them. METHODS: To remedy the above issue, we propose a novel Biomedical Named Entity Recognition (BioNER) framework with label re-correction and knowledge distillation strategies, which could not only create large and high-quality datasets but also obtain a high-performance recognition model. Our framework is inspired by two points: (1) named entity recognition should be considered from the perspective of both coverage and accuracy; (2) trustable annotations should be yielded by iterative correction. Firstly, for coverage, we annotate chemical and disease entities in a large-scale unlabeled dataset by PubTator to generate a weakly labeled dataset. For accuracy, we then filter it by utilizing multiple knowledge bases to generate another weakly labeled dataset. Next, the two datasets are revised by a label re-correction strategy to construct two high-quality datasets, which are used to train two recognition models, respectively. Finally, we compress the knowledge in the two models into a single recognition model with knowledge distillation. RESULTS: Experiments on the BioCreative V chemical-disease relation corpus and NCBI Disease corpus show that knowledge from large-scale datasets significantly improves the performance of BioNER, especially the recall of it, leading to new state-of-the-art results. CONCLUSIONS: We propose a framework with label re-correction and knowledge distillation strategies. Comparison results show that the two perspectives of knowledge in the two re-corrected datasets respectively are complementary and both effective for BioNER.

Erratum in BMC Bioinformatics. 2021 Aug 4;22(1):393.

BACKGROUND: Nucleosome plays an important role in the process of genome expression, DNA replication, DNA repair and transcription. Therefore, the research of nucleosome positioning has invariably received extensive attention. Considering the diversity of DNA sequence representation methods, we tried to integrate multiple features to analyze its effect in the process of nucleosome positioning analysis. This process can also deepen our understanding of the theoretical analysis of nucleosome positioning. RESULTS: Here, we not only used frequency chaos game representation (FCGR) to construct DNA sequence features, but also integrated it with other features and adopted the principal component analysis (PCA) algorithm. Simultaneously, support vector machine (SVM), extreme learning machine (ELM), extreme gradient boosting (XGBoost), multilayer perceptron (MLP) and convolutional neural networks (CNN) are used as predictors for nucleosome positioning prediction analysis, respectively. The integrated feature vector prediction quality is significantly superior to a single feature. After using principal component analysis (PCA) to reduce the feature dimension, the prediction quality of H. sapiens dataset has been significantly improved. CONCLUSIONS: Comparative analysis and prediction on H. sapiens, C. elegans, D. melanogaster and S. cerevisiae datasets, demonstrate that the application of FCGR to nucleosome positioning is feasible, and we also found that integrative feature representation would be better.

BACKGROUND: Understanding the functional effects of non-coding variants is important as they are often associated with gene-expression alteration and disease development. Over the past few years, many computational tools have been developed to predict their functional impact. However, the intrinsic difficulty in dealing with the scarcity of data leads to the necessity to further improve the algorithms. In this work, we propose a novel method, employing a semi-supervised deep-learning model with pseudo labels, which takes advantage of learning from both experimentally annotated and unannotated data. RESULTS: We prepared known functional non-coding variants with histone marks, DNA accessibility, and sequence context in GM12878, HepG2, and K562 cell lines. Applying our method to the dataset demonstrated its outstanding performance, compared with that of existing tools. Our results also indicated that the semi-supervised model with pseudo labels achieves higher predictive performance than the supervised model without pseudo labels. Interestingly, a model trained with the data in a certain cell line is unlikely to succeed in other cell lines, which implies the cell-type-specific nature of the non-coding variants. Remarkably, we found that DNA accessibility significantly contributes to the functional consequence of variants, which suggests the importance of open chromatin conformation prior to establishing the interaction of non-coding variants with gene regulation. CONCLUSIONS: The semi-supervised deep learning model coupled with pseudo labeling has advantages in studying with limited datasets, which is not unusual in biology. Our study provides an effective approach in finding non-coding mutations potentially associated with various biological phenomena, including human diseases.

