A5083809384- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Metabolomics and Mass Spectrometry Studies
- Spectroscopy and Chemometric Analyses
- Protein Structure and Dynamics
- Analytical Chemistry and Chromatography
- Machine Learning in Bioinformatics
- Pharmacogenetics and Drug Metabolism
- Advanced Chemical Sensor Technologies
- Microbial Natural Products and Biosynthesis
- Bioinformatics and Genomic Networks
- Chemical Synthesis and Analysis
- vaccines and immunoinformatics approaches
- Water Quality Monitoring and Analysis
- Ubiquitin and proteasome pathways
- Gene expression and cancer classification
- Click Chemistry and Applications
- Biomedical Text Mining and Ontologies
- RNA and protein synthesis mechanisms
- Biosimilars and Bioanalytical Methods
- Analytical Methods in Pharmaceuticals
- Micro and Nano Robotics
- Genetics, Bioinformatics, and Biomedical Research
- Cholinesterase and Neurodegenerative Diseases
- Spectroscopy Techniques in Biomedical and Chemical Research
Central South University
2016-2025
Tianjin University
2023-2025
Hong Kong Baptist University
2016-2024
Xiangya Hospital Central South University
2013-2024
Second Hospital of Anhui Medical University
2015-2024
Anhui Medical University
2015-2024
Hunan University
2024
Xinjiang University
2023
Nanyang Institute of Technology
2023
Hunan Cancer Hospital
2020-2023
Because undesirable pharmacokinetics and toxicity of candidate compounds are the main reasons for failure drug development, it has been widely recognized that absorption, distribution, metabolism, excretion (ADMET) should be evaluated as early possible. In silico ADMET evaluation models have developed an additional tool to assist medicinal chemists in design optimization leads. Here, we announced release ADMETlab 2.0, a completely redesigned version used AMDETlab web server predictions...
Current pharmaceutical research and development (R&D) is a high-risk investment which usually faced with some unexpected even disastrous failures in different stages of drug discovery. One main reason for R&D the efficacy safety deficiencies are related largely to absorption, distribution, metabolism excretion (ADME) properties various toxicities (T). Therefore, rapid ADMET evaluation urgently needed minimize discovery process. Here, we developed web-based platform called ADMETlab systematic...
Abstract Summary: Sequence-derived structural and physiochemical features have been frequently used for analysing predicting structural, functional, expression interaction profiles of proteins peptides. To facilitate extensive studies peptides, we developed a freely available, open source python package called protein in (propy) calculating the widely physicochemical peptides from amino acid sequence. It computes five feature groups composed 13 features, including composition, dipeptide...
Abstract Graph neural networks (GNN) has been considered as an attractive modelling method for molecular property prediction, and numerous studies have shown that GNN could yield more promising results than traditional descriptor-based methods. In this study, based on 11 public datasets covering various endpoints, the predictive capacity computational efficiency of prediction models developed by eight machine learning (ML) algorithms, including four (SVM, XGBoost, RF DNN) graph-based (GCN,...
Molecular descriptors and fingerprints have been routinely used in QSAR/SAR analysis, virtual drug screening, compound search/ranking, ADME/T prediction other discovery processes. Since the calculation of such quantitative representations molecules may require substantial computational skills efforts, several tools previously developed to make an attempt ease process. However, there are still hurdles for users overcome fully harness power these tools. First, most distributed as standalone...
Abstract Summary: Amino acid sequence-derived structural and physiochemical descriptors are extensively utilized for the research of structural, functional, expression interaction profiles proteins peptides. We developed protr, a comprehensive R package generating various numerical representation schemes peptides from amino sequence. The calculates eight descriptor groups composed 22 types commonly used that include about 700 values. It allows users to select properties AAindex database, use...
Abstract Molecule docking has been regarded as a routine tool for drug discovery, but its accuracy highly depends on the reliability of scoring functions (SFs). With rapid development machine learning (ML) techniques, ML‐based SFs have gradually emerged promising alternative protein–ligand binding affinity prediction and virtual screening, most them shown significantly better performance than wide range classical SFs. Emergence more data‐hungry deep (DL) approaches in recent years further...
