BACKGROUND: Ontology-based semantic similarity measures based on SNOMED-CT, MeSH, and Gene Ontology are being extensively used in many applications in biomedical text mining and genomics respectively, which has encouraged the development of semantic measures libraries based on the aforementioned ontologies. However, current state-of-the-art semantic measures libraries have some performance and scalability drawbacks derived from their ontology representations based on relational databases, or naive in-memory graph representations. Likewise, a recent reproducible survey on word similarity shows that one hybrid IC-based measure which integrates a shortest-path computation sets the state of the art in the family of ontology-based semantic measures. However, the lack of an efficient shortest-path algorithm for their real-time computation prevents both their practical use in any application and the use of any other path-based semantic similarity measure. RESULTS: To bridge the two aforementioned gaps, this work introduces for the first time an updated version of the HESML Java software library especially designed for the biomedical domain, which implements the most efficient and scalable ontology representation reported in the literature, together with a new method for the approximation of the Dijkstra's algorithm for taxonomies, called Ancestors-based Shortest-Path Length (AncSPL), which allows the real-time computation of any path-based semantic similarity measure. CONCLUSIONS: We introduce a set of reproducible benchmarks showing that HESML outperforms by several orders of magnitude the current state-of-the-art libraries in the three aforementioned biomedical ontologies, as well as the real-time performance and approximation quality of the new AncSPL shortest-path algorithm. Likewise, we show that AncSPL linearly scales regarding the dimension of the common ancestor subgraph regardless of the ontology size. Path-based measures based on the new AncSPL algorithm are up to six orders of magnitude faster than their exact implementation in large ontologies like SNOMED-CT and GO. Finally, we provide a detailed reproducibility protocol and dataset as supplementary material to allow the exact replication of all our experiments and results.

BACKGROUND: Next-generation sequencing (NGS) is nowadays the most used high-throughput technology for DNA sequencing. Among others NGS enables the in-depth analysis of immune repertoires. Research in the field of T cell receptor (TCR) and immunoglobulin (IG) repertoires aids in understanding immunological diseases. A main objective is the analysis of the V(D)J recombination defining the structure and specificity of the immune repertoire. Accurate processing, evaluation and visualization of immune repertoire NGS data is important for better understanding immune responses and immunological behavior. RESULTS: ImmunoDataAnalyzer (IMDA) is a pipeline we have developed for automatizing the analysis of immunological NGS data. IMDA unites the functionality from carefully selected immune repertoire analysis software tools and covers the whole spectrum from initial quality control up to the comparison of multiple immune repertoires. It provides methods for automated pre-processing of barcoded and UMI tagged immune repertoire NGS data, facilitates the assembly of clonotypes and calculates key figures for describing the immune repertoire. These include commonly used clonality and diversity measures, as well as indicators for V(D)J gene segment usage and between sample similarity. IMDA reports all relevant information in a compact summary containing visualizations, calculations, and sample details, all of which serve for a more detailed overview. IMDA further generates an output file including key figures for all samples, designed to serve as input for machine learning frameworks to find models for differentiating between specific traits of samples. CONCLUSIONS: IMDA constructs TCR and IG repertoire data from raw NGS reads and facilitates descriptive data analysis and comparison of immune repertoires. The IMDA workflow focus on quality control and ease of use for non-computer scientists. The provided output directly facilitates the interpretation of input data and includes information about clonality, diversity, clonotype overlap as well as similarity, and V(D)J gene segment usage. IMDA further supports the detection of sample swaps and cross-sample contamination that potentially occurred during sample preparation. In summary, IMDA reduces the effort usually required for immune repertoire data analysis by providing an automated workflow for processing raw NGS data into immune repertoires and subsequent analysis. The implementation is open-source and available on https://bioinformatics.fh-hagenberg.at/immunoanalyzer/ .

BACKGROUND: RIFINs and STEVORs are variant surface antigens expressed by P. falciparum that play roles in severe malaria pathogenesis and immune evasion. These two highly diverse multigene families feature multiple paralogs, making their classification challenging using traditional bioinformatic methods. RESULTS: STRIDE (STevor and RIfin iDEntifier) is an HMM-based, command-line program that automates the identification and classification of RIFIN and STEVOR protein sequences in the malaria parasite Plasmodium falciparum. STRIDE is more sensitive in detecting RIFINs and STEVORs than available PFAM and TIGRFAM tools and reports RIFIN subtypes and the number of sequences with a FHEYDER amino acid motif, which has been associated with severe malaria pathogenesis. CONCLUSIONS: STRIDE will be beneficial to malaria research groups analyzing genome sequences and transcripts of clinical field isolates, providing insight into parasite biology and virulence.

BACKGROUND: Sequencing technologies are prone to errors, making error correction (EC) necessary for downstream applications. EC tools need to be manually configured for optimal performance. We find that the optimal parameters (e.g., k-mer size) are both tool- and dataset-dependent. Moreover, evaluating the performance (i.e., Alignment-rate or Gain) of a given tool usually relies on a reference genome, but quality reference genomes are not always available. We introduce Lerna for the automated configuration of k-mer-based EC tools. Lerna first creates a language model (LM) of the uncorrected genomic reads, and then, based on this LM, calculates a metric called the perplexity metric to evaluate the corrected reads for different parameter choices. Next, it finds the one that produces the highest alignment rate without using a reference genome. The fundamental intuition of our approach is that the perplexity metric is inversely correlated with the quality of the assembly after error correction. Therefore, Lerna leverages the perplexity metric for automated tuning of k-mer sizes without needing a reference genome. RESULTS: First, we show that the best k-mer value can vary for different datasets, even for the same EC tool. This motivates our design that automates k-mer size selection without using a reference genome. Second, we show the gains of our LM using its component attention-based transformers. We show the model's estimation of the perplexity metric before and after error correction. The lower the perplexity after correction, the better the k-mer size. We also show that the alignment rate and assembly quality computed for the corrected reads are strongly negatively correlated with the perplexity, enabling the automated selection of k-mer values for better error correction, and hence, improved assembly quality. We validate our approach on both short and long reads. Additionally, we show that our attention-based models have significant runtime improvement for the entire pipeline-18[Formula: see text] faster than previous works, due to parallelizing the attention mechanism and the use of JIT compilation for GPU inferencing. CONCLUSION: Lerna improves de novo genome assembly by optimizing EC tools. Our code is made available in a public repository at: https://github.com/icanforce/lerna-genomics .

BACKGROUND: The gene-specific sweep is a selection process where an advantageous mutation along with the nearby neutral sites in a gene region increases the frequency in the population. It has been demonstrated to play important roles in ecological differentiation or phenotypic divergence in microbial populations. Therefore, identifying gene-specific sweeps in microorganisms will not only provide insights into the evolutionary mechanisms, but also unravel potential genetic markers associated with biological phenotypes. However, current methods were mainly developed for detecting selective sweeps in eukaryotic data of sparse genotypes and are not readily applicable to prokaryotic data. Furthermore, some challenges have not been sufficiently addressed by the methods, such as the low spatial resolution of sweep regions and lack of consideration of the spatial distribution of mutations. RESULTS: We proposed a novel gene-centric and spatial-aware approach for identifying gene-specific sweeps in prokaryotes and implemented it in a python tool SweepCluster. Our method searches for gene regions with a high level of spatial clustering of pre-selected polymorphisms in genotype datasets assuming a null distribution model of neutral selection. The pre-selection of polymorphisms is based on their genetic signatures, such as elevated population subdivision, excessive linkage disequilibrium, or significant phenotype association. Performance evaluation using simulation data showed that the sensitivity and specificity of the clustering algorithm in SweepCluster is above 90%. The application of SweepCluster in two real datasets from the bacteria Streptococcus pyogenes and Streptococcus suis showed that the impact of pre-selection was dramatic and significantly reduced the uninformative signals. We validated our method using the genotype data from Vibrio cyclitrophicus, the only available dataset of gene-specific sweeps in bacteria, and obtained a concordance rate of 78%. We noted that the concordance rate could be underestimated due to distinct reference genomes and clustering strategies. The application to the human genotype datasets showed that SweepCluster is also applicable to eukaryotic data and is able to recover 80% of a catalog of known sweep regions. CONCLUSION: SweepCluster is applicable to a broad category of datasets. It will be valuable for detecting gene-specific sweeps in diverse genotypic data and provide novel insights on adaptive evolution.

BACKGROUND: Amplicon sequencing of marker genes such as 16S rDNA have been widely used to survey and characterize microbial community. However, the complex data analyses have required many interfering manual steps often leading to inconsistencies in results. RESULTS: Here, we have developed a pipeline, amplicon sequence analysis pipeline 2 (ASAP 2), to automate and glide through the processes without the usual manual inspections and user's interference, for instance, in the detection of barcode orientation, selection of high-quality region of reads, and determination of resampling depth and many more. The pipeline integrates all the analytical processes such as importing data, demultiplexing, summarizing read profiles, trimming quality, denoising, removing chimeric sequences and making the feature table among others. The pipeline accepts multiple file formats as input including multiplexed or demultiplexed, paired-end or single-end, barcode inside or outside and raw or intermediate data (e.g. feature table). The outputs include taxonomic classification, alpha/beta diversity, community composition, ordination analysis and statistical tests. ASAP 2 supports merging multiple sequencing runs which helps integrate and compare data from different sources (public databases and collaborators). CONCLUSIONS: Our pipeline minimizes hands-on interference and runs amplicon sequence variant (ASV)-based amplicon sequencing analysis automatically and consistently. Our web server assists researchers that have no access to high performance computer (HPC) or have limited bioinformatics skills. The pipeline and web server can be accessed at https://github.com/tianrenmaogithub/asap2 and https://hts.iit.edu/asap2 , respectively.

BACKGROUND: A limitation of traditional differential expression analysis on small datasets involves the possibility of false positives and false negatives due to sample variation. Considering the recent advances in deep learning (DL) based models, we wanted to expand the state-of-the-art in disease biomarker prediction from RNA-seq data using DL. However, application of DL to RNA-seq data is challenging due to absence of appropriate labels and smaller sample size as compared to number of genes. Deep learning coupled with transfer learning can improve prediction performance on novel data by incorporating patterns learned from other related data. With the emergence of new disease datasets, biomarker prediction would be facilitated by having a generalized model that can transfer the knowledge of trained feature maps to the new dataset. To the best of our knowledge, there is no Convolutional Neural Network (CNN)-based model coupled with transfer learning to predict the significant upregulating (UR) and downregulating (DR) genes from both trained and untrained datasets. RESULTS: We implemented a CNN model, DEGnext, to predict UR and DR genes from gene expression data obtained from The Cancer Genome Atlas database. DEGnext uses biologically validated data along with logarithmic fold change values to classify differentially expressed genes (DEGs) as UR and DR genes. We applied transfer learning to our model to leverage the knowledge of trained feature maps to untrained cancer datasets. DEGnext's results were competitive (ROC scores between 88 and 99[Formula: see text]) with those of five traditional machine learning methods: Decision Tree, K-Nearest Neighbors, Random Forest, Support Vector Machine, and XGBoost. DEGnext was robust and effective in terms of transferring learned feature maps to facilitate classification of unseen datasets. Additionally, we validated that the predicted DEGs from DEGnext were mapped to significant Gene Ontology terms and pathways related to cancer. CONCLUSIONS: DEGnext can classify DEGs into UR and DR genes from RNA-seq cancer datasets with high performance. This type of analysis, using biologically relevant fine-tuning data, may aid in the exploration of potential biomarkers and can be adapted for other disease datasets.