BACKGROUND: The increasing use of whole metagenome sequencing has spurred the need to improve de novo assemblers to facilitate the discovery of unknown species and the analysis of their genomic functions. MetaVelvet-SL is a short-read de novo metagenome assembler that partitions a multi-species de Bruijn graph into single-species sub-graphs. This study aimed to improve the performance of MetaVelvet-SL by using a deep learning-based model to predict the partition nodes in a multi-species de Bruijn graph. RESULTS: This study showed that the recent advances in deep learning offer the opportunity to better exploit sequence information and differentiate genomes of different species in a metagenomic sample. We developed an extension to MetaVelvet-SL, which we named MetaVelvet-DL, that builds an end-to-end architecture using Convolutional Neural Network and Long Short-Term Memory units. The deep learning model in MetaVelvet-DL can more accurately predict how to partition a de Bruijn graph than the Support Vector Machine-based model in MetaVelvet-SL can. Assembly of the Critical Assessment of Metagenome Interpretation (CAMI) dataset showed that after removing chimeric assemblies, MetaVelvet-DL produced longer single-species contigs, with less misassembled contigs than MetaVelvet-SL did. CONCLUSIONS: MetaVelvet-DL provides more accurate de novo assemblies of whole metagenome data. The authors believe that this improvement can help in furthering the understanding of microbiomes by providing a more accurate description of the metagenomic samples under analysis.

BACKGROUND: Coxiella burnetii is the Gram-negative bacterium responsible for Q fever in humans and coxiellosis in domesticated agricultural animals. Previous vaccination efforts with whole cell inactivated bacteria or surface isolated proteins confer protection but can produce a reactogenic immune responses. Thereby a protective vaccine that does not cause aberrant immune reactions is required. The critical role of T-cell immunity in control of C. burnetii has been made clear, since either CD8+ or CD4+ T cells can empower clearance. The purpose of this study was to identify C. burnetii proteins bearing epitopes that interact with major histocompatibility complexes (MHC) from multiple host species (human, mouse, and cattle). RESULTS: Of the annotated 1815 proteins from the Nine Mile Phase I (RSA 493) assembly, 402 proteins were removed from analysis due to a lack of inter-isolate conservation. An additional 391 proteins were eliminated from assessment to avoid potential autoimmune responses due to the presence of host homology. We analyzed the remaining 1022 proteins for their ability to produce peptides that bind MHCI or MHCII. MHCI and MHCII predicted epitopes were filtered and compared between species yielding 777 MHCI epitopes and 453 MHCII epitopes. These epitopes were further examined for presentation by both MHCI and MHCII, and for proteins that contained multiple epitopes. There were 31 epitopes that overlapped positionally between MHCI and MHCII across host species. Of these, there were 9 epitopes represented within proteins containing ≥ 5 total epitopes, where an additional 24 proteins were also epitope dense. In all, 55 proteins were found to contain high scoring T-cell epitopes. Besides the well-studied protein Com1, most identified proteins were novel when compared to previously studied vaccine candidates. CONCLUSION: These data represent the first proteome-wide evaluation of C. burnetii peptide epitopes. Furthermore, the inclusion of human, mouse, and bovine data capture a range of hosts for this zoonotic pathogen plus an important model organism. This work provides new vaccine targets for future vaccination efforts and enhances opportunities for selecting multiple T-cell epitope types to include within a vaccine.

