BACKGROUND: Cis-regulatory elements (CREs) are DNA sequence segments that regulate gene expression. Among CREs are promoters, enhancers, Boundary Elements (BEs) and Polycomb Response Elements (PREs), all of which are enriched in specific sequence motifs that form particular occurrence landscapes. We have recently introduced a hierarchical machine learning approach (SVM-MOCCA) in which Support Vector Machines (SVMs) are applied on the level of individual motif occurrences, modelling local sequence composition, and then combined for the prediction of whole regulatory elements. We used SVM-MOCCA to predict PREs in Drosophila and found that it was superior to other methods. However, we did not publish a polished implementation of SVM-MOCCA, which can be useful for other researchers, and we only tested SVM-MOCCA with IUPAC motifs and PREs. RESULTS: We here present an expanded suite for modelling CRE sequences in terms of motif occurrence combinatorics-Motif Occurrence Combinatorics Classification Algorithms (MOCCA). MOCCA contains efficient implementations of several modelling methods, including SVM-MOCCA, and a new method, RF-MOCCA, a Random Forest-derivative of SVM-MOCCA. We used SVM-MOCCA and RF-MOCCA to model Drosophila PREs and BEs in cross-validation experiments, making this the first study to model PREs with Random Forests and the first study that applies the hierarchical MOCCA approach to the prediction of BEs. Both models significantly improve generalization to PREs and boundary elements beyond that of previous methods-including 4-spectrum and motif occurrence frequency Support Vector Machines and Random Forests-, with RF-MOCCA yielding the best results. CONCLUSION: MOCCA is a flexible and powerful suite of tools for the motif-based modelling of CRE sequences in terms of motif composition. MOCCA can be applied to any new CRE modelling problems where motifs have been identified. MOCCA supports IUPAC and Position Weight Matrix (PWM) motifs. For ease of use, MOCCA implements generation of negative training data, and additionally a mode that requires only that the user specifies positives, motifs and a genome. MOCCA is licensed under the MIT license and is available on Github at https://github.com/bjornbredesen/MOCCA .

BACKGROUND: Genes implicated in tumorigenesis often exhibit diverse sets of genomic variants in the tumor cohorts within which they are frequently mutated. For many genes, neither the transcriptomic effects of these variants nor their relationship to one another in cancer processes have been well-characterized. We sought to identify the downstream expression effects of these mutations and to determine whether this heterogeneity at the genomic level is reflected in a corresponding heterogeneity at the transcriptomic level. RESULTS: By applying a novel hierarchical framework for organizing the mutations present in a cohort along with machine learning pipelines trained on samples' expression profiles we systematically interrogated the signatures associated with combinations of mutations recurrent in cancer. This allowed us to catalogue the mutations with discernible downstream expression effects across a number of tumor cohorts as well as to uncover and characterize over a hundred cases where subsets of a gene's mutations are clearly divergent in their function from the remaining mutations of the gene. These findings successfully replicated across a number of disease contexts and were found to have clear implications for the delineation of cancer processes and for clinical decisions. CONCLUSIONS: The results of cataloguing the downstream effects of mutation subgroupings across cancer cohorts underline the importance of incorporating the diversity present within oncogenes in models designed to capture the downstream effects of their mutations.

BACKGROUND: Energy proxy traits (EPTs) are a novel approach to high dimensional organismal phenotyping that quantify the spectrum of energy levels within different temporal frequencies associated with mean pixel value fluctuations from video. They offer significant potential in addressing the phenotyping bottleneck in biology and are effective at identifying lethal endpoints and measuring specific functional traits, but the extent to which they might contribute additional understanding of the phenotype remains unknown. Consequently, here we test the biological significance of EPTs and their responses relative to fundamental thermodynamic principles. We achieve this using the entire embryonic development of Radix balthica, a freshwater pond snail, at different temperatures (20, 25 & 30 °C) and comparing responses against predictions from Arrhenius' equation (Q10 = 2). RESULTS: We find that EPTs are thermally sensitive and their spectra of frequency response enable effective high-dimensional treatment clustering throughout organismal development. Temperature-specific deviation in EPTs from thermodynamic predictions were evident and indicative of physiological mitigation, although they differed markedly in their responses from manual measures. The EPT spectrum was effective in capturing aspects of the phenotype predictive of biological outcomes, and suggest that EPTs themselves may reflect levels of energy turnover. CONCLUSIONS: Whole-organismal biology is incredibly complex, and this contributes to the challenge of developing universal phenotyping approaches. Here, we demonstrate the biological relevance of a new holistic approach to phenotyping that is not constrained by preconceived notions of biological importance. Furthermore, we find that EPTs are an effective approach to measuring even the most dynamic life history stages.

BACKGROUND: Epitope prediction is a useful approach in cancer immunology and immunotherapy. Many computational methods, including machine learning and network analysis, have been developed quickly for such purposes. However, regarding clinical applications, the existing tools are insufficient because few of the predicted binding molecules are immunogenic. Hence, to develop more potent and effective vaccines, it is important to understand binding and immunogenic potential. Here, we observed that the interactive association constituted by human leukocyte antigen (HLA)-peptide pairs can be regarded as a network in which each HLA and peptide is taken as a node. We speculated whether this network could detect the essential interactive propensities embedded in HLA-peptide pairs. Thus, we developed a network-based deep learning method called DeepNetBim by harnessing binding and immunogenic information to predict HLA-peptide interactions. RESULTS: Quantitative class I HLA-peptide binding data and qualitative immunogenic data (including data generated from T cell activation assays, major histocompatibility complex (MHC) binding assays and MHC ligand elution assays) were retrieved from the Immune Epitope Database database. The weighted HLA-peptide binding network and immunogenic network were integrated into a network-based deep learning algorithm constituted by a convolutional neural network and an attention mechanism. The results showed that the integration of network centrality metrics increased the power of both binding and immunogenicity predictions, while the new model significantly outperformed those that did not include network features and those with shuffled networks. Applied on benchmark and independent datasets, DeepNetBim achieved an AUC score of 93.74% in HLA-peptide binding prediction, outperforming 11 state-of-the-art relevant models. Furthermore, the performance enhancement of the combined model, which filtered out negative immunogenic predictions, was confirmed on neoantigen identification by an increase in both positive predictive value (PPV) and the proportion of neoantigen recognition. CONCLUSIONS: We developed a network-based deep learning method called DeepNetBim as a pan-specific epitope prediction tool. It extracted the attributes of the network as new features from HLA-peptide binding and immunogenic models. We observed that not only did DeepNetBim binding model outperform other updated methods but the combination of our two models showed better performance. This indicates further applications in clinical practice.

BACKGROUND: The identification of gene-gene and gene-environment interactions in genome-wide association studies is challenging due to the unknown nature of the interactions and the overwhelmingly large number of possible combinations. Parametric regression models are suitable to look for prespecified interactions. Nonparametric models such as tree ensemble models, with the ability to detect any unspecified interaction, have previously been difficult to interpret. However, with the development of methods for model explainability, it is now possible to interpret tree ensemble models efficiently and with a strong theoretical basis. RESULTS: We propose a tree ensemble- and SHAP-based method for identifying as well as interpreting potential gene-gene and gene-environment interactions on large-scale biobank data. A set of independent cross-validation runs are used to implicitly investigate the whole genome. We apply and evaluate the method using data from the UK Biobank with obesity as the phenotype. The results are in line with previous research on obesity as we identify top SNPs previously associated with obesity. We further demonstrate how to interpret and visualize interaction candidates. CONCLUSIONS: The new method identifies interaction candidates otherwise not detected with parametric regression models. However, further research is needed to evaluate the uncertainties of these candidates. The method can be applied to large-scale biobanks with high-dimensional data.

Erratum in BMC Bioinformatics. 2021 Jul 15;22(1):370.

BACKGROUND: DNA-Binding Proteins (DBP) plays a pivotal role in biological system. A mounting number of researchers are studying the mechanism and detection methods. To detect DBP, the tradition experimental method is time-consuming and resource-consuming. In recent years, Machine Learning methods have been used to detect DBP. However, it is difficult to adequately describe the information of proteins in predicting DNA-binding proteins. In this study, we extract six features from protein sequence and use Multiple Kernel Learning-based on Centered Kernel Alignment to integrate these features. The integrated feature is fed into Support Vector Machine to build predictive model and detect new DBP. RESULTS: In our work, date sets of PDB1075 and PDB186 are employed to test our method. From the results, our model obtains better results (accuracy) than other existing methods on PDB1075 ([Formula: see text]) and PDB186 ([Formula: see text]), respectively. CONCLUSION: Multiple kernel learning could fuse the complementary information between different features. Compared with existing methods, our method achieves comparable and best results on benchmark data sets.

BACKGROUND: Germline cells are important carriers of genetic and epigenetic information transmitted across generations in mammals. During the mammalian germline cell development cycle (i.e., the germline cycle), cell potency changes cyclically, accompanied by dynamic transcriptional changes and epigenetic reprogramming. Recently, to understand these dynamic and regulatory mechanisms, multiomic analyses, including transcriptomic and epigenomic analyses of DNA methylation, chromatin accessibility and histone modifications of germline cells, have been performed for different stages in human and mouse germline cycles. However, the long time span of the germline cycle and material scarcity of germline cells have largely limited the understanding of these dynamic characteristic changes. A tool that integrates the existing multiomics data and visualizes the overall continuous dynamic trends in the germline cycle can partially overcome such limitations. RESULTS: Here, we present GLEANER, a web server for GermLine cycle Expression ANalysis and Epigenetics Roadmap visualization. GLEANER provides a comprehensive collection of the transcriptome, DNA methylome, chromatin accessibility, and H3K4me3, H3K27me3, and H3K9me3 histone modification characteristics in human and mouse germline cycles. For each input gene, GLEANER shows the integrative analysis results of its transcriptional and epigenetic features, the genes with correlated transcriptional changes, and the overall continuous dynamic trends in the germline cycle. We further used two case studies to demonstrate the detailed functionality of GLEANER and highlighted that it can provide valuable clues to the epigenetic regulation mechanisms in the genetic and epigenetic information transmitted during the germline cycle. CONCLUSIONS: To the best of our knowledge, GLEANER is the first web server dedicated to the analysis and visualization of multiomics data related to the mammalian germline cycle. GLEANER is freely available at http://compbio-zhanglab.org/GLEANER .