BACKGROUND: In biomedical research, chemical and disease relation extraction from unstructured biomedical literature is an essential task. Effective context understanding and knowledge integration are two main research problems in this task. Most work of relation extraction focuses on classification for entity mention pairs. Inspired by the effectiveness of machine reading comprehension (RC) in the respect of context understanding, solving biomedical relation extraction with the RC framework at both intra-sentential and inter-sentential levels is a new topic worthy to be explored. Except for the unstructured biomedical text, many structured knowledge bases (KBs) provide valuable guidance for biomedical relation extraction. Utilizing knowledge in the RC framework is also worthy to be investigated. We propose a knowledge-enhanced reading comprehension (KRC) framework to leverage reading comprehension and prior knowledge for biomedical relation extraction. First, we generate questions for each relation, which reformulates the relation extraction task to a question answering task. Second, based on the RC framework, we integrate knowledge representation through an efficient knowledge-enhanced attention interaction mechanism to guide the biomedical relation extraction. RESULTS: The proposed model was evaluated on the BioCreative V CDR dataset and CHR dataset. Experiments show that our model achieved a competitive document-level F1 of 71.18% and 93.3%, respectively, compared with other methods. CONCLUSION: Result analysis reveals that open-domain reading comprehension data and knowledge representation can help improve biomedical relation extraction in our proposed KRC framework. Our work can encourage more research on bridging reading comprehension and biomedical relation extraction and promote the biomedical relation extraction.

BACKGROUND: Single-cell RNA sequencing is becoming a powerful tool to identify cell states, reconstruct developmental trajectories, and deconvolute spatial expression. The rapid development of computational methods promotes the insight of heterogeneous single-cell data. An increasing number of tools have been provided for biological analysts, of which two programming languages- R and Python are widely used among researchers. R and Python are complementary, as many methods are implemented specifically in R or Python. However, the different platforms immediately caused the data sharing and transformation problem, especially for Scanpy, Seurat, and SingleCellExperiemnt. Currently, there is no efficient and user-friendly software to perform data transformation of single-cell omics between platforms, which makes users spend unbearable time on data Input and Output (IO), significantly reducing the efficiency of data analysis. RESULTS: We developed scDIOR for single-cell data transformation between platforms of R and Python based on Hierarchical Data Format Version 5 (HDF5). We have created a data IO ecosystem between three R packages (Seurat, SingleCellExperiment, Monocle) and a Python package (Scanpy). Importantly, scDIOR accommodates a variety of data types across programming languages and platforms in an ultrafast way, including single-cell RNA-seq and spatial resolved transcriptomics data, using only a few codes in IDE or command line interface. For large scale datasets, users can partially load the needed information, e.g., cell annotation without the gene expression matrices. scDIOR connects the analytical tasks of different platforms, which makes it easy to compare the performance of algorithms between them. CONCLUSIONS: scDIOR contains two modules, dior in R and diopy in Python. scDIOR is a versatile and user-friendly tool that implements single-cell data transformation between R and Python rapidly and stably. The software is freely accessible at https://github.com/JiekaiLab/scDIOR .

BACKGROUND: Understanding the transcriptome has become an essential step towards the full interpretation of the biological function of a cell, a tissue or even an organ. Many tools are available for either processing, analysing transcriptome data, or visualizing analysis results. However, most existing tools are limited to data from a single sequencing platform and only several of them could handle more than one analysis module, which are far from enough to meet the requirements of users, especially those without advanced programming skills. Hence, we still lack an open-source toolkit that enables both bioinformatician and non-bioinformatician users to process and analyze the large transcriptome data from different sequencing platforms and visualize the results. RESULTS: We present a Linux-based toolkit, RNA-combine, to automatically perform the quality assessment, downstream analysis of the transcriptome data generated from different sequencing platforms, including bulk RNA-seq (Illumina platform), single cell RNA-seq (10x Genomics) and Iso-Seq (PacBio) and visualization of the results. Besides, this toolkit is implemented with at least 10 analysis modules more than other toolkits examined in this study. Source codes of RNA-combine are available on GitHub: https://github.com/dongxuemin666/RNA-combine . CONCLUSION: Our results suggest that RNA-combine is a reliable tool for transcriptome data processing and result interpretation for both bioinformaticians and non-bioinformaticians.

BACKGROUND: Identifying protein complexes from protein-protein interaction (PPI) networks is a crucial task, and many related algorithms have been developed. Most algorithms usually employ direct neighbors of nodes and ignore resource allocation and second-order neighbors. The effective use of such information is crucial to protein complex detection. RESULT: Based on this observation, we propose a new way by combining node resource allocation and gene expression information to weight protein network (NRAGE-WPN), in which protein complexes are detected based on core-attachment and second-order neighbors. CONCLUSIONS: Through comparison with eleven methods in Yeast and Human PPI network, the experimental results demonstrate that this algorithm not only performs better than other methods on 75% in terms of f-measure+, but also can achieve an ideal overall performance in terms of a composite score consisting of five performance measures. This identification method is simple and can accurately identify more complexes.

BACKGROUND: As antibiotic resistance creates a significant global health threat, we need not only to accelerate the development of novel antibiotics but also to develop better treatment strategies using existing drugs to improve their efficacy and prevent the selection of further resistance. We require new tools to rationally design dosing regimens from data collected in early phases of antibiotic and dosing development. Mathematical models such as mechanistic pharmacodynamic drug-target binding explain mechanistic details of how the given drug concentration affects its targeted bacteria. However, there are no available tools in the literature that allow non-quantitative scientists to develop computational models to simulate antibiotic-target binding and its effects on bacteria. RESULTS: In this work, we have devised an extension of a mechanistic binding-kinetic model to incorporate clinical drug concentration data. Based on the extended model, we develop a novel and interactive web-based tool that allows non-quantitative scientists to create and visualize their own computational models of bacterial antibiotic target-binding based on their considered drugs and bacteria. We also demonstrate how Rifampicin affects bacterial populations of Tuberculosis bacteria using our vCOMBAT tool. CONCLUSIONS: The vCOMBAT online tool is publicly available at https://combat-bacteria.org/ .

BACKGROUND: The function of non-coding RNA sequences is largely determined by their spatial conformation, namely the secondary structure of the molecule, formed by Watson-Crick interactions between nucleotides. Hence, modern RNA alignment algorithms routinely take structural information into account. In order to discover yet unknown RNA families and infer their possible functions, the structural alignment of RNAs is an essential task. This task demands a lot of computational resources, especially for aligning many long sequences, and it therefore requires efficient algorithms that utilize modern hardware when available. A subset of the secondary structures contains overlapping interactions (called pseudoknots), which add additional complexity to the problem and are often ignored in available software. RESULTS: We present the SeqAn-based software LaRA 2 that is significantly faster than comparable software for accurate pairwise and multiple alignments of structured RNA sequences. In contrast to other programs our approach can handle arbitrary pseudoknots. As an improved re-implementation of the LaRA tool for structural alignments, LaRA 2 uses multi-threading and vectorization for parallel execution and a new heuristic for computing a lower boundary of the solution. Our algorithmic improvements yield a program that is up to 130 times faster than the previous version. CONCLUSIONS: With LaRA 2 we provide a tool to analyse large sets of RNA secondary structures in relatively short time, based on structural alignment. The produced alignments can be used to derive structural motifs for the search in genomic databases.

BACKGROUND: Understanding the synergetic and antagonistic effects of combinations of drugs and toxins is vital for many applications, including treatment of multifactorial diseases and ecotoxicological monitoring. Synergy is usually assessed by comparing the response of drug combinations to a predicted non-interactive response from reference (null) models. Possible choices of null models are Loewe additivity, Bliss independence and the recently rediscovered Hand model. A different approach is taken by the MuSyC model, which directly fits a generalization of the Hill model to the data. All of these models, however, fit the dose-response relationship with a parametric model. RESULTS: We propose the Hand-GP model, a non-parametric model based on the combination of the Hand model with Gaussian processes. We introduce a new logarithmic squared exponential kernel for the Gaussian process which captures the logarithmic dependence of response on dose. From the monotherapeutic response and the Hand principle, we construct a null reference response and synergy is assessed from the difference between this null reference and the Gaussian process fitted response. Statistical significance of the difference is assessed from the confidence intervals of the Gaussian process fits. We evaluate performance of our model on a simulated data set from Greco, two simulated data sets of our own design and two benchmark data sets from Chou and Talalay. We compare the Hand-GP model to standard synergy models and show that our model performs better on these data sets. We also compare our model to the MuSyC model as an example of a recent method on these five data sets and on two-drug combination screens: Mott et al. anti-malarial screen and O'Neil et al. anti-cancer screen. We identify cases in which the HandGP model is preferred and cases in which the MuSyC model is preferred. CONCLUSION: The Hand-GP model is a flexible model to capture synergy. Its non-parametric and probabilistic nature allows it to model a wide variety of response patterns.

BACKGROUND: The temporal progression of many fundamental processes in cells and organisms, including homeostasis, differentiation and development, are governed by gene regulatory networks (GRNs). GRNs balance fluctuations in the output of their genes, which trace back to the stochasticity of molecular interactions. Although highly desirable to understand life processes, predicting the temporal progression of gene products within a GRN is challenging when considering stochastic events such as transcription factor-DNA interactions or protein production and degradation. RESULTS: We report a method to simulate and infer GRNs including genes and biochemical reactions at molecular detail. In our approach, we consider each network element to be isolated from other elements during small time intervals, after which we synchronize molecule numbers across all network elements. Thereby, the temporal behaviour of network elements is decoupled and can be treated by local stochastic or deterministic solutions. We demonstrate the working principle of this modular approach with a repressive gene cascade comprising four genes. By considering a deterministic time evolution within each time interval for all elements, our method approaches the solution of the system of deterministic differential equations associated with the GRN. By allowing genes to stochastically switch between on and off states or by considering stochastic production of gene outputs, we are able to include increasing levels of stochastic detail and approximate the solution of a Gillespie simulation. Thereby, CaiNet is able to reproduce noise-induced bi-stability and oscillations in dynamically complex GRNs. Notably, our modular approach further allows for a simple consideration of deterministic delays. We further infer relevant regulatory connections and steady-state parameters of a GRN of up to ten genes from steady-state measurements by identifying each gene of the network with a single perceptron in an artificial neuronal network and using a gradient decent method originally designed to train recurrent neural networks. To facilitate setting up GRNs and using our simulation and inference method, we provide a fast computer-aided interactive network simulation environment, CaiNet. CONCLUSION: We developed a method to simulate GRNs at molecular detail and to infer the topology and steady-state parameters of GRNs. Our method and associated user-friendly framework CaiNet should prove helpful to analyze or predict the temporal progression of reaction networks or GRNs in cellular and organismic biology. CaiNet is freely available at https://gitlab.com/GebhardtLab/CaiNet .

