Ppdx: Automated modeling of protein–protein interaction descriptors for use with machine learning. Issue 25 (5th August 2022)

• Record Type: Journal Article
• Authors: Conti, Simone; Ovchinnikov, Victor; Karplus, Martin
• Is Part Of: Journal of computational chemistry. Volume 43:Issue 25(2022)
• Page Start: 1747
• Page End: 1757
• Publication Date: 2022-08-05
• Subjects: binding affinity -- machine learning -- protein interaction descriptors -- protein–protein interactions -- scoring functions; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.26974
• Languages: English
• ISSNs: 0192-8651

Abstract

Abstract: This paper describes ppdx, a python workflow tool that combines protein sequence alignment, homology modeling, and structural refinement, to compute a broad array of descriptors for characterizing protein–protein interactions. The descriptors can be used to predict various properties of interest, such as protein–protein binding affinities, or inhibitory concentrations (IC50 ), using approaches that range from simple regression to more complex machine learning models. The software is highly modular. It supports different protocols for generating structures, and 95 descriptors can be currently computed. More protocols and descriptors can be easily added. The implementation is highly parallel and can fully exploit the available cores in a single workstation, or multiple nodes on a supercomputer, allowing many systems to be analyzed simultaneously. As an illustrative application, ppdx is used to parametrize a model that predicts the IC50 of a set of antigens and a class of antibodies directed to the influenza hemagglutinin stalk. Abstract : Computational modeling of protein–protein interactions, such as binding affinities, inhibition concentrations (IC50 ), and rates of binding, is notoriously difficult. Machine learning models trained on experimental datasets can help, but they require meaningful descriptors, or features, to represent the protein–protein complex. We describe ppdx, a python workflow tool to automate and parallelize protein complex modeling and computation of a broad array of descriptors.