Code

ProteinWordwise

Description：Protein Wordwise is a protein functional analysis tool, aim to parse analyte protein sequences into function-related residual clusters, or “protein words”.

Github: https://github.com/TianBoxue-lab/ProteinWordwise

Paper: Automatically Defining Protein Words for Diverse Functional Predictions Based on Attention Analysis of a Protein Language Model

SynthMol

Description：a deep learning framework that integrates pre-trained 3D structural features, graph attention networks, and molecular fingerprints to achieve high

accuracy in molecular property prediction.

Github: https://github.com/TianBoxue-lab/SynthMol

Paper: SynthMol: A Drug Safety Prediction Framework Integrating Graph Attention and Molecular Descriptors into Pre-Trained Geometric Models

GLMCyp-Predictor

Description：a deep learning-based approach, for predicting CYP450 reaction sites on small molecules.

Github: https://github.com/TianBoxue-lab/GLMCyp-Predictor

Paper: GLMCyp: A Deep Learning-Based Method for CYP450-Mediated Reaction Site Prediction

CLAPE-SMB

Description：This repo holds the code of CLAPE (Contrastive Learning And Pre-trained Encoder) for protein-small molecule binding (SMB) site prediction.

Github: https://github.com/TianBoxue-lab/CLAPE-SMB

Paper: Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning

PointGAT

Description：a quantum chemical property prediction model that learns molecular representation through GAT and 3D molecular geometry.

Github: https://github.com/TianBoxue-lab/PointGAT

Paper: PointGAT: A Quantum Chemical Property Prediction Model Integrating Graph Attention and 3D Geometry

DeepP450

Description：Predicting Human P450 Activities of Small Molecules by Integrating Pretrained Protein Language Model and Molecular Representation.

Github: https://github.com/TianBoxue-lab/DeepP450

Paper: DeepP450: Predicting Human P450 Activities of Small Molecules by Integrating Pretrained Protein Language Model and Molecular Representation

CLAPE

Description：CLAPE (Contrastive Learning And Pre-trained Encoder) framework for protein-ligands binding sites prediction.

Github: https://github.com/TianBoxue-lab/CLAPE

Paper: Protein–DNA binding sites prediction based on pre-trained protein language model and contrastive learning

H3-OPT

Description：A method for CDR-H3 optimization.

Github: https://github.com/TianBoxue-lab/H3-OPT

Paper: H3-OPT: Accurate prediction of CDR-H3 loop structures of antibodies with deep learning