Erratum in BMC Bioinformatics. 2022 Nov 4;23(1):462.

BACKGROUND: Long non-coding RNAs (lncRNAs) are related to human diseases by regulating gene expression. Identifying lncRNA-disease associations (LDAs) will contribute to diagnose, treatment, and prognosis of diseases. However, the identification of LDAs by the biological experiments is time-consuming, costly and inefficient. Therefore, the development of efficient and high-accuracy computational methods for predicting LDAs is of great significance. RESULTS: In this paper, we propose a novel computational method (gGATLDA) to predict LDAs based on graph-level graph attention network. Firstly, we extract the enclosing subgraphs of each lncRNA-disease pair. Secondly, we construct the feature vectors by integrating lncRNA similarity and disease similarity as node attributes in subgraphs. Finally, we train a graph neural network (GNN) model by feeding the subgraphs and feature vectors to it, and use the trained GNN model to predict lncRNA-disease potential association scores. The experimental results show that our method can achieve higher area under the receiver operation characteristic curve (AUC), area under the precision recall curve (AUPR), accuracy and F1-Score than the state-of-the-art methods in five fold cross-validation. Case studies show that our method can effectively identify lncRNAs associated with breast cancer, gastric cancer, prostate cancer, and renal cancer. CONCLUSION: The experimental results indicate that our method is a useful approach for predicting potential LDAs.

BACKGROUND: Detecting pathogenic proteins is the origin way to understand the mechanism and resist the invasion of diseases, making pathogenic protein prediction develop into an urgent problem to be solved. Prediction for genome-wide proteins may be not necessarily conducive to rapidly cure diseases as developing new drugs specifically for the predicted pathogenic protein always need major expenditures on time and cost. In order to facilitate disease treatment, computational method to predict pathogenic proteins which are targeted by existing drugs should be exploited. RESULTS: In this study, we proposed a novel computational model to predict drug-targeted pathogenic proteins, named as M2PP. Three types of features were presented on our constructed heterogeneous network (including target proteins, diseases and drugs), which were based on the neighborhood similarity information, drug-inferred information and path information. Then, a random forest regression model was trained to score unconfirmed target-disease pairs. Five-fold cross-validation experiment was implemented to evaluate model's prediction performance, where M2PP achieved advantageous results compared with other state-of-the-art methods. In addition, M2PP accurately predicted high ranked pathogenic proteins for common diseases with public biomedical literature as supporting evidence, indicating its excellent ability. CONCLUSIONS: M2PP is an effective and accurate model to predict drug-targeted pathogenic proteins, which could provide convenience for the future biological researches.

BACKGROUND: Dietary restriction (DR) is the most studied pro-longevity intervention; however, a complete understanding of its underlying mechanisms remains elusive, and new research directions may emerge from the identification of novel DR-related genes and DR-related genetic features. RESULTS: This work used a Machine Learning (ML) approach to classify ageing-related genes as DR-related or NotDR-related using 9 different types of predictive features: PathDIP pathways, two types of features based on KEGG pathways, two types of Protein-Protein Interactions (PPI) features, Gene Ontology (GO) terms, Genotype Tissue Expression (GTEx) expression features, GeneFriends co-expression features and protein sequence descriptors. Our findings suggested that features biased towards curated knowledge (i.e. GO terms and biological pathways), had the greatest predictive power, while unbiased features (mainly gene expression and co-expression data) have the least predictive power. Moreover, a combination of all the feature types diminished the predictive power compared to predictions based on curated knowledge. Feature importance analysis on the two most predictive classifiers mostly corroborated existing knowledge and supported recent findings linking DR to the Nuclear Factor Erythroid 2-Related Factor 2 (NRF2) signalling pathway and G protein-coupled receptors (GPCR). We then used the two strongest combinations of feature type and ML algorithm to predict DR-relatedness among ageing-related genes currently lacking DR-related annotations in the data, resulting in a set of promising candidate DR-related genes (GOT2, GOT1, TSC1, CTH, GCLM, IRS2 and SESN2) whose predicted DR-relatedness remain to be validated in future wet-lab experiments. CONCLUSIONS: This work demonstrated the strong potential of ML-based techniques to identify DR-associated features as our findings are consistent with literature and recent discoveries. Although the inference of new DR-related mechanistic findings based solely on GO terms and biological pathways was limited due to their knowledge-driven nature, the predictive power of these two features types remained useful as it allowed inferring new promising candidate DR-related genes.

Cellular heterogeneity underlies cancer evolution and metastasis. Advances in single-cell technologies such as single-cell RNA sequencing and mass cytometry have enabled interrogation of cell type-specific expression profiles and abundance across heterogeneous cancer samples obtained from clinical trials and preclinical studies. However, challenges remain in determining sample sizes needed for ascertaining changes in cell type abundances in a controlled study. To address this statistical challenge, we have developed a new approach, named Sensei, to determine the number of samples and the number of cells that are required to ascertain such changes between two groups of samples in single-cell studies. Sensei expands the t-test and models the cell abundances using a beta-binomial distribution. We evaluate the mathematical accuracy of Sensei and provide practical guidelines on over 20 cell types in over 30 cancer types based on knowledge acquired from the cancer cell atlas (TCGA) and prior single-cell studies. We provide a web application to enable user-friendly study design via https://kchen-lab.github.io/sensei/table_beta.html .

BACKGROUND: Biomedical named entity recognition (BioNER) is a basic and important medical information extraction task to extract medical entities with special meaning from medical texts. In recent years, deep learning has become the main research direction of BioNER due to its excellent data-driven context coding ability. However, in BioNER task, deep learning has the problem of poor generalization and instability. RESULTS: we propose the hierarchical shared transfer learning, which combines multi-task learning and fine-tuning, and realizes the multi-level information fusion between the underlying entity features and the upper data features. We select 14 datasets containing 4 types of entities for training and evaluate the model. The experimental results showed that the F1-scores of the five gold standard datasets BC5CDR-chemical, BC5CDR-disease, BC2GM, BC4CHEMD, NCBI-disease and LINNAEUS were increased by 0.57, 0.90, 0.42, 0.77, 0.98 and - 2.16 compared to the single-task XLNet-CRF model. BC5CDR-chemical, BC5CDR-disease and BC4CHEMD achieved state-of-the-art results.The reasons why LINNAEUS's multi-task results are lower than single-task results are discussed at the dataset level. CONCLUSION: Compared with using multi-task learning and fine-tuning alone, the model has more accurate recognition ability of medical entities, and has higher generalization and stability.

MOTIVATION: Protein-protein interactions (PPIs) are critical to normal cellular function and are related to many disease pathways. A range of protein functions are mediated and regulated by protein interactions through post-translational modifications (PTM). However, only 4% of PPIs are annotated with PTMs in biological knowledge databases such as IntAct, mainly performed through manual curation, which is neither time- nor cost-effective. Here we aim to facilitate annotation by extracting PPIs along with their pairwise PTM from the literature by using distantly supervised training data using deep learning to aid human curation. METHOD: We use the IntAct PPI database to create a distant supervised dataset annotated with interacting protein pairs, their corresponding PTM type, and associated abstracts from the PubMed database. We train an ensemble of BioBERT models-dubbed PPI-BioBERT-x10-to improve confidence calibration. We extend the use of ensemble average confidence approach with confidence variation to counteract the effects of class imbalance to extract high confidence predictions. RESULTS AND CONCLUSION: The PPI-BioBERT-x10 model evaluated on the test set resulted in a modest F1-micro 41.3 (P =5 8.1, R = 32.1). However, by combining high confidence and low variation to identify high quality predictions, tuning the predictions for precision, we retained 19% of the test predictions with 100% precision. We evaluated PPI-BioBERT-x10 on 18 million PubMed abstracts and extracted 1.6 million (546507 unique PTM-PPI triplets) PTM-PPI predictions, and filter [Formula: see text] (4584 unique) high confidence predictions. Of the 5700, human evaluation on a small randomly sampled subset shows that the precision drops to 33.7% despite confidence calibration and highlights the challenges of generalisability beyond the test set even with confidence calibration. We circumvent the problem by only including predictions associated with multiple papers, improving the precision to 58.8%. In this work, we highlight the benefits and challenges of deep learning-based text mining in practice, and the need for increased emphasis on confidence calibration to facilitate human curation efforts.

MOTIVATION: Protein backbone angle prediction has achieved significant accuracy improvement with the development of deep learning methods. Usually the same deep learning model is used in making prediction for all residues regardless of the categories of secondary structures they belong to. In this paper, we propose to train separate deep learning models for each category of secondary structures. Machine learning methods strive to achieve generality over the training examples and consequently loose accuracy. In this work, we explicitly exploit classification knowledge to restrict generalisation within the specific class of training examples. This is to compensate the loss of generalisation by exploiting specialisation knowledge in an informed way. RESULTS: The new method named SAP4SS obtains mean absolute error (MAE) values of 15.59, 18.87, 6.03, and 21.71 respectively for four types of backbone angles [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text]. Consequently, SAP4SS significantly outperforms existing state-of-the-art methods SAP, OPUS-TASS, and SPOT-1D: the differences in MAE for all four types of angles are from 1.5 to 4.1% compared to the best known results. AVAILABILITY: SAP4SS along with its data is available from https://gitlab.com/mahnewton/sap4ss .

BACKGROUND: Theoretical analysis of signaling pathways can provide a substantial amount of insight into their function. One particular area of research considers signaling pathways capable of assuming two or more stable states given the same amount of signaling ligand. This phenomenon of bistability can give rise to switch-like behavior, a mechanism that governs cellular decision making. Investigation of whether or not a signaling pathway can confer bistability and switch-like behavior, without knowledge of specific kinetic rate constant values, is a mathematically challenging problem. Recently a technique based on optimization has been introduced, which is capable of finding example parameter values that confer switch-like behavior for a given pathway. Although this approach has made it possible to analyze moderately sized pathways, it is limited to reaction networks that presume a uniterminal structure. It is this limited structure we address by developing a general technique that applies to any mass action reaction network with conservation laws. RESULTS: In this paper we developed a generalized method for detecting switch-like bistable behavior in any mass action reaction network with conservation laws. The method involves (1) construction of a constrained optimization problem using the determinant of the Jacobian of the underlying rate equations, (2) minimization of the objective function to search for conditions resulting in a zero eigenvalue, (3) computation of a confidence level that describes if the global minimum has been found and (4) evaluation of optimization values, using either numerical continuation or directly simulating the ODE system, to verify that a bistability region exists. The generalized method has been tested on three motifs known to be capable of bistability. CONCLUSIONS: We have developed a variation of an optimization-based method for the discovery of bistability, which is not limited to uniterminal chemical reaction networks. Successful completion of the method provides an S-shaped bifurcation diagram, which indicates that the network acts as a bistable switch for the given optimization parameters.

