Vladimiras Oleinikovas

CryptoBank identifies cryptic binding sites in proteins using structural alignments and a machine learning model, enabling prediction from sequence data with high precision.

The paper predicts over 1,400 CRBN-compatible β-hairpin G-loop proteins and validates 22 neosubstrates, redefining rules for molecular glue-induced degradation.

PLINDER provides a large, annotated PLI dataset with diverse annotations and improved evaluation splits to better assess computational methods for drug design.