Protein ligand docking is an indispensable tool for computational prediction of protein functions and screening drug candidates. Despite significant progress over the past two decades, it is still a challenging problem, characterized by the still limited understanding of the energetics between proteins and ligands, and the vast conformational space that has to be searched to find a satisfactory solution. In this project, we developed a novel reinforcement learning (RL) approach, the asynchronous advantage actor-critic model (A3C), to address the protein ligand docking problem. The overall framework consists of two models. During the search process, the agent takes an action selected by the actor model based on the current location. The critic model then evaluates this action and predict the distance between the current location and true binding site. Experimental results showed that in both single- and multi-atom cases, our model improves binding site prediction substantially compared to a naïve model. For the single-atom ligand, copper ion (Cu2+), the model predicted binding sites have a median root-mean-square-deviation (RMSD) of 2.39 Å to the true binding sites when starting from random starting locations. For the multi-atom ligand, sulfate ion (SO42-), the predicted binding sites have a median RMSD of 3.82 Å to the true binding sites. The ligand-specific models built in this study can be used in solvent mapping studies and the RL framework can be readily scaled up to larger and more diverse sets of ligands.

Though proposing algorithmic approaches for protein domain decomposition has been of high interest, the inherent ambiguity to the problem makes it still an active area of research. Besides, accurate automated methods are in high demand as the number of solved structures for complex proteins is on the rise. While majority of the previous efforts for decomposition of 3D structures are centered on the developing clustering algorithms, employing enhanced measures of proximity between the amino acids has remained rather uncharted. If there exists a kernel function that in its reproducing kernel Hilbert space, structural domains of proteins become well separated, then protein structures can be parsed into domains without the need to use a complex clustering algorithm. Inspired by this idea, we developed a protein domain decomposition method based on diffusion kernels on protein graphs. We examined all combinations of four graph node kernels and two clustering algorithms to investigate their capability to decompose protein structures. The proposed method is tested on five of the most commonly used benchmark datasets for protein domain assignment plus a comprehensive non-redundant dataset. The results show a competitive performance of the method utilizing one of the diffusion kernels compared to four of the best automatic methods. Our method is also able to offer alternative partitionings for the same structure which is in line with the subjective definition of protein domain. With a competitive accuracy and balanced performance for the simple and complex structures despite relying on a relatively naive criterion to choose optimal decomposition, the proposed method revealed that diffusion kernels on graphs in particular, and kernel functions in general are promising measures to facilitate parsing proteins into domains and performing different structural analysis on proteins. The size and interconnectedness of the protein graphs make them promising targets for diffusion kernels as measures of affinity between amino acids. The versatility of our method allows the implementation of future kernels with higher performance. The source code of the proposed method is accessible at https://github.com/taherimo/kludo . Also, the proposed method is available as a web application from https://cbph.ir/tools/kludo .

BACKGROUND: In various fields, searching for the Longest Common Subsequences (LCS) of Multiple (i.e., three or more) sequences (MLCS) is a classic but difficult problem to solve. The primary bottleneck in this problem is that present state-of-the-art algorithms require the construction of a huge graph (called a direct acyclic graph, or DAG), which the computer usually has not enough space to handle. Because of their massive time and space consumption, present algorithms are inapplicable to issues with lengthy and large-scale sequences. RESULTS: A mini Directed Acyclic Graph (mini-DAG) model and a novel Path Elimination Algorithm are proposed to address large-scale MLCS issues efficiently. In mini-DAG, we employ the branch and bound approach to reduce paths during DAG construction, resulting in a very mini DAG (mini-DAG), which saves memory space and search time. CONCLUSION: Empirical experiments have been performed on a standard benchmark set of DNA sequences. The experimental results show that our model outperforms the leading algorithms, especially for large-scale MLCS problems.

BACKGROUND: Accurately predicting drug-target binding affinity (DTA) in silico plays an important role in drug discovery. Most of the computational methods developed for predicting DTA use machine learning models, especially deep neural networks, and depend on large-scale labelled data. However, it is difficult to learn enough feature representation from tens of millions of compounds and hundreds of thousands of proteins only based on relatively limited labelled drug-target data. There are a large number of unknown drugs, which never appear in the labelled drug-target data. This is a kind of out-of-distribution problems in bio-medicine. Some recent studies adopted self-supervised pre-training tasks to learn structural information of amino acid sequences for enhancing the feature representation of proteins. However, the task gap between pre-training and DTA prediction brings the catastrophic forgetting problem, which hinders the full application of feature representation in DTA prediction and seriously affects the generalization capability of models for unknown drug discovery. RESULTS: To address these problems, we propose the GeneralizedDTA, which is a new DTA prediction model oriented to unknown drug discovery, by combining pre-training and multi-task learning. We introduce self-supervised protein and drug pre-training tasks to learn richer structural information from amino acid sequences of proteins and molecular graphs of drug compounds, in order to alleviate the problem of high variance caused by encoding based on deep neural networks and accelerate the convergence of prediction model on small-scale labelled data. We also develop a multi-task learning framework with a dual adaptation mechanism to narrow the task gap between pre-training and prediction for preventing overfitting and improving the generalization capability of DTA prediction model on unknown drug discovery. To validate the effectiveness of our model, we construct an unknown drug data set to simulate the scenario of unknown drug discovery. Compared with existing DTA prediction models, the experimental results show that our model has the higher generalization capability in the DTA prediction of unknown drugs. CONCLUSIONS: The advantages of our model are mainly attributed to two kinds of pre-training tasks and the multi-task learning framework, which can learn richer structural information of proteins and drugs from large-scale unlabeled data, and then effectively integrate it into the downstream prediction task for obtaining a high-quality DTA prediction in unknown drug discovery.

BACKGROUND: It is now widespread in livestock and plant breeding to use genotyping data to predict phenotypes with genomic prediction models. In parallel, genomic annotations related to a variety of traits are increasing in number and granularity, providing valuable insight into potentially important positions in the genome. The BayesRC model integrates this prior biological information by factorizing the genome according to disjoint annotation categories, in some cases enabling improved prediction of heritable traits. However, BayesRC is not adapted to cases where markers may have multiple annotations. RESULTS: We propose two novel Bayesian approaches to account for multi-annotated markers through a cumulative (BayesRC+) or preferential (BayesRC[Formula: see text]) model of the contribution of multiple annotation categories. We illustrate their performance on simulated data with various genetic architectures and types of annotations. We also explore their use on data from a backcross population of growing pigs in conjunction with annotations constructed using the PigQTLdb. In both simulated and real data, we observed a modest improvement in prediction quality with our models when used with informative annotations. In addition, our results show that BayesRC+ successfully prioritizes multi-annotated markers according to their posterior variance, while BayesRC[Formula: see text] provides a useful interpretation of informative annotations for multi-annotated markers. Finally, we explore several strategies for constructing annotations from a public database, highlighting the importance of careful consideration of this step. CONCLUSION: When used with annotations that are relevant to the trait under study, BayesRC[Formula: see text] and BayesRC+ allow for improved prediction and prioritization of multi-annotated markers, and can provide useful biological insight into the genetic architecture of traits.

BACKGROUND: Representing the complex interplay between different types of biomolecules across different omics layers in multi-omics networks bears great potential to gain a deep mechanistic understanding of gene regulation and disease. However, multi-omics networks easily grow into giant hairball structures that hamper biological interpretation. Module detection methods can decompose these networks into smaller interpretable modules. However, these methods are not adapted to deal with multi-omics data nor consider topological features. When deriving very large modules or ignoring the broader network context, interpretability remains limited. To address these issues, we developed a SUbgraph BAsed mulTi-OMIcs Clustering framework (SUBATOMIC), which infers small and interpretable modules with a specific topology while keeping track of connections to other modules and regulators. RESULTS: SUBATOMIC groups specific molecular interactions in composite network subgraphs of two and three nodes and clusters them into topological modules. These are functionally annotated, visualized and overlaid with expression profiles to go from static to dynamic modules. To preserve the larger network context, SUBATOMIC investigates statistically the connections in between modules as well as between modules and regulators such as miRNAs and transcription factors. We applied SUBATOMIC to analyze a composite Homo sapiens network containing transcription factor-target gene, miRNA-target gene, protein-protein, homologous and co-functional interactions from different databases. We derived and annotated 5586 modules with diverse topological, functional and regulatory properties. We created novel functional hypotheses for unannotated genes. Furthermore, we integrated modules with condition specific expression data to study the influence of hypoxia in three cancer cell lines. We developed two prioritization strategies to identify the most relevant modules in specific biological contexts: one considering GO term enrichments and one calculating an activity score reflecting the degree of differential expression. Both strategies yielded modules specifically reacting to low oxygen levels. CONCLUSIONS: We developed the SUBATOMIC framework that generates interpretable modules from integrated multi-omics networks and applied it to hypoxia in cancer. SUBATOMIC can infer and contextualize modules, explore condition or disease specific modules, identify regulators and functionally related modules, and derive novel gene functions for uncharacterized genes. The software is available at https://github.com/CBIGR/SUBATOMIC .