BACKGROUND: Statistical geneticists employ simulation to estimate the power of proposed studies, test new analysis tools, and evaluate properties of causal models. Although there are existing trait simulators, there is ample room for modernization. For example, most phenotype simulators are limited to Gaussian traits or traits transformable to normality, while ignoring qualitative traits and realistic, non-normal trait distributions. Also, modern computer languages, such as Julia, that accommodate parallelization and cloud-based computing are now mainstream but rarely used in older applications. To meet the challenges of contemporary big studies, it is important for geneticists to adopt new computational tools. RESULTS: We present TraitSimulation, an open-source Julia package that makes it trivial to quickly simulate phenotypes under a variety of genetic architectures. This package is integrated into our OpenMendel suite for easy downstream analyses. Julia was purpose-built for scientific programming and provides tremendous speed and memory efficiency, easy access to multi-CPU and GPU hardware, and to distributed and cloud-based parallelization. TraitSimulation is designed to encourage flexible trait simulation, including via the standard devices of applied statistics, generalized linear models (GLMs) and generalized linear mixed models (GLMMs). TraitSimulation also accommodates many study designs: unrelateds, sibships, pedigrees, or a mixture of all three. (Of course, for data with pedigrees or cryptic relationships, the simulation process must include the genetic dependencies among the individuals.) We consider an assortment of trait models and study designs to illustrate integrated simulation and analysis pipelines. Step-by-step instructions for these analyses are available in our electronic Jupyter notebooks on Github. These interactive notebooks are ideal for reproducible research. CONCLUSION: The TraitSimulation package has three main advantages. (1) It leverages the computational efficiency and ease of use of Julia to provide extremely fast, straightforward simulation of even the most complex genetic models, including GLMs and GLMMs. (2) It can be operated entirely within, but is not limited to, the integrated analysis pipeline of OpenMendel. And finally (3), by allowing a wider range of more realistic phenotype models, TraitSimulation brings power calculations and diagnostic tools closer to what investigators might see in real-world analyses.

BACKGROUND: Leveraging previously identified viral interactions with human host proteins, we apply a machine learning-based approach to connect SARS-CoV-2 viral proteins to relevant host biological functions, diseases, and pathways in a large-scale knowledge graph derived from the biomedical literature. Our goal is to explore how SARS-CoV-2 could interfere with various host cell functions, and to identify drug targets amongst the host genes that could potentially be modulated against COVID-19 by repurposing existing drugs. The machine learning model employed here involves gene embeddings that leverage causal gene expression signatures curated from literature. In contrast to other network-based approaches for drug repurposing, our approach explicitly takes the direction of effects into account, distinguishing between activation and inhibition. RESULTS: We have constructed 70 networks connecting SARS-CoV-2 viral proteins to various biological functions, diseases, and pathways reflecting viral biology, clinical observations, and co-morbidities in the context of COVID-19. Results are presented in the form of interactive network visualizations through a web interface, the Coronavirus Network Explorer (CNE), that allows exploration of underlying experimental evidence. We find that existing drugs targeting genes in those networks are strongly enriched in the set of drugs that are already in clinical trials against COVID-19. CONCLUSIONS: The approach presented here can identify biologically plausible hypotheses for COVID-19 pathogenesis, explicitly connected to the immunological, virological and pathological observations seen in SARS-CoV-2 infected patients. The discovery of repurposable drugs is driven by prior knowledge of relevant functional endpoints that reflect known viral biology or clinical observations, therefore suggesting potential mechanisms of action. We believe that the CNE offers relevant insights that go beyond more conventional network approaches, and can be a valuable tool for drug repurposing. The CNE is available at https://digitalinsights.qiagen.com/coronavirus-network-explorer .

BACKGROUND: As a common and abundant RNA methylation modification, N6-methyladenosine (m6A) is widely spread in various species' transcriptomes, and it is closely related to the occurrence and development of various life processes and diseases. Thus, accurate identification of m6A methylation sites has become a hot topic. Most biological methods rely on high-throughput sequencing technology, which places great demands on the sequencing library preparation and data analysis. Thus, various machine learning methods have been proposed to extract various types of features based on sequences, then occupied conventional classifiers, such as SVM, RF, etc., for m6A methylation site identification. However, the identification performance relies heavily on the extracted features, which still need to be improved. RESULTS: This paper mainly studies feature extraction and classification of m6A methylation sites in a natural language processing way, which manages to organically integrate the feature extraction and classification simultaneously, with consideration of upstream and downstream information of m6A sites. One-hot, RNA word embedding, and Word2vec are adopted to depict sites from the perspectives of the base as well as its upstream and downstream sequence. The BiLSTM model, a well-known sequence model, was then constructed to discriminate the sequences with potential m6A sites. Since the above-mentioned three feature extraction methods focus on different perspectives of m6A sites, an ensemble deep learning predictor (EDLm6APred) was finally constructed for m6A site prediction. Experimental results on human and mouse data sets show that EDLm6APred outperforms the other single ones, indicating that base, upstream, and downstream information are all essential for m6A site detection. Compared with the existing m6A methylation site prediction models without genomic features, EDLm6APred obtains 86.6% of the area under receiver operating curve on the human data sets, indicating the effectiveness of sequential modeling on RNA. To maximize user convenience, a webserver was developed as an implementation of EDLm6APred and made publicly available at www.xjtlu.edu.cn/biologicalsciences/EDLm6APred . CONCLUSIONS: Our proposed EDLm6APred method is a reliable predictor for m6A methylation sites.

BACKGROUND: Representing biological networks as graphs is a powerful approach to reveal underlying patterns, signatures, and critical components from high-throughput biomolecular data. However, graphs do not natively capture the multi-way relationships present among genes and proteins in biological systems. Hypergraphs are generalizations of graphs that naturally model multi-way relationships and have shown promise in modeling systems such as protein complexes and metabolic reactions. In this paper we seek to understand how hypergraphs can more faithfully identify, and potentially predict, important genes based on complex relationships inferred from genomic expression data sets. RESULTS: We compiled a novel data set of transcriptional host response to pathogenic viral infections and formulated relationships between genes as a hypergraph where hyperedges represent significantly perturbed genes, and vertices represent individual biological samples with specific experimental conditions. We find that hypergraph betweenness centrality is a superior method for identification of genes important to viral response when compared with graph centrality. CONCLUSIONS: Our results demonstrate the utility of using hypergraphs to represent complex biological systems and highlight central important responses in common to a variety of highly pathogenic viruses.

BACKGROUND: Cancer is one of the major causes of death worldwide. To treat cancer, the use of anticancer peptides (ACPs) has attracted increased attention in recent years. ACPs are a unique group of small molecules that can target and kill cancer cells fast and directly. However, identifying ACPs by wet-lab experiments is time-consuming and labor-intensive. Therefore, it is significant to develop computational tools for ACPs prediction. Though some ACP prediction tools have been developed recently, their performances are not well enough and most of them do not offer a function to distinguish ACPs from antimicrobial peptides (AMPs). Considering the fact that a growing number of studies have shown that some AMPs exhibit anticancer function, this work tries to build a model for distinguishing AMPs from ACPs in addition to a model that predicts ACPs from whole peptides. RESULTS: This study chooses amino acid composition, N5C5, k-space, position-specific scoring matrix (PSSM) as features, and analyzes them by machine learning methods, including support vector machine (SVM) and sequential minimal optimization (SMO) to build a model (model 2) for distinguishing ACPs from whole peptides. Another model (model 1) that distinguishes ACPs from AMPs is also developed. Comparing to previous models, models developed in this research show better performance (accuracy: 85.5% for model 1 and 95.2% for model 2). CONCLUSIONS: This work utilizes a new feature, PSSM, which contributes to better performance than other features. In addition to SVM, SMO is used in this research for optimizing SVM and the SMO-optimized models show better performance than non-optimized models. Last but not least, this work provides two different functions, including distinguishing ACPs from AMPs and distinguishing ACPs from all peptides. The second SMO-optimized model, which utilizes PSSM as a feature, performs better than all other existing tools.

BACKGROUND: Many important applications in bioinformatics, including sequence alignment and protein family profiling, employ sequence weighting schemes to mitigate the effects of non-independence of homologous sequences and under- or over-representation of certain taxa in a dataset. These schemes aim to assign high weights to sequences that are 'novel' compared to the others in the same dataset, and low weights to sequences that are over-represented. RESULTS: We formalise this principle by rigorously defining the evolutionary 'novelty' of a sequence within an alignment. This results in new sequence weights that we call 'phylogenetic novelty scores'. These scores have various desirable properties, and we showcase their use by considering, as an example application, the inference of character frequencies at an alignment column-important, for example, in protein family profiling. We give computationally efficient algorithms for calculating our scores and, using simulations, show that they are versatile and can improve the accuracy of character frequency estimation compared to existing sequence weighting schemes. CONCLUSIONS: Our phylogenetic novelty scores can be useful when an evolutionarily meaningful system for adjusting for uneven taxon sampling is desired. They have numerous possible applications, including estimation of evolutionary conservation scores and sequence logos, identification of targets in conservation biology, and improving and measuring sequence alignment accuracy.

BACKGROUND: Direct link between metabolism and cell and organism phenotype in health and disease makes metabolomics, a high throughput study of small molecular metabolites, an essential methodology for understanding and diagnosing disease development and progression. Machine learning methods have seen increasing adoptions in metabolomics thanks to their powerful prediction abilities. However, the "black-box" nature of many machine learning models remains a major challenge for wide acceptance and utility as it makes the interpretation of decision process difficult. This challenge is particularly predominant in biomedical research where understanding of the underlying decision making mechanism is essential for insuring safety and gaining new knowledge. RESULTS: In this article, we proposed a novel computational framework, Systems Metabolomics using Interpretable Learning and Evolution (SMILE), for supervised metabolomics data analysis. Our methodology uses an evolutionary algorithm to learn interpretable predictive models and to identify the most influential metabolites and their interactions in association with disease. Moreover, we have developed a web application with a graphical user interface that can be used for easy analysis, interpretation and visualization of the results. Performance of the method and utilization of the web interface is shown using metabolomics data for Alzheimer's disease. CONCLUSIONS: SMILE was able to identify several influential metabolites on AD and to provide interpretable predictive models that can be further used for a better understanding of the metabolic background of AD. SMILE addresses the emerging issue of interpretability and explainability in machine learning, and contributes to more transparent and powerful applications of machine learning in bioinformatics.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) has emerged has a main strategy to study transcriptional activity at the cellular level. Clustering analysis is routinely performed on scRNA-seq data to explore, recognize or discover underlying cell identities. The high dimensionality of scRNA-seq data and its significant sparsity accentuated by frequent dropout events, introducing false zero count observations, make the clustering analysis computationally challenging. Even though multiple scRNA-seq clustering techniques have been proposed, there is no consensus on the best performing approach. On a parallel research track, self-supervised contrastive learning recently achieved state-of-the-art results on images clustering and, subsequently, image classification. RESULTS: We propose contrastive-sc, a new unsupervised learning method for scRNA-seq data that perform cell clustering. The method consists of two consecutive phases: first, an artificial neural network learns an embedding for each cell through a representation training phase. The embedding is then clustered in the second phase with a general clustering algorithm (i.e. KMeans or Leiden community detection). The proposed representation training phase is a new adaptation of the self-supervised contrastive learning framework, initially proposed for image processing, to scRNA-seq data. contrastive-sc has been compared with ten state-of-the-art techniques. A broad experimental study has been conducted on both simulated and real-world datasets, assessing multiple external and internal clustering performance metrics (i.e. ARI, NMI, Silhouette, Calinski scores). Our experimental analysis shows that constastive-sc compares favorably with state-of-the-art methods on both simulated and real-world datasets. CONCLUSION: On average, our method identifies well-defined clusters in close agreement with ground truth annotations. Our method is computationally efficient, being fast to train and having a limited memory footprint. contrastive-sc maintains good performance when only a fraction of input cells is provided and is robust to changes in hyperparameters or network architecture. The decoupling between the creation of the embedding and the clustering phase allows the flexibility to choose a suitable clustering algorithm (i.e. KMeans when the number of expected clusters is known, Leiden otherwise) or to integrate the embedding with other existing techniques.