BACKGROUND: More and more evidence showed that long non-coding RNAs (lncRNAs) play important roles in the development and progression of human sophisticated diseases. Therefore, predicting human lncRNA-disease associations is a challenging and urgently task in bioinformatics to research of human sophisticated diseases. RESULTS: In the work, a global network-based computational framework called as LRWRHLDA were proposed which is a universal network-based method. Firstly, four isomorphic networks include lncRNA similarity network, disease similarity network, gene similarity network and miRNA similarity network were constructed. And then, six heterogeneous networks include known lncRNA-disease, lncRNA-gene, lncRNA-miRNA, disease-gene, disease-miRNA, and gene-miRNA associations network were applied to design a multi-layer network. Finally, the Laplace normalized random walk with restart algorithm in this global network is suggested to predict the relationship between lncRNAs and diseases. CONCLUSIONS: The ten-fold cross validation is used to evaluate the performance of LRWRHLDA. As a result, LRWRHLDA achieves an AUC of 0.98402, which is higher than other compared methods. Furthermore, LRWRHLDA can predict isolated disease-related lnRNA (isolated lnRNA related disease). The results for colorectal cancer, lung adenocarcinoma, stomach cancer and breast cancer have been verified by other researches. The case studies indicated that our method is effective.

BACKGROUND: Drug-disease associations (DDAs) can provide important information for exploring the potential efficacy of drugs. However, up to now, there are still few DDAs verified by experiments. Previous evidence indicates that the combination of information would be conducive to the discovery of new DDAs. How to integrate different biological data sources and identify the most effective drugs for a certain disease based on drug-disease coupled mechanisms is still a challenging problem. RESULTS: In this paper, we proposed a novel computation model for DDA predictions based on graph representation learning over multi-biomolecular network (GRLMN). More specifically, we firstly constructed a large-scale molecular association network (MAN) by integrating the associations among drugs, diseases, proteins, miRNAs, and lncRNAs. Then, a graph embedding model was used to learn vector representations for all drugs and diseases in MAN. Finally, the combined features were fed to a random forest (RF) model to predict new DDAs. The proposed model was evaluated on the SCMFDD-S data set using five-fold cross-validation. Experiment results showed that GRLMN model was very accurate with the area under the ROC curve (AUC) of 87.9%, which outperformed all previous works in terms of both accuracy and AUC in benchmark dataset. To further verify the high performance of GRLMN, we carried out two case studies for two common diseases. As a result, in the ranking of drugs that were predicted to be related to certain diseases (such as kidney disease and fever), 15 of the top 20 drugs have been experimentally confirmed. CONCLUSIONS: The experimental results show that our model has good performance in the prediction of DDA. GRLMN is an effective prioritization tool for screening the reliable DDAs for follow-up studies concerning their participation in drug reposition.

BACKGROUND: Cell-based models are becoming increasingly popular for applications in developmental biology. However, the impact of numerical choices on the accuracy and efficiency of the simulation of these models is rarely meticulously tested. Without concrete studies to differentiate between solid model conclusions and numerical artifacts, modelers are at risk of being misled by their experiments' results. Most cell-based modeling frameworks offer a feature-rich environment, providing a wide range of biological components, but are less suitable for numerical studies. There is thus a need for software specifically targeted at this use case. RESULTS: We present CBMOS, a Python framework for the simulation of the center-based or cell-centered model. Contrary to other implementations, CBMOS' focus is on facilitating numerical study of center-based models by providing access to multiple ordinary differential equation solvers and force functions through a flexible, user-friendly interface and by enabling rapid testing through graphics processing unit (GPU) acceleration. We show-case its potential by illustrating two common workflows: (1) comparison of the numerical properties of two solvers within a Jupyter notebook and (2) measuring average wall times of both solvers on a high performance computing cluster. More specifically, we confirm that although for moderate accuracy levels the backward Euler method allows for larger time step sizes than the commonly used forward Euler method, its additional computational cost due to being an implicit method prohibits its use for practical test cases. CONCLUSIONS: CBMOS is a flexible, easy-to-use Python implementation of the center-based model, exposing both basic model assumptions and numerical components to the user. It is available on GitHub and PyPI under an MIT license. CBMOS allows for fast prototyping on a central processing unit for small systems through the use of NumPy. Using CuPy on a GPU, cell populations of up to 10,000 cells can be simulated within a few seconds. As such, it will substantially lower the time investment for any modeler to check the crucial assumption that model conclusions are independent of numerical issues.

BACKGROUND: Recent development of bioinformatics tools for Next Generation Sequencing data has facilitated complex analyses and prompted large scale experimental designs for comparative genomics. When combined with the advances in network inference tools, this can lead to powerful methodologies for mining genomics data, allowing development of pipelines that stretch from sequence reads mapping to network inference. However, integrating various methods and tools available over different platforms requires a programmatic framework to fully exploit their analytic capabilities. Integrating multiple genomic analysis tools faces challenges from standardization of input and output formats, normalization of results for performing comparative analyses, to developing intuitive and easy to control scripts and interfaces for the genomic analysis pipeline. RESULTS: We describe here NetSeekR, a network analysis R package that includes the capacity to analyze time series of RNA-Seq data, to perform correlation and regulatory network inferences and to use network analysis methods to summarize the results of a comparative genomics study. The software pipeline includes alignment of reads, differential gene expression analysis, correlation network analysis, regulatory network analysis, gene ontology enrichment analysis and network visualization of differentially expressed genes. The implementation provides support for multiple RNA-Seq read mapping methods and allows comparative analysis of the results obtained by different bioinformatics methods. CONCLUSION: Our methodology increases the level of integration of genomics data analysis tools to network inference, facilitating hypothesis building, functional analysis and genomics discovery from large scale NGS data. When combined with network analysis and simulation tools, the pipeline allows for developing systems biology methods using large scale genomics data.

BACKGROUND: Despite enormous achievements in the production of high-throughput datasets, constructing comprehensive maps of interactions remains a major challenge. Lack of sufficient experimental evidence on interactions is more significant for heterogeneous molecular types. Hence, developing strategies to predict inter-omics connections is essential to construct holistic maps of disease. RESULTS: Here, as a novel nonlinear deep learning method, Data Integration with Deep Learning (DIDL) was proposed to predict inter-omics interactions. It consisted of an encoder that performs automatic feature extraction for biomolecules according to existing interactions coupled with a predictor that predicts unforeseen interactions. Applicability of DIDL was assessed on different networks, namely drug-target protein, transcription factor-DNA element, and miRNA-mRNA. Also, validity of the novel predictions was evaluated by literature surveys. According to the results, the DIDL outperformed state-of-the-art methods. For all three networks, the areas under the curve and the precision-recall curve exceeded 0.85 and 0.83, respectively. CONCLUSIONS: DIDL offers several advantages like automatic feature extraction from raw data, end-to-end training, and robustness to network sparsity. In addition, reliance solely on existing inter-layer interactions and independence of biochemical features of interacting molecules make this algorithm applicable for a wide variety of networks. DIDL paves the way to understand the underlying mechanisms of complex disorders through constructing integrative networks.

Author information: (1)Department of Genetic Epidemiology, University Medical Center, Georg-August-University Göttingen, Göttingen, Germany. arosenb@gwdg.de. (2)Institut für Genetische Epidemiologie, Universitätsmedizin Göttingen, Humboldtallee 32, 37073, Göttingen, Germany. arosenb@gwdg.de. (3)Department of Genetic Epidemiology, University Medical Center, Georg-August-University Göttingen, Göttingen, Germany.

BACKGROUND: Parasites use polymorphic gene families to evade the immune system or interact with the host. Assessing the diversity and expression of such gene families in pathogens can inform on the repertoire or host interaction phenotypes of clinical relevance. However, obtaining the sequences and quantifying their expression is a challenge. In Plasmodium falciparum, the highly polymorphic var genes encode the major virulence protein, PfEMP1, which bind a range of human receptors through varying combinations of DBL and CIDR domains. Here we present a tool, Varia, to predict near full-length gene sequences and domain compositions of query genes from database genes sharing short sequence tags. Varia generates output through two complementary pipelines. Varia_VIP returns all putative gene sequences and domain compositions of the query gene from any partial sequence provided, thereby enabling experimental validation of specific genes of interest and detailed assessment of their putative domain structure. Varia_GEM accommodates rapid profiling of var gene expression in complex patient samples from DBLα expression sequence tags (EST), by computing a sample overall transcript profile stratified by PfEMP1 domain types. RESULTS: Varia_VIP was tested querying sequence tags from all DBL domain types using different search criteria. On average 92% of query tags had one or more 99% identical database hits, resulting in the full-length query gene sequence being identified (> 99% identical DNA > 80% of query gene) among the five most prominent database hits, for ~ 33% of the query genes. Optimized Varia_GEM settings allowed correct prediction of > 90% of domains placed among the four most N-terminal domains, including the DBLα domain, and > 70% of C-terminal domains. With this accuracy, N-terminal domains could be predicted for > 80% of queries, whereas prediction rates of C-terminal domains dropped with the distance from the DBLα from 70 to 40%. CONCLUSION: Prediction of var sequence and domain composition is possible from short sequence tags. Varia can be used to guide experimental validation of PfEMP1 sequences of interest and conduct high-throughput analysis of var type expression in patient samples.

BACKGROUND: Elucidating the modes of action (MoAs) of drugs and drug candidate compounds is critical for guiding translation from drug discovery to clinical application. Despite the development of several data-driven approaches for predicting chemical-disease associations, the molecular cues that organize the epigenetic landscape of drug responses remain poorly understood. RESULTS: With the use of a computational method, we attempted to elucidate the epigenetic landscape of drug responses, in terms of transcription factors (TFs), through large-scale ChIP-seq data analyses. In the algorithm, we systematically identified TFs that regulate the expression of chemically induced genes by integrating transcriptome data from chemical induction experiments and almost all publicly available ChIP-seq data (consisting of 13,558 experiments). By relating the resultant chemical-TF associations to a repository of associated proteins for a wide range of diseases, we made a comprehensive prediction of chemical-TF-disease associations, which could then be used to account for drug MoAs. Using this approach, we predicted that: (1) cisplatin promotes the anti-tumor activity of TP53 family members but suppresses the cancer-inducing function of MYCs; (2) inhibition of RELA and E2F1 is pivotal for leflunomide to exhibit antiproliferative activity; and (3) CHD8 mediates valproic acid-induced autism. CONCLUSIONS: Our proposed approach has the potential to elucidate the MoAs for both approved drugs and candidate compounds from an epigenetic perspective, thereby revealing new therapeutic targets, and to guide the discovery of unexpected therapeutic effects, side effects, and novel targets and actions.