BACKGROUND: Pathogenic mutations in genes that control chromatin function have been implicated in rare genetic syndromes. These chromatin modifiers exhibit extraordinary diversity in the scale of the epigenetic changes they affect, from single basepair modifications by DNMT1 to whole genome structural changes by PRM1/2. Patterns of DNA methylation are related to a diverse set of epigenetic features across this full range of epigenetic scale, making DNA methylation valuable for mapping regions of general epigenetic dysregulation. However, existing methods are unable to accurately identify regions of differential methylation across this full range of epigenetic scale directly from DNA methylation data. RESULTS: To address this, we developed DMRscaler, a novel method that uses an iterative windowing procedure to capture regions of differential DNA methylation (DMRs) ranging in size from single basepairs to whole chromosomes. We benchmarked DMRscaler against several DMR callers in simulated and natural data comparing XX and XY peripheral blood samples. DMRscaler was the only method that accurately called DMRs ranging in size from 100 bp to 1 Mb (pearson's r = 0.94) and up to 152 Mb on the X-chromosome. We then analyzed methylation data from rare-disease cohorts that harbor chromatin modifier gene mutations in NSD1, EZH2, and KAT6A where DMRscaler identified novel DMRs spanning gene clusters involved in development. CONCLUSION: Taken together, our results show DMRscaler is uniquely able to capture the size of DMR features across the full range of epigenetic scale and identify novel, co-regulated regions that drive epigenetic dysregulation in human disease.

BACKGROUND: Bioinformatics has gained much attention as a fast growing interdisciplinary field. Several attempts have been conducted to explore the field of bioinformatics by bibliometric analysis, however, such works did not elucidate the role of visualization in analysis, nor focus on the relationship between sub-topics of bioinformatics. RESULTS: First, the hotspot of bioinformatics has moderately shifted from traditional molecular biology to omics research, and the computational method has also shifted from mathematical model to data mining and machine learning. Second, DNA-related topics are bridge topics in bioinformatics research. These topics gradually connect various sub-topics that are relatively independent at first. Third, only a small part of topics we have obtained involves a number of computational methods, and the other topics focus more on biological aspects. Fourth, the proportion of computing-related topics hit a trough in the 1980s. During this period, the use of traditional calculation methods such as mathematical model declined in a large proportion while the new calculation methods such as machine learning have not been applied in a large scale. This proportion began to increase gradually after the 1990s. Fifth, although the proportion of computing-related topics is only slightly higher than the original, the connection between other topics and computing-related topics has become closer, which means the support of computational methods is becoming increasingly important for the research of bioinformatics. CONCLUSIONS: The results of our analysis imply that research on bioinformatics is becoming more diversified and the ranking of computational methods in bioinformatics research is also gradually improving.

BACKGROUND: Identifying protein complexes from protein-protein interaction network is one of significant tasks in the postgenome era. Protein complexes, none of which exceeds 10 in size play an irreplaceable role in life activities and are also a hotspot of scientific research, such as PSD-95, CD44, PKM2 and BRD4. And in MIPS, CYC2008, SGD, Aloy and TAP06 datasets, the proportion of small protein complexes is over 75%. But up to now, protein complex identification methods do not perform well in the field of small protein complexes. RESULTS: In this paper, we propose a novel method, called BOPS. It is a three-step procedure. Firstly, it calculates the balanced weights to replace the original weights. Secondly, it divides the graphs larger than MAXP until the original PPIN is divided into small PPINs. Thirdly, it enumerates the connected subset of each small PPINs, identifies potential protein complexes based on cohesion and removes those that are similar. CONCLUSIONS: In four yeast PPINs, experimental results have shown that BOPS has an improvement of about 5% compared with the SOTA model. In addition, we constructed a weighted Homo sapiens PPIN based on STRINGdb and BioGRID, and BOPS gets the best result in it. These results give new insights into the identification of small protein complexes, and the weighted Homo sapiens PPIN provides more data for related research.

BACKGROUND: To date, there are no effective treatments for most neurodegenerative diseases. Knowledge graphs can provide comprehensive and semantic representation for heterogeneous data, and have been successfully leveraged in many biomedical applications including drug repurposing. Our objective is to construct a knowledge graph from literature to study the relations between Alzheimer's disease (AD) and chemicals, drugs and dietary supplements in order to identify opportunities to prevent or delay neurodegenerative progression. We collected biomedical annotations and extracted their relations using SemRep via SemMedDB. We used both a BERT-based classifier and rule-based methods during data preprocessing to exclude noise while preserving most AD-related semantic triples. The 1,672,110 filtered triples were used to train with knowledge graph completion algorithms (i.e., TransE, DistMult, and ComplEx) to predict candidates that might be helpful for AD treatment or prevention. RESULTS: Among three knowledge graph completion models, TransE outperformed the other two (MR = 10.53, Hits@1 = 0.28). We leveraged the time-slicing technique to further evaluate the prediction results. We found supporting evidence for most highly ranked candidates predicted by our model which indicates that our approach can inform reliable new knowledge. CONCLUSION: This paper shows that our graph mining model can predict reliable new relationships between AD and other entities (i.e., dietary supplements, chemicals, and drugs). The knowledge graph constructed can facilitate data-driven knowledge discoveries and the generation of novel hypotheses.

BACKGROUND: Artificial intelligence (AI) and machine learning (ML) have resulted in significant enthusiasm for their promise in healthcare. Despite this, prospective randomized controlled trials and successful clinical implementation remain limited. One clinical application of ML is mitigation of the increased risk for acute care during outpatient cancer therapy. We previously reported the results of the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) study (NCT04277650), which was a prospective, randomized quality improvement study demonstrating that ML based on electronic health record (EHR) data can direct supplemental clinical evaluations and reduce the rate of acute care during cancer radiotherapy with and without chemotherapy. The objective of this study is to report the workflow and operational challenges encountered during ML implementation on the SHIELD-RT study. RESULTS: Data extraction and manual review steps in the workflow represented significant time commitments for implementation of clinical ML on a prospective, randomized study. Barriers include limited data availability through the standard clinical workflow and commercial products, the need to aggregate data from multiple sources, and logistical challenges from altering the standard clinical workflow to deliver adaptive care. CONCLUSIONS: The SHIELD-RT study was an early randomized controlled study which enabled assessment of barriers to clinical ML implementation, specifically those which leverage the EHR. These challenges build on a growing body of literature and may provide lessons for future healthcare ML adoption. TRIAL REGISTRATION: NCT04277650. Registered 20 February 2020. Retrospectively registered quality improvement study.

BACKGROUND: Oxidative stress plays an important role in the progression of various types of tumors. However, its role in esophageal squamous cell carcinoma (ESCC) has seldom been explored. This study aimed to discover prognostic markers associated with oxidative stress in ESCC to improve the prediction of prognosis and help in the selection of effective immunotherapy for patients. RESULTS: A consensus cluster was constructed using 14 prognostic differentially expressed oxidative stress-related genes (DEOSGs) that were remarkably related to the prognosis of patients with ESCC. The infiltration levels of neutrophils, plasma cells, and activated mast cells, along with immune score, stromal score, and estimated score, were higher in cluster 1 than in cluster 2. A prognostic signature based on 10 prognostic DEOSGs was devised that could evaluate the prognosis of patients with ESCC. Calculated risk score proved to be an independent clinical prognostic factor in the training, testing, and entire sets. P53 signaling pathway was highly enriched in the high-risk group. The calculated risk score was positively related to the infiltration levels of resting mast cells, memory B cells, and activated natural killer (NK) cells and negatively associated with the infiltration levels of M1 and M2 macrophages. The relationship between clinical characteristics and risk score has not been certified. The half-maximal inhibitory concentration (IC50) values for sorafenib and gefitinib were lower for patients in the low-risk group. CONCLUSION: Our prognostic signature based on 10 prognostic DEOSGs could predict the disease outcomes of patients with ESCC and had strong clinical value. Our study improves the understanding of oxidative stress in tumor immune microenvironment (TIME) and provides insights for developing improved and efficient immunotherapy strategies.