BACKGROUND: The combination of the bisulfite treatment and the next-generation sequencing is an important method for methylation analysis, and aligning the bisulfite-treated reads (BS-reads) is the critical step for the downstream applications. As bisulfite treatment reduces the complexity of the sequences, a large portion of BS-reads might be aligned to multiple locations of the reference genome ambiguously, called multireads. These multireads cannot be employed in the downstream applications since they are likely to introduce artifacts. To identify the best mapping location of each multiread, existing Bayesian-based methods calculate the probability of the read at each position by considering how does it overlap with unique mapped reads. However, [Formula: see text]% of multireads are not overlapped with any unique reads, which are unresolvable for existing method. RESULTS: Here we propose a novel method (EM-MUL) that not only rescues multireads overlapped with unique reads, but also uses the overall coverage and accurate base-level alignment to resolve multireads that cannot be handled by current methods. We benchmark our method on both simulated datasets and real datasets. Experimental results show that it is able to align more than 80% of multireads to the best mapping position with very high accuracy. CONCLUSIONS: EM-MUL is an effective method designed to accurately determine the best mapping position of multireads in BS-reads. For the downstream applications, it is useful to improve the methylation resolution on the repetitive regions of genome. EM-MUL is free available at https://github.com/lmylynn/EM-MUL.

BACKGROUND: With the rapid development of accurate sequencing and assembly technologies, an increasing number of high-quality chromosome-level and haplotype-resolved assemblies of genomic sequences have been derived, from which there will be great opportunities for computational pangenomics. Although genome graphs are among the most useful models for pangenome representation, their structural complexity makes it difficult to present genome information intuitively, such as the linear reference genome. Thus, efficiently and accurately analyzing the genome graph spatial structure and coordinating the information remains a substantial challenge. RESULTS: We developed a new method, a colored superbubble (cSupB), that can overcome the complexity of graphs and organize a set of species- or population-specific haplotype sequences of interest. Based on this model, we propose a tri-tuple coordinate system that combines an offset value, topological structure and sample information. Additionally, cSupB provides a novel method that utilizes complete topological information and efficiently detects small indels (< 50 bp) for highly similar samples, which can be validated by simulated datasets. Moreover, we demonstrated that cSupB can adapt to the complex cycle structure. CONCLUSIONS: Although the solution is made suitable for increasingly complex genome graphs by relaxing the constraint, the directed acyclic graph, the motif cSupB and the cSupB method can be extended to any colored directed acyclic graph. We anticipate that our method will facilitate the analysis of individual haplotype variants and population genomic diversity. We have developed a C +  + program for implementing our method that is available at https://github.com/eggleader/cSupB .

BACKGROUND: Biomedical question answering (QA) is a sub-task of natural language processing in a specific domain, which aims to answer a question in the biomedical field based on one or more related passages and can provide people with accurate healthcare-related information. Recently, a lot of approaches based on the neural network and large scale pre-trained language model have largely improved its performance. However, considering the lexical characteristics of biomedical corpus and its small scale dataset, there is still much improvement room for biomedical QA tasks. RESULTS: Inspired by the importance of syntactic and lexical features in the biomedical corpus, we proposed a new framework to extract external features, such as part-of-speech and named-entity recognition, and fused them with the original text representation encoded by pre-trained language model, to enhance the biomedical question answering performance. Our model achieves an overall improvement of all three metrics on BioASQ 6b, 7b, and 8b factoid question answering tasks. CONCLUSIONS: The experiments on BioASQ question answering dataset demonstrated the effectiveness of our external feature-enriched framework. It is proven by the experiments conducted that external lexical and syntactic features can improve Pre-trained Language Model's performance in biomedical domain question answering task.

BACKGROUND: Histone post-translational modifications (PTMs) play an important role in our system by regulating the structure of chromatin and therefore contribute to the regulation of gene and protein expression. Irregularities in histone PTMs can lead to a variety of different diseases including various forms of cancer. Histone modifications are analyzed using high resolution mass spectrometry, which generate large amounts of data that requires sophisticated bioinformatics tools for analysis and visualization. PTMViz is designed for downstream differential abundance analysis and visualization of both protein and/or histone modifications. RESULTS: PTMViz provides users with data tables and visualization plots of significantly differentiated proteins and histone PTMs between two sample groups. All the data is packaged into interactive data tables and graphs using the Shiny platform to help the user explore the results in a fast and efficient manner to assess if changes in the system are due to protein abundance changes or epigenetic changes. In the example data provided, we identified several proteins differentially regulated in the dopaminergic pathway between mice treated with methamphetamine compared to a saline control. We also identified histone post-translational modifications including histone H3K9me, H3K27me3, H4K16ac, and that were regulated due to drug exposure. CONCLUSIONS: Histone modifications play an integral role in the regulation of gene expression. PTMViz provides an interactive platform for analyzing proteins and histone post-translational modifications from mass spectrometry data in order to quickly identify differentially expressed proteins and PTMs.

BACKGROUND: The investigation of molecular alterations associated with the conservation and variation of DNA methylation in eukaryotes is gaining interest in the biomedical research community. Among the different determinants of methylation stability, the DNA composition of the CpG surrounding regions has been shown to have a crucial role in the maintenance and establishment of methylation statuses. This aspect has been previously characterized in a quantitative manner by inspecting the nucleotidic composition in the region. Research in this field still lacks a qualitative perspective, linked to the identification of certain sequences (or DNA motifs) related to particular DNA methylation phenomena. RESULTS: Here we present a novel computational strategy based on short DNA motif discovery in order to characterize sequence patterns related to aberrant CpG methylation events. We provide our framework as a user-friendly, shiny-based application, CpGmotifs, to easily retrieve and characterize DNA patterns related to CpG methylation in the human genome. Our tool supports the functional interpretation of deregulated methylation events by predicting transcription factors binding sites (TFBS) encompassing the identified motifs. CONCLUSIONS: CpGmotifs is an open source software. Its source code is available on GitHub https://github.com/Greco-Lab/CpGmotifs and a ready-to-use docker image is provided on DockerHub at https://hub.docker.com/r/grecolab/cpgmotifs .

BACKGROUND: Small Proteins have received increasing attention in recent years. They have in particular been implicated as signals contributing to the coordination of bacterial communities. In genome annotations they are often missing or hidden among large numbers of hypothetical proteins because genome annotation pipelines often exclude short open reading frames or over-predict hypothetical proteins based on simple models. The validation of novel proteins, and in particular of small proteins (sProteins), therefore requires additional evidence. Proteogenomics is considered the gold standard for this purpose. It extends beyond established annotations and includes all possible open reading frames (ORFs) as potential sources of peptides, thus allowing the discovery of novel, unannotated proteins. Typically this results in large numbers of putative novel small proteins fraught with large fractions of false-positive predictions. RESULTS: We observe that number and quality of the peptide-spectrum matches (PSMs) that map to a candidate ORF can be highly informative for the purpose of distinguishing proteins from spurious ORF annotations. We report here on a workflow that aggregates PSM quality information and local context into simple descriptors and reliably separates likely proteins from the large pool of false-positive, i.e., most likely untranslated ORFs. We investigated the artificial gut microbiome model SIHUMIx, comprising eight different species, for which we validate 5114 proteins that have previously been annotated only as hypothetical ORFs. In addition, we identified 37 non-annotated protein candidates for which we found evidence at the proteomic and transcriptomic level. Half (19) of these candidates have close functional homologs in other species. Another 12 candidates have homologs designated as hypothetical proteins in other species. The remaining six candidates are short (< 100 AA) and are most likely bona fide novel proteins. CONCLUSIONS: The aggregation of PSM quality information for predicted ORFs provides a robust and efficient method to identify novel proteins in proteomics data. The workflow is in particular capable of identifying small proteins and frameshift variants. Since PSMs are explicitly mapped to genomic locations, it furthermore facilitates the integration of transcriptomics data and other sources of genome-level information.

BACKGROUND: Clinically effective and safe genotyping relies on correct reference sequences, often represented by haplotypes. The 1000 Genomes Project recorded individual genotypes across 26 different populations and, using computerized genotype phasing, reported haplotype data. In contrast, we identified long reference sequences by analyzing the homozygous genomic regions in this online database, a concept that has rarely been reported since next generation sequencing data became available. STUDY DESIGN AND METHODS: Phased genotype data for a 80.6 kb region of chromosome 1 was downloaded for all 2,504 unrelated individuals of the 1000 Genome Project Phase 3 cohort. The data was centered on the ACKR1 gene and bordered by the CADM3 and FCER1A genes. Individuals with heterozygosity at a single site or with complete homozygosity allowed unambiguous assignment of an ACKR1 haplotype. A computer algorithm was developed for extracting these haplotypes from the 1000 Genome Project in an automated fashion. A manual analysis validated the data extracted by the algorithm. RESULTS: We confirmed 902 ACKR1 haplotypes of varying lengths, the longest at 80,584 nucleotides and shortest at 1,901 nucleotides. The combined length of haplotype sequences comprised 19,895,388 nucleotides with a median of 16,014 nucleotides. Based on our approach, all haplotypes can be considered experimentally confirmed and not affected by the known errors of computerized genotype phasing. CONCLUSIONS: Tracts of homozygosity can provide definitive reference sequences for any gene. They are particularly useful when observed in unrelated individuals of large scale sequence databases. As a proof of principle, we explored the 1000 Genomes Project database for ACKR1 gene data and mined long haplotypes. These haplotypes are useful for high throughput analysis with next generation sequencing. Our approach is scalable, using automated bioinformatics tools, and can be applied to any gene.