BACKGROUND: With the rapid growth in the use of high-throughput methods for characterizing translation and the continued expansion of multi-omics, there is a need for back-end functions and streamlined tools for processing, analyzing, and characterizing data produced by these assays. RESULTS: Here, we introduce ORFik, a user-friendly R/Bioconductor API and toolbox for studying translation and its regulation. It extends GenomicRanges from the genome to the transcriptome and implements a framework that integrates data from several sources. ORFik streamlines the steps to process, analyze, and visualize the different steps of translation with a particular focus on initiation and elongation. It accepts high-throughput sequencing data from ribosome profiling to quantify ribosome elongation or RCP-seq/TCP-seq to also quantify ribosome scanning. In addition, ORFik can use CAGE data to accurately determine 5'UTRs and RNA-seq for determining translation relative to RNA abundance. ORFik supports and calculates over 30 different translation-related features and metrics from the literature and can annotate translated regions such as proteins or upstream open reading frames (uORFs). As a use-case, we demonstrate using ORFik to rapidly annotate the dynamics of 5' UTRs across different tissues, detect their uORFs, and characterize their scanning and translation in the downstream protein-coding regions. CONCLUSION: In summary, ORFik introduces hundreds of tested, documented and optimized methods. ORFik is designed to be easily customizable, enabling users to create complete workflows from raw data to publication-ready figures for several types of sequencing data. Finally, by improving speed and scope of many core Bioconductor functions, ORFik offers enhancement benefiting the entire Bioconductor environment. AVAILABILITY: http://bioconductor.org/packages/ORFik .

BACKGROUND: Once aligned, long-reads can be a useful source of information to identify the type and position of structural variations. However, due to the high sequencing error of long reads, long-read structural variation detection methods are far from precise in low-coverage cases. To be accurate, they need to use high-coverage data, which in turn, results in an extremely time-consuming pipeline, especially in the alignment phase. Therefore, it is of utmost importance to have a structural variation calling pipeline which is both fast and precise for low-coverage data. RESULTS: In this paper, we present SVNN, a fast yet accurate, structural variation calling pipeline for PacBio long-reads that takes raw reads as the input and detects structural variants of size larger than 50 bp. Our pipeline utilizes state-of-the-art long-read aligners, namely NGMLR and Minimap2, and structural variation callers, videlicet Sniffle and SVIM. We found that by using a neural network, we can extract features from Minimap2 output to detect a subset of reads that provide useful information for structural variation detection. By only mapping this subset with NGMLR, which is far slower than Minimap2 but better serves downstream structural variation detection, we can increase the sensitivity in an efficient way. As a result of using multiple tools intelligently, SVNN achieves up to 20 percentage points of sensitivity improvement in comparison with state-of-the-art methods and is three times faster than a naive combination of state-of-the-art tools to achieve almost the same accuracy. CONCLUSION: Since prohibitive costs of using high-coverage data have impeded long-read applications, with SVNN, we provide the users with a much faster structural variation detection platform for PacBio reads with high precision and sensitivity in low-coverage scenarios.

MOTIVATION: In eukaryotes, proteins targeted for secretion contain a signal peptide, which allows them to proceed through the conventional ER/Golgi-dependent pathway. However, an important number of proteins lacking a signal peptide can be secreted through unconventional routes, including that mediated by exosomes. Currently, no method is available to predict protein secretion via exosomes. RESULTS: Here, we first assembled a dataset including the sequences of 2992 proteins secreted by exosomes and 2961 proteins that are not secreted by exosomes. Subsequently, we trained different random forests models on feature vectors derived from the sequences in this dataset. In tenfold cross-validation, the best model was trained on dipeptide composition, reaching an accuracy of 69.88% ± 2.08 and an area under the curve (AUC) of 0.76 ± 0.03. In an independent dataset, this model reached an accuracy of 75.73% and an AUC of 0.840. After these results, we developed ExoPred, a web-based tool that uses random forests to predict protein secretion by exosomes. CONCLUSION: ExoPred is available for free public use at http://imath.med.ucm.es/exopred/ . Datasets are available at http://imath.med.ucm.es/exopred/datasets/ .