BACKGROUND: Microbes are associated with many human diseases and influence drug efficacy. Small-molecule drugs may revolutionize biomedicine by fine-tuning the microbiota on the basis of individual patient microbiome signatures. However, emerging endeavors in small-molecule microbiome drug discovery continue to follow a conventional "one-drug-one-target-one-disease" process. A systematic pharmacology approach that would suppress multiple interacting pathogenic species in the microbiome, could offer an attractive alternative solution. RESULTS: We construct a disease-centric signed microbe-microbe interaction network using curated microbe metabolite information and their effects on host. We develop a Signed Random Walk with Restart algorithm for the accurate prediction of effect of microbes on human health and diseases. With a survey on the druggable and evolutionary space of microbe proteins, we find that 8-10% of them can be targeted by existing drugs or drug-like chemicals and that 25% of them have homologs to human proteins. We demonstrate that drugs for diabetes can be the lead compounds for development of microbiota-targeted therapeutics. We further show that the potential drug targets that specifically exist in pathogenic microbes are periplasmic and cellular outer membrane proteins. CONCLUSION: The systematic studies of the polypharmacological landscape of the microbiome network may open a new avenue for the small-molecule drug discovery of the microbiome. We believe that the application of systematic method on the polypharmacological investigation could lead to the discovery of novel drug therapies.

BACKGROUND: Population variant analysis is of great importance for gathering insights into the links between human genotype and phenotype. The 1000 Genomes Project established a valuable reference for human genetic variation; however, the integrative use of the corresponding data with other datasets within existing repositories and pipelines is not fully supported. Particularly, there is a pressing need for flexible and fast selection of population partitions based on their variant and metadata-related characteristics. RESULTS: Here, we target general germline or somatic mutation data sources for their seamless inclusion within an interoperable-format repository, supporting integration among them and with other genomic data, as well as their integrated use within bioinformatic workflows. In addition, we provide VarSum, a data summarization service working on sub-populations of interest selected using filters on population metadata and/or variant characteristics. The service is developed as an optimized computational framework with an Application Programming Interface (API) that can be called from within any existing computing pipeline or programming script. Provided example use cases of biological interest show the relevance, power and ease of use of the API functionalities. CONCLUSIONS: The proposed data integration pipeline and data set extraction and summarization API pave the way for solid computational infrastructures that quickly process cumbersome variation data, and allow biologists and bioinformaticians to easily perform scalable analysis on user-defined partitions of large cohorts from increasingly available genetic variation studies. With the current tendency to large (cross)nation-wide sequencing and variation initiatives, we expect an ever growing need for the kind of computational support hereby proposed.

BACKGROUND: Biomedical translational science is increasingly using computational reasoning on repositories of structured knowledge (such as UMLS, SemMedDB, ChEMBL, Reactome, DrugBank, and SMPDB in order to facilitate discovery of new therapeutic targets and modalities. The NCATS Biomedical Data Translator project is working to federate autonomous reasoning agents and knowledge providers within a distributed system for answering translational questions. Within that project and the broader field, there is a need for a framework that can efficiently and reproducibly build an integrated, standards-compliant, and comprehensive biomedical knowledge graph that can be downloaded in standard serialized form or queried via a public application programming interface (API). RESULTS: To create a knowledge provider system within the Translator project, we have developed RTX-KG2, an open-source software system for building-and hosting a web API for querying-a biomedical knowledge graph that uses an Extract-Transform-Load approach to integrate 70 knowledge sources (including the aforementioned core six sources) into a knowledge graph with provenance information including (where available) citations. The semantic layer and schema for RTX-KG2 follow the standard Biolink model to maximize interoperability. RTX-KG2 is currently being used by multiple Translator reasoning agents, both in its downloadable form and via its SmartAPI-registered interface. Serializations of RTX-KG2 are available for download in both the pre-canonicalized form and in canonicalized form (in which synonyms are merged). The current canonicalized version (KG2.7.3) of RTX-KG2 contains 6.4M nodes and 39.3M edges with a hierarchy of 77 relationship types from Biolink. CONCLUSION: RTX-KG2 is the first knowledge graph that integrates UMLS, SemMedDB, ChEMBL, DrugBank, Reactome, SMPDB, and 64 additional knowledge sources within a knowledge graph that conforms to the Biolink standard for its semantic layer and schema. RTX-KG2 is publicly available for querying via its API at arax.rtx.ai/api/rtxkg2/v1.2/openapi.json . The code to build RTX-KG2 is publicly available at github:RTXteam/RTX-KG2 .

BACKGROUND: Advances in imagery at atomic and near-atomic resolution, such as cryogenic electron microscopy (cryo-EM), have led to an influx of high resolution images of proteins and other macromolecular structures to data banks worldwide. Producing a protein structure from the discrete voxel grid data of cryo-EM maps involves interpolation into the continuous spatial domain. We present a novel data format called the neural cryo-EM map, which is formed from a set of neural networks that accurately parameterize cryo-EM maps and provide native, spatially continuous data for density and gradient. As a case study of this data format, we create graph-based interpretations of high resolution experimental cryo-EM maps. RESULTS: Normalized cryo-EM map values interpolated using the non-linear neural cryo-EM format are more accurate, consistently scoring less than 0.01 mean absolute error, than a conventional tri-linear interpolation, which scores up to 0.12 mean absolute error. Our graph-based interpretations of 115 experimental cryo-EM maps from 1.15 to 4.0 Å resolution provide high coverage of the underlying amino acid residue locations, while accuracy of nodes is correlated with resolution. The nodes of graphs created from atomic resolution maps (higher than 1.6 Å) provide greater than 99% residue coverage as well as 85% full atomic coverage with a mean of 0.19 Å root mean squared deviation. Other graphs have a mean 84% residue coverage with less specificity of the nodes due to experimental noise and differences of density context at lower resolutions. CONCLUSIONS: The fully continuous and differentiable nature of the neural cryo-EM map enables the adaptation of the voxel data to alternative data formats, such as a graph that characterizes the atomic locations of the underlying protein or macromolecular structure. Graphs created from atomic resolution maps are superior in finding atom locations and may serve as input to predictive residue classification and structure segmentation methods. This work may be generalized to transform any 3D grid-based data format into non-linear, continuous, and differentiable format for downstream geometric deep learning applications.

BACKGROUND: Making clear what kinds of metabolic pathways a drug compound involves in can help researchers understand how the drug is absorbed, distributed, metabolized, and excreted. The characteristics of a compound such as structure, composition and so on directly determine the metabolic pathways it participates in. METHODS: We developed a novel hybrid framework based on the graph attention network (GAT) to predict the metabolic pathway classes that a compound involves in, named HFGAT, by making use of its global and local characteristics. The framework mainly consists of a two-branch feature extracting layer and a fully connected (FC) layer. In the two-branch feature extracting layer, one branch is responsible to extract global features of the compound; and the other branch introduces a GAT consisting of two graph attention layers to extract local structural features of the compound. Both the global and the local features of the compound are then integrated into the FC layer which outputs the predicted result of metabolic pathway categories that the compound belongs to. RESULTS: We compared the multi-class classification performance of HFGAT with six other representative methods, including five classic machine learning methods and one graph convolutional network (GCN) based deep learning method, on the benchmark dataset containing 6999 compounds belonging to 11 pathway categories. The results showed that the deep learning-based methods (HFGAT, GCN-based method) outperformed the traditional machine learning methods in the prediction of metabolic pathways and our proposed HFGAT method performed better than the GCN-based method. Moreover, HFGAT achieved higher [Formula: see text] scores on 8 of 11 classes than the GCN-based method. CONCLUSIONS: Our proposed HFGAT makes use of both the global and local information of the compounds to predict their metabolic pathway categories and has achieved a significant performance. Compared with the GCN model, the introduction of the GAT can help our model pay more attention to substructures of the compound that are useful for the prediction task. The study provided a potential method for drug discovery with all types of metabolic reactions that may be involved in the decomposition and synthesis of pharmaceutical compounds in the organism.