BACKGROUND: With advancements in omics technologies, the range of biological processes where long non-coding RNAs (lncRNAs) are involved, is expanding extensively, thereby generating the need to develop lncRNA annotation resources. Although, there are a plethora of resources for annotating genes, despite the extensive corpus of lncRNA literature, the available resources with lncRNA ontology annotations are rare. RESULTS: We present a lncRNA annotation extractor and repository (Lantern), developed using PubMed's abstract retrieval engine and NCBO's recommender annotation system. Lantern's annotations were benchmarked against lncRNAdb's manually curated free text. Benchmarking analysis suggested that Lantern has a recall of 0.62 against lncRNAdb for 182 lncRNAs and precision of 0.8. Additionally, we also annotated lncRNAs with multiple omics annotations, including predicted cis-regulatory TFs, interactions with RBPs, tissue-specific expression profiles, protein co-expression networks, coding potential, sub-cellular localization, and SNPs for ~ 11,000 lncRNAs in the human genome, providing a one-stop dynamic visualization platform. CONCLUSIONS: Lantern integrates a novel, accurate semi-automatic ontology annotation engine derived annotations combined with a variety of multi-omics annotations for lncRNAs, to provide a central web resource for dissecting the functional dynamics of long non-coding RNAs and to facilitate future hypothesis-driven experiments. The annotation pipeline and a web resource with current annotations for human lncRNAs are freely available on sysbio.lab.iupui.edu/lantern.

BACKGROUND: Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal carcinoma and patients at advanced stage showed poor survival rate. Despite microRNAs (miRNAs) are used as potential biomarkers in many cancers, miRNA biomarkers for predicting the tumor stage of ccRCC are still limitedly identified. Therefore, we proposed a new integrated machine learning (ML) strategy to identify a novel miRNA signature related to tumor stage and prognosis of ccRCC patients using miRNA expression profiles. A multivariate Cox regression model with three hybrid penalties including Least absolute shrinkage and selection operator (Lasso), Adaptive lasso and Elastic net algorithms was used to screen relevant prognostic related miRNAs. The best subset regression (BSR) model was used to identify optimal prognostic model. Five ML algorithms were used to develop stage classification models. The biological significance of the miRNA signature was analyzed by utilizing DIANA-mirPath. RESULTS: A four-miRNA signature associated with survival was identified and the expression of this signature was strongly correlated with high risk patients. The high risk patients had unfavorable overall survival compared with the low risk group (HR = 4.523, P-value = 2.86e-08). Univariate and multivariate analyses confirmed independent and translational value of this predictive model. A combined ML algorithm identified six miRNA signatures for cancer staging prediction. After using the data balancing algorithm SMOTE, the Support Vector Machine (SVM) algorithm achieved the best classification performance (accuracy = 0.923, sensitivity = 0.927, specificity = 0.919, MCC = 0.843) when compared with other classifiers. Furthermore, enrichment analysis indicated that the identified miRNA signature involved in cancer-associated pathways. CONCLUSIONS: A novel miRNA classification model using the identified prognostic and tumor stage associated miRNA signature will be useful for risk and stage stratification for clinical practice, and the identified miRNA signature can provide promising insight to understand the progression mechanism of ccRCC.

BACKGROUND: Network-based analysis of gene expression through co-expression networks can be used to investigate modular relationships occurring between genes performing different biological functions. An extended description of each of the network modules is therefore a critical step to understand the underlying processes contributing to a disease or a phenotype. Biological integration, topology study and conditions comparison (e.g. wild vs mutant) are the main methods to do so, but to date no tool combines them all into a single pipeline. RESULTS: Here we present GWENA, a new R package that integrates gene co-expression network construction and whole characterization of the detected modules through gene set enrichment, phenotypic association, hub genes detection, topological metric computation, and differential co-expression. To demonstrate its performance, we applied GWENA on two skeletal muscle datasets from young and old patients of GTEx study. Remarkably, we prioritized a gene whose involvement was unknown in the muscle development and growth. Moreover, new insights on the variations in patterns of co-expression were identified. The known phenomena of connectivity loss associated with aging was found coupled to a global reorganization of the relationships leading to expression of known aging related functions. CONCLUSION: GWENA is an R package available through Bioconductor ( https://bioconductor.org/packages/release/bioc/html/GWENA.html ) that has been developed to perform extended analysis of gene co-expression networks. Thanks to biological and topological information as well as differential co-expression, the package helps to dissect the role of genes relationships in diseases conditions or targeted phenotypes. GWENA goes beyond existing packages that perform co-expression analysis by including new tools to fully characterize modules, such as differential co-expression, additional enrichment databases, and network visualization.

BACKGROUND: In recent years, various sequencing techniques have been used to collect biomedical omics datasets. It is usually possible to obtain multiple types of omics data from a single patient sample. Clustering of omics data plays an indispensable role in biological and medical research, and it is helpful to reveal data structures from multiple collections. Nevertheless, clustering of omics data consists of many challenges. The primary challenges in omics data analysis come from high dimension of data and small size of sample. Therefore, it is difficult to find a suitable integration method for structural analysis of multiple datasets. RESULTS: In this paper, a multi-view clustering based on Stiefel manifold method (MCSM) is proposed. The MCSM method comprises three core steps. Firstly, we established a binary optimization model for the simultaneous clustering problem. Secondly, we solved the optimization problem by linear search algorithm based on Stiefel manifold. Finally, we integrated the clustering results obtained from three omics by using k-nearest neighbor method. We applied this approach to four cancer datasets on TCGA. The result shows that our method is superior to several state-of-art methods, which depends on the hypothesis that the underlying omics cluster class is the same. CONCLUSION: Particularly, our approach has better performance than compared approaches when the underlying clusters are inconsistent. For patients with different subtypes, both consistent and differential clusters can be identified at the same time.

BACKGROUND: Full-length isoform quantification from RNA-Seq is a key goal in transcriptomics analyses and has been an area of active development since the beginning. The fundamental difficulty stems from the fact that RNA transcripts are long, while RNA-Seq reads are short. RESULTS: Here we use simulated benchmarking data that reflects many properties of real data, including polymorphisms, intron signal and non-uniform coverage, allowing for systematic comparative analyses of isoform quantification accuracy and its impact on differential expression analysis. Genome, transcriptome and pseudo alignment-based methods are included; and a simple approach is included as a baseline control. CONCLUSIONS: Salmon, kallisto, RSEM, and Cufflinks exhibit the highest accuracy on idealized data, while on more realistic data they do not perform dramatically better than the simple approach. We determine the structural parameters with the greatest impact on quantification accuracy to be length and sequence compression complexity and not so much the number of isoforms. The effect of incomplete annotation on performance is also investigated. Overall, the tested methods show sufficient divergence from the truth to suggest that full-length isoform quantification and isoform level DE should still be employed selectively.

BACKGROUND: Predicting the drug response of a patient is important for precision oncology. In recent studies, multi-omics data have been used to improve the prediction accuracy of drug response. Although multi-omics data are good resources for drug response prediction, the large dimension of data tends to hinder performance improvement. In this study, we aimed to develop a new method, which can effectively reduce the large dimension of data, based on the supervised deep learning model for predicting drug response. RESULTS: We proposed a novel method called Supervised Feature Extraction Learning using Triplet loss (Super.FELT) for drug response prediction. Super.FELT consists of three stages, namely, feature selection, feature encoding using a supervised method, and binary classification of drug response (sensitive or resistant). We used multi-omics data including mutation, copy number aberration, and gene expression, and these were obtained from cell lines [Genomics of Drug Sensitivity in Cancer (GDSC), Cancer Cell Line Encyclopedia (CCLE), and Cancer Therapeutics Response Portal (CTRP)], patient-derived tumor xenografts (PDX), and The Cancer Genome Atlas (TCGA). GDSC was used for training and cross-validation tests, and CCLE, CTRP, PDX, and TCGA were used for external validation. We performed ablation studies for the three stages and verified that the use of multi-omics data guarantees better performance of drug response prediction. Our results verified that Super.FELT outperformed the other methods at external validation on PDX and TCGA and was good at cross-validation on GDSC and external validation on CCLE and CTRP. In addition, through our experiments, we confirmed that using multi-omics data is useful for external non-cell line data. CONCLUSION: By separating the three stages, Super.FELT achieved better performance than the other methods. Through our results, we found that it is important to train encoders and a classifier independently, especially for external test on PDX and TCGA. Moreover, although gene expression is the most powerful data on cell line data, multi-omics promises better performance for external validation on non-cell line data than gene expression data. Source codes of Super.FELT are available at  https://github.com/DMCB-GIST/Super.FELT .

BACKGROUND: Translational regulation is one important aspect of gene expression regulation. Dysregulation of translation results in abnormal cell physiology and leads to diseases. Ribosome profiling (RP), also called ribo-seq, is a powerful experimental technique to study translational regulation. It can capture a snapshot of translation by deep sequencing of ribosome-protected mRNA fragments. Many ribosome profiling data processing tools have been developed. However, almost all tools analyze ribosome profiling data at the gene level. Since different isoforms of a gene may produce different proteins with distinct biological functions, it is advantageous to analyze ribosome profiling data at the isoform level. To meet this need, previously we developed a pipeline to analyze 610 public human ribosome profiling data at the isoform level and constructed HRPDviewer database. RESULTS: To allow other researchers to use our pipeline as well, here we implement our pipeline as an easy-to-use software tool called RPiso. Compared to Ribomap (a widely used tool which provides isoform-level ribosome profiling analyses), our RPiso (1) estimates isoform abundance more accurately, (2) supports analyses on more species, and (3) provides a web-based viewer for interactively visualizing ribosome profiling data on the selected mRNA isoforms. CONCLUSIONS: In this study, we developed RPiso software tool ( http://cosbi7.ee.ncku.edu.tw/RPiso/ ) to provide isoform-level ribosome profiling analyses. RPiso is very easy to install and execute. RPiso also provides a web-based viewer for interactively visualizing ribosome profiling data on the selected mRNA isoforms. We believe that RPiso is a useful tool for researchers to analyze and visualize their own ribosome profiling data at the isoform level.

BACKGROUND: Testing for differential abundance of microbes in disease is a common practice in microbiome studies. Numerous differential abundance (DA) testing methods exist and range from traditional statistical tests to methods designed for microbiome data. Comparison studies of DA testing methods have been performed, but none performed on microbiome datasets collected for the study of real, complex disease. Due to this, DA testing was performed here using various DA methods in two large, uniformly collected gut microbiome datasets on Parkinson disease (PD), and their results compared. RESULTS: Overall, 78-92% of taxa tested were detected as differentially abundant by at least one method, while 5-22% were called differentially abundant by the majority of methods (depending on dataset and filtering of taxonomic data prior to testing). Concordances between method results ranged from 1 to 100%. Average concordance for datasets 1 and 2 were 24% and 28% respectively, and 27% for replicated DA signatures. Concordances increased when removing rarer taxa before testing, increasing average concordances by 2-32%. Certain methods consistently resulted in higher concordances (e.g. ANCOM-BC, LEfSe), while others consistently resulted in lower (e.g. edgeR, fitZIG). Hierarchical clustering revealed three groups of DA signatures that were (1) replicated by the majority of methods on average and included taxa previously associated with PD, (2) replicated by a subset of methods and included taxa largely enriched in PD, and (3) replicated by few to one method(s). CONCLUSIONS: Differential abundance tests yielded varied concordances, and amounts of detected DA signatures. Some methods were more concordant than others on both filtered and unfiltered data, therefore, if consistency with other study methodology is a key goal, one might choose among these methods. Even still, using one method on one dataset may find true associations, but may also detect false positives. To help lower false positives, one might analyze data with two or more DA methods to gauge concordance, and use a built-in replication dataset. This study will hopefully serve to complement previously reported DA method comparison studies by implementing and coalescing a large number of both previously and yet to be compared methods on two real gut microbiome datasets.