BACKGROUND: Accurately forecasting the prognosis could improve cervical cancer management, however, the currently used clinical features are difficult to provide enough information. The aim of this study is to improve forecasting capability by developing a miRNAs-based machine learning survival prediction model. RESULTS: The expression characteristics of miRNAs were chosen as features for model development. The cervical cancer miRNA expression data was obtained from The Cancer Genome Atlas database. Preprocessing, including unquantified data removal, missing value imputation, samples normalization, log transformation, and feature scaling, was performed. In total, 42 survival-related miRNAs were identified by Cox Proportional-Hazards analysis. The patients were optimally clustered into four groups with three different 5-years survival outcome (≥ 90%, ≈ 65%, ≤ 40%) by K-means clustering algorithm base on top 10 survival-related miRNAs. According to the K-means clustering result, a prediction model with high performance was established. The pathways analysis indicated that the miRNAs used play roles involved in the regulation of cancer stem cells. CONCLUSION: A miRNAs-based machine learning cervical cancer survival prediction model was developed that robustly stratifies cervical cancer patients into high survival rate (5-years survival rate ≥ 90%), moderate survival rate (5-years survival rate ≈ 65%), and low survival rate (5-years survival rate ≤ 40%).

BACKGROUND: LncRNAs (Long non-coding RNAs) are a type of non-coding RNA molecule with transcript length longer than 200 nucleotides. LncRNA has been novel candidate biomarkers in cancer diagnosis and prognosis. However, it is difficult to discover the true association mechanism between lncRNAs and complex diseases. The unprecedented enrichment of multi-omics data and the rapid development of machine learning technology provide us with the opportunity to design a machine learning framework to study the relationship between lncRNAs and complex diseases. RESULTS: In this article, we proposed a new machine learning approach, namely LGDLDA (LncRNA-Gene-Disease association networks based LncRNA-Disease Association prediction), for disease-related lncRNAs association prediction based multi-omics data, machine learning methods and neural network neighborhood information aggregation. Firstly, LGDLDA calculates the similarity matrix of lncRNA, gene and disease respectively, and it calculates the similarity between lncRNAs through the lncRNA expression profile matrix, lncRNA-miRNA interaction matrix and lncRNA-protein interaction matrix. We obtain gene similarity matrix by calculating the lncRNA-gene association matrix and the gene-disease association matrix, and we obtain disease similarity matrix by calculating the disease ontology, the disease-miRNA association matrix, and Gaussian interaction profile kernel similarity. Secondly, LGDLDA integrates the neighborhood information in similarity matrices by using nonlinear feature learning of neural network. Thirdly, LGDLDA uses embedded node representations to approximate the observed matrices. Finally, LGDLDA ranks candidate lncRNA-disease pairs and then selects potential disease-related lncRNAs. CONCLUSIONS: Compared with lncRNA-disease prediction methods, our proposed method takes into account more critical information and obtains the performance improvement cancer-related lncRNA predictions. Randomly split data experiment results show that the stability of LGDLDA is better than IDHI-MIRW, NCPLDA, LncDisAP and NCPHLDA. The results on different simulation data sets show that LGDLDA can accurately and effectively predict the disease-related lncRNAs. Furthermore, we applied the method to three real cancer data including gastric cancer, colorectal cancer and breast cancer to predict potential cancer-related lncRNAs.

BACKGROUND: Viruses, including bacteriophages, are important components of environmental and human associated microbial communities. Viruses can act as extracellular reservoirs of bacterial genes, can mediate microbiome dynamics, and can influence the virulence of clinical pathogens. Various targeted metagenomic analysis techniques detect viral sequences, but these methods often exclude large and genome integrated viruses. In this study, we evaluate and compare the ability of nine state-of-the-art bioinformatic tools, including Vibrant, VirSorter, VirSorter2, VirFinder, DeepVirFinder, MetaPhinder, Kraken 2, Phybrid, and a BLAST search using identified proteins from the Earth Virome Pipeline to identify viral contiguous sequences (contigs) across simulated metagenomes with different read distributions, taxonomic compositions, and complexities. RESULTS: Of the tools tested in this study, VirSorter achieved the best F1 score while Vibrant had the highest average F1 score at predicting integrated prophages. Though less balanced in its precision and recall, Kraken2 had the highest average precision by a substantial margin. We introduced the machine learning tool, Phybrid, which demonstrated an improvement in average F1 score over tools such as MetaPhinder. The tool utilizes machine learning with both gene content and nucleotide features. The addition of nucleotide features improves the precision and recall compared to the gene content features alone.Viral identification by all tools was not impacted by underlying read distribution but did improve with contig length. Tool performance was inversely related to taxonomic complexity and varied by the phage host. For instance, Rhizobium and Enterococcus phages were identified consistently by the tools; whereas, Neisseria prophage sequences were commonly missed in this study. CONCLUSION: This study benchmarked the performance of nine state-of-the-art bioinformatic tools to identify viral contigs across different simulation conditions. This study explored the ability of the tools to identify integrated prophage elements traditionally excluded from targeted sequencing approaches. Our comprehensive analysis of viral identification tools to assess their performance in a variety of situations provides valuable insights to viral researchers looking to mine viral elements from publicly available metagenomic data.