BACKGROUND: Twitter is a popular social networking site where short messages or "tweets" of users have been used extensively for research purposes. However, not much research has been done in mining the medical professions, such as detecting the occupations of users from their biographical contents. Mining such professions can be used to build efficient recommender systems for cost-effective targeted advertisements. Moreover, it is highly important to develop effective methods to identify the occupation of users since conventional classification methods rely on features developed by human intelligence. Although, the result may be favorable for the classification problem. However, it is still extremely challenging for traditional classifiers to predict the medical occupations accurately since it involves predicting multiple occupations. Hence this study emphasizes predicting the medical occupational class of users through their public biographical ("Bio") content. We have conducted our analysis by annotating the bio content of Twitter users. In this paper, we propose a method of combining word embedding with state-of-art neural network models that include: Long Short Term Memory (LSTM), Bidirectional LSTM, Gated Recurrent Unit, Bidirectional Encoder Representations from Transformers, and A lite BERT. Moreover, we have also observed that by composing the word embedding with the neural network models there is no need to construct any particular attribute or feature. By using word embedding, the bio contents are formatted as dense vectors which are fed as input into the neural network models as a sequence of vectors. RESULT: Performance metrics that include accuracy, precision, recall, and F1-score have shown a significant difference between our method of combining word embedding with neural network models than with the traditional methods. The scores have proved that our proposed approach has outperformed the traditional machine learning techniques for detecting medical occupations among users. ALBERT has performed the best among the deep learning networks with an F1 score of 0.90. CONCLUSION: In this study, we have presented a novel method of detecting the occupations of Twitter users engaged in the medical domain by merging word embedding with state-of-art neural networks. The outcomes of our approach have demonstrated that our method can further advance the process of analyzing corpora of social media without going through the trouble of developing computationally expensive features.

BACKGROUND: The eukaryotic genome is capable of producing multiple isoforms from a gene by alternative polyadenylation (APA) during pre-mRNA processing. APA in the 3'-untranslated region (3'-UTR) of mRNA produces transcripts with shorter or longer 3'-UTR. Often, 3'-UTR serves as a binding platform for microRNAs and RNA-binding proteins, which affect the fate of the mRNA transcript. Thus, 3'-UTR APA is known to modulate translation and provides a mean to regulate gene expression at the post-transcriptional level. Current bioinformatics pipelines have limited capability in profiling 3'-UTR APA events due to incomplete annotations and a low-resolution analyzing power: widely available bioinformatics pipelines do not reference actionable polyadenylation (cleavage) sites but simulate 3'-UTR APA only using RNA-seq read coverage, causing false positive identifications. To overcome these limitations, we developed APA-Scan, a robust program that identifies 3'-UTR APA events and visualizes the RNA-seq short-read coverage with gene annotations. METHODS: APA-Scan utilizes either predicted or experimentally validated actionable polyadenylation signals as a reference for polyadenylation sites and calculates the quantity of long and short 3'-UTR transcripts in the RNA-seq data. APA-Scan works in three major steps: (i) calculate the read coverage of the 3'-UTR regions of genes; (ii) identify the potential APA sites and evaluate the significance of the events among two biological conditions; (iii) graphical representation of user specific event with 3'-UTR annotation and read coverage on the 3'-UTR regions. APA-Scan is implemented in Python3. Source code and a comprehensive user's manual are freely available at https://github.com/compbiolabucf/APA-Scan . RESULT: APA-Scan was applied to both simulated and real RNA-seq datasets and compared with two widely used baselines DaPars and APAtrap. In simulation APA-Scan significantly improved the accuracy of 3'-UTR APA identification compared to the other baselines. The performance of APA-Scan was also validated by 3'-end-seq data and qPCR on mouse embryonic fibroblast cells. The experiments confirm that APA-Scan can detect unannotated 3'-UTR APA events and improve genome annotation. CONCLUSION: APA-Scan is a comprehensive computational pipeline to detect transcriptome-wide 3'-UTR APA events. The pipeline integrates both RNA-seq and 3'-end-seq data information and can efficiently identify the significant events with a high-resolution short reads coverage plots.

BACKGROUND: Protein histidine phosphorylation (pHis) plays critical roles in prokaryotic signal transduction pathways and various eukaryotic cellular processes. It is estimated to account for 6-10% of the phosphoproteome, however only hundreds of pHis sites have been discovered to date. Due to the inherent disadvantages of experimental methods, it is an urgent task for developing efficient computational approaches to identify pHis sites. RESULTS: Here, we present a novel tool, pHisPred, for accurately identifying pHis sites from protein sequences. We manually collected the largest number of experimental validated pHis sites to build benchmark datasets. Using randomized tenfold CV, the weighted SVM-RBF model shows the best performance than other four commonly used classification models (LR, KNN, RF, and MLP). From ten thousands of features, 140 and 150 most informative features were individually selected out for eukaryotic and prokaryotic models. The average AUC and F1-score values of pHisPred were (0.81, 0.40) and (0.78, 0.46) for tenfold CV on the eukaryotic and prokaryotic training datasets, respectively. In addition, pHisPred significantly outperforms other tools on testing datasets, in particular on the eukaryotic one. CONCLUSION: We implemented a python program of pHisPred, which is freely available for non-commercial use at https://github.com/xiaofengsong/pHisPred . Moreover, users can use it to train new models with their own data.

Recent research has already shown that circular RNAs (circRNAs) are functional in gene expression regulation and potentially related to diseases. Due to their stability, circRNAs can also be used as biomarkers for diagnosis. However, the function of most circRNAs remains unknown, and it is expensive and time-consuming to discover it through biological experiments. In this paper, we predict circRNA annotations from the knowledge of their interaction with miRNAs and subsequent miRNA-mRNA interactions. First, we construct an interaction network for a target circRNA and secondly spread the information from the network nodes with the known function to the root circRNA node. This idea itself is not new; our main contribution lies in proposing an efficient and exact deterministic procedure based on the principle of probability-generating functions to calculate the p-value of association test between a circRNA and an annotation term. We show that our publicly available algorithm is both more effective and efficient than the commonly used Monte-Carlo sampling approach that may suffer from difficult quantification of sampling convergence and subsequent sampling inefficiency. We experimentally demonstrate that the new approach is two orders of magnitude faster than the Monte-Carlo sampling, which makes summary annotation of large circRNA files feasible; this includes their reannotation after periodical interaction network updates, for example. We provide a summary annotation of a current circRNA database as one of our outputs. The proposed algorithm could be generalized towards other types of RNA in way that is straightforward.

BACKGROUND: Pathway-based analysis of transcriptomic data has shown greater stability and better performance than traditional gene-based analysis. Until now, some pathway-based deep learning models have been developed for bioinformatic analysis, but these models have not fully considered the topological features of pathways, which limits the performance of the final prediction result. RESULTS: To address this issue, we propose a novel model, called PathGNN, which constructs a Graph Neural Networks (GNNs) model that can capture topological features of pathways. As a case, PathGNN was applied to predict long-term survival of four types of cancer and achieved promising predictive performance when compared to other common methods. Furthermore, the adoption of an interpretation algorithm enabled the identification of plausible pathways associated with survival. CONCLUSION: PathGNN demonstrates that GNN can be effectively applied to build a pathway-based model, resulting in promising predictive power.

In this paper we introduce a new representation for the multistationarity region of a reaction network, using polynomial superlevel sets. The advantages of using this polynomial superlevel set representation over the already existing representations (cylindrical algebraic decompositions, numeric sampling, rectangular divisions) is discussed, and algorithms to compute this new representation are provided. The results are given for the general mathematical formalism of a parametric system of equations and so may be applied to other application domains.

BACKGROUND: Collagen VI family (COL6A) is a major member of extracellular matrix protein. There is accumulating evidence that COL6A is involved in tumorigenesis and tumor progression. In this study, we performed a systematic analysis of COL6A in pan-cancer based on their molecular features and clinical significance. METHODS: Based on updated public databases, we integrated several bioinformatics analysis methods to investigate the expression levels of COL6A as well as the relationship between their expression and patient survival, immune subtypes, tumor microenvironment, stemness scores, drug sensitivity, and DNA methylation. RESULTS: The expression levels of COL6A members varied in different cancers, suggesting their expression was cancer-dependent. Among COL6A members, COL6A1/2/3 were predicted poor prognosis in specific cancers. Furthermore, COL6A1/2/3 expression levels revealed a clear correlation with immune subtypes, and COL6A1/2/3 were associated with tumor purity, that is, gene expression levels were generally higher in tumors with higher stromal scores and immune scores. COL6A1/2/3 had a significantly negative correlation with RNA stemness scores, and meanwhile they were also related to DNA stemness scores in different degrees. In addition, the expression of COL6A1/2/3 was significantly related to drug sensitivity of cancer cells. Finally, our study revealed that COL6A1/2/3 expression was mainly negatively correlated with gene methylation, and the methylation levels showed remarkable differences in various cancers. CONCLUSIONS: These findings highlight both the similarities and differences in the molecular characteristics of COL6A members in pan-cancer, and provide comprehensive insights for further investigation into the mechanism of COL6A.

BACKGROUND: Microarrays can perform large scale studies of differential expressed gene (DEGs) and even single nucleotide polymorphisms (SNPs), thereby screening thousands of genes for single experiment simultaneously. However, DEGs and SNPs are still just as enigmatic as the first sequence of the genome. Because they are independent from the affected biological context. Pathway enrichment analysis (PEA) can overcome this obstacle by linking both DEGs and SNPs to the affected biological pathways and consequently to the underlying biological functions and processes. RESULTS: To improve the enrichment analysis results, we present a new statistical network pre-processing method by mapping DEGs and SNPs on a biological network that can improve the relevance and significance of the DEGs or SNPs of interest to incorporate pathway topology information into the PEA. The proposed methodology improves the statistical significance of the PEA analysis in terms of computed p value for each enriched pathways and limit the number of enriched pathways. This helps reduce the number of relevant biological pathways with respect to a non-specific list of genes. CONCLUSION: The proposed method provides two-fold enhancements. Network analysis reveals fewer DEGs, by selecting only relevant DEGs and the detected DEGs improve the enriched pathways' statistical significance, rather than simply using a general list of genes.

BACKGROUND: Deep learning's automatic feature extraction has proven to give superior performance in many sequence classification tasks. However, deep learning models generally require a massive amount of data to train, which in the case of Hemolytic Activity Prediction of Antimicrobial Peptides creates a challenge due to the small amount of available data. RESULTS: Three different datasets for hemolysis activity prediction of therapeutic and antimicrobial peptides are gathered and the AMPDeep pipeline is implemented for each. The result demonstrate that AMPDeep outperforms the previous works on all three datasets, including works that use physicochemical features to represent the peptides or those who solely rely on the sequence and use deep learning to learn representation for the peptides. Moreover, a combined dataset is introduced for hemolytic activity prediction to address the problem of sequence similarity in this domain. AMPDeep fine-tunes a large transformer based model on a small amount of peptides and successfully leverages the patterns learned from other protein and peptide databases to assist hemolysis activity prediction modeling. CONCLUSIONS: In this work transfer learning is leveraged to overcome the challenge of small data and a deep learning based model is successfully adopted for hemolysis activity classification of antimicrobial peptides. This model is first initialized as a protein language model which is pre-trained on masked amino acid prediction on many unlabeled protein sequences in a self-supervised manner. Having done so, the model is fine-tuned on an aggregated dataset of labeled peptides in a supervised manner to predict secretion. Through transfer learning, hyper-parameter optimization and selective fine-tuning, AMPDeep is able to achieve state-of-the-art performance on three hemolysis datasets using only the sequence of the peptides. This work assists the adoption of large sequence-based models for peptide classification and modeling tasks in a practical manner.

The recent global focus on big data in medicine has been associated with the rise of artificial intelligence (AI) in diagnosis and decision-making following recent advances in computer technology. Up to now, AI has been applied to various aspects of medicine, including disease diagnosis, surveillance, treatment, predicting future risk, targeted interventions and understanding of the disease. There have been plenty of successful examples in medicine of using big data, such as radiology and pathology, ophthalmology cardiology and surgery. Combining medicine and AI has become a powerful tool to change health care, and even to change the nature of disease screening in clinical diagnosis. As all we know, clinical laboratories produce large amounts of testing data every day and the clinical laboratory data combined with AI may establish a new diagnosis and treatment has attracted wide attention. At present, a new concept of radiomics has been created for imaging data combined with AI, but a new definition of clinical laboratory data combined with AI has lacked so that many studies in this field cannot be accurately classified. Therefore, we propose a new concept of clinical laboratory omics (Clinlabomics) by combining clinical laboratory medicine and AI. Clinlabomics can use high-throughput methods to extract large amounts of feature data from blood, body fluids, secretions, excreta, and cast clinical laboratory test data. Then using the data statistics, machine learning, and other methods to read more undiscovered information. In this review, we have summarized the application of clinical laboratory data combined with AI in medical fields. Undeniable, the application of Clinlabomics is a method that can assist many fields of medicine but still requires further validation in a multi-center environment and laboratory.

BACKGROUND: In RNA-sequencing studies a large number of hypothesis tests are performed to compare the differential expression of genes between several conditions. Filtering has been proposed to remove candidate genes with a low expression level which may not be relevant and have little or no chance of showing a difference between conditions. This step may reduce the multiple testing burden and increase power. RESULTS: We show in a simulation study that filtering can lead to some increase in power for RNA-sequencing data, too aggressive filtering, however, can lead to a decline. No uniformly optimal filter in terms of power exists. Depending on the scenario different filters may be optimal. We propose an adaptive filtering strategy which selects one of several filters to maximise the number of rejections. No additional adjustment for multiplicity has to be included, but a rule has to be considered if the number of rejections is too small. CONCLUSIONS: For a large range of simulation scenarios, the adaptive filter maximises the power while the simulated False Discovery Rate is bounded by the pre-defined significance level. Using the adaptive filter, it is not necessary to pre-specify a single individual filtering method optimised for a specific scenario.

BACKGROUND: Due to the ever-expanding gap between the number of proteins being discovered and their functional characterization, protein function inference remains a fundamental challenge in computational biology. Currently, known protein annotations are organized in human-curated ontologies, however, all possible protein functions may not be organized accurately. Meanwhile, recent advancements in natural language processing and machine learning have developed models which embed amino acid sequences as vectors in n-dimensional space. So far, these embeddings have primarily been used to classify protein sequences using manually constructed protein classification schemes. RESULTS: In this work, we describe the use of amino acid sequence embeddings as a systematic framework for studying protein ontologies. Using a sequence embedding, we show that the bacterial carbohydrate metabolism class within the SEED annotation system contains 48 clusters of embedded sequences despite this class containing 29 functional labels. Furthermore, by embedding Bacillus amino acid sequences with unknown functions, we show that these unknown sequences form clusters that are likely to have similar biological roles. CONCLUSIONS: This study demonstrates that amino acid sequence embeddings may be a powerful tool for developing more robust ontologies for annotating protein sequence data. In addition, embeddings may be beneficial for clustering protein sequences with unknown functions and selecting optimal candidate proteins to characterize experimentally.

BACKGROUND: Public Data Commons (PDC) have been highlighted in the scientific literature for their capacity to collect and harmonize big data. On the other hand, local data commons (LDC), located within an institution or organization, have been underrepresented in the scientific literature, even though they are a critical part of research infrastructure. Being closest to the sources of data, LDCs provide the ability to collect and maintain the most up-to-date, high-quality data within an organization, closest to the sources of the data. As a data provider, LDCs have many challenges in both collecting and standardizing data, moreover, as a consumer of PDC, they face problems of data harmonization stemming from the monolithic harmonization pipeline designs commonly adapted by many PDCs. Unfortunately, existing guidelines and resources for building and maintaining data commons exclusively focus on PDC and provide very little information on LDC. RESULTS: This article focuses on four important observations. First, there are three different types of LDC service models that are defined based on their roles and requirements. These can be used as guidelines for building new LDC or enhancing the services of existing LDC. Second, the seven core services of LDC are discussed, including cohort identification and facilitation of genomic sequencing, the management of molecular reports and associated infrastructure, quality control, data harmonization, data integration, data sharing, and data access control. Third, instead of commonly developed monolithic systems, we propose a new data sharing method for data harmonization that combines both divide-and-conquer and bottom-up approaches. Finally, an end-to-end LDC implementation is introduced with real-world examples. CONCLUSIONS: Although LDCs are an optimal place to identify and address data quality issues, they have traditionally been relegated to the role of passive data provider for much larger PDC. Indeed, many LDCs limit their functions to only conducting routine data storage and transmission tasks due to a lack of information on how to design, develop, and improve their services using limited resources. We hope that this work will be the first small step in raising awareness among the LDCs of their expanded utility and to publicize to a wider audience the importance of LDC.