BACKGROUND: Cancer develops due to "driver" alterations. Numerous approaches exist for predicting cancer drivers from cohort-scale genomics data. However, methods for personalized analysis of driver genes are underdeveloped. In this study, we developed a novel personalized/batch analysis approach for driver gene prioritization utilizing somatic genomics data, called driveR. RESULTS: Combining genomics information and prior biological knowledge, driveR accurately prioritizes cancer driver genes via a multi-task learning model. Testing on 28 different datasets, this study demonstrates that driveR performs adequately, achieving a median AUC of 0.684 (range 0.651-0.861) on the 28 batch analysis test datasets, and a median AUC of 0.773 (range 0-1) on the 5157 personalized analysis test samples. Moreover, it outperforms existing approaches, achieving a significantly higher median AUC than all of MutSigCV (Wilcoxon rank-sum test p < 0.001), DriverNet (p < 0.001), OncodriveFML (p < 0.001) and MutPanning (p < 0.001) on batch analysis test datasets, and a significantly higher median AUC than DawnRank (p < 0.001) and PRODIGY (p < 0.001) on personalized analysis datasets. CONCLUSIONS: This study demonstrates that the proposed method is an accurate and easy-to-utilize approach for prioritizing driver genes in cancer genomes in personalized or batch analyses. driveR is available on CRAN: https://cran.r-project.org/package=driveR .

BACKGROUND: Biological tissues consist of heterogenous populations of cells. Because gene expression patterns from bulk tissue samples reflect the contributions from all cells in the tissue, understanding the contribution of individual cell types to the overall gene expression in the tissue is fundamentally important. We recently developed a computational method, CDSeq, that can simultaneously estimate both sample-specific cell-type proportions and cell-type-specific gene expression profiles using only bulk RNA-Seq counts from multiple samples. Here we present an R implementation of CDSeq (CDSeqR) with significant performance improvement over the original implementation in MATLAB and an added new function to aid cell type annotation. The R package would be of interest for the broader R community. RESULT: We developed a novel strategy to substantially improve computational efficiency in both speed and memory usage. In addition, we designed and implemented a new function for annotating the CDSeq estimated cell types using single-cell RNA sequencing (scRNA-seq) data. This function allows users to readily interpret and visualize the CDSeq estimated cell types. In addition, this new function further allows the users to annotate CDSeq-estimated cell types using marker genes. We carried out additional validations of the CDSeqR software using synthetic, real cell mixtures, and real bulk RNA-seq data from the Cancer Genome Atlas (TCGA) and the Genotype-Tissue Expression (GTEx) project. CONCLUSIONS: The existing bulk RNA-seq repositories, such as TCGA and GTEx, provide enormous resources for better understanding changes in transcriptomics and human diseases. They are also potentially useful for studying cell-cell interactions in the tissue microenvironment. Bulk level analyses neglect tissue heterogeneity, however, and hinder investigation of a cell-type-specific expression. The CDSeqR package may aid in silico dissection of bulk expression data, enabling researchers to recover cell-type-specific information.

BACKGROUND: MicroRNAs (miRNAs) are small non-coding RNAs that regulate gene expression post-transcriptionally via base-pairing with complementary sequences on messenger RNAs (mRNAs). Due to the technical challenges involved in the application of high-throughput experimental methods, datasets of direct bona fide miRNA targets exist only for a few model organisms. Machine learning (ML)-based target prediction models were successfully trained and tested on some of these datasets. There is a need to further apply the trained models to organisms in which experimental training data are unavailable. However, it is largely unknown how the features of miRNA-target interactions evolve and whether some features have remained fixed during evolution, raising questions regarding the general, cross-species applicability of currently available ML methods. RESULTS: We examined the evolution of miRNA-target interaction rules and used data science and ML approaches to investigate whether these rules are transferable between species. We analyzed eight datasets of direct miRNA-target interactions in four species (human, mouse, worm, cattle). Using ML classifiers, we achieved high accuracy for intra-dataset classification and found that the most influential features of all datasets overlap significantly. To explore the relationships between datasets, we measured the divergence of their miRNA seed sequences and evaluated the performance of cross-dataset classification. We found that both measures coincide with the evolutionary distance between the compared species. CONCLUSIONS: The transferability of miRNA-targeting rules between species depends on several factors, the most associated factors being the composition of seed families and evolutionary distance. Furthermore, our feature-importance results suggest that some miRNA-target features have evolved while others remained fixed during the evolution of the species. Our findings lay the foundation for the future development of target prediction tools that could be applied to "non-model" organisms for which minimal experimental data are available. AVAILABILITY AND IMPLEMENTATION: The code is freely available at https://github.com/gbenor/TPVOD .

Erratum in BMC Bioinformatics. 2021 Jul 9;22(1):366.

BACKGROUND: Recent advances in tissue clearing techniques, combined with high-speed image acquisition through light sheet microscopy, enable rapid three-dimensional (3D) imaging of biological specimens, such as whole mouse brains, in a matter of hours. Quantitative analysis of such 3D images can help us understand how changes in brain structure lead to differences in behavior or cognition, but distinguishing densely packed features of interest, such as nuclei, from background can be challenging. Recent deep learning-based nuclear segmentation algorithms show great promise for automated segmentation, but require large numbers of accurate manually labeled nuclei as training data. RESULTS: We present Segmentor, an open-source tool for reliable, efficient, and user-friendly manual annotation and refinement of objects (e.g., nuclei) within 3D light sheet microscopy images. Segmentor employs a hybrid 2D-3D approach for visualizing and segmenting objects and contains features for automatic region splitting, designed specifically for streamlining the process of 3D segmentation of nuclei. We show that editing simultaneously in 2D and 3D using Segmentor significantly decreases time spent on manual annotations without affecting accuracy as compared to editing the same set of images with only 2D capabilities. CONCLUSIONS: Segmentor is a tool for increased efficiency of manual annotation and refinement of 3D objects that can be used to train deep learning segmentation algorithms, and is available at https://www.nucleininja.org/ and https://github.com/RENCI/Segmentor .

BACKGROUND: The insertion sequence elements (IS elements) represent the smallest and the most abundant mobile elements in prokaryotic genomes. It has been shown that they play a significant role in genome organization and evolution. To better understand their function in the host genome, it is desirable to have an effective detection and annotation tool. This need becomes even more crucial when considering rapid-growing genomic and metagenomic data. The existing tools for IS elements detection and annotation are usually based on comparing sequence similarity with a database of known IS families. Thus, they have limited ability to discover distant and putative novel IS elements. RESULTS: In this paper, we present digIS, a software tool based on profile hidden Markov models assembled from catalytic domains of transposases. It shows a very good performance in detecting known IS elements when tested on datasets with manually curated annotation. The main contribution of digIS is in its ability to detect distant and putative novel IS elements while maintaining a moderate level of false positives. In this category it outperforms existing tools, especially when tested on large datasets of archaeal and bacterial genomes. CONCLUSION: We provide digIS, a software tool using a novel approach based on manually curated profile hidden Markov models, which is able to detect distant and putative novel IS elements. Although digIS can find known IS elements as well, we expect it to be used primarily by scientists interested in finding novel IS elements. The tool is available at https://github.com/janka2012/digIS.

BACKGROUND: Improvements in sequencing technology continue to drive sequencing cost towards $100 per genome. However, mapping sequenced data to a reference genome remains a computationally-intensive task due to the dependence on edit distance for dealing with INDELs and mismatches introduced by sequencing. All modern aligners use seed-filter-extend methodology and rely on filtration heuristics to reduce the overhead of edit distance computation. However, filtering has inherent performance-accuracy trade-offs that limits its effectiveness. RESULTS: Motivated by algorithmic advances in randomized low-distortion embedding, we introduce SEE, a new methodology for developing sequence mappers and aligners. While SFE focuses on eliminating sub-optimal candidates, SEE focuses instead on identifying optimal candidates. To do so, SEE transforms the read and reference strings from edit distance regime to the Hamming regime by embedding them using a randomized algorithm, and uses Hamming distance over the embedded set to identify optimal candidates. To show that SEE performs well in practice, we present Accel-Align an SEE-based short-read sequence mapper and aligner that is 3-12[Formula: see text] faster than state-of-the-art aligners on commodity CPUs, without any special-purpose hardware, while providing comparable accuracy. CONCLUSIONS: As sequencing technologies continue to increase read length while improving throughput and accuracy, we believe that randomized embeddings open up new avenues for optimization that cannot be achieved by using edit distance. Thus, the techniques presented in this paper have a much broader scope as they can be used for other applications like graph alignment, multiple sequence alignment, and sequence assembly.

BACKGROUND: Whole exome sequencing (WES) is widely adopted in clinical and research settings; however, one of the practical concerns is the potential false negatives due to incomplete breadth and depth of coverage for several exons in clinically implicated genes. In some cases, a targeted gene panel testing may be a dependable option to ascertain true negatives for genomic variants in known disease-associated genes. We developed a web-based tool to quickly gauge whether all genes of interest would be reliably covered by WES or whether targeted gene panel testing should be considered instead to minimize false negatives in candidate genes. RESULTS: WEScover is a novel web application that provides an intuitive user interface for discovering breadth and depth of coverage across population-scale WES datasets, searching either by phenotype, by targeted gene panel(s) or by gene(s). Moreover, the application shows metrics from the Genome Aggregation Database to provide gene-centric view on breadth of coverage. CONCLUSIONS: WEScover allows users to efficiently query genes and phenotypes for the coverage of associated exons by WES and recommends use of panel tests for the genes with potential incomplete coverage by WES.

