Bo Chen

MSAGPT improves protein structure prediction by generating virtual MSAs through pre-training, enhancing accuracy in low-MSA scenarios.

This paper investigates optimal training of protein language models by analyzing the relationship between model size, training data, and performance, finding that diverse training data and scaling laws improve results.

A 100-billion-parameter protein language model trained with masked and autoregressive objectives together, topping prior results on 15 of 18 benchmarks and powering a fast structure predictor.

This paper introduces ESMPair, a method using protein language models to improve interolog identification, leading to better protein complex structure prediction than AlphaFold-Multimer.