BACKGROUND: Quality control checks are the first step in RNA-Sequencing analysis, which enable the identification of common issues that occur in the sequenced reads. Checks for sequence quality, contamination, and complexity are commonplace, and allow users to implement steps downstream which can account for these issues. Strand-specificity of reads is frequently overlooked and is often unavailable even in published data, yet when unknown or incorrectly specified can have detrimental effects on the reproducibility and accuracy of downstream analyses. RESULTS: To address these issues, we developed how_are_we_stranded_here, a Python library that helps to quickly infer strandedness of paired-end RNA-Sequencing data. Testing on both simulated and real RNA-Sequencing reads showed that it correctly measures strandedness, and measures outside the normal range may indicate sample contamination. CONCLUSIONS: how_are_we_stranded_here is fast and user friendly, making it easy to implement in quality control pipelines prior to analysing RNA-Sequencing data. how_are_we_stranded_here is freely available at https://github.com/betsig/how_are_we_stranded_here .

BACKGROUND: Fluorescence image analysis in biochemical science often involves the complex tasks of identifying samples for analysis and calculating the desired information from the intensity traces. Analyzing giant unilamellar vesicles (GUVs) is one of these tasks. Researchers need to identify many vesicles to statistically analyze the degree of molecular interaction or state of molecular organization on the membranes. This analysis is complicated, requiring a careful manual examination by researchers, so automating the analysis can significantly aid in improving its efficiency and reliability. RESULTS: We developed a convolutional neural network (CNN) assisted intelligent analysis routine based on the whole 3D z-stack images. The programs identify the vesicles with desired morphology and analyzes the data automatically. The programs can perform protein binding analysis on the membranes or state decision analysis of domain phase separation. We also show that the method can easily be applied to similar problems, such as intensity analysis of phase-separated protein droplets. CNN-based classification approach enables the identification of vesicles even from relatively complex samples. We demonstrate that the proposed artificial intelligence-assisted classification can further enhance the accuracy of the analysis close to the performance of manual examination in vesicle selection and vesicle state determination analysis. CONCLUSIONS: We developed a MATLAB based software capable of efficiently analyzing confocal fluorescence image data of giant unilamellar vesicles. The program can automatically identify GUVs with desired morphology and perform intensity-based calculation and state decision for each vesicle. We expect our method of CNN implementation can be expanded and applied to many similar problems in image data analysis.

BACKGROUND: The identification of cancer types is of great significance for early diagnosis and clinical treatment of cancer. Clustering cancer samples is an important means to identify cancer types, which has been paid much attention in the field of bioinformatics. The purpose of cancer clustering is to find expression patterns of different cancer types, so that the samples with similar expression patterns can be gathered into the same type. In order to improve the accuracy and reliability of cancer clustering, many clustering methods begin to focus on the integration analysis of cancer multi-omics data. Obviously, the methods based on multi-omics data have more advantages than those using single omics data. However, the high heterogeneity and noise of cancer multi-omics data pose a great challenge to the multi-omics analysis method. RESULTS: In this study, in order to extract more complementary information from cancer multi-omics data for cancer clustering, we propose a low-rank subspace clustering method called multi-view manifold regularized compact low-rank representation (MmCLRR). In MmCLRR, each omics data are regarded as a view, and it learns a consistent subspace representation by imposing a consistence constraint on the low-rank affinity matrix of each view to balance the agreement between different views. Moreover, the manifold regularization and concept factorization are introduced into our method. Relying on the concept factorization, the dictionary can be updated in the learning, which greatly improves the subspace learning ability of low-rank representation. We adopt linearized alternating direction method with adaptive penalty to solve the optimization problem of MmCLRR method. CONCLUSIONS: Finally, we apply MmCLRR into the clustering of cancer samples based on multi-omics data, and the clustering results show that our method outperforms the existing multi-view methods.

BACKGROUND: Clustering and feature selection act major roles in many communities. As a matrix factorization, Low-Rank Representation (LRR) has attracted lots of attentions in clustering and feature selection, but sometimes its performance is frustrated when the data samples are insufficient or contain a lot of noise. RESULTS: To address this drawback, a novel LRR model named TGLRR is proposed by integrating the truncated nuclear norm with graph-Laplacian. Different from the nuclear norm minimizing all singular values, the truncated nuclear norm only minimizes some smallest singular values, which can dispel the harm of shrinkage of the leading singular values. Finally, an efficient algorithm based on Linearized Alternating Direction with Adaptive Penalty is applied to resolving the optimization problem. CONCLUSIONS: The results show that the TGLRR method exceeds the existing state-of-the-art methods in aspect of tumor clustering and gene selection on integrated gene expression data.

BACKGROUND: Bioinformatics is a subject produced by the combination of life science and computer science. It mainly uses computer technology to study the laws of biological systems. The design and realization of DNA circuit reaction is one of the important contents of bioinformatics. RESULTS: In this paper, nonlinear dynamic system model with Lévy jump based on entropy-driven amplifier (EDA) circuit response is studied. Firstly, nonlinear biochemical reaction system model is established based on EDA circuit response. Considering the influence of disturbance factors on the system, nonlinear biochemical reaction system with Lévy jump is built. Secondly, in order to prove that the constructed system conforms to the actual meaning, the existence and uniqueness of the system solution is analyzed. Next, the sufficient conditions for the end and continuation of EDA circuit reaction are certified. Finally, the correctness of the theoretical results is proved by numerical simulation, and the reactivity of THTSignal in EDA circuit under different noise intensity is verified. CONCLUSIONS: In EDA circuit reaction, the intensity of external noise has a significant impact on the system. The end of EDA circuit reaction is closely related to the intensity of Lévy noise, and Lévy jump has a significant impact on the nature of biochemical reaction system.

BACKGROUND: Metagenomics technology can directly extract microbial genetic material from the environmental samples to obtain their sequencing reads, which can be further assembled into contigs through assembly tools. Clustering methods of contigs are subsequently applied to recover complete genomes from environmental samples. The main problems with current clustering methods are that they cannot recover more high-quality genes from complex environments. Firstly, there are multiple strains under the same species, resulting in assembly of chimeras. Secondly, different strains under the same species are difficult to be classified. Thirdly, it is difficult to determine the number of strains during the clustering process. RESULTS: In view of the shortcomings of current clustering methods, we propose an unsupervised clustering method which can improve the ability to recover genes from complex environments and a new method for selecting the number of sample's strains in clustering process. The sequence composition characteristics (tetranucleotide frequency) and co-abundance are combined to train the probability model for clustering. A new recursive method that can continuously reduce the complexity of the samples is proposed to improve the ability to recover genes from complex environments. The new clustering method was tested on both simulated and real metagenomic datasets, and compared with five state-of-the-art methods including CONCOCT, Maxbin2.0, MetaBAT, MyCC and COCACOLA. In terms of the number and quality of recovered genes from metagenomic datasets, the results show that our proposed method is more effective. CONCLUSIONS: A new contigs clustering method is proposed, which can recover more high-quality genes from complex environmental samples.

BACKGROUND: Recently, with the foundation and development of gene ontology (GO) resources, numerous works have been proposed to compute functional similarity of genes and achieved series of successes in some research fields. Focusing on the calculation of the information content (IC) of terms is the main idea of these methods, which is essential for measuring functional similarity of genes. However, most approaches have some deficiencies, especially when measuring the IC of both GO terms and their corresponding annotated term sets. To this end, measuring functional similarity of genes accurately is still challenging. RESULTS: In this article, we proposed a novel gene functional similarity calculation method, which especially encapsulates the specificity of terms and edges (STE). The proposed method mainly contains three steps. Firstly, a novel computing model is put forward to compute the IC of terms. This model has the ability to exploit the specific structural information of GO terms. Secondly, the IC of term sets are computed by capturing the genetic structure between the terms contained in the set. Lastly, we measure the gene functional similarity according to the IC overlap ratio of the corresponding annotated genes sets. The proposed method accurately measures the IC of not only GO terms but also the annotated term sets by leveraging the specificity of edges in the GO graph. CONCLUSIONS: We conduct experiments on gene functional classification in biological pathways, gene expression datasets, and protein-protein interaction datasets. Extensive experimental results show the better performances of our proposed STE against several baseline methods.

BACKGROUND: Computational prediction of the interaction between drugs and protein targets is very important for the new drug discovery, as the experimental determination of drug-target interaction (DTI) is expensive and time-consuming. However, different protein targets are with very different numbers of interactions. Specifically, most interactions focus on only a few targets. As a result, targets with larger numbers of interactions could own enough positive samples for predicting their interactions but the positive samples for targets with smaller numbers of interactions could be not enough. Only using a classification strategy may not be able to deal with the above two cases at the same time. To overcome the above problem, in this paper, a drug-target interaction prediction method based on multiple classification strategies (MCSDTI) is proposed. In MCSDTI, targets are firstly divided into two parts according to the number of interactions of the targets, where one part contains targets with smaller numbers of interactions (TWSNI) and another part contains targets with larger numbers of interactions (TWLNI). And then different classification strategies are respectively designed for TWSNI and TWLNI to predict the interaction. Furthermore, TWSNI and TWLNI are evaluated independently, which can overcome the problem that result could be mainly determined by targets with large numbers of interactions when all targets are evaluated together. RESULTS: We propose a new drug-target interaction (MCSDTI) prediction method, which uses multiple classification strategies. MCSDTI is tested on five DTI datasets, such as nuclear receptors (NR), ion channels (IC), G protein coupled receptors (GPCR), enzymes (E), and drug bank (DB). Experiments show that the AUCs of our method are respectively 3.31%, 1.27%, 2.02%, 2.02% and 1.04% higher than that of the second best methods on NR, IC, GPCR and E for TWLNI; And AUCs of our method are respectively 1.00%, 3.20% and 2.70% higher than the second best methods on NR, IC, and E for TWSNI. CONCLUSION: MCSDTI is a competitive method compared to the previous methods for all target parts on most datasets, which administrates that different classification strategies for different target parts is an effective way to improve the effectiveness of DTI prediction.

