Protein Binding Pose Prediction via Conditional Variational Autoencoding for Plasmodium Falciparum

Malaria is a disease caused by single-celled blood parasites of the genus Plasmodium. The protozoan Plasmodium Falciparum (PF) inflicts the most damage and is responsible for most malaria-related deaths. The high mutational capacity of the Plasmodium parasite coupled with its changing metabolism makes the development of new effective drug treatments an evolving and open problem. In this work, we propose a machine learning approach to predict the binding pose structure of ligand families for this parasite. Identifying appropriate protein-ligand binding poses is essential in structure-based drug design and important for the evaluation of protein-ligand binding affinity. Specifically, a conditional variational autoencoder is trained to learn the distribution which represents the binding structures conditioned on the given binding sites. Using this well-trained conditional variational autoencoder, our approach generates binding poses for the ligand's receptor for a particular binding site by sampling from this learned distribution. We demonstrate that our model is able to accurately predict the binding structures of multiple binding sites for the PF parasite invasion ligand families in the erythrocyte invasion and compare it with other states of the art methods like HADDOCK, Hdock, and GRAMMX.