Publications

GTAM: A Molecular Pretraining Model with Geometric Triangle Awareness

Published in Bioinformatics, 2024

Author: Xiaoyang Hou*, Tian Zhu*, Milong Ren*, Bo Duan, Chunming Zhang, Dongbo Bu, Shiwei Sun

We present a novel contrastive learning strategy for molecular representation learning, named Geometric Triangle Awareness Model (GTAM). This method integrates innovative molecular encoders for both 2D graphs and 3D conformations, enabling the accurate capture of geometric dependencies among edges in graph-based molecular structures. Read more

CarbonNovo: Joint Design of Protein Structure and Sequence Using a Unified Energy-based Model

Published in Forty-first International Conference on Machine Learning (ICML 2024), 2024

Author: Milong Ren, Tian Zhu, Haicang Zhang

We propose CarbonNovo, a unified energy-based model for jointly generating protein structure and sequence. Specifically, we leverage a score-based generative model and Markov Random Fields for describing the energy landscape of protein structure and sequence. Read more

Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints

Published in Forty-first International Conference on Machine Learning (ICML 2024), 2024

Author: Tian Zhu, Milong Ren, Haicang Zhang

We present AbX, a new score-based diffusion generative model guided by evolutionary, physical, and geometric constraints for antibody design. AbX is the first score-based diffusion model with continuous timesteps for antibody design, jointly modeling the discrete sequence space and the $SE(3)$ structure space. Read more

Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model

Published in Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), 2023

Author: Shiwei Liu*, Tian Zhu*, Milong Ren, Chungong Yu, Dongbo Bu, Haicang Zhang

In this work, we propose SidechainDiff, a representation learning-based approach that leverages unlabelled experimental protein structures. SidechainDiff utilizes a Riemannian diffusion model to learn the generative process of side-chain conformations and can also give the structural context representations of mutations on the protein-protein interface. Read more