BACKGROUND: Pseudogenes are non-functional copies of protein coding genes that typically follow a different molecular evolutionary path as compared to functional genes. The inclusion of pseudogene sequences in DNA barcoding and metabarcoding analysis can lead to misleading results. None of the most widely used bioinformatic pipelines used to process marker gene (metabarcode) high throughput sequencing data specifically accounts for the presence of pseudogenes in protein-coding marker genes. The purpose of this study is to develop a method to screen for nuclear mitochondrial DNA segments (nuMTs) in large COI datasets. We do this by: (1) describing gene and nuMT characteristics from an artificial COI barcode dataset, (2) show the impact of two different pseudogene removal methods on perturbed community datasets with simulated nuMTs, and (3) incorporate a pseudogene filtering step in a bioinformatic pipeline that can be used to process Illumina paired-end COI metabarcode sequences. Open reading frame length and sequence bit scores from hidden Markov model (HMM) profile analysis were used to detect pseudogenes. RESULTS: Our simulations showed that it was more difficult to identify nuMTs from shorter amplicon sequences such as those typically used in metabarcoding compared with full length DNA barcodes that are used in the construction of barcode libraries. It was also more difficult to identify nuMTs in datasets where there is a high percentage of nuMTs. Existing bioinformatic pipelines used to process metabarcode sequences already remove some nuMTs, especially in the rare sequence removal step, but the addition of a pseudogene filtering step can remove up to 5% of sequences even when other filtering steps are in place. CONCLUSIONS: Open reading frame length filtering alone or combined with hidden Markov model profile analysis can be used to effectively screen out apparent pseudogenes from large datasets. There is more to learn from COI nuMTs such as their frequency in DNA barcoding and metabarcoding studies, their taxonomic distribution, and evolution. Thus, we encourage the submission of verified COI nuMTs to public databases to facilitate future studies.

BACKGROUND: With the development of the technology of single-cell sequence, revealing homogeneity and heterogeneity between cells has become a new area of computational systems biology research. However, the clustering of cell types becomes more complex with the mutual penetration between different types of cells and the instability of gene expression. One way of overcoming this problem is to group similar, related single cells together by the means of various clustering analysis methods. Although some methods such as spectral clustering can do well in the identification of cell types, they only consider the similarities between cells and ignore the influence of dissimilarities on clustering results. This methodology may limit the performance of most of the conventional clustering algorithms for the identification of clusters, it needs to develop special methods for high-dimensional sparse categorical data. RESULTS: Inspired by the phenomenon that same type cells have similar gene expression patterns, but different types of cells evoke dissimilar gene expression patterns, we improve the existing spectral clustering method for clustering single-cell data that is based on both similarities and dissimilarities between cells. The method first measures the similarity/dissimilarity among cells, then constructs the incidence matrix by fusing similarity matrix with dissimilarity matrix, and, finally, uses the eigenvalues of the incidence matrix to perform dimensionality reduction and employs the K-means algorithm in the low dimensional space to achieve clustering. The proposed improved spectral clustering method is compared with the conventional spectral clustering method in recognizing cell types on several real single-cell RNA-seq datasets. CONCLUSIONS: In summary, we show that adding intercellular dissimilarity can effectively improve accuracy and achieve robustness and that improved spectral clustering method outperforms the traditional spectral clustering method in grouping cells.

BACKGROUND: Motivated by the size and availability of cell line drug sensitivity data, researchers have been developing machine learning (ML) models for predicting drug response to advance cancer treatment. As drug sensitivity studies continue generating drug response data, a common question is whether the generalization performance of existing prediction models can be further improved with more training data. METHODS: We utilize empirical learning curves for evaluating and comparing the data scaling properties of two neural networks (NNs) and two gradient boosting decision tree (GBDT) models trained on four cell line drug screening datasets. The learning curves are accurately fitted to a power law model, providing a framework for assessing the data scaling behavior of these models. RESULTS: The curves demonstrate that no single model dominates in terms of prediction performance across all datasets and training sizes, thus suggesting that the actual shape of these curves depends on the unique pair of an ML model and a dataset. The multi-input NN (mNN), in which gene expressions of cancer cells and molecular drug descriptors are input into separate subnetworks, outperforms a single-input NN (sNN), where the cell and drug features are concatenated for the input layer. In contrast, a GBDT with hyperparameter tuning exhibits superior performance as compared with both NNs at the lower range of training set sizes for two of the tested datasets, whereas the mNN consistently performs better at the higher range of training sizes. Moreover, the trajectory of the curves suggests that increasing the sample size is expected to further improve prediction scores of both NNs. These observations demonstrate the benefit of using learning curves to evaluate prediction models, providing a broader perspective on the overall data scaling characteristics. CONCLUSIONS: A fitted power law learning curve provides a forward-looking metric for analyzing prediction performance and can serve as a co-design tool to guide experimental biologists and computational scientists in the design of future experiments in prospective research studies.

BACKGROUND: RNA viruses possess remarkable evolutionary versatility driven by the high mutability of their genomes. Frameshifting nucleotide insertions or deletions (indels), which cause the premature termination of proteins, are frequently observed in the coding sequences of various viral genomes. When a secondary indel occurs near the primary indel site, the open reading frame can be restored to produce functional proteins, a phenomenon known as the compensatory frameshift. RESULTS: In this study, we systematically analyzed publicly available viral genome sequences and identified compensatory frameshift events in hundreds of viral protein-coding sequences. Compensatory frameshift events resulted in large-scale amino acid differences between the compensatory frameshift form and the wild type even though their nucleotide sequences were almost identical. Phylogenetic analyses revealed that the evolutionary distance between proteins with and without a compensatory frameshift were significantly overestimated because amino acid mismatches caused by compensatory frameshifts were counted as substitutions. Further, this could cause compensatory frameshift forms to branch in different locations in the protein and nucleotide trees, which may obscure the correct interpretation of phylogenetic relationships between variant viruses. CONCLUSIONS: Our results imply that the compensatory frameshift is one of the mechanisms driving the rapid protein evolution of RNA viruses and potentially assisting their host-range expansion and adaptation.

BACKGROUND: DNA-binding hot spots are dominant and fundamental residues that contribute most of the binding free energy yet accounting for a small portion of protein-DNA interfaces. As experimental methods for identifying hot spots are time-consuming and costly, high-efficiency computational approaches are emerging as alternative pathways to experimental methods. RESULTS: Herein, we present a new computational method, termed inpPDH, for hot spot prediction. To improve the prediction performance, we extract hybrid features which incorporate traditional features and new interfacial neighbor properties. To remove redundant and irrelevant features, feature selection is employed using a two-step feature selection strategy. Finally, a subset of 7 optimal features are chosen to construct the predictor using support vector machine. The results on the benchmark dataset show that this proposed method yields significantly better prediction accuracy than those previously published methods in the literature. Moreover, a user-friendly web server for inpPDH is well established and is freely available at http://bioinfo.ahu.edu.cn/inpPDH . CONCLUSIONS: We have developed an accurate improved prediction model, inpPDH, for hot spot residues in protein-DNA binding interfaces by given the structure of a protein-DNA complex. Moreover, we identify a comprehensive and useful feature subset including the proposed interfacial neighbor features that has an important strength for identifying hot spot residues. Our results indicate that these features are more effective than the conventional features considered previously, and that the combination of interfacial neighbor features and traditional features may support the creation of a discriminative feature set for efficient prediction of hot spot residues in protein-DNA complexes.

BACKGROUND: Colocalization is a statistical method used in genetics to determine whether the same variant is causal for multiple phenotypes, for example, complex traits and gene expression. It provides stronger mechanistic evidence than shared significance, which can be produced through separate causal variants in linkage disequilibrium. Current colocalization methods require full summary statistics for both traits, limiting their use with the majority of reported GWAS associations (e.g. GWAS Catalog). We propose a new approximation to the popular coloc method that can be applied when limited summary statistics are available. Our method (POint EstiMation of Colocalization, POEMColoc) imputes missing summary statistics for one or both traits using LD structure in a reference panel, and performs colocalization using the imputed summary statistics. RESULTS: We evaluate the performance of POEMColoc using real (UK Biobank phenotypes and GTEx eQTL) and simulated datasets. We show good correlation between posterior probabilities of colocalization computed from imputed and observed datasets and similar accuracy in simulation. We evaluate scenarios that might reduce performance and show that multiple independent causal variants in a region and imputation from a limited subset of typed variants have a larger effect while mismatched ancestry in the reference panel has a modest effect. Further, we find that POEMColoc is a better approximation of coloc when the imputed association statistics are from a well powered study (e.g., relatively larger sample size or effect size). Applying POEMColoc to estimate colocalization of GWAS Catalog entries and GTEx eQTL, we find evidence for colocalization of 150,000 trait-gene-tissue triplets. CONCLUSIONS: We find that colocalization analysis performed with full summary statistics can be closely approximated when only the summary statistics of the top SNP are available for one or both traits. When applied to the full GWAS Catalog and GTEx eQTL, we find that colocalized trait-gene pairs are enriched in tissues relevant to disease etiology and for matches to approved drug mechanisms. POEMColoc R package is available at https://github.com/AbbVie-ComputationalGenomics/POEMColoc .

BACKGROUND: A pair of genes is defined as synthetically lethal if defects on both cause the death of the cell but a defect in only one of the two is compatible with cell viability. Ideally, if A and B are two synthetic lethal genes, inhibiting B should kill cancer cells with a defect on A, and should have no effects on normal cells. Thus, synthetic lethality can be exploited for highly selective cancer therapies, which need to exploit differences between normal and cancer cells. RESULTS: In this paper, we present a new method for predicting synthetic lethal (SL) gene pairs. As neighbouring genes in the genome have highly correlated profiles of copy number variations (CNAs), our method clusters proximal genes with a similar CNA profile, then predicts mutually exclusive group pairs, and finally identifies the SL gene pairs within each group pairs. For mutual-exclusion testing we use a graph-based method which takes into account the mutation frequencies of different subjects and genes. We use two different methods for selecting the pair of SL genes; the first is based on the gene essentiality measured in various conditions by means of the "Gene Activity Ranking Profile" GARP score; the second leverages the annotations of gene to biological pathways. CONCLUSIONS: This method is unique among current SL prediction approaches, it reduces false-positive SL predictions compared to previous methods, and it allows establishing explicit collateral lethality relationship of gene pairs within mutually exclusive group pairs.

BACKGROUND: With the continuous maturity of sequencing technology, different laboratories or different sequencing platforms have generated a large amount of single-cell transcriptome sequencing data for the same or different tissues. Due to batch effects and high dimensions of scRNA data, downstream analysis often faces challenges. Although a number of algorithms and tools have been proposed for removing batch effects, the current mainstream algorithms have faced the problem of data overcorrection when the cell type composition varies greatly between batches. RESULTS: In this paper, we propose a novel method named SSBER by utilizing biological prior knowledge to guide the correction, aiming to solve the problem of poor batch-effect correction when the cell type composition differs greatly between batches. CONCLUSIONS: SSBER effectively solves the above problems and outperforms other algorithms when the cell type structure among batches or distribution of cell population varies considerably, or some similar cell types exist across batches.

