Yunxin Xu

The paper introduces Cerebra-Epistasis, a framework that improves multi-mutant fitness prediction by modeling epistatic effects and integrating structure-aware sequence analysis.

MutCleaner standardizes mutation datasets for variant effect prediction by cleaning, validating, and organizing mutation records across 16 datasets with over 12.14 million entries.

The paper introduces three geometric learning models for predicting protein stability changes upon mutations, achieving improved performance over existing methods.

SPIRED-Fitness predicts protein structure and fitness from single sequences using an end-to-end framework combining SPIRED with downstream neural networks.