BACKGROUND: With the development of high-throughput sequencing technology, a huge amount of multi-omics data has been accumulated. Although there are many software tools for statistical analysis and visual development of omics data, these tools are not suitable for private data and non-technical users. Besides, most of these tools have specialized in only one or perhaps a few data typesare, without combining clinical information. What's more, users could not choose data processing and model selection flexibly when using these tools. RESULTS: To help non-technical users to understand and analyze private multi-omics data and ensure data security, we developed an interactive desk tool for statistical analysis and visualization of omics and clinical data (shortly IOAT). Our mainly targets csv format data, and combines clinical data with high-dimensional multi-omics data. It also contains various operations, such as data preprocessing, feature selection, risk assessment, clustering, and survival analysis. By using this tool, users can safely and conveniently try a combination of various methods on their private multi-omics data to find a model suitable for their data, conduct risk assessment and determine their cancer subtypes. At the same time, the tool can also provide them with references to genes that are closely related to tumor staging, facilitating the development of precision oncology. We review IOAT's main features and demonstrate its analysis capabilities on a lung from TCGA. CONCLUSIONS: IOAT is a local desktop tool, which provides a set of multi-omics data integration solutions. It can quickly perform a complete analysis of cancer genome data for subtype discovery and biomarker identification without security issues and writing any code. Thus, our tool can enable cancer biologists and biomedicine researchers to analyze their data more easily and safely. IOAT can be downloaded for free from https://github.com/WlSunshine/IOAT-software .

BACKGROUND: Automated segmentation of nuclei in microscopic images has been conducted to enhance throughput in pathological diagnostics and biological research. Segmentation accuracy and speed has been significantly enhanced with the advent of convolutional neural networks. A barrier in the broad application of neural networks to nuclei segmentation is the necessity to train the network using a set of application specific images and image labels. Previous works have attempted to create broadly trained networks for universal nuclei segmentation; however, such networks do not work on all imaging modalities, and best results are still commonly found when the network is retrained on user specific data. Stochastic optical reconstruction microscopy (STORM) based super-resolution fluorescence microscopy has opened a new avenue to image nuclear architecture at nanoscale resolutions. Due to the large size and discontinuous features typical of super-resolution images, automatic nuclei segmentation can be difficult. In this study, we apply commonly used networks (Mask R-CNN and UNet architectures) towards the task of segmenting super-resolution images of nuclei. First, we assess whether networks broadly trained on conventional fluorescence microscopy datasets can accurately segment super-resolution images. Then, we compare the resultant segmentations with results obtained using networks trained directly on our super-resolution data. We next attempt to optimize and compare segmentation accuracy using three different neural network architectures. RESULTS: Results indicate that super-resolution images are not broadly compatible with neural networks trained on conventional bright-field or fluorescence microscopy images. When the networks were trained on super-resolution data, however, we attained nuclei segmentation accuracies (F1-Score) in excess of 0.8, comparable to past results found when conducting nuclei segmentation on conventional fluorescence microscopy images. Overall, we achieved the best results utilizing the Mask R-CNN architecture. CONCLUSIONS: We found that convolutional neural networks are powerful tools capable of accurately and quickly segmenting localization-based super-resolution microscopy images of nuclei. While broadly trained and widely applicable segmentation algorithms are desirable for quick use with minimal input, optimal results are still found when the network is both trained and tested on visually similar images. We provide a set of Colab notebooks to disseminate the software into the broad scientific community ( https://github.com/YangLiuLab/Super-Resolution-Nuclei-Segmentation ).

