Jimin Pei

The paper validates and analyzes 12,000 AI-designed CAR-T binders from a global competition, identifying successful designs and factors improving their performance.

The paper uses AI to compare biological information from UniProt records and their cited literature for human kinases, finding literature provides better coverage for certain topics.

The paper classifies archaeal proteomes at the domain level, revealing that structural diversity is conserved across archaea and that unclassified proteins are due to classification limitations, not structural novelty.

This paper evaluates progress in predicting protein complex structures in CASP16, finding moderate improvements but ongoing challenges in model ranking, stoichiometry prediction, and handling difficult targets.

The paper predicts 18,316 human protein-protein interactions with 90% precision using enhanced coevolutionary analysis and a new deep learning model.

This paper develops hDIRECT, a platform using human-derived proteins to control cytokine activity in cell-based therapies, demonstrating orthogonalization through protease regulation.

This study uses deep learning to predict protein-protein interactions in bacterial pathogens, identifying new complexes involving essential genes and virulence factors, with half of tested predictions validated.

This study identifies COA8 as a COX10-binding protein essential for COX10 stability and catalytic activity in human cytochrome c oxidase biogenesis.

This study identifies a genetic variant in COL11A1 associated with adolescent idiopathic scoliosis and proposes a molecular model involving Pax1, Col11a1, and Mmp3 in spinal chondrocytes.

The paper uses AlphaFold to predict cancer protein-protein interactions and maps somatic mutations to these interfaces, revealing functional insights and potential drug targets.

The paper investigates the evolutionary origins of myoblast fusion mechanisms in chordates, identifying the emergence of Myomaker and Myomixer and their roles in muscle development across species.

The paper uses deep learning to predict mitochondrial protein complexes and interactions, identifying known and novel protein pairs with structural and functional insights.

The paper develops DeepSAV, a deep-learning model to predict the pathogenicity of single-amino acid variations, and uses it to assess mutation severity across genes, identifying intolerant and tolerant genes for different disease categories.