A5046574920- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Protein Structure and Dynamics
- Bioinformatics and Genomic Networks
- Chemical Synthesis and Analysis
- Immune Cell Function and Interaction
- Protein Degradation and Inhibitors
- Cancer Immunotherapy and Biomarkers
- Microbial Natural Products and Biosynthesis
- Ferroptosis and cancer prognosis
- Pharmacogenetics and Drug Metabolism
- Analytical Chemistry and Chromatography
- Receptor Mechanisms and Signaling
- interferon and immune responses
- Biomedical Text Mining and Ontologies
- Medical Imaging Techniques and Applications
- Peptidase Inhibition and Analysis
- Advanced Text Analysis Techniques
- Microbial Metabolic Engineering and Bioproduction
- Semantic Web and Ontologies
- RNA modifications and cancer
- Gene Regulatory Network Analysis
- Fibroblast Growth Factor Research
- Paleontology and Evolutionary Biology
- Remote Sensing and Land Use
Shanghai Institute of Materia Medica
2018-2025
Chinese Academy of Sciences
2018-2025
University of Chinese Academy of Sciences
2019-2025
First Affiliated Hospital of Anhui Medical University
2023-2025
Anhui Medical University
2023-2025
Qingdao Municipal Hospital
2022-2024
Tongji Hospital
2024
Tongji University
2024
State Key Laboratory of Drug Research
2020-2024
Qingdao University
2009-2024
Hunting for chemicals with favorable pharmacological, toxicological, and pharmacokinetic properties remains a formidable challenge drug discovery. Deep learning provides us powerful tools to build predictive models that are appropriate the rising amounts of data, but gap between what these neural networks learn human beings can comprehend is growing. Moreover, this may induce distrust restrict deep applications in practice. Here, we introduce new graph network architecture called Attentive...
Abstract PROteolysis TArgeting Chimeras (PROTACs) has been exploited to degrade putative protein targets. However, the antitumor performance of PROTACs is impaired by their insufficient tumour distribution. Herein, we present de novo designed polymeric PROTAC (POLY-PROTAC) nanotherapeutics for tumour-specific degradation. The POLY-PROTACs are engineered covalently grafting small molecular onto backbone an amphiphilic diblock copolymer via disulfide bonds. self-assemble into micellar...
The kinome-wide virtual profiling of small molecules with high-dimensional structure–activity data is a challenging task in drug discovery. Here, we present model against panel 391 kinases based on large-scale bioactivity and the multitask deep neural network algorithm. obtained yields excellent internal prediction capability an auROC 0.90 consistently outperforms conventional single-task models external tests, especially for insufficient activity data. Moreover, more rigorous experimental...
Abstract Artificial intelligence transforms drug discovery, with phenotype-based approaches emerging as a promising alternative to target-based methods, overcoming limitations like lack of well-defined targets. While chemical-induced transcriptional profiles offer comprehensive view mechanisms, inherent noise often obscures the true signal, hindering their potential for meaningful insights. Here, we highlight development TranSiGen, deep generative model employing self-supervised...
Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study explored power fine-tuned large models (LLMs) on five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data...
Alterations of discoidin domain receptor1 (DDR1) may lead to increased production inflammatory cytokines, making DDR1 an attractive target for bowel disease (IBD) therapy. A scaffold-based molecular design workflow was established and performed by integrating a deep generative model, kinase selectivity screening docking, leading novel inhibitor compound 2, which showed potent inhibition profile (IC50 = 10.6 ± 1.9 nM) excellent against panel 430 kinases (S (10) 0.002 at 0.1 μM). Compound 2...
Blood-brain barrier is a pivotal factor to be considered in the process of central nervous system (CNS) drug development, and it great significance rapidly explore blood-brain permeability (BBBp) compounds silico early discovery process. Here, we focus on whether how uncertainty estimation methods improve BBBp models. We briefly surveyed current state prediction deep learning models, curated an independent dataset determine reliability state-of-the-art algorithms. The results exhibit that,...
Ensuring drug safety in the early stages of development is crucial to avoid costly failures subsequent phases. However, economic burden associated with detecting off-targets and potential side effects through
Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study explored power fine-tuned large models (LLMs) on five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data...
Land-use and land-cover changes constitute pivotal components in global environmental change research. Through an examination of spatiotemporal variations land cover, we can deepen our understanding dynamics, shape appropriate policy frameworks, implement targeted conservation strategies. The judicious management is a critical determinant fostering the sustainable growth urban economies enhancing quality life for residents. This study harnessed remote sensing data to analyze patterns Tianjin...
A fundamental challenge that arises in biomedicine is the need to characterize compounds a relevant cellular context order reveal potential on-target or off-target effects. Recently, fast accumulation of gene transcriptional profiling data provides us an unprecedented opportunity explore protein targets chemical from perspective cell transcriptomics and RNA biology. Here, we propose novel Siamese spectral-based graph convolutional network (SSGCN) model for inferring profiles. Although...
Reliable uncertainty quantification for statistical models is crucial in various downstream applications, especially drug design and discovery where mistakes may incur a large amount of cost. This topic has therefore absorbed much attention plethora methods have been proposed over the past years. The approaches that reported so far can be mainly categorized into two classes: distance-based Bayesian approaches. Although these widely used many scenarios shown promising performance with their...
Abstract Artificial intelligence (AI)-based molecular design methods, especially deep generative models for generating novel molecule structures, have gratified our imagination to explore unknown chemical space without relying on brute-force exploration. However, whether designed by AI or human experts, the molecules need be accessibly synthesized and biologically evaluated, trial-and-error process remains a resources-intensive endeavor. Therefore, AI-based drug methods face major challenge...
Abstract Structure-based lead optimization is an open challenge in drug discovery, which still largely driven by hypotheses and depends on the experience of medicinal chemists. Here we propose a pairwise binding comparison network (PBCNet) based physics-informed graph attention mechanism, specifically tailored for ranking relative affinity among congeneric ligands. Benchmarking two held-out sets (provided Schrödinger Merck) containing over 460 ligands 16 targets, PBCNet demonstrated...
In pharmaceutical development, the crystallization process is crucial for isolating and purifying Active Pharmaceutical Ingredients (APIs) using solvents. However, residual solvents left after drying can form solvates, altering crystal properties potentially affecting drug quality. We developed a graph neural network model based on attention mechanisms to predict solvates. The results show that our achieves SOTA compared baseline most metrics predicting solvates by capturing molecular...