BACKGROUND: Proteins are of extremely vital importance in the human body, and no movement or activity can be performed without proteins. Currently, microscopy imaging technologies developed rapidly are employed to observe proteins in various cells and tissues. In addition, due to the complex and crowded cellular environments as well as various types and sizes of proteins, a considerable number of protein images are generated every day and cannot be classified manually. Therefore, an automatic and accurate method should be designed to properly solve and analyse protein images with mixed patterns. RESULTS: In this paper, we first propose a novel customized architecture with adaptive concatenate pooling and "buffering" layers in the classifier part, which could make the networks more adaptive to training and testing datasets, and develop a novel hard sampler at the end of our network to effectively mine the samples from small classes. Furthermore, a new loss is presented to handle the label imbalance based on the effectiveness of samples. In addition, in our method, several novel and effective optimization strategies are adopted to solve the difficult training-time optimization problem and further increase the accuracy by post-processing. CONCLUSION: Our methods outperformed the SOTA method of multi-labelled protein classification on the HPA dataset, GapNet-PL, by above 2% in the F1 score. Therefore, experimental results based on the test set split from the Human Protein Atlas dataset show that our methods have good performance in automatically classifying multi-class and multi-labelled high-throughput microscopy protein images.

BACKGROUND: Histone modification constitutes a basic mechanism for the genetic regulation of gene expression. In early 2000s, a powerful technique has emerged that couples chromatin immunoprecipitation with high-throughput sequencing (ChIP-seq). This technique provides a direct survey of the DNA regions associated to these modifications. In order to realize the full potential of this technique, increasingly sophisticated statistical algorithms have been developed or adapted to analyze the massive amount of data it generates. Many of these algorithms were built around natural assumptions such as the Poisson distribution to model the noise in the count data. In this work we start from these natural assumptions and show that it is possible to improve upon them. RESULTS: Our comparisons on seven reference datasets of histone modifications (H3K36me3 & H3K4me3) suggest that natural assumptions are not always realistic under application conditions. We show that the unconstrained multiple changepoint detection model with alternative noise assumptions and supervised learning of the penalty parameter reduces the over-dispersion exhibited by count data. These models, implemented in the R package CROCS ( https://github.com/aLiehrmann/CROCS ), detect the peaks more accurately than algorithms which rely on natural assumptions. CONCLUSION: The segmentation models we propose can benefit researchers in the field of epigenetics by providing new high-quality peak prediction tracks for H3K36me3 and H3K4me3 histone modifications.

BACKGROUND: Nucleosome organization is involved in many regulatory activities in various organisms. However, studies integrating nucleosome organization in mammalian genomes are very limited mainly due to the lack of comprehensive data quality control (QC) assessment and uneven data quality of public data sets. RESULTS: The NUCOME is a database focused on filtering qualified nucleosome organization referenced landscapes covering various cell types in human and mouse based on QC metrics. The filtering strategy guarantees the quality of nucleosome organization referenced landscapes and exempts users from redundant data set selection and processing. The NUCOME database provides standardized, qualified data source and informative nucleosome organization features at a whole-genome scale and on the level of individual loci. CONCLUSIONS: The NUCOME provides valuable data resources for integrative analyses focus on nucleosome organization. The NUCOME is freely available at http://compbio-zhanglab.org/NUCOME .

