Back

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening

Jang, W.; Shin, W.-H.

2026-01-08 bioinformatics
10.64898/2026.01.07.698135 bioRxiv
Show abstract

MotivationStructure-based virtual screening (SBVS) is limited by the rigid-receptor assumption, which is particularly problematic for kinases that adopt multiple active-site conformations but are experimentally biased toward a single state. Although ensemble screening can address this limitation, it remains computationally expensive. ResultsWe introduce KASSPer (Kinase Active Site Structure Predictor), a framework that predicts kinase active-site conformational states using protein and compound language models. Given a kinase amino acid sequence and a ligand SMILES string, KASSPer enables ligand-specific conformer selection prior to SBVS, substantially reducing the computational cost associated with ensemble screening. Benchmarking on the DUD-E kinase subset demonstrates that KASSPer-guided screening consistently outperforms ensemble-based approaches across all evaluation metrics. Availability and ImplementationThe implementation for model loading and inference is available at the GitHub repository https://github.com/kucm-lsbi/KASSPer

Published in Bioinformatics (predicted rank #4) · training set

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.