Protein p<i>K</i>_a Prediction by Tree-Based Machine Learning.

ABSTRACT: Protonation states of ionizable protein residues modulate many essential biological processes. For correct modeling and understanding of these processes, it is crucial to accurately determine their pK_a values. Here, we present four tree-based machine learning models for protein pK_a prediction. The four models, Random Forest, Extra Trees, eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were trained on three experimental PDB and pK_a datasets, two of which included a notable portion of internal residues. We observed similar performance among the four machine learning algorithms. The best model trained on the largest dataset performs 37% better than the widely used empirical pK_a predict

SUBMITTER: Chen AY 

PROVIDER: S-EPMC10510853 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature