A5009826239- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- RNA and protein synthesis mechanisms
- Bioinformatics and Genomic Networks
- RNA Research and Splicing
- RNA modifications and cancer
- Machine Learning in Materials Science
- Enzyme Structure and Function
- Genomics and Chromatin Dynamics
- Genomics and Phylogenetic Studies
- Single-cell and spatial transcriptomics
- Machine Learning in Bioinformatics
- Gene expression and cancer classification
- Gene Regulatory Network Analysis
- Chromosomal and Genetic Variations
- Cell Image Analysis Techniques
- Monoclonal and Polyclonal Antibodies Research
- vaccines and immunoinformatics approaches
- Cancer-related molecular mechanisms research
- Immunotherapy and Immune Responses
- Microbial Metabolic Engineering and Bioproduction
- Genetics, Bioinformatics, and Biomedical Research
- Advanced Electron Microscopy Techniques and Applications
- Microbial Natural Products and Biosynthesis
- Genetic Mapping and Diversity in Plants and Animals
Mengchao Hepatobiliary Hospital
2020-2025
Fujian Medical University
2020-2025
Westlake University
2023-2024
Tsinghua University
2015-2024
Sichuan University
2024
West China Second University Hospital of Sichuan University
2024
Hubei Engineering University
2020
Silexon AI Technology (China)
2020
Institut de Biologie systémique et synthétique
2019
Institute of Bioinformatics
2019
The emergence of large-scale genomic, chemical and pharmacological data provides new opportunities for drug discovery repositioning. In this work, we develop a computational pipeline, called DTINet, to predict novel drug-target interactions from constructed heterogeneous network, which integrates diverse drug-related information. DTINet focuses on learning low-dimensional vector representation features, accurately explains the topological properties individual nodes in then makes prediction...
Abstract Motivation Accurately predicting drug–target interactions (DTIs) in silico can guide the drug discovery process and thus facilitate development. Computational approaches for DTI prediction that adopt systems biology perspective generally exploit rationale properties of drugs targets be characterized by their functional roles biological networks. Results Inspired recent advance information passing aggregation techniques generalize convolution neural networks to mine large-scale graph...
RNA-binding proteins (RBPs) play important roles in the post-transcriptional control of RNAs. Identifying RBP binding sites and characterizing preferences are key steps toward understanding basic mechanisms gene regulation. Though numerous computational methods have been developed for modeling preferences, discovering a complete structural representation targets by integrating their available features all three dimensions is still challenging task. In this paper, we develop general flexible...
Identification of cancer subtypes plays an important role in revealing useful insights into disease pathogenesis and advancing personalized therapy. The recent development high-throughput sequencing technologies has enabled the rapid collection multi-platform genomic data (e.g., gene expression, miRNA DNA methylation) for same set tumor samples. Although numerous integrative clustering approaches have been developed to analyze data, few them are particularly designed exploit both deep...
Abstract Motivation: In silico prediction of drug-target interactions plays an important role toward identifying and developing new uses existing or abandoned drugs. Network-based approaches have recently become a popular tool for discovering (DTIs). Unfortunately, most these network-based can only predict binary between drugs targets, information about different types has not been well exploited DTI in previous studies. On the other hand, incorporating additional relationships drug modes...
Computational approaches for understanding compound-protein interactions (CPIs) can greatly facilitate drug development. Recently, a number of deep-learning-based methods have been proposed to predict binding affinities and attempt capture local interaction sites in compounds proteins through neural attentions (i.e., network architectures that enable the interpretation feature importance). Here, we compiled benchmark dataset containing inter-molecular non-covalent more than 10,000 pairs...
Abstract The global spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) requires an urgent need to find effective therapeutics for the treatment disease 2019 (COVID-19). In this study, we developed integrative drug repositioning framework, which fully takes advantage machine learning and statistical analysis approaches systematically integrate mine large-scale knowledge graph, literature transcriptome data discover potential candidates against SARS-CoV-2. Our in silico...