BACKGROUND: Assessing the nucleosome-forming potential of specific DNA sequences is important for understanding complex chromatin organization. Methods for predicting nucleosome positioning include bioinformatics and biophysical approaches. An advantage of bioinformatics methods, which are based on in vivo nucleosome maps, is the use of natural sequences that may contain previously unknown elements involved in nucleosome positioning in vivo. The accuracy of such prediction attempts reflects the genomic coordinate resolution of the nucleosome maps applied. Nucleosome maps are constructed using micrococcal nuclease digestion followed by high-throughput sequencing (MNase-seq). However, as MNase has a strong preference for A/T-rich sequences, MNase-seq may not be appropriate for this purpose. In addition to MNase-seq-based maps, base pair-resolution chemical maps of in vivo nucleosomes from three different species (budding and fission yeasts, and mice) are currently available. However, these chemical maps have yet to be integrated into publicly available computational methods. RESULTS: We developed a Bioconductor package (named nuCpos) to demonstrate the superiority of chemical maps in predicting nucleosome positioning. The accuracy of chemical map-based prediction in rotational settings was higher than that of the previously developed MNase-seq-based approach. With our method, predicted nucleosome occupancy reasonably matched in vivo observations and was not affected by A/T nucleotide frequency. Effects of genetic alterations on nucleosome positioning that had been observed in living yeast cells could also be predicted. nuCpos calculates individual histone binding affinity (HBA) scores for given 147-bp sequences to examine their suitability for nucleosome formation. We also established local HBA as a new parameter to predict nucleosome formation, which was calculated for 13 overlapping nucleosomal DNA subsequences. HBA and local HBA scores for various sequences agreed well with previous in vitro and in vivo studies. Furthermore, our results suggest that nucleosomal subsegments that are disfavored in different rotational settings contribute to the defined positioning of nucleosomes. CONCLUSIONS: Our results demonstrate that chemical map-based statistical models are beneficial for studying nucleosomal DNA features. Studies employing nuCpos software can enhance understanding of chromatin regulation and the interpretation of genetic alterations and facilitate the design of artificial sequences.

BACKGROUND: Assignment of chemical compounds to biological pathways is a crucial step to understand the relationship between the chemical repertory of an organism and its biology. Protein sequence profiles are very successful in capturing the main structural and functional features of a protein family, and can be used to assign new members to it based on matching of their sequences against these profiles. In this work, we extend this idea to chemical compounds, constructing a profile-inspired model for a set of related metabolites (those in the same biological pathway), based on a fragment-based vectorial representation of their chemical structures. RESULTS: We use this representation to predict the biological pathway of a chemical compound with good overall accuracy (AUC 0.74-0.90 depending on the database tested), and analyzed some factors that affect performance. The approach, which is compared with equivalent methods, can in addition detect those molecular fragments characteristic of a pathway. CONCLUSIONS: The method is available as a graphical interactive web server http://csbg.cnb.csic.es/iFragMent .

BACKGROUND: Drug-drug interaction (DDI) is a serious public health issue. The L1000 database of the LINCS project has collected millions of genome-wide expressions induced by 20,000 small molecular compounds on 72 cell lines. Whether this unified and comprehensive transcriptome data resource can be used to build a better DDI prediction model is still unclear. Therefore, we developed and validated a novel deep learning model for predicting DDI using 89,970 known DDIs extracted from the DrugBank database (version 5.1.4). RESULTS: The proposed model consists of a graph convolutional autoencoder network (GCAN) for embedding drug-induced transcriptome data from the L1000 database of the LINCS project; and a long short-term memory (LSTM) for DDI prediction. Comparative evaluation of various machine learning methods demonstrated the superior performance of our proposed model for DDI prediction. Many of our predicted DDIs were revealed in the latest DrugBank database (version 5.1.7). In the case study, we predicted drugs interacting with sulfonylureas to cause hypoglycemia and drugs interacting with metformin to cause lactic acidosis, and showed both to induce effects on the proteins involved in the metabolic mechanism in vivo. CONCLUSIONS: The proposed deep learning model can accelerate the discovery of new DDIs. It can support future clinical research for safer and more effective drug co-prescription.