BACKGROUND: Alkaline earth metal ions are important protein binding ligands in human body, and it is of great significance to predict their binding residues. RESULTS: In this paper, Mg2+ and Ca2+ ligands are taken as the research objects. Based on the characteristic parameters of protein sequences, amino acids, physicochemical characteristics of amino acids and predicted structural information, deep neural network algorithm is used to predict the binding sites of proteins. By optimizing the hyper-parameters of the deep learning algorithm, the prediction results by the fivefold cross-validation are better than those of the Ionseq method. In addition, to further verify the performance of the proposed model, the undersampling data processing method is adopted, and the prediction results on independent test are better than those obtained by the support vector machine algorithm. CONCLUSIONS: An efficient method for predicting Mg2+ and Ca2+ ligand binding sites was presented.

BACKGROUND: During the pathogenesisof complex diseases, a sudden health deterioration will occur as results of the cumulative effect of various internal or external factors. The prediction of an early warning signal (pre-disease state) before such deterioration is very important in clinical practice, especially for a single sample. The single-sample landscape entropy (SLE) was proposed to tackle this issue. However, the PPI used in SLE was lack of definite biological meanings. Besides, the calculation of multiple correlations based on limited reference samples in SLE is time-consuming and suspect. RESULTS: Abnormal signals generally exert their effect through the static definite biological functions in signaling pathways across the development of diseases. Thus, it is a natural way to study the propagation of the early-warning signals based on the signaling pathways in the KEGG database. In this paper, we propose a signaling perturbation method named SSP, to study the early-warning signal in signaling pathways for single dynamic time-series data. Results in three real datasets including the influenza virus infection, lung adenocarcinoma, and acute lung injury show that the proposed SSP outperformed the SLE. Moreover, the early-warning signal can be detected by one important signaling pathway PI3K-Akt. CONCLUSIONS: These results all indicate that the static model in pathways could simplify the detection of the early-warning signals.

BACKGROUND: Mining gene regulatory network (GRN) is an important avenue for addressing cancer mechanism. Mutations in cancer genome perturb GRN and cause a rewiring in an orchestrated network. Hence, the exploration of gene regulatory network rewiring is significant to discover potential biomarkers and indicators for discriminating cancer phenotypes. RESULTS: Here, we propose a new bioinformatics method of identifying biomarkers based on network rewiring in different states. It firstly reconstructs GRN in different phenotypic conditions from gene expression data with a priori background network. We employ the algorithm based on path consistency algorithm and conditional mutual information to delete false-positive regulatory interactions between independent nodes/genes or not closely related gene pairs. And then a differential gene regulatory network (D-GRN) is constructed from the rewiring parts in the two phenotype-specific GRNs. Community detection technique is then applied for D-GRN to detect functional modules. Finally, we apply logistic regression classifier with recursive feature elimination to select biomarker genes in each module individually. The extracted feature genes result in a gene set of biomarkers with impressing ability to distinguish normal samples from controls. We verify the identified biomarkers in external independent validation datasets. For a proof-of-concept study, we apply the framework to identify diagnostic biomarkers of breast cancer. The identified biomarkers obtain a maximum AUC of 0.985 in the internal sample classification experiments. And these biomarkers achieve a maximum AUC of 0.989 in the external validations. CONCLUSION: In conclusion, network rewiring reveals significant differences between different phenotypes, which indicating cancer dysfunctional mechanisms. With the development of sequencing technology, the amount and quality of gene expression data become available. Condition-specific gene regulatory networks that are close to the real regulations in different states will be established. Revealing the network rewiring will greatly benefit the discovery of biomarkers or signatures for phenotypes. D-GRN is a general method to meet this demand of deciphering the high-throughput data for biomarker discovery. It is also easy to be extended for identifying biomarkers of other complex diseases beyond breast cancer.

BACKGROUND: Differential isoform usage is an important driver of inter-individual phenotypic diversity and is linked to various diseases and traits. However, accurately detecting the differential usage of different gene transcripts between groups can be difficult, in particular in less well annotated genomes where the spectrum of transcript isoforms is largely unknown. RESULTS: We investigated whether machine learning approaches can detect differential isoform usage based purely on the distribution of reads across a gene region. We illustrate that gradient boosting and elastic net approaches can successfully identify large numbers of genes showing potential differential isoform usage between Europeans and Africans, that are enriched among relevant biological pathways and significantly overlap those identified by previous approaches. We demonstrate that diversity at the 3' and 5' ends of genes are primary drivers of these differences between populations. CONCLUSION: Machine learning methods can effectively detect differential isoform usage from read fraction data, and can provide novel insights into the biological differences between groups.

BACKGROUND: Algorithmic cellular segmentation is an essential step for the quantitative analysis of highly multiplexed tissue images. Current segmentation pipelines often require manual dataset annotation and additional training, significant parameter tuning, or a sophisticated understanding of programming to adapt the software to the researcher's need. Here, we present CellSeg, an open-source, pre-trained nucleus segmentation and signal quantification software based on the Mask region-convolutional neural network (R-CNN) architecture. CellSeg is accessible to users with a wide range of programming skills. RESULTS: CellSeg performs at the level of top segmentation algorithms in the 2018 Kaggle Data Challenge both qualitatively and quantitatively and generalizes well to a diverse set of multiplexed imaged cancer tissues compared to established state-of-the-art segmentation algorithms. Automated segmentation post-processing steps in the CellSeg pipeline improve the resolution of immune cell populations for downstream single-cell analysis. Finally, an application of CellSeg to a highly multiplexed colorectal cancer dataset acquired on the CO-Detection by indEXing (CODEX) platform demonstrates that CellSeg can be integrated into a multiplexed tissue imaging pipeline and lead to accurate identification of validated cell populations. CONCLUSION: CellSeg is a robust cell segmentation software for analyzing highly multiplexed tissue images, accessible to biology researchers of any programming skill level.

BACKGROUND: Automatic cell type identification is essential to alleviate a key bottleneck in scRNA-seq data analysis. While most existing classification tools show good sensitivity and specificity, they often fail to adequately not-classify cells that are missing in the used reference. Additionally, many tools do not scale to the continuously increasing size of current scRNA-seq datasets. Therefore, additional tools are needed to solve these challenges. RESULTS: scAnnotatR is a novel R package that provides a complete framework to classify cells in scRNA-seq datasets using pre-trained classifiers. It supports both Seurat and Bioconductor's SingleCellExperiment and is thereby compatible with the vast majority of R-based analysis workflows. scAnnotatR uses hierarchically organised SVMs to distinguish a specific cell type versus all others. It shows comparable or even superior accuracy, sensitivity and specificity compared to existing tools while being able to not-classify unknown cell types. Moreover, scAnnotatR is the only of the best performing tools able to process datasets containing more than 600,000 cells. CONCLUSIONS: scAnnotatR is freely available on GitHub ( https://github.com/grisslab/scAnnotatR ) and through Bioconductor (from version 3.14). It is consistently among the best performing tools in terms of classification accuracy while scaling to the largest datasets.

BACKGROUND: There has been a simultaneous increase in demand and accessibility across genomics, transcriptomics, proteomics and metabolomics data, known as omics data. This has encouraged widespread application of omics data in life sciences, from personalized medicine to the discovery of underlying pathophysiology of diseases. Causal analysis of omics data may provide important insight into the underlying biological mechanisms. Existing causal analysis methods yield promising results when identifying potential general causes of an observed outcome based on omics data. However, they may fail to discover the causes specific to a particular stratum of individuals and missing from others. METHODS: To fill this gap, we introduce the problem of stratified causal discovery and propose a method, Aristotle, for solving it. Aristotle addresses the two challenges intrinsic to omics data: high dimensionality and hidden stratification. It employs existing biological knowledge and a state-of-the-art patient stratification method to tackle the above challenges and applies a quasi-experimental design method to each stratum to find stratum-specific potential causes. RESULTS: Evaluation based on synthetic data shows better performance for Aristotle in discovering true causes under different conditions compared to existing causal discovery methods. Experiments on a real dataset on Anthracycline Cardiotoxicity indicate that Aristotle's predictions are consistent with the existing literature. Moreover, Aristotle makes additional predictions that suggest further investigations.

BACKGROUND: Protein function prediction remains a key challenge. Domain composition affects protein function. Here we present DomFun, a Ruby gem that uses associations between protein domains and functions, calculated using multiple indices based on tripartite network analysis. These domain-function associations are combined at the protein level, to generate protein-function predictions. RESULTS: We analysed 16 tripartite networks connecting homologous superfamily and FunFam domains from CATH-Gene3D with functional annotations from the three Gene Ontology (GO) sub-ontologies, KEGG, and Reactome. We validated the results using the CAFA 3 benchmark platform for GO annotation, finding that out of the multiple association metrics and domain datasets tested, Simpson index for FunFam domain-function associations combined with Stouffer's method leads to the best performance in almost all scenarios. We also found that using FunFams led to better performance than superfamilies, and better results were found for GO molecular function compared to GO biological process terms. DomFun performed as well as the highest-performing method in certain CAFA 3 evaluation procedures in terms of [Formula: see text] and [Formula: see text] We also implemented our own benchmark procedure, Pathway Prediction Performance (PPP), which can be used to validate function prediction for additional annotations sources, such as KEGG and Reactome. Using PPP, we found similar results to those found with CAFA 3 for GO, moreover we found good performance for the other annotation sources. As with CAFA 3, Simpson index with Stouffer's method led to the top performance in almost all scenarios. CONCLUSIONS: DomFun shows competitive performance with other methods evaluated in CAFA 3 when predicting proteins function with GO, although results vary depending on the evaluation procedure. Through our own benchmark procedure, PPP, we have shown it can also make accurate predictions for KEGG and Reactome. It performs best when using FunFams, combining Simpson index derived domain-function associations using Stouffer's method. The tool has been implemented so that it can be easily adapted to incorporate other protein features, such as domain data from other sources, amino acid k-mers and motifs. The DomFun Ruby gem is available from https://rubygems.org/gems/DomFun . Code maintained at https://github.com/ElenaRojano/DomFun . Validation procedure scripts can be found at https://github.com/ElenaRojano/DomFun_project .

Erratum in BMC Bioinformatics. 2022 Jun 1;23(1):209.

BACKGROUND: DNA methylation is commonly measured using bisulfite sequencing (BS-seq). The quality of a BS-seq library is measured by its bisulfite conversion efficiency. Libraries with low conversion rates are typically excluded from analysis resulting in reduced coverage and increased costs. RESULTS: We have developed a probabilistic method and software, LuxRep, that implements a general linear model and simultaneously accounts for technical replicates (libraries from the same biological sample) from different bisulfite-converted DNA libraries. Using simulations and actual DNA methylation data, we show that including technical replicates with low bisulfite conversion rates generates more accurate estimates of methylation levels and differentially methylated sites. Moreover, using variational inference speeds up computation time necessary for whole genome analysis. CONCLUSIONS: In this work we show that taking into account technical replicates (i.e. libraries) of BS-seq data of varying bisulfite conversion rates, with their corresponding experimental parameters, improves methylation level estimation and differential methylation detection.