BACKGROUND: The placental barrier protects the fetus from exposure to some toxicants and is vital for drug development and risk assessment of environmental chemicals. However, in vivo experiments for assessing the placental barrier permeability of chemicals is not ethically acceptable. Although ex vivo placental perfusion methods provide good alternatives for the assessment of placental barrier permeability, the application to a large number of test chemicals could be time- and resource-consuming. Computational prediction models for ex vivo placental barrier permeability are therefore desirable. METHODS: A total of 87 chemicals and corresponding 1444 physicochemical properties were divided into training and test datasets. Three types of algorithms including linear regression, random forest, and ensemble models were applied to develop prediction models for ex vivo placental barrier permeability. RESULTS: Among the tested models, the ensemble model integrating the previous two methods performed best for predicting ex vivo human placental barrier permeability with correlation coefficients of 0.887 and 0.825 when considering the applicability domain. An additional test on seven newly curated chemicals from the literature showed a good correlation coefficient of 0.879 which was further improved to 0.921 by considering the variation of experiments. CONCLUSION: In this study, the first valid predicting model for ex vivo human placental barrier permeability was developed following the OECD guideline. The model is expected to be useful for assessing the human placental barrier permeability and can be integrated with developmental toxicity prediction models for investigating the toxic effects of chemicals on the fetus.

BACKGROUND: The technologies advances of single-cell Assay for Transposase Accessible Chromatin using sequencing (scATAC-seq) allowed to generate thousands of single cells in a relatively easy and economic manner and it is rapidly advancing the understanding of the cellular composition of complex organisms and tissues. The data structure and feature in scRNA-seq is similar to that in scATAC-seq, therefore, it's encouraged to identify and classify the cell types in scATAC-seq through traditional supervised machine learning methods, which are proved reliable in scRNA-seq datasets. RESULTS: In this study, we evaluated the classification performance of 6 well-known machine learning methods on scATAC-seq. A total of 4 public scATAC-seq datasets vary in tissues, sizes and technologies were applied to the evaluation of the performance of the methods. We assessed these methods using a 5-folds cross validation experiment, called intra-dataset experiment, based on recall, precision and the percentage of correctly predicted cells. The results show that these methods performed well in some specific types of the cell in a specific scATAC-seq dataset, while the overall performance is not as well as that in scRNA-seq analysis. In addition, we evaluated the classification performance of these methods by training and predicting in different datasets generated from same sample, called inter-datasets experiments, which may help us to assess the performance of these methods in more realistic scenarios. CONCLUSIONS: Both in intra-dataset and in inter-dataset experiment, SVM and NMC are overall outperformed others across all 4 datasets. Thus, we recommend researchers to use SVM and NMC as the underlying classifier when developing an automatic cell-type classification method for scATAC-seq.

BACKGROUND: Retrosynthesis prediction is the task of deducing reactants from reaction products, which is of great importance for designing the synthesis routes of the target products. The product molecules are generally represented with some descriptors such as simplified molecular input line entry specification (SMILES) or molecular fingerprints in order to build the prediction models. However, most of the existing models utilize only one molecular descriptor and simply consider the molecular descriptors in a whole rather than further mining multi-scale features, which cannot fully and finely utilizes molecules and molecular descriptors features. RESULTS: We propose a novel model to address the above concerns. Firstly, we build a new convolutional neural network (CNN) based feature extraction network to extract multi-scale features from the molecular descriptors by utilizing several filters with different sizes. Then, we utilize a two-branch feature extraction layer to fusion the multi-scale features of several molecular descriptors to perform the retrosynthesis prediction without expert knowledge. The comparing result with other models on the benchmark USPTO-50k chemical dataset shows that our model surpasses the state-of-the-art model by 7.4%, 10.8%, 11.7% and 12.2% in terms of the top-1, top-3, top-5 and top-10 accuracies. Since there is no related work in the field of bioretrosynthesis prediction due to the fact that compounds in metabolic reactions are much more difficult to be featured than those in chemical reactions, we further test the feasibility of our model in task of bioretrosynthesis prediction by using the well-known MetaNetX metabolic dataset, and achieve top-1, top-3, top-5 and top-10 accuracies of 45.2%, 67.0%, 73.6% and 82.2%, respectively. CONCLUSION: The comparison result on USPTO-50k indicates that our proposed model surpasses the existing state-of-the-art model. The evaluation result on MetaNetX dataset indicates that the models used for retrosynthesis prediction can also be used for bioretrosynthesis prediction.

BACKGROUND: Breast cancer is currently one of the cancers with a higher mortality rate in the world. The biological research on anti-breast cancer drugs focuses on the activity of estrogen receptors alpha (ER[Formula: see text]), the pharmacokinetic properties and the safety of the compounds, which, however, is an expensive and time-consuming process. Developments of deep learning bring potential to efficiently facilitate the candidate drug selection against breast cancer. METHODS: In this paper, we propose an Anti-Breast Cancer Drug selection method utilizing Gated Graph Neural Networks (ABCD-GGNN) to topologically enhance the molecular representation of candidate drugs. By constructing atom-level graphs through atomic descriptors for each distinct compound, ABCD-GGNN can topologically learn both the implicit structure and substructure characteristics of a candidate drug and then integrate the representation with explicit discrete molecular descriptors to generate a molecule-level representation. As a result, the representation of ABCD-GGNN can inductively predict the ER[Formula: see text], the pharmacokinetic properties and the safety of each candidate drug. Finally, we design a ranking operator whose inputs are the predicted properties so as to statistically select the appropriate drugs against breast cancer. RESULTS: Extensive experiments conducted on our collected anti-breast cancer candidate drug dataset demonstrate that our proposed method outperform all the other representative methods in the tasks of predicting ER[Formula: see text], and the pharmacokinetic properties and safety of the compounds. Extended result analysis demonstrates the efficiency and biological rationality of the operator we design to calculate the candidate drug ranking from the predicted properties. CONCLUSION: In this paper, we propose the ABCD-GGNN representation method to efficiently integrate the topological structure and substructure features of the molecules with the discrete molecular descriptors. With a ranking operator applied, the predicted properties efficiently facilitate the candidate drug selection against breast cancer.

BACKGROUND: Many novel long noncoding RNAs have been discovered in recent years due to advances in high-throughput sequencing experiments. Finding orthologues of these novel lncRNAs might facilitate clarification of their functional role in living organisms. However, lncRNAs exhibit low sequence conservation, so specific methods for enhancing the signal-to-noise ratio were developed. Nevertheless, current methods such as transcriptomes comparison approaches or searches for conserved secondary structures are not applicable to novel, previously unannotated lncRNAs by design. RESULTS: We present ortho2align-a versatile sensitive synteny-based lncRNA orthologue search tool with statistical assessment of sequence conservation. This tool allows control of the specificity of the search process and optional annotation of found orthologues. ortho2align shows similar performance in terms of sensitivity and resource usage as the state-of-the-art method for aligning orthologous lncRNAs but also enables scientists to predict unannotated orthologous sequences for lncRNAs in question. Using ortho2align, we predicted orthologues of three distinct classes of novel human lncRNAs in six Vertebrata species to estimate their degree of conservation. CONCLUSIONS: Being designed for the discovery of unannotated orthologues of novel lncRNAs in distant species, ortho2align is a versatile tool applicable to any genomic regions, especially weakly conserved ones. A small amount of input files makes ortho2align easy to use in orthology studies as a single tool or in bundle with other steps that researchers will consider sensible. ortho2align is available as an Anaconda package with its source code hosted at https://github.com/dmitrymyl/ortho2align .

BACKGROUND: DNA methylation is an important epigenetic modification that is known to regulate gene expression. Whole-genome bisulfite sequencing (WGBS) is a powerful method for studying cytosine methylation in a whole genome. However, it is difficult to obtain methylation profiles using the WGBS raw reads and is necessary to be proficient in all types of bioinformatic tools for the study of DNA methylation. In addition, recent end-to-end pipelines for DNA methylation analyses are not sufficient for addressing those difficulties. RESULTS: Here we present msPIPE, a pipeline for DNA methylation analyses with WGBS data seamlessly connecting all the required tasks ranging from data pre-processing to multiple downstream DNA methylation analyses. The msPIPE can generate various methylation profiles to analyze methylation patterns in the given sample, including statistical summaries and methylation levels. Also, the methylation levels in the functional regions of a genome are computed with proper annotation. The results of methylation profiles, hypomethylation, and differential methylation analysis are plotted in publication-quality figures. The msPIPE can be easily and conveniently used with a Docker image, which includes all dependent packages and software related to DNA methylation analyses. CONCLUSION: msPIPE is a new end-to-end pipeline designed for methylation calling, profiling, and various types of downstream DNA methylation analyses, leading to the creation of publication-quality figures. msPIPE allows researchers to process and analyze the WGBS data in an easy and convenient way. It is available at https://github.com/jkimlab/msPIPE and https://hub.docker.com/r/jkimlab/mspipe .