BACKGROUND: The novel coronavirus (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2, and within a few months, it has become a global pandemic. This forced many affected countries to take stringent measures such as complete lockdown, shutting down businesses and trade, as well as travel restrictions, which has had a tremendous economic impact. Therefore, having knowledge and foresight about how a country might be able to contain the spread of COVID-19 will be of paramount importance to the government, policy makers, business partners and entrepreneurs. To help social and administrative decision making, a model that will be able to forecast when a country might be able to contain the spread of COVID-19 is needed. RESULTS: The results obtained using our long short-term memory (LSTM) network-based model are promising as we validate our prediction model using New Zealand's data since they have been able to contain the spread of COVID-19 and bring the daily new cases tally to zero. Our proposed forecasting model was able to correctly predict the dates within which New Zealand was able to contain the spread of COVID-19. Similarly, the proposed model has been used to forecast the dates when other countries would be able to contain the spread of COVID-19. CONCLUSION: The forecasted dates are only a prediction based on the existing situation. However, these forecasted dates can be used to guide actions and make informed decisions that will be practically beneficial in influencing the real future. The current forecasting trend shows that more stringent actions/restrictions need to be implemented for most of the countries as the forecasting model shows they will take over three months before they can possibly contain the spread of COVID-19.

BACKGROUND: To assign structural and functional annotations to the ever increasing amount of sequenced proteins, the main approach relies on sequence-based homology search methods, e.g. BLAST or the current state-of-the-art methods based on profile Hidden Markov Models, which rely on significant alignments of query sequences to annotated proteins or protein families. While powerful, these approaches do not take coevolution between residues into account. Taking advantage of recent advances in the field of contact prediction, we propose here to represent proteins by Potts models, which model direct couplings between positions in addition to positional composition, and to compare proteins by aligning these models. Due to non-local dependencies, the problem of aligning Potts models is hard and remains the main computational bottleneck for their use. METHODS: We introduce here an Integer Linear Programming formulation of the problem and PPalign, a program based on this formulation, to compute the optimal pairwise alignment of Potts models representing proteins in tractable time. The approach is assessed with respect to a non-redundant set of reference pairwise sequence alignments from SISYPHUS benchmark which have lowest sequence identity (between [Formula: see text] and [Formula: see text]) and enable to build reliable Potts models for each sequence to be aligned. This experimentation confirms that Potts models can be aligned in reasonable time ([Formula: see text] in average on these alignments). The contribution of couplings is evaluated in comparison with HHalign and independent-site PPalign. Although Potts models were not fully optimized for alignment purposes and simple gap scores were used, PPalign yields a better mean [Formula: see text] score and finds significantly better alignments than HHalign and PPalign without couplings in some cases. CONCLUSIONS: These results show that pairwise couplings from protein Potts models can be used to improve the alignment of remotely related protein sequences in tractable time. Our experimentation suggests yet that new research on the inference of Potts models is now needed to make them more comparable and suitable for homology search. We think that PPalign's guaranteed optimality will be a powerful asset to perform unbiased investigations in this direction.

BACKGROUND: Drug repositioning, meanings finding new uses for existing drugs, which can accelerate the processing of new drugs research and development. Various computational methods have been presented to predict novel drug-disease associations for drug repositioning based on similarity measures among drugs and diseases. However, there are some known associations between drugs and diseases that previous studies not utilized. METHODS: In this work, we develop a deep gated recurrent units model to predict potential drug-disease interactions using comprehensive similarity measures and Gaussian interaction profile kernel. More specifically, the similarity measure is used to exploit discriminative feature for drugs based on their chemical fingerprints. Meanwhile, the Gaussian interactions profile kernel is employed to obtain efficient feature of diseases based on known disease-disease associations. Then, a deep gated recurrent units model is developed to predict potential drug-disease interactions. RESULTS: The performance of the proposed model is evaluated on two benchmark datasets under tenfold cross-validation. And to further verify the predictive ability, case studies for predicting new potential indications of drugs were carried out. CONCLUSION: The experimental results proved the proposed model is a useful tool for predicting new indications for drugs or new treatments for diseases, and can accelerate drug repositioning and related drug research and discovery.