BACKGROUND: Extrachromosomal circular DNAs (eccDNAs) are ring-like DNA structures physically separated from the chromosomes with 100 bp to several megabasepairs in size. Apart from carrying tandemly repeated DNA, eccDNAs may also harbor extra copies of genes or recently activated transposable elements. As eccDNAs occur in all eukaryotes investigated so far and likely play roles in stress, cancer, and aging, they have been prime targets in recent research-with their investigation limited by the scarcity of computational tools. RESULTS: Here, we present the ECCsplorer, a bioinformatics pipeline to detect eccDNAs in any kind of organism or tissue using next-generation sequencing techniques. Following Illumina-sequencing of amplified circular DNA (circSeq), the ECCsplorer enables an easy and automated discovery of eccDNA candidates. The data analysis encompasses two major procedures: first, read mapping to the reference genome allows the detection of informative read distributions including high coverage, discordant mapping, and split reads. Second, reference-free comparison of read clusters from amplified eccDNA against control sample data reveals specifically enriched DNA circles. Both software parts can be run separately or jointly, depending on the individual aim or data availability. To illustrate the wide applicability of our approach, we analyzed semi-artificial and published circSeq data from the model organisms Homo sapiens and Arabidopsis thaliana, and generated circSeq reads from the non-model crop plant Beta vulgaris. We clearly identified eccDNA candidates from all datasets, with and without reference genomes. The ECCsplorer pipeline specifically detected mitochondrial mini-circles and retrotransposon activation, showcasing the ECCsplorer's sensitivity and specificity. CONCLUSION: The ECCsplorer (available online at https://github.com/crimBubble/ECCsplorer ) is a bioinformatics pipeline to detect eccDNAs in any kind of organism or tissue using next-generation sequencing data. The derived eccDNA targets are valuable for a wide range of downstream investigations-from analysis of cancer-related eccDNAs over organelle genomics to identification of active transposable elements.

BACKGROUND: Accurate cancer classification is essential for correct treatment selection and better prognostication. microRNAs (miRNAs) are small RNA molecules that negatively regulate gene expression, and their dyresgulation is a common disease mechanism in many cancers. Through a clearer understanding of miRNA dysregulation in cancer, improved mechanistic knowledge and better treatments can be sought. RESULTS: We present a topology-preserving deep learning framework to study miRNA dysregulation in cancer. Our study comprises miRNA expression profiles from 3685 cancer and non-cancer tissue samples and hierarchical annotations on organ and neoplasticity status. Using unsupervised learning, a two-dimensional topological map is trained to cluster similar tissue samples. Labelled samples are used after training to identify clustering accuracy in terms of tissue-of-origin and neoplasticity status. In addition, an approach using activation gradients is developed to determine the attention of the networks to miRNAs that drive the clustering. Using this deep learning framework, we classify the neoplasticity status of held-out test samples with an accuracy of 91.07%, the tissue-of-origin with 86.36%, and combined neoplasticity status and tissue-of-origin with an accuracy of 84.28%. The topological maps display the ability of miRNAs to recognize tissue types and neoplasticity status. Importantly, when our approach identifies samples that do not cluster well with their respective classes, activation gradients provide further insight in cancer subtypes or grades. CONCLUSIONS: An unsupervised deep learning approach is developed for cancer classification and interpretation. This work provides an intuitive approach for understanding molecular properties of cancer and has significant potential for cancer classification and treatment selection.

BACKGROUND: The number of studies using single-cell RNA sequencing (scRNA-seq) is constantly growing. This powerful technique provides a sampling of the whole transcriptome of a cell. However, sparsity of the data can be a major hurdle when studying the distribution of the expression of a specific gene or the correlation between the expressions of two genes. RESULTS: We show that the main technical noise associated with these scRNA-seq experiments is due to the sampling, i.e., Poisson noise. We present a new tool named baredSC, for Bayesian Approach to Retrieve Expression Distribution of Single-Cell data, which infers the intrinsic expression distribution in scRNA-seq data using a Gaussian mixture model. baredSC can be used to obtain the distribution in one dimension for individual genes and in two dimensions for pairs of genes, in particular to estimate the correlation in the two genes' expressions. We apply baredSC to simulated scRNA-seq data and show that the algorithm is able to uncover the expression distribution used to simulate the data, even in multi-modal cases with very sparse data. We also apply baredSC to two real biological data sets. First, we use it to measure the anti-correlation between Hoxd13 and Hoxa11, two genes with known genetic interaction in embryonic limb. Then, we study the expression of Pitx1 in embryonic hindlimb, for which a trimodal distribution has been identified through flow cytometry. While other methods to analyze scRNA-seq are too sensitive to sampling noise, baredSC reveals this trimodal distribution. CONCLUSION: baredSC is a powerful tool which aims at retrieving the expression distribution of few genes of interest from scRNA-seq data.

BACKGROUND: LINCS, "Library of Integrated Network-based Cellular Signatures", and IDG, "Illuminating the Druggable Genome", are both NIH projects and consortia that have generated rich datasets for the study of the molecular basis of human health and disease. LINCS L1000 expression signatures provide unbiased systems/omics experimental evidence. IDG provides compiled and curated knowledge for illumination and prioritization of novel drug target hypotheses. Together, these resources can support a powerful new approach to identifying novel drug targets for complex diseases, such as Parkinson's disease (PD), which continues to inflict severe harm on human health, and resist traditional research approaches. RESULTS: Integrating LINCS and IDG, we built the Knowledge Graph Analytics Platform (KGAP) to support an important use case: identification and prioritization of drug target hypotheses for associated diseases. The KGAP approach includes strong semantics interpretable by domain scientists and a robust, high performance implementation of a graph database and related analytical methods. Illustrating the value of our approach, we investigated results from queries relevant to PD. Approved PD drug indications from IDG's resource DrugCentral were used as starting points for evidence paths exploring chemogenomic space via LINCS expression signatures for associated genes, evaluated as target hypotheses by integration with IDG. The KG-analytic scoring function was validated against a gold standard dataset of genes associated with PD as elucidated, published mechanism-of-action drug targets, also from DrugCentral. IDG's resource TIN-X was used to rank and filter KGAP results for novel PD targets, and one, SYNGR3 (Synaptogyrin-3), was manually investigated further as a case study and plausible new drug target for PD. CONCLUSIONS: The synergy of LINCS and IDG, via KG methods, empowers graph analytics methods for the investigation of the molecular basis of complex diseases, and specifically for identification and prioritization of novel drug targets. The KGAP approach enables downstream applications via integration with resources similarly aligned with modern KG methodology. The generality of the approach indicates that KGAP is applicable to many disease areas, in addition to PD, the focus of this paper.

BACKGROUND: With the precision of the mass spectrometry (MS) going higher, the MS file size increases rapidly. Beyond the widely-used open format mzML, near-lossless or lossless compression algorithms and formats emerged in scenarios with different precision requirements. The data precision is often related to the instrument and subsequent processing algorithms. Unlike storage-oriented formats, which focus more on lossless compression rate, computation-oriented formats concentrate as much on decoding speed as the compression rate. RESULTS: Here we introduce "Aird", an opensource and computation-oriented format with controllable precision, flexible indexing strategies, and high compression rate. Aird provides a novel compressor called Zlib-Diff-PforDelta (ZDPD) for m/z data. Compared with Zlib only, m/z data size is about 55% lower in Aird average. With the high-speed decoding and encoding performance of the single instruction multiple data technology used in the ZDPD, Aird merely takes 33% decoding time compared with Zlib. We have downloaded seven datasets from ProteomeXchange and Metabolights. They are from different SCIEX, Thermo, and Agilent instruments. Then we convert the raw data into mzML, mgf, and mz5 file formats by MSConvert and compare them with Aird format. Aird uses JavaScript Object Notation for metadata storage. Aird-SDK is written in Java, and AirdPro is a GUI client for vendor file converting written in C#. They are freely available at https://github.com/CSi-Studio/Aird-SDK and https://github.com/CSi-Studio/AirdPro . CONCLUSIONS: With the innovation of MS acquisition mode, MS data characteristics are also constantly changing. New data features can bring more effective compression methods and new index modes to achieve high search performance. The MS data storage mode will also become professional and customized. ZDPD uses multiple MS digital features, and researchers also can use it in other formats like mzML. Aird is designed to become a computing-oriented data format with high scalability, compression rate, and fast decoding speed.

BACKGROUND: Researchers have attempted to apply deep learning methods of artificial intelligence for rapidly and accurately detecting acute lymphoblastic leukemia (ALL) in microscopic images. RESULTS: A Resnet101-9 ensemble model was developed for classifying ALL in microscopic images. The proposed Resnet101-9 ensemble model combined the use of the nine trained Resnet-101 models with a majority voting strategy. Each trained Resnet-101 model integrated the well-known pre-trained Resnet-101 model and its algorithm hyperparameters by using transfer learning method to classify ALL in microscopic images. The best combination of algorithm hyperparameters for the pre-trained Resnet-101 model was determined by Taguchi experimental method. The microscopic images used for training of the pre-trained Resnet-101 model and for performance tests of the trained Resnet-101 model were obtained from the C-NMC dataset. In experimental tests of performance, the Resnet101-9 ensemble model achieved an accuracy of 85.11% and an F1-score of 88.94 in classifying ALL in microscopic images. The accuracy of the Resnet101-9 ensemble model was superior to that of the nine trained Resnet-101 individual models. All other performance measures (i.e., precision, recall, and specificity) for the Resnet101-9 ensemble model exceeded those for the nine trained Resnet-101 individual models. CONCLUSION: Compared to the nine trained Resnet-101 individual models, the Resnet101-9 ensemble model had superior accuracy in classifying ALL in microscopic images obtained from the C-NMC dataset.

BACKGROUND: Drug combination, offering an insight into the increased therapeutic efficacy and reduced toxicity, plays an essential role in the therapy of many complex diseases. Although significant efforts have been devoted to the identification of drugs, the identification of drug combination is still a challenge. The current algorithms assume that the independence of feature selection and drug prediction procedures, which may result in an undesirable performance. RESULTS: To address this issue, we develop a novel Semi-supervised Heterogeneous Network Embedding algorithm (called SeHNE) to predict the combination patterns of drugs by exploiting the graph embedding. Specifically, the ATC similarity of drugs, drug-target, and protein-protein interaction networks are integrated to construct the heterogeneous networks. Then, SeHNE jointly learns drug features by exploiting the topological structure of heterogeneous networks and predicting drug combination. One distinct advantage of SeHNE is that features of drugs are extracted under the guidance of classification, which improves the quality of features, thereby enhancing the performance of prediction of drugs. Experimental results demonstrate that the proposed algorithm is more accurate than state-of-the-art methods on various data, implying that the joint learning is promising for the identification of drug combination. CONCLUSIONS: The proposed model and algorithm provide an effective strategy for the prediction of combinatorial patterns of drugs, implying that the graph-based drug prediction is promising for the discovery of drugs.

