Bozitao Zhong

VenusGenome: Genome-Aware Masked Autoencoding for Microbial Genome Representation Learning

VenusGenome improves microbial genome representation learning by using a genome-aware masked autoencoder, achieving high performance in phenotype prediction and gene-level tasks.

Deep learning-guided design of hydrolases for crystalline PET depolymerization

This paper designs an engineered PET hydrolase, VenusPETase, using deep learning to enhance PET depolymerization efficiency and thermostability, achieving high TPA yields and complete degradation of commercial PET.

Scaffold-Lab: Critical Evaluation and Ranking of Protein Backbone Generation Methods in A Unified Framework

The paper evaluates and ranks protein backbone generation methods using a unified benchmark, identifying top-performing models in both unconditional and conditional generation.

Reaction-Conditioned Enzyme Discovery with Multimodal Deep Learning

This paper introduces VenusRXN, a deep learning framework for reaction-conditioned enzyme discovery, achieving high accuracy in identifying enzymes for novel reactions.

Harnessing Protein Language Model for Structure-Based Discovery of Highly Efficient and Robust PET Hydrolases

This paper uses a protein language model and structural representation tree to discover improved PET hydrolases, identifying KbPETase with higher thermal stability and degradation activity.

Harnessing A Unified Multi-modal SequenceModeling to unveil Protein-DNA Interdependency

ProDMM is a multimodal sequence modeling framework that captures interdependencies between protein motifs, coding DNA, and regulatory elements to predict phenotypes and generate optimized regulatory sequences.

AI-enabled Alkaline-resistant Evolution of Protein to Apply in Mass Production

This study uses a large language model to design an antibody with enhanced alkali resistance, validated for mass production.

Discovery of Expression-Governing Residues in Proteins

This study introduces Venus-TIGER, a deep learning model that identifies critical amino acids for protein expression, showing improved accuracy and transferability across datasets.

Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models

The paper introduces Venus-MAXWELL, a framework for predicting protein mutant stability using sequence-to-landscape learning, achieving higher accuracy and faster inference than existing methods.

How to select the best zero-shot model for the viral proteins?

This paper introduces ProPEC, a perplexity-based ensemble model for zero-shot prediction of viral protein fitness, showing improved performance over individual models.

Unlearning Virus Knowledge Toward Safe and Responsible Mutation Effect Predictions

This paper introduces PROEDIT, a method to remove virus-related knowledge from pre-trained protein models to improve safety in mutation effect predictions without affecting performance on non-virus proteins.

Pretrainable Geometric Graph Neural Network for Antibody Affinity Maturation

This paper introduces GearBind, a geometric graph neural network for in silico antibody affinity maturation, achieving significant improvements in binding affinity.

DeepReweighting: Reparameterizing Force Field under Explainable Deep Learning Framework

This paper introduces DeepReweighting, a deep learning framework for optimizing molecular force fields with improved efficiency and accuracy compared to traditional methods.

Precise Generation of Conformational Ensembles for Intrinsically Disordered Proteins via Fine-tuned Diffusion Models

This paper introduces IDPFold, a diffusion model that generates conformational ensembles for intrinsically disordered proteins directly from sequences, without requiring MSA or experimental data.

ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention

ProSST integrates protein sequences and structures into a Transformer-based model, achieving state-of-the-art performance in mutation effect prediction and downstream tasks.