Abstract Motivation: Molecular representation for small molecules has been routinely used in QSAR/SAR, virtual screening, database search, ranking, drug ADME/T prediction and other discovery processes. To facilitate extensive studies of molecules, we developed a freely available, open-source python package called chemoinformatics (ChemoPy) calculating the commonly structural physicochemical features. It computes 16 feature groups composed 19 descriptors that include 1135 descriptor values....
The Caco-2 cell monolayer model is a popular surrogate in predicting the vitro human intestinal permeability of drug due to its morphological and functional similarity with enterocytes. A quantitative structure-property relationship (QSPR) study was carried out predict large data set consisting 1272 compounds. Four different methods including multivariate linear regression (MLR), partial least-squares (PLS), support vector machine (SVM) Boosting were employed build prediction models 30...
Abstract Proteolysis-targeting chimeras (PROTACs), which selectively degrade targeted proteins by the ubiquitin-proteasome system, have emerged as a novel therapeutic technology with potential advantages over traditional inhibition strategies. In past few years, this has achieved substantial progress and two PROTACs been advanced into phase I clinical trials. However, is still maturing design of remains great challenge. order to promote rational PROTACs, we present PROTAC-DB, web-based...
Accurate quantification of protein–ligand interactions remains a key challenge to structure-based drug design. However, traditional machine learning (ML)-based methods based on handcrafted descriptors, one-dimensional protein sequences, and/or two-dimensional graph representations limit their capability learn the generalized molecular in 3D space. Here, we proposed novel deep representation framework named InteractionGraphNet (IGN) from structures complexes. In IGN, two independent...
Prediction of drug-target interactions (DTI) plays a vital role in drug development various areas, such as virtual screening, repurposing and identification potential side effects. Despite extensive efforts have been invested perfecting DTI prediction, existing methods still suffer from the high sparsity datasets cold start problem. Here, we develop KGE_NFM, unified framework for prediction by combining knowledge graph (KG) recommendation system. This firstly learns low-dimensional...
Abstract ADMETlab 3.0 is the second updated version of web server that provides a comprehensive and efficient platform for evaluating ADMET-related parameters as well physicochemical properties medicinal chemistry characteristics involved in drug discovery process. This new release addresses limitations previous offers broader coverage, improved performance, API functionality, decision support. For supporting data endpoints, this includes 119 features, an increase 31 compared to version. The...
Abstract Motivation: Accurate and efficient prediction of molecular properties is one the fundamental issues in drug design discovery pipelines. Traditional feature engineering-based approaches require extensive expertise selection process. With development artificial intelligence (AI) technologies, data-driven methods exhibit unparalleled advantages over various domains. Nevertheless, when applied to property prediction, AI models usually suffer from scarcity labeled data show poor...
Proteolysis targeting chimeras (PROTACs), which harness the ubiquitin-proteasome system to selectively induce targeted protein degradation, represent an emerging therapeutic technology with potential modulate traditional undruggable targets. Over past few years, this has moved from academia industry and more than 10 PROTACs have been advanced into clinical trials. However, designing potent desirable drug-like properties still remains a great challenge. Here, we report updated online...
Abstract Drug development is time‐consuming and expensive. Repurposing existing drugs for new therapies an attractive solution that accelerates drug at reduced experimental costs, specifically Coronavirus Disease 2019 (COVID‐19), infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2). However, comprehensively obtaining productively integrating available knowledge big biomedical data to effectively advance deep learning models still challenging repurposing...
Predicting the native or near-native binding pose of a small molecule within protein pocket is an extremely important task in structure-based drug design, especially hit-to-lead and lead optimization phases. In this study, fastDRH, free open accessed web server, was developed to predict analyze protein-ligand complex structures. fastDRH AutoDock Vina AutoDock-GPU docking engines, structure-truncated MM/PB(GB)SA energy calculation procedures multiple poses based per-residue decomposition...
Abstract Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs chemistry focus on attributing model to individual nodes, edges or fragments that are not necessarily derived from chemically meaningful segmentation of molecules. To address this challenge, we propose method named substructure mask (SME). SME based well-established and provides an...