S. S. Ray

Are Deep Learning Structural Models Sufficiently Accurate for Virtual Screening? Application of Docking Algorithms to AlphaFold2 Predicted Structures

This study evaluates the accuracy of AlphaFold2 structures for virtual screening, finding that out-of-the-box models are insufficient for hit-finding in low sequence identity targets and suggest post-processing improvements.

Are Deep Learning Structural Models Sufficiently Accurate for Free Energy Calculations? Application of FEP+ to AlphaFold2 Predicted Structures

The paper assesses if AlphaFold2 structures are accurate enough for FEP calculations in drug discovery, finding they perform comparably to X-ray structures in most cases.