Protein Function Analysis through Machine Learning

Abstract

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

Deep Learning in Phosphoproteomics: Methods and Application in Cancer Drug Discovery

“…Over the last decade, the integration of ML into a wide range of computational models has improved prediction accuracy and gained a better understanding of protein function and PTMs [ 26 , 27 ]. With the explosion of DL methods, ML-based approaches for phosphorylation site prediction have become more popular.…”

MSF-PFP: A Novel Multisource Feature Fusion Model for Protein Function Prediction

“…As such, research on protein functions is essential for the development of new treatments for a wide range of biological processes. 2 Protein function prediction is a vital tool in modern biological research, offering a deeper understanding of proteins and their roles in various biological processes. By employing computational and mathematical techniques, scientists can predict a protein's structure, stability, and activity.…”

“…In recent years, the exploration of proteins’ role in life activities and the accurate identification of their functions have become a major focus in the field of biomedical research. As such, research on protein functions is essential for the development of new treatments for a wide range of biological processes …”

ESM-Scan - a tool to guide amino acid substitutions

“…While achieving success rates in the modest range of 20% to 40%, these tools require substantial additional knowledge of the methods and the systems on the user's part (Schmitz et al 2020, Yamaguchi and Saito 2021, Hsu et al 2022. Early machine learning approaches demonstrated good predictive power; however, they tended to overfit training data limiting their ability to generalise to proteins beyond the original training dataset (Bradford and Westhead 2004, Rao et al 2019, Avery et al 2022, Verkuil et al 2022. Expanding beyond these early approaches, deep learning models harness vast sequence datasets and experimental information, autonomously learning from them in an unsupervised manner (Gilmer et al 2017, Riesselman, Ingraham andMarks 2018).…”

“…Moreover, data availability and curation are fundamental in the training and testing phases. The absence of a computational gold standard method currently hinders the direct transferability of model performances to varied use cases (Avery et al 2022).…”