BACKGROUND: Some proposed methods for identifying essential proteins have better results by using biological information. Gene expression data is generally used to identify essential proteins. However, gene expression data is prone to fluctuations, which may affect the accuracy of essential protein identification. Therefore, we propose an essential protein identification method based on gene expression and the PPI network data to calculate the similarity of "active" and "inactive" state of gene expression in a cluster of the PPI network. Our experiments show that the method can improve the accuracy in predicting essential proteins. RESULTS: In this paper, we propose a new measure named JDC, which is based on the PPI network data and gene expression data. The JDC method offers a dynamic threshold method to binarize gene expression data. After that, it combines the degree centrality and Jaccard similarity index to calculate the JDC score for each protein in the PPI network. We benchmark the JDC method on four organisms respectively, and evaluate our method by using ROC analysis, modular analysis, jackknife analysis, overlapping analysis, top analysis, and accuracy analysis. The results show that the performance of JDC is better than DC, IC, EC, SC, BC, CC, NC, PeC, and WDC. We compare JDC with both NF-PIN and TS-PIN methods, which predict essential proteins through active PPI networks constructed from dynamic gene expression. CONCLUSIONS: We demonstrate that the new centrality measure, JDC, is more efficient than state-of-the-art prediction methods with same input. The main ideas behind JDC are as follows: (1) Essential proteins are generally densely connected clusters in the PPI network. (2) Binarizing gene expression data can screen out fluctuations in gene expression profiles. (3) The essentiality of the protein depends on the similarity of "active" and "inactive" state of gene expression in a cluster of the PPI network.

BACKGROUND: One of the main advantages of the Oxford Nanopore Technology (ONT) is the possibility of real-time sequencing. This gives access to information during the experiment and allows either to control the sequencing or to stop the sequencing once the results have been obtained. However, the ONT sequencing interface is not sufficient to explore the quality of sequencing data in depth and existing quality control tools do not take full advantage of real-time data streaming. RESULTS: Herein, we present BoardION, an interactive web application to analyze the efficiency of ONT sequencing runs. The interactive interface of BoardION allows users to easily explore sequencing metrics and optimize the quantity and the quality of the data generated during the experiment. It also enables the comparison of multiple flowcells to assess library preparation protocols or the quality of input samples. CONCLUSION: BoardION is dedicated to people who manage ONT sequencing instruments and allows them to remotely and in real time monitor their experiments and compare multiple sequencing runs. Source code, a Docker image and a demo version are available at http://www.genoscope.cns.fr/boardion/ .

BACKGROUND: The prediction of long non-coding RNA (lncRNA) has attracted great attention from researchers, as more and more evidence indicate that various complex human diseases are closely related to lncRNAs. In the era of bio-med big data, in addition to the prediction of lncRNAs by biological experimental methods, many computational methods based on machine learning have been proposed to make better use of the sequence resources of lncRNAs. RESULTS: We developed the lncRNA prediction method by integrating information-entropy-based features and machine learning algorithms. We calculate generalized topological entropy and generate 6 novel features for lncRNA sequences. By employing these 6 features and other features such as open reading frame, we apply supporting vector machine, XGBoost and random forest algorithms to distinguish human lncRNAs. We compare our method with the one which has more K-mer features and results show that our method has higher area under the curve up to 99.7905%. CONCLUSIONS: We develop an accurate and efficient method which has novel information entropy features to analyze and classify lncRNAs. Our method is also extendable for research on the other functional elements in DNA sequences.

BACKGROUND: Long noncoding RNAs (lncRNAs) play important roles in multiple biological processes. Identifying LncRNA-protein interactions (LPIs) is key to understanding lncRNA functions. Although some LPIs computational methods have been developed, the LPIs prediction problem remains challenging. How to integrate multimodal features from more perspectives and build deep learning architectures with better recognition performance have always been the focus of research on LPIs. RESULTS: We present a novel multichannel capsule network framework to integrate multimodal features for LPI prediction, Capsule-LPI. Capsule-LPI integrates four groups of multimodal features, including sequence features, motif information, physicochemical properties and secondary structure features. Capsule-LPI is composed of four feature-learning subnetworks and one capsule subnetwork. Through comprehensive experimental comparisons and evaluations, we demonstrate that both multimodal features and the architecture of the multichannel capsule network can significantly improve the performance of LPI prediction. The experimental results show that Capsule-LPI performs better than the existing state-of-the-art tools. The precision of Capsule-LPI is 87.3%, which represents a 1.7% improvement. The F-value of Capsule-LPI is 92.2%, which represents a 1.4% improvement. CONCLUSIONS: This study provides a novel and feasible LPI prediction tool based on the integration of multimodal features and a capsule network. A webserver ( http://csbg-jlu.site/lpc/predict ) is developed to be convenient for users.

BACKGROUND: Rapid analysis of SARS-CoV-2 genomic data plays a crucial role in surveillance and adoption of measures in controlling spread of Covid-19. Fast, inclusive and adaptive methods are required for the heterogenous SARS-CoV-2 sequence data generated at an unprecedented rate. RESULTS: We present an updated version of the SARS-CoV-2 analysis module of our automated computational pipeline, Infectious Pathogen Detector (IPD) 2.0, to perform genomic analysis to understand the variability and dynamics of the virus. It adopts the recent clade nomenclature and demonstrates the clade prediction accuracy of 92.8%. IPD 2.0 also contains a SARS-CoV-2 updater module, allowing automatic upgrading of the variant database using genome sequences from GISAID. As a proof of principle, analyzing 208,911 SARS-CoV-2 genome sequences, we generate an extensive database of 2.58 million sample-wise variants. A comparative account of lineage-specific mutations in the newer SARS-CoV-2 strains emerging in the UK, South Africa and Brazil and data reported from India identify overlapping and lineages specific acquired mutations suggesting a repetitive convergent and adaptive evolution. CONCLUSIONS: A novel and dynamic feature of the SARS-CoV-2 module of IPD 2.0 makes it a contemporary tool to analyze the diverse and growing genomic strains of the virus and serve as a vital tool to help facilitate rapid genomic surveillance in a population to identify variants involved in breakthrough infections. IPD 2.0 is freely available from http://www.actrec.gov.in/pi-webpages/AmitDutt/IPD/IPD.html and the web-application is available at http://ipd.actrec.gov.in/ipdweb/ .

BACKGROUND: In the development of science and technology, there are increasing evidences that there are some associations between lncRNAs and human diseases. Therefore, finding these associations between them will have a huge impact on our treatment and prevention of some diseases. However, the process of finding the associations between them is very difficult and requires a lot of time and effort. Therefore, it is particularly important to find some good methods for predicting lncRNA-disease associations (LDAs). RESULTS: In this paper, we propose a method based on dual sparse collaborative matrix factorization (DSCMF) to predict LDAs. The DSCMF method is improved on the traditional collaborative matrix factorization method. To increase the sparsity, the L2,1-norm is added in our method. At the same time, Gaussian interaction profile kernel is added to our method, which increase the network similarity between lncRNA and disease. Finally, the AUC value obtained by the experiment is used to evaluate the quality of our method, and the AUC value is obtained by the ten-fold cross-validation method. CONCLUSIONS: The AUC value obtained by the DSCMF method is 0.8523. At the end of the paper, simulation experiment is carried out, and the experimental results of prostate cancer, breast cancer, ovarian cancer and colorectal cancer are analyzed in detail. The DSCMF method is expected to bring some help to lncRNA-disease associations research. The code can access the https://github.com/Ming-0113/DSCMF website.

BACKGROUND: Long noncoding RNAs (lncRNAs) play an important role in regulating biological activities and their prediction is significant for exploring biological processes. Long short-term memory (LSTM) and convolutional neural network (CNN) can automatically extract and learn the abstract information from the encoded RNA sequences to avoid complex feature engineering. An ensemble model learns the information from multiple perspectives and shows better performance than a single model. It is feasible and interesting that the RNA sequence is considered as sentence and image to train LSTM and CNN respectively, and then the trained models are hybridized to predict lncRNAs. Up to present, there are various predictors for lncRNAs, but few of them are proposed for plant. A reliable and powerful predictor for plant lncRNAs is necessary. RESULTS: To boost the performance of predicting lncRNAs, this paper proposes a hybrid deep learning model based on two encoding styles (PlncRNA-HDeep), which does not require prior knowledge and only uses RNA sequences to train the models for predicting plant lncRNAs. It not only learns the diversified information from RNA sequences encoded by p-nucleotide and one-hot encodings, but also takes advantages of lncRNA-LSTM proposed in our previous study and CNN. The parameters are adjusted and three hybrid strategies are tested to maximize its performance. Experiment results show that PlncRNA-HDeep is more effective than lncRNA-LSTM and CNN and obtains 97.9% sensitivity, 95.1% precision, 96.5% accuracy and 96.5% F1 score on Zea mays dataset which are better than those of several shallow machine learning methods (support vector machine, random forest, k-nearest neighbor, decision tree, naive Bayes and logistic regression) and some existing tools (CNCI, PLEK, CPC2, LncADeep and lncRNAnet). CONCLUSIONS: PlncRNA-HDeep is feasible and obtains the credible predictive results. It may also provide valuable references for other related research.

BACKGROUND: The state-of-the-art deep learning based cancer type prediction can only predict cancer types whose samples are available during the training where the sample size is commonly large. In this paper, we consider how to utilize the existing training samples to predict cancer types unseen during the training. We hypothesize the existence of a set of type-agnostic expression representations that define the similarity/dissimilarity between samples of the same/different types and propose a novel one-shot learning model called CancerSiamese to learn this common representation. CancerSiamese accepts a pair of query and support samples (gene expression profiles) and learns the representation of similar or dissimilar cancer types through two parallel convolutional neural networks joined by a similarity function. RESULTS: We trained CancerSiamese for cancer type prediction for primary and metastatic tumors using samples from the Cancer Genome Atlas (TCGA) and MET500. Network transfer learning was utilized to facilitate the training of the CancerSiamese models. CancerSiamese was tested for different N-way predictions and yielded an average accuracy improvement of 8% and 4% over the benchmark 1-Nearest Neighbor (1-NN) classifier for primary and metastatic tumors, respectively. Moreover, we applied the guided gradient saliency map and feature selection to CancerSiamese to examine 100 and 200 top marker-gene candidates for the prediction of primary and metastatic cancers, respectively. Functional analysis of these marker genes revealed several cancer related functions between primary and metastatic tumors. CONCLUSION: This work demonstrated, for the first time, the feasibility of predicting unseen cancer types whose samples are limited. Thus, it could inspire new and ingenious applications of one-shot and few-shot learning solutions for improving cancer diagnosis, prognostic, and our understanding of cancer.

BACKGROUND: tRNA-derived fragments have been reported to be key regulatory factors in human tumors. However, their roles in the progression of multiple myeloma remain unknown. RESULTS: This study employed RNA-sequencing to explore the expression profiles of tRFs/tiRNAs in new diagnosed MM and relapsed/refractory MM samples. The expression of selected tRFs/tiRNAs were further validated in clinical specimens and myeloma cell lines by qPCR. Bioinformatic analysis was performed to predict their roles in multiple myeloma progression.We identified 10 upregulated tRFs/tiRNAs and 16 downregulated tRFs/tiRNAs. GO enrichment and KEGG pathway analysis were performed to analyse the functions of 1 significantly up-regulated and 1 significantly down-regulated tRNA-derived fragments. tRFs/tiRNAs may be involved in MM progression and drug-resistance. CONCLUSION: tRFs/tiRNAs were dysregulated and could be potential biomarkers for relapsed/refractory MM.

