Model Development
Developing task-specific predictive models for biomolecular sequences, structures, and interaction data.
AI-DRIVEN BIOLOGICS & SMALL-MOLECULE DISCOVERY
AI-powered discovery for proteins & antibodies and small molecules
We build a computational R&D platform spanning protein–small-molecule virtual screening, binding-affinity prediction, antibody sequence optimization, structural design, candidate generation, and multi-stage prioritization.
Protein–Ligand
Binding prediction and virtual screening
Antibody Design
Generation, optimization, and prioritization
Multi-scale
Sequence, structure, and graph learning
AI-DRIVEN DISCOVERY
Protein · Ligand · Antibody
01 / ABOUT
About Us
Using computation to shorten the path from candidate discovery to validation.
We focus on artificial intelligence, computational biology, and structure-guided drug discovery, building an intelligent R&D platform for protein–small-molecule screening, antibody design, and protein engineering.
The platform integrates sequence models, molecular graph neural networks, three-dimensional structural representations, molecular docking, and dynamics evaluation. It supports candidate generation, scoring, screening, optimization, and risk assessment for research collaborations and drug-discovery programs.
Candidate Screening
Reducing candidate space through multi-stage computational screening to improve downstream experimental efficiency.
Molecular Optimization
Conducting multi-objective optimization of affinity, specificity, stability, and developability.
02 / RESEARCH FOCUS
Core Research Areas
From protein pockets to antibody sequences, and from candidate generation to prioritization.
01
Protein–Small-Molecule Virtual Screening
We screen ultra-large compound libraries against target protein pockets by integrating molecular fingerprints, graph neural networks, structural scoring, and molecular docking to identify high-potential compounds.
Binding Affinity
Virtual Screening
Docking
Ranking
02
AI-Guided Antibody Design
For antibody discovery and optimization, we support sequence generation, CDR mutation design, structural prediction, affinity ranking, and developability assessment.
03
Protein Engineering and Functional Optimization
We predict and design protein stability, binding capacity, and functional properties using sequence, structural, and evolutionary information.
04
Multimodal Interaction Modeling
We combine protein sequences, ligand graphs, pocket structures, and experimental labels to build predictive models with improved generalization.
05
Pharmacokinetics and Safety Prediction
We perform early assessment and prioritization of toxicity, ADME, specificity, and drug-likeness risks.
03 / CAPABILITIES
Platform Capabilities
Modular capabilities for different stages of drug discovery.
Sequence Models
Protein language models, antibody sequence modeling, mutation-effect prediction, and generative design.
Structural Modeling
Protein-pocket identification, complex modeling, geometric graph learning, and structural quality assessment.
Large-Scale Screening
Batch processing, model inference, filtering, and ranking for large candidate libraries.
Multi-Objective Optimization
Balancing affinity, specificity, stability, and drug-likeness.
04 / RELATED ARTICLES
Related Publications
Browse representative publications covering antibody design, protein–small-molecule prediction, virtual screening, peptide generation, toxicity prediction, and molecular dynamics.
01
NEW
Antibody Screening
A bio-inspired computational pipeline for antibody screening and repurposing
Volume 27, Issue 2 · bbag183
查看DOI
02
NEW
Antibody Optimization
Significantly enhancing human antibody affinity via deep learning and computational biology-guided single-point mutations
Volume 26, Issue 5 · bbaf445
查看DOI
03
NEW
Virtual Screening
Graph_RG: Dominating CASP16's Small Molecule Affinity Prediction Subcategory—A Pose-Free Framework for Billion-Scale Virtual Screening
CASP16 small-molecule affinity prediction
查看DOI
04
抗体设计
Development and experimental validation of computational methods for human antibody affinity enhancement
05
Virtual Screening
Targeting ATP catalytic activity of chromodomain helicase CHD1L for the anticancer inhibitor discovery
06
Interaction Prediction
Revolutionizing GPCR-Ligand Predictions: DeepGPCR with Experimental Validation for High-Precision Drug Discovery
07
Virtual Screening
Identification and Validation of New DNA-PKcs Inhibitors through High-Throughput Virtual Screening and Experimental Verification
08
Virtual Screening
Small-Molecule Inhibitors of TIPE3 Protein Identified through Deep Learning Suppress Cancer Cell Growth In Vitro
09
Virtual Screening
Deep Learning-Based Construction of a Drug-Like Compound Database and Its Application in Virtual Screening of HsDHODH Inhibitors
10
Safety Prediction
A deep learning based multi-model approach for predicting drug-like chemical compound's toxicity
11
Review
Advances in Deep Learning Assisted Drug Discovery Methods: A Self-review
12
Interaction Prediction
DeepBindGCN: Integrating Molecular Vector Representation with Graph Convolutional Neural Networks for Protein–Ligand Interaction Prediction
13
Peptide Design
Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening
14
Generative Design
Generating and screening de novo compounds against given targets using ultrafast deep learning models as core components
15
Virtual Screening
Validation of Deep Learning-Based DFCNN in Extremely Large-Scale Virtual Screening and Application in Trypsin I Protease Inhibitor Discovery
16
Virtual Screening
An efficient modern strategy to screen drug candidates targeting RdRp of SARS-CoV-2 with potentially high selectivity and specificity
17
Pose Recognition
DeepBindBC: a practical deep learning method for identifying native-like protein-ligand complexes in virtual screening
18
Virtual Screening
A novel virtual screening procedure identifies Pralatrexate as inhibitor of SARS-CoV-2 RdRp and it reduces viral replication in vitro
19
Molecular Dynamics
An integrated deep learning and molecular dynamics simulation-based screening pipeline identifies inhibitors of a new cancer drug target TIPE2
20
Inverse Screening
IVS2vec: A tool of Inverse Virtual Screening based on word2vec and deep learning techniques
21
Affinity Prediction
DeepBindRG: A Deep Learning Based Method for Estimating Effective Protein-Ligand Affinity
22
Reverse Docking
Large-Scale Target Identification of Herbal Medicine Using a Reverse Docking Approach
23
Molecular Dynamics
Investigating the stability of dengue virus envelope protein dimer using well-tempered metadynamics simulations
24
Network Pharmacology
Network Understanding of Herb Medicine via Rapid Identification of Ingredient-Target Interactions
25
Pocket Prediction
DeepBindPoc: a deep learning method to rank ligand binding pockets using molecular vector representation
26
Virtual Screening
Deep learning based drug screening for novel coronavirus 2019-nCov
27
Molecular Dynamics
On the conformational dynamics of β-amyloid forming peptides: a computational perspective
28
Virtual Screening
Structural basis for the inhibition of SARS-CoV2 main protease by Indian medicinal plant derived antiviral compounds
Publication titles and bibliographic information are presented directly on this website.
05 / CONTACT
zhanghaiping@suat-sz.edu.cn
Technology Partnerships for Drug Discovery
We welcome collaborations in protein-target screening, antibody optimization, protein engineering, model development, and candidate prioritization.