Chao Hou

This study shows that larger protein language models can overestimate sequence likelihood, leading to poor fitness prediction, and recommends moderate model sizes for better performance.

The paper develops MDmis, a method using molecular dynamics simulations of intrinsically disordered regions to predict variant pathogenicity, finding Long IDRs show stronger pathogenic effects than Short IDRs.

This paper introduces two protein language models trained on dynamic biophysical data to better predict mutation effects and protein behavior.

MotifAE discovers functional sequence patterns from protein language models through an unsupervised framework, improving motif identification and enabling stability prediction.

PhaSeDis is a database that curates phase separation-disease associations and small molecules, expanding on MloDisDB with more entries and molecular interaction data.