BACKGROUND: Current methods in machine learning provide approaches for solving challenging, multiple constraint design problems. While deep learning and related neural networking methods have state-of-the-art performance, their vulnerability in decision making processes leading to irrational outcomes is a major concern for their implementation. With the rising antibiotic resistance, antimicrobial peptides (AMPs) have increasingly gained attention as novel therapeutic agents. This challenging design problem requires peptides which meet the multiple constraints of limiting drug-resistance in bacteria, preventing secondary infections from imbalanced microbial flora, and avoiding immune system suppression. AMPs offer a promising, bioinspired design space to targeting antimicrobial activity, but their versatility also requires the curated selection from a combinatorial sequence space. This space is too large for brute-force methods or currently known rational design approaches outside of machine learning. While there has been progress in using the design space to more effectively target AMP activity, a widely applicable approach has been elusive. The lack of transparency in machine learning has limited the advancement of scientific knowledge of how AMPs are related among each other, and the lack of general applicability for fully rational approaches has limited a broader understanding of the design space. METHODS: Here we combined an evolutionary method with rough set theory, a transparent machine learning approach, for designing antimicrobial peptides (AMPs). Our method achieves the customization of AMPs using supervised learning boundaries. Our system employs in vitro bacterial assays to measure fitness, codon-representation of peptides to gain flexibility of sequence selection in DNA-space with a genetic algorithm and machine learning to further accelerate the process. RESULTS: We use supervised machine learning and a genetic algorithm to find a peptide active against S. epidermidis, a common bacterial strain for implant infections, with an improved aggregation propensity average for an improved ease of synthesis. CONCLUSIONS: Our results demonstrate that AMP design can be customized to maintain activity and simplify production. To our knowledge, this is the first time when codon-based genetic algorithms combined with rough set theory methods is used for computational search on peptide sequences.

BACKGROUND: The temporal coordination of biological processes by the circadian clock is an important mechanism, and its disruption has negative health outcomes, including cancer. Experimental and theoretical evidence suggests that the oscillators driving the circadian clock and the cell cycle are coupled through phase locking. RESULTS: We present a detailed and documented map of known mechanisms related to the regulation of the circadian clock, and its coupling with an existing cell cycle map which includes main interactions of the mammalian cell cycle. The coherence of the merged map has been validated with a qualitative dynamics analysis. We verified that the coupled circadian clock and cell cycle maps reproduce the observed sequence of phase markers. Moreover, we predicted mutations that contribute to regulating checkpoints of the two oscillators. CONCLUSIONS: Our approach underlined the potential key role of the core clock protein NR1D1 in regulating cell cycle progression. We predicted that its activity influences negatively the progression of the cell cycle from phase G2 to M. This is consistent with the earlier experimental finding that pharmacological activation of NR1D1 inhibits tumour cell proliferation and shows that our approach can identify biologically relevant species in the context of large and complex networks.

BACKGROUND: Innovations in single cell technologies have lead to a flurry of datasets and computational tools to process and interpret them, including analyses of cell composition changes and transition in cell states. The diffcyt workflow for differential discovery in cytometry data consist of several steps, including preprocessing, cell population identification and differential testing for an association with a binary or continuous covariate. However, the commonly measured quantity of survival time in clinical studies often results in a censored covariate where classical differential testing is inapplicable. RESULTS: To overcome this limitation, multiple methods to directly include censored covariates in differential abundance analysis were examined with the use of simulation studies and a case study. Results show that multiple imputation based methods offer on-par performance with the Cox proportional hazards model in terms of sensitivity and error control, while offering flexibility to account for covariates. The tested methods are implemented in the R package censcyt as an extension of diffcyt and are available at https://bioconductor.org/packages/censcyt . CONCLUSION: Methods for the direct inclusion of a censored variable as a predictor in GLMMs are a valid alternative to classical survival analysis methods, such as the Cox proportional hazard model, while allowing for more flexibility in the differential analysis.

BACKGROUND: MicroRNAs (miRNAs) function in post-transcriptional regulation of gene expression by binding to target messenger RNAs (mRNAs). Because of the key part that miRNAs play, understanding the correct regulatory role of miRNAs in diverse patho-physiological conditions is of great interest. Although it is known that miRNAs act combinatorially to regulate genes, precise identification of miRNA-gene interactions and their specific functional roles in regulatory comodules remains a challenge. We developed THEIA, an effective method for simultaneously predicting miRNA-gene interactions and regulatory comodules, which group functionally related miRNAs and genes via non-negative matrix factorization (NMF). RESULTS: We apply THEIA to RNA sequencing data from breast invasive carcinoma samples and demonstrate its effectiveness in discovering biologically significant regulatory comodules that are significantly enriched in spatial miRNA clusters, biological pathways, and various cancers. CONCLUSIONS: THEIA is a theoretically rigorous optimization algorithm that simultaneously predicts the strength and direction (i.e., up-regulation or down-regulation) of the effect of modules of miRNAs on a gene. We posit that if THEIA is capable of recovering known clusters of genes and miRNA, then the clusters found by our method not previously identified by literature are also likely to have biological significance. We believe that these novel regulatory comodules found by our method will be a springboard for further research into the specific functional roles of these new functional ensembles of miRNAs and genes,especially those related to diseases like breast cancer.

BACKGROUND: High resolution HLA genotyping of donors and recipients is a crucially important prerequisite for haematopoetic stem-cell transplantation and relies heavily on the quality and completeness of immunogenetic reference sequence databases of allelic variation. RESULTS: Here, we report on DR2S, an R package that leverages the strengths of two sequencing technologies-the accuracy of next-generation sequencing with the read length of third-generation sequencing technologies like PacBio's SMRT sequencing or ONT's nanopore sequencing-to reconstruct fully-phased high-quality full-length haplotype sequences. Although optimised for HLA and KIR genes, DR2S is applicable to all loci with known reference sequences provided that full-length sequencing data is available for analysis. In addition, DR2S integrates supporting tools for easy visualisation and quality control of the reconstructed haplotype to ensure suitability for submission to public allele databases. CONCLUSIONS: DR2S is a largely automated workflow designed to create high-quality fully-phased reference allele sequences for highly polymorphic gene regions such as HLA or KIR. It has been used by biologists to successfully characterise and submit more than 500 HLA alleles and more than 500 KIR alleles to the IPD-IMGT/HLA and IPD-KIR databases.

BACKGROUND: Simulated metagenomic reads are widely used to benchmark software and workflows for metagenome interpretation. The results of metagenomic benchmarks depend on the assumptions about their underlying ecosystems. Conclusions from benchmark studies are therefore limited to the ecosystems they mimic. Ideally, simulations are therefore based on genomes, which resemble particular metagenomic communities realistically. RESULTS: We developed Tamock to facilitate the realistic simulation of metagenomic reads according to a metagenomic community, based on real sequence data. Benchmarks samples can be created from all genomes and taxonomic domains present in NCBI RefSeq. Tamock automatically determines taxonomic profiles from shotgun sequence data, selects reference genomes accordingly and uses them to simulate metagenomic reads. We present an example use case for Tamock by assessing assembly and binning method performance for selected microbiomes. CONCLUSIONS: Tamock facilitates automated simulation of habitat-specific benchmark metagenomic data based on real sequence data and is implemented as a user-friendly command-line application, providing extensive additional information along with the simulated benchmark data. Resulting benchmarks enable an assessment of computational methods, workflows, and parameters specifically for a metagenomic habitat or ecosystem of a metagenomic study. AVAILABILITY: Source code, documentation and install instructions are freely available at GitHub ( https://github.com/gerners/tamock ).

Erratum in BMC Bioinformatics. 2021 Jul 22;22(1):381.

BACKGROUND: In phylogenetic analysis, it is common to infer unrooted trees. However, knowing the root location is desirable for downstream analyses and interpretation. There exist several methods to recover a root, such as molecular clock analysis (including midpoint rooting) or rooting the tree using an outgroup. Non-reversible Markov models can also be used to compute the likelihood of a potential root position. RESULTS: We present a software called RootDigger which uses a non-reversible Markov model to compute the most likely root location on a given tree and to infer a confidence value for each possible root placement. We find that RootDigger is successful at finding roots when compared to similar tools such as IQ-TREE and MAD, and will occasionally outperform them. Additionally, we find that the exhaustive mode of RootDigger is useful in quantifying and explaining uncertainty in rooting positions. CONCLUSIONS: RootDigger can be used on an existing phylogeny to find a root, or to asses the uncertainty of the root placement. RootDigger is available under the MIT licence at https://www.github.com/computations/root_digger .

BACKGROUND: Principal component analysis (PCA) is commonly applied to the atomic trajectories of biopolymers to extract essential dynamics that describe biologically relevant motions. Although application of PCA is straightforward, specialized software to facilitate workflows and analysis of molecular dynamics simulation data to fully harness the power of PCA is lacking. The Java Essential Dynamics inspector (JEDi) software is a major upgrade from the previous JED software. RESULTS: Employing multi-threading, JEDi features a user-friendly interface to control rapid workflows for interrogating conformational motions of biopolymers at various spatial resolutions and within subregions, including multiple chain proteins. JEDi has options for Cartesian-based coordinates (cPCA) and internal distance pair coordinates (dpPCA) to construct covariance (Q), correlation (R), and partial correlation (P) matrices. Shrinkage and outlier thresholding are implemented for the accurate estimation of covariance. The effect of rare events is quantified using outlier and inlier filters. Applying sparsity thresholds in statistical models identifies latent correlated motions. Within a hierarchical approach, small-scale atomic motion is first calculated with a separate local cPCA calculation per residue to obtain eigenresidues. Then PCA on the eigenresidues yields rapid and accurate description of large-scale motions. Local cPCA on all residue pairs creates a map of all residue-residue dynamical couplings. Additionally, kernel PCA is implemented. JEDi output gives high quality PNG images by default, with options for text files that include aligned coordinates, several metrics that quantify mobility, PCA modes with their eigenvalues, and displacement vector projections onto the top principal modes. JEDi provides PyMol scripts together with PDB files to visualize individual cPCA modes and the essential dynamics occurring within user-selected time scales. Subspace comparisons performed on the most relevant eigenvectors using several statistical metrics quantify similarity/overlap of high dimensional vector spaces. Free energy landscapes are available for both cPCA and dpPCA. CONCLUSION: JEDi is a convenient toolkit that applies best practices in multivariate statistics for comparative studies on the essential dynamics of similar biopolymers. JEDi helps identify functional mechanisms through many integrated tools and visual aids for inspecting and quantifying similarity/differences in mobility and dynamic correlations.