Abstract The global spread of SARS-CoV-2 requires an urgent need to find effective therapeutics for the treatment COVID-19. We developed a data-driven drug repositioning framework, which applies both machine learning and statistical analysis approaches systematically integrate mine large-scale knowledge graph, literature transcriptome data discover potential candidates against SARS-CoV-2. retrospective study using past SARS-CoV MERS-CoV demonstrated that our based method can successfully...
Abstract Peptide-protein interactions are involved in various fundamental cellular functions and their identification is crucial for designing efficacious peptide therapeutics. Recently, a number of computational methods have been developed to predict peptide-protein interactions. However, most the existing prediction approaches heavily depend on high-resolution structure data. Here, we present deep learning framework multi-level interaction prediction, called CAMP, including binary...
Abstract Motivation Translation initiation is a key step in the regulation of gene expression. In addition to annotated translation sites (TISs), process may also start at multiple alternative TISs (including both AUG and non-AUG codons), which makes it challenging predict study underlying regulatory mechanisms. Meanwhile, advent several high-throughput sequencing techniques for profiling initiating ribosomes single-nucleotide resolution, e.g. GTI-seq QTI-seq, provides abundant data...
Abstract Motivation Prediction of peptide binding to the major histocompatibility complex (MHC) plays a vital role in development therapeutic vaccines for treatment cancer. Algorithms with improved correlations between predicted and actual affinities are needed increase precision reduce number false positive predictions. Results We present ACME (Attention-based Convolutional neural networks MHC Epitope prediction), new pan-specific algorithm accurately predict peptides class I molecules,...
For eukaryotic cells, the biological processes involving regulatory DNA elements play an important role in cell cycle. Understanding 3D spatial arrangements of chromosomes and revealing long-range chromatin interactions are critical to decipher these processes. In recent years, chromosome conformation capture (3C) related techniques have been developed measure interaction frequencies between genome loci, which provided a great opportunity decode organization genome. this paper, we develop...
Abstract Accurate identification of compound–protein interactions (CPIs) in silico may deepen our understanding the underlying mechanisms drug action and thus remarkably facilitate discovery development. Conventional similarity- or docking-based computational methods for predicting CPIs rarely exploit latent features from currently available large-scale unlabeled compound protein data often limit their usage to relatively small-scale datasets. In present study, we propose DeepCPI, a novel...
Abstract Despite decades of intensive search for compounds that modulate the activity particular protein targets, a large proportion human kinome remains as yet undrugged. Effective approaches are therefore required to map massive space unexplored compound–kinase interactions novel and potent activities. Here, we carry out crowdsourced benchmarking predictive algorithms kinase inhibitor potencies across multiple families tested on unpublished bioactivity data. We find top-performing...
The Columbia Cancer Target Discovery and Development (CTD2) Center is developing PANACEA, a resource comprising dose-responses RNA sequencing (RNA-seq) profiles of 25 cell lines perturbed with ∼400 clinical oncology drugs, to study tumor-specific drug mechanism action. Here, this serves as the basis for DREAM Challenge assessing accuracy sensitivity computational algorithms de novo polypharmacology predictions. Dose-response perturbational 32 kinase inhibitors are provided 21 teams who blind...
Abstract Learning effective molecular feature representation to facilitate property prediction is of great significance for drug discovery. Recently, there has been a surge interest in pre-training graph neural networks (GNNs) via self-supervised learning techniques overcome the challenge data scarcity prediction. However, current learning-based methods suffer from two main obstacles: lack well-defined strategy and limited capacity GNNs. Here, we propose Knowledge-guided Pre-training Graph...
Abstract Accurately identifying compound-protein interactions in silico can deepen our understanding of the mechanisms drug action and significantly facilitate discovery development process. Traditional similarity-based computational models for interaction prediction rarely exploit latent features from current available large-scale unlabelled compound protein data, often limit their usage on relatively small-scale datasets. We propose a new scheme that combines feature embedding (a technique...
Abstract The new advances in various experimental techniques that provide complementary information about the spatial conformations of chromosomes have inspired researchers to develop computational methods fully exploit merits individual data sources and combine them improve modeling chromosome structure. Here we propose GEM-FISH, a method for reconstructing 3D models through systematically integrating both Hi-C FISH with prior biophysical knowledge polymer model. Comprehensive tests on set...