Tigran M. Abramyan

Overcoming the accuracy-generalization tradeoff in docking and scoring for prospective virtual screening

This paper introduces DODock and DOScore, hybrid ML/physics frameworks for docking and scoring that improve accuracy while generalizing better to novel molecules, showing significant improvements in hit rates for virtual screening.

Developing inhibitors of the guanosine triphosphate hydrolysis accelerating activity of Regulator of G protein Signaling-14

This paper identifies and validates non-covalent inhibitors of RGS14 GAP activity using structure-guided virtual screening and machine learning, showing improved potency and CNS penetration.

Deep Mutational Scanning Reveals EGFR Mutations Conferring Resistance to the 4th-generation EGFR tyrosine kinase inhibitor BLU-945

This study identifies EGFR mutations conferring resistance to BLU-945 using deep mutational scanning and shows that combination treatment may suppress resistance mechanisms.