BACKGROUND: Compound-protein interaction prediction is necessary to investigate health regulatory functions and promotes drug discovery. Machine learning is becoming increasingly important in bioinformatics for applications such as analyzing protein-related data to achieve successful solutions. Modeling the properties and functions of proteins is important but challenging, especially when dealing with predictions of the sequence type. RESULT: We propose a method to model compounds and proteins for compound-protein interaction prediction. A graph neural network is used to represent the compounds, and a convolutional layer extended with a bidirectional recurrent neural network framework, Long Short-Term Memory, and Gate Recurrent unit is used for protein sequence vectorization. The convolutional layer captures regulatory protein functions, while the recurrent layer captures long-term dependencies between protein functions, thus improving the accuracy of interaction prediction with compounds. A database of 7000 sets of annotated compound protein interaction, containing 1000 base length proteins is taken into consideration for the implementation. The results indicate that the proposed model performs effectively and can yield satisfactory accuracy regarding compound protein interaction prediction. CONCLUSION: The performance of GCRNN is based on the classification accordiong to a binary class of interactions between proteins and compounds The architectural design of GCRNN model comes with the integration of the Bi-Recurrent layer on top of CNN to learn dependencies of motifs on protein sequences and improve the accuracy of the predictions.

BACKGROUND: The recent advancements in high-throughput sequencing have resulted in the availability of annotated genomes, as well as of multi-omics data for many living organisms. This has increased the need for graphic tools that allow the concurrent visualization of genomes and feature-associated multi-omics data on single publication-ready plots. RESULTS: We present chromoMap, an R package, developed for the construction of interactive visualizations of chromosomes/chromosomal regions, mapping of any chromosomal feature with known coordinates (i.e., protein coding genes, transposable elements, non-coding RNAs, microsatellites, etc.), and chromosomal regional characteristics (i.e. genomic feature density, gene expression, DNA methylation, chromatin modifications, etc.) of organisms with a genome assembly. ChromoMap can also integrate multi-omics data (genomics, transcriptomics and epigenomics) in relation to their occurrence across chromosomes. ChromoMap takes tab-delimited files (BED like) or alternatively R objects to specify the genomic co-ordinates of the chromosomes and elements to annotate. Rendered chromosomes are composed of continuous windows of a given range, which, on hover, display detailed information about the elements annotated within that range. By adjusting parameters of a single function, users can generate a variety of plots that can either be saved as static image or as HTML documents. CONCLUSIONS: ChromoMap's flexibility allows for concurrent visualization of genomic data in each strand of a given chromosome, or of more than one homologous chromosome; allowing the comparison of multi-omic data between genotypes (e.g. species, varieties, etc.) or between homologous chromosomes of phased diploid/polyploid genomes. chromoMap is an extensive tool that can be potentially used in various bioinformatics analysis pipelines for genomic visualization of multi-omics data.

BACKGROUND: Plant variety identification is the one most important of agricultural systems. Development of DNA marker profiles of released varieties to compare with candidate variety or future variety is required. However, strictly speaking, scientists did not use most existing variety identification techniques for "identification" but for "distinction of a limited number of cultivars," of which generalization ability always not be well estimated. Because many varieties have similar genetic backgrounds, even some essentially derived varieties (EDVs) are involved, which brings difficulties for identification and breeding progress. A fast, accurate variety identification method, which also has good performance on EDV determination, needs to be developed. RESULTS: In this study, with the strategy of "Divide and Conquer," a variety identification method Conditional Random Selection (CRS) method based on SNP of the whole genome of 3024 rice varieties was developed and be applied in essentially derived variety (EDV) identification of rice. CRS is a fast, efficient, and automated variety identification method. Meanwhile, in practical, with the optimal threshold of identity score searched in this study, the set of SNP (including 390 SNPs) showed optimal performance on EDV and non-EDV identification in two independent testing datasets. CONCLUSION: This approach first selected a minimal set of SNPs to discriminate non-EDVs in the 3000 Rice Genome Project, then united several simplified SNP sets to improve its generalization ability for EDV and non-EDV identification in testing datasets. The results suggested that the CRS method outperformed traditional feature selection methods. Furthermore, it provides a new way to screen out core SNP loci from the whole genome for DNA fingerprinting of crop varieties and be useful for crop breeding.

BACKGROUND: Analysis of dynamic metabolomics data holds the promise to improve our understanding of underlying mechanisms in metabolism. For example, it may detect changes in metabolism due to the onset of a disease. Dynamic or time-resolved metabolomics data can be arranged as a three-way array with entries organized according to a subjects mode, a metabolites mode and a time mode. While such time-evolving multiway data sets are increasingly collected, revealing the underlying mechanisms and their dynamics from such data remains challenging. For such data, one of the complexities is the presence of a superposition of several sources of variation: induced variation (due to experimental conditions or inborn errors), individual variation, and measurement error. Multiway data analysis (also known as tensor factorizations) has been successfully used in data mining to find the underlying patterns in multiway data. To explore the performance of multiway data analysis methods in terms of revealing the underlying mechanisms in dynamic metabolomics data, simulated data with known ground truth can be studied. RESULTS: We focus on simulated data arising from different dynamic models of increasing complexity, i.e., a simple linear system, a yeast glycolysis model, and a human cholesterol model. We generate data with induced variation as well as individual variation. Systematic experiments are performed to demonstrate the advantages and limitations of multiway data analysis in analyzing such dynamic metabolomics data and their capacity to disentangle the different sources of variations. We choose to use simulations since we want to understand the capability of multiway data analysis methods which is facilitated by knowing the ground truth. CONCLUSION: Our numerical experiments demonstrate that despite the increasing complexity of the studied dynamic metabolic models, tensor factorization methods CANDECOMP/PARAFAC(CP) and Parallel Profiles with Linear Dependences (Paralind) can disentangle the sources of variations and thereby reveal the underlying mechanisms and their dynamics.

BACKGROUND/AIM: The polygenic risk score (PRS) shows promise as a potentially effective approach to summarize genetic risk for complex diseases such as alcohol use disorder that is influenced by a combination of multiple variants, each of which has a very small effect. Yet, conventional PRS methods tend to over-adjust confounding factors in the discovery sample and thus have low power to predict the phenotype in the target sample. This study aims to address this important methodological issue. METHODS: This study proposed a new method to construct PRS by (1) approximating the polygenic model using a few principal components selected based on eigen-correlation in the discovery data; and (2) conducting principal component projection on the target data. Secondary data analysis was conducted on two large scale databases: the Study of Addiction: Genetics and Environment (SAGE; discovery data) and the National Longitudinal Study of Adolescent to Adult Health (Add Health; target data) to compare performance of the conventional and proposed methods. RESULT AND CONCLUSION: The results show that the proposed method has higher prediction power and can handle participants from different ancestry backgrounds. We also provide practical recommendations for setting the linkage disequilibrium (LD) and p value thresholds.

BACKGROUND: Representations of the relationships among data using networks are widely used in several research fields such as computational biology, medical informatics and social network mining. Recently, complex networks have been introduced to better capture the insights of the modelled scenarios. Among others, dual networks (DNs) consist of mapping information as pairs of networks containing the same set of nodes but with different edges: one, called physical network, has unweighted edges, while the other, called conceptual network, has weighted edges. RESULTS: We focus on DNs and we propose a tool to find common subgraphs (aka communities) in DNs with particular properties. The tool, called Dual-Network-Analyser, is based on the identification of communities that induce optimal modular subgraphs in the conceptual network and connected subgraphs in the physical one. It includes the Louvain algorithm applied to the considered case. The Dual-Network-Analyser can be used to study DNs, to find common modular communities. We report results on using the tool to identify communities on synthetic DNs as well as real cases in social networks and biological data. CONCLUSION: The proposed method has been tested by using synthetic and biological networks. Results demonstrate that it is well able to detect meaningful information from DNs.

BACKGROUND: Glucocorticoid-remediable aldosteronism (GRA) is a form of heritable hypertension caused by a chimeric fusion resulting from unequal crossing over between 11β-hydroxylase (CYP11B1) and aldosterone synthase (CYP11B2), which are two genes with similar sequences. Different crossover patterns of the CYP11B1 and CYP11B2 chimeric genes may be associated with a variety of clinical presentations. It is therefore necessary to develop an efficient approach for identifying the differences between the hybrid genes of a patient with GRA. RESULTS: We developed a long-read analysis pipeline named GRAde (GRA deciphering), which utilizes the nonidentical bases in the CYP11B1 and CYP11B2 genomic sequences to identify and visualize the chimeric form. We sequenced the polymerase chain reaction (PCR) products of the CYP11B1/CYP11B2 chimeric gene from 36 patients with GRA using the Nanopore MinION device and analyzed the sequences using GRAde. Crossover events were identified for 30 out of the 36 samples. The crossover sites appeared in the region exhibiting high sequence similarity between CYP11B1 and CYP11B2, and 53.3% of the cases were identified as having a gene conversion in intron 2. More importantly, there were six cases for whom the PCR products indicated a chimeric gene, but the GRAde results revealed no crossover pattern. The crossover regions were further verified by Sanger sequencing analysis. CONCLUSIONS: PCR-based target enrichment followed by long-read sequencing is an efficient and precise approach to dissecting complex genomic regions, such as those involved in GRA mutations, which could be directly applied to clinical diagnosis. The scripts of GRAde are available at https://github.com/hsu-binfo/GRAde .

BACKGROUND: DNA methylation has long been known as an epigenetic gene silencing mechanism. For a motivating example, the methylomes of cancer and non-cancer cells show a number of methylation differences, indicating that certain features characteristics of cancer cells may be related to methylation characteristics. Robust methods for detecting differentially methylated regions (DMRs) could help scientists narrow down genome regions and even find biologically important regions. Although some statistical methods were developed for detecting DMR, there is no default or strongest method. Fisher's exact test is direct, but not suitable for data with multiple replications, while regression-based methods usually come with a large number of assumptions. More complicated methods have been proposed, but those methods are often difficult to interpret. RESULTS: In this paper, we propose a three-step nonparametric kernel smoothing method that is both flexible and straightforward to implement and interpret. The proposed method relies on local quadratic fitting to find the set of equilibrium points (points at which the first derivative is 0) and the corresponding set of confidence windows. Potential regions are further refined using biological criteria, and finally selected based on a Bonferroni adjusted t-test cutoff. Using a comparison of three senescent and three proliferating cell lines to illustrate our method, we were able to identify a total of 1077 DMRs on chromosome 21. CONCLUSIONS: We proposed a completely nonparametric, statistically straightforward, and interpretable method for detecting differentially methylated regions. Compared with existing methods, the non-reliance on model assumptions and the straightforward nature of our method makes it one competitive alternative to the existing statistical methods for defining DMRs.