Biclustering algorithm is an effective tool for processing gene expression datasets. There are two kinds of data matrices, binary data and non-binary data, which are processed by biclustering method. A binary matrix is usually converted from pre-processed gene expression data, which can effectively reduce the interference from noise and abnormal data, and is then processed using a biclustering algorithm. However, biclustering algorithms of dealing with binary data have a poor balance between running time and performance. In this paper, we propose a new biclustering algorithm called the Adjacency Difference Matrix Binary Biclustering algorithm (AMBB) for dealing with binary data to address the drawback. The AMBB algorithm constructs the adjacency matrix based on the adjacency difference values, and the submatrix obtained by continuously updating the adjacency difference matrix is called a bicluster. The adjacency matrix allows for clustering of gene that undergo similar reactions under different conditions into clusters, which is important for subsequent genes analysis. Meanwhile, experiments on synthetic and real datasets visually demonstrate that the AMBB algorithm has high practicability.

Microbial communities are widely studied using high-throughput sequencing techniques, such as 16S rRNA gene sequencing. These techniques have attracted biologists as they offer powerful tools to explore microbial communities and investigate their patterns of diversity in biological and biomedical samples at remarkable resolution. However, the accuracy of these methods can negatively affected by the presence of contamination. Several studies have recognized that contamination is a common problem in microbial studies and have offered promising computational and laboratory-based approaches to assess and remove contaminants. Here we propose a novel strategy, MI-based (mutual information based) filtering method, which uses information theoretic functionals and graph theory to identify and remove contaminants. We applied MI-based filtering method to a mock community data set and evaluated the amount of information loss due to filtering taxa. We also compared our method to commonly practice traditional filtering methods. In a mock community data set, MI-based filtering approach maintained the true bacteria in the community without significant loss of information. Our results indicate that MI-based filtering method effectively identifies and removes contaminants in microbial communities and hence it can be beneficial as a filtering method to microbiome studies. We believe our filtering method has two advantages over traditional filtering methods. First, it does not required an arbitrary choice of threshold and second, it is able to detect true taxa with low abundance.

BACKGROUND: The retina is a complex tissue containing multiple cell types that are essential for vision. Understanding the gene expression patterns of various retinal cell types has potential applications in regenerative medicine. Retinal organoids (optic vesicles) derived from pluripotent stem cells have begun to yield insights into the transcriptomics of developing retinal cell types in humans through single cell RNA-sequencing studies. Previous methods of gene reporting have relied upon techniques in vivo using microarray data, or correlational and dimension reduction methods for analyzing single cell RNA-sequencing data computationally. We aimed to develop a state-of-the-art Boolean method that filtered out noise, could be applied to a wide variety of datasets and lent insight into gene expression over differentiation. RESULTS: Here, we present a bioinformatic approach using Boolean implication to discover genes which are retinal cell type-specific or involved in retinal cell fate. We apply this approach to previously published retina and retinal organoid datasets and improve upon previously published correlational methods. Our method improves the prediction accuracy of marker genes of retinal cell types and discovers several new high confidence cone and rod-specific genes. CONCLUSIONS: The results of this study demonstrate the benefits of a Boolean approach that considers asymmetric relationships. We have shown a statistically significant improvement from correlational, symmetric methods in the prediction accuracy of retinal cell-type specific genes. Furthermore, our method contains no cell or tissue-specific tuning and hence could impact other areas of gene expression analyses in cancer and other human diseases.

BACKGROUND: Transcription factors (TFs) play central roles in maintaining "stemness" of embryonic stem (ES) cells and their differentiation into several hundreds of adult cell types. The regulatory competence of TFs is routinely assessed by detecting target genes to which they bind. However, these data do not indicate which target genes are activated, repressed, or not affected by the change of TF abundance. There is a lack of large-scale studies that compare the genome binding of TFs with the expression change of target genes after manipulation of each TF. RESULTS: In this paper we associated human TFs with their target genes by two criteria: binding to genes, evaluated from published ChIP-seq data (n = 1868); and change of target gene expression shortly after induction of each TF in human ES cells. Lists of direction- and strength-specific regulated target genes are generated for 311 TFs (out of 351 TFs tested) with expected proportion of false positives less than or equal to 0.30, including 63 new TFs not present in four existing databases of target genes. Our lists of direction-specific targets for 152 TFs (80.0%) are larger that in the TRRUST database. In average, 30.9% of genes that respond greater than or equal to twofold to the induction of TFs are regulated targets. Regulated target genes indicate that the majority of TFs are either strong activators or strong repressors, whereas sets of genes that responded greater than or equal to twofold to the induction of TFs did not show strong asymmetry in the direction of expression change. The majority of human TFs (82.1%) regulated their target genes primarily via binding to enhancers. Repression of target genes is more often mediated by promoter-binding than activation of target genes. Enhancer-promoter loops are more abundant among strong activator and repressor TFs. CONCLUSIONS: We developed an atlas of regulated targets of TFs (ART-TF) in human ES cells by combining data on TF binding with data on gene expression change after manipulation of individual TFs. Sets of regulated gene targets were identified with a controlled rate of false positives. This approach contributes to the understanding of biological functions of TFs and organization of gene regulatory networks. This atlas should be a valuable resource for ES cell-based regenerative medicine studies.

Metabolomic time course analyses of biofluids are highly relevant for clinical diagnostics. However, many sampling methods suffer from unknown sample sizes, commonly known as size effects. This prevents absolute quantification of biomarkers. Recently, several mathematical post acquisition normalization methods have been developed to overcome these problems either by exploiting already known pharmacokinetic information or by statistical means. Here we present an improved normalization method, MIX, that combines the advantages of both approaches. It couples two normalization terms, one based on a pharmacokinetic model (PKM) and the other representing a popular statistical approach, probabilistic quotient normalization (PQN), in a single model. To test the performance of MIX, we generated synthetic data closely resembling real finger sweat metabolome measurements. We show that MIX normalization successfully tackles key weaknesses of the individual strategies: it (i) reduces the risk of overfitting with PKM, and (ii), contrary to PQN, it allows to compute sample volumes. Finally, we validate MIX by using real finger sweat as well as blood plasma metabolome data and demonstrate that MIX allows to better and more robustly correct for size effects. In conclusion, the MIX method improves the reliability and robustness of quantitative biomarker detection in finger sweat and other biofluids, paving the way for biomarker discovery and hypothesis generation from metabolomic time course data.

The L1000 technology, a cost-effective high-throughput transcriptomics technology, has been applied to profile a collection of human cell lines for their gene expression response to > 30,000 chemical and genetic perturbations. In total, there are currently over 3 million available L1000 profiles. Such a dataset is invaluable for the discovery of drug and target candidates and for inferring mechanisms of action for small molecules. The L1000 assay only measures the mRNA expression of 978 landmark genes while 11,350 additional genes are computationally reliably inferred. The lack of full genome coverage limits knowledge discovery for half of the human protein coding genes, and the potential for integration with other transcriptomics profiling data. Here we present a Deep Learning two-step model that transforms L1000 profiles to RNA-seq-like profiles. The input to the model are the measured 978 landmark genes while the output is a vector of 23,614 RNA-seq-like gene expression profiles. The model first transforms the landmark genes into RNA-seq-like 978 gene profiles using a modified CycleGAN model applied to unpaired data. The transformed 978 RNA-seq-like landmark genes are then extrapolated into the full genome space with a fully connected neural network model. The two-step model achieves 0.914 Pearson's correlation coefficients and 1.167 root mean square errors when tested on a published paired L1000/RNA-seq dataset produced by the LINCS and GTEx programs. The processed RNA-seq-like profiles are made available for download, signature search, and gene centric reverse search with unique case studies.

