AUTHOR=Yamane Haruki , Ishida Takashi TITLE=Helix encoder: a compound-protein interaction prediction model specifically designed for class A GPCRs JOURNAL=Frontiers in Bioinformatics VOLUME=Volume 3 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/bioinformatics/articles/10.3389/fbinf.2023.1193025 DOI=10.3389/fbinf.2023.1193025 ISSN=2673-7647 ABSTRACT=Class A G protein-coupled receptors (GPCRs) represent the largest class of GPCRs and are important for drug discovery. Various computational approaches have been applied to predict their ligands. Among them, the compound-protein interaction (CPI) prediction has been considered one of the most suitable for class A GPCRs due to a large number of orphan receptors. However, the accuracy of CPI prediction is still insufficient. The current CPI prediction model employs the whole protein sequence as the input. However, only a few transmembrane helices of class A GPCRs play a critical role in ligand binding. Therefore, using such domain knowledge, the CPI prediction performance could be improved by developing an encoding method that is specifically designed for this family.