BACKGROUND: Long interspersed element 1 (LINE-1 or L1) retrotransposons are mobile elements that constitute 17-20% of the human genome. Strong correlations between abnormal L1 expression and several human diseases have been reported. This has motivated increasing interest in accurate quantification of the number of L1 copies present in any given biologic specimen. A main obstacle toward this aim is that L1s are relatively long DNA segments with regions of high variability, or largely present in the human genome as truncated fragments. These particularities render traditional alignment strategies, such as seed-and-extend inefficient, as the number of segments that are similar to L1s explodes exponentially. This study uses the pattern matching methodology for more accurate identification of L1s. We validate experimentally the superiority of pattern matching for L1 detection over alternative methods and discuss some of its potential applications. RESULTS: Pattern matching detected full-length L1 copies with high precision, reasonable computational time, and no prior input information. It also detected truncated and significantly altered copies of L1 with relatively high precision. The method was effectively used to annotate L1s in a target genome and to calculate copy number variation with respect to a reference genome. Crucial to the success of implementation was the selection of a small set of k-mer probes from a set of sequences presenting a stable pattern of distribution in the genome. As in seed-and-extend methods, the pattern matching algorithm sowed these k-mer probes, but instead of using heuristic extensions around the seeds, the analysis was based on distribution patterns within the genome. The desired level of precision could be adjusted, with some loss of recall. CONCLUSION: Pattern matching is more efficient than seed-and-extend methods for the detection of L1 segments whose characterization depends on a finite set of sequences with common areas of low variability. We propose that pattern matching may help establish correlations between L1 copy number and disease states associated with L1 mobilization and evolution.

BACKGROUND: Chimeric antigen receptor T-cell (CAR-T) therapy is a new and efficient cellular immunotherapy. The therapy shows significant efficacy, but also has serious side effects, collectively known as cytokine release syndrome (CRS). At present, some CRS-related cytokines and their roles in CAR-T therapy have been confirmed by experimental studies. However, the mechanism of CRS remains to be fully understood. METHODS: Based on big data for human protein interactions and meta-learning graph neural network, we employed known CRS-related cytokines to comprehensively investigate the CRS associated cytokines in CAR-T therapy through protein interactions. Subsequently, the clinical data for 119 patients who received CAR-T therapy were examined to validate our prediction results. Finally, we systematically explored the roles of the predicted cytokines in CRS occurrence by protein interaction network analysis, functional enrichment analysis, and pathway crosstalk analysis. RESULTS: We identified some novel cytokines that would play important roles in biological process of CRS, and investigated the biological mechanism of CRS from the perspective of functional analysis. CONCLUSIONS: 128 cytokines and related molecules had been found to be closely related to CRS in CAR-T therapy, where several important ones such as IL6, IFN-γ, TNF-α, ICAM-1, VCAM-1 and VEGFA were highlighted, which can be the key factors to predict CRS.

BACKGROUND: The main focus of in silico drug repurposing, which is a promising area for using artificial intelligence in drug discovery, is the prediction of drug-disease relationships. Although many computational models have been proposed recently, it is still difficult to reliably predict drug-disease associations from a variety of sources of data. RESULTS: In order to identify potential drug-disease associations, this paper introduces a novel end-to-end model called Graph convolution network based on a multimodal attention mechanism (GCMM). In particular, GCMM incorporates known drug-disease relations, drug-drug chemical similarity, drug-drug therapeutic similarity, disease-disease semantic similarity, and disease-disease target-based similarity into a heterogeneous network. A Graph Convolution Network encoder is used to learn how diseases and drugs are embedded in various perspectives. Additionally, GCMM can enhance performance by applying a multimodal attention layer to assign various levels of value to various features and the inputting of multi-source information. CONCLUSION: 5 fold cross-validation evaluations show that the GCMM outperforms four recently proposed deep-learning models on the majority of the criteria. It shows that GCMM can predict drug-disease relationships reliably and suggests improvement in the desired metrics. Hyper-parameter analysis and exploratory ablation experiments are also provided to demonstrate the necessity of each module of the model and the highest possible level of prediction performance. Additionally, a case study on Alzheimer's disease (AD). Four of the five medications indicated by GCMM to have the highest potential correlation coefficient with AD have been demonstrated through literature or experimental research, demonstrating the viability of GCMM. All of these results imply that GCMM can provide a strong and effective tool for drug development and repositioning.

BACKGROUND: Epigenetic modifications established in mammalian gametes are largely reprogrammed during early development, however, are partly inherited by the embryo to support its development. In this study, we examine CpG island (CGI) sequences to predict whether a mouse blastocyst CGI inherits oocyte-derived DNA methylation from the maternal genome. Recurrent neural networks (RNNs), including that based on gated recurrent units (GRUs), have recently been employed for variable-length inputs in classification and regression analyses. One advantage of this strategy is the ability of RNNs to automatically learn latent features embedded in inputs by learning their model parameters. However, the available CGI dataset applied for the prediction of oocyte-derived DNA methylation inheritance are not large enough to train the neural networks. RESULTS: We propose a GRU-based model called CMIC (CGI Methylation Inheritance Classifier) to augment CGI sequence by converting it into variable-length k-mers, where the length k is randomly selected from the range [Formula: see text] to [Formula: see text], N times, which were then used as neural network input. N was set to 1000 in the default setting. In addition, we proposed a new embedding vector generator for k-mers called splitDNA2vec. The randomness of this procedure was higher than the previous work, dna2vec. CONCLUSIONS: We found that CMIC can predict the inheritance of oocyte-derived DNA methylation at CGIs in the maternal genome of blastocysts with a high F-measure (0.93). We also show that the F-measure can be improved by increasing the parameter N, that is, the number of sequences of variable-length k-mers derived from a single CGI sequence. This implies the effectiveness of augmenting input data by converting a DNA sequence to N sequences of variable-length k-mers. This approach can be applied to different DNA sequence classification and regression analyses, particularly those involving a small amount of data.

BACKGROUND: Development of new methods for analysis of protein-protein interactions (PPIs) at molecular and nanometer scales gives insights into intracellular signaling pathways and will improve understanding of protein functions, as well as other nanoscale structures of biological and abiological origins. Recent advances in computational tools, particularly the ones involving modern deep learning algorithms, have been shown to complement experimental approaches for describing and rationalizing PPIs. However, most of the existing works on PPI predictions use protein-sequence information, and thus have difficulties in accounting for the three-dimensional organization of the protein chains. RESULTS: In this study, we address this problem and describe a PPI analysis based on a graph attention network, named Struct2Graph, for identifying PPIs directly from the structural data of folded protein globules. Our method is capable of predicting the PPI with an accuracy of 98.89% on the balanced set consisting of an equal number of positive and negative pairs. On the unbalanced set with the ratio of 1:10 between positive and negative pairs, Struct2Graph achieves a fivefold cross validation average accuracy of 99.42%. Moreover, Struct2Graph can potentially identify residues that likely contribute to the formation of the protein-protein complex. The identification of important residues is tested for two different interaction types: (a) Proteins with multiple ligands competing for the same binding area, (b) Dynamic protein-protein adhesion interaction. Struct2Graph identifies interacting residues with 30% sensitivity, 89% specificity, and 87% accuracy. CONCLUSIONS: In this manuscript, we address the problem of prediction of PPIs using a first of its kind, 3D-structure-based graph attention network (code available at https://github.com/baranwa2/Struct2Graph ). Furthermore, the novel mutual attention mechanism provides insights into likely interaction sites through its unsupervised knowledge selection process. This study demonstrates that a relatively low-dimensional feature embedding learned from graph structures of individual proteins outperforms other modern machine learning classifiers based on global protein features. In addition, through the analysis of single amino acid variations, the attention mechanism shows preference for disease-causing residue variations over benign polymorphisms, demonstrating that it is not limited to interface residues.

BACKGROUND: Presently, there is a wide variety of classification methods and deep neural network approaches in bioinformatics. Deep neural networks have proven their effectiveness for classification tasks, and have outperformed classical methods, but they suffer from a lack of interpretability. Therefore, these innovative methods are not appropriate for decision support systems in healthcare. Indeed, to allow clinicians to make informed and well thought out decisions, the algorithm should provide the main pieces of information used to compute the predicted diagnosis and/or prognosis, as well as a confidence score for this prediction. METHODS: Herein, we used a new supervised autoencoder (SAE) approach for classification of clinical metabolomic data. This new method has the advantage of providing a confidence score for each prediction thanks to a softmax classifier and a meaningful latent space visualization and to include a new efficient feature selection method, with a structured constraint, which allows for biologically interpretable results. RESULTS: Experimental results on three metabolomics datasets of clinical samples illustrate the effectiveness of our SAE and its confidence score. The supervised autoencoder provides an accurate localization of the patients in the latent space, and an efficient confidence score. Experiments show that the SAE outperforms classical methods (PLS-DA, Random Forests, SVM, and neural networks (NN)). Furthermore, the metabolites selected by the SAE were found to be biologically relevant. CONCLUSION: In this paper, we describe a new efficient SAE method to support diagnostic or prognostic evaluation based on metabolomics analyses.