The behavior of proteins is closely related to the protonation states of the residues. Therefore, prediction and measurement of pKa are essential to understand the basic functions of proteins. In this work, we develop a new empirical scheme for protein pKa prediction that is based on deep representation learning. It combines machine learning with atomic environment vector (AEV) and learned quantum mechanical representation from ANI-2x neural network potential (J. Chem. Theory Comput. 2020, 16, 4192). The scheme requires only the coordinate information of a protein as the input and separately estimates the pKa for all five titratable amino acid types. The accuracy of the approach was analyzed with both cross-validation and an external test set of proteins. Obtained results were compared with the widely used empirical approach PROPKA. The new empirical model provides accuracy with MAEs below 0.5 for all amino acid types. It surpasses the accuracy of PROPKA and performs significantly better than the null model. Our model is also sensitive to the local conformational changes and molecular interactions. 5-Bromo-2-(difluoromethyl)pyrimidine site 5-Chloro-4-methylpyridin-3-amine custom synthesis PMID:23381626
Headquartered in New Jersey, USA, ChemScence is a global leading manufacturer and supplier of building blocks and fine research chemicals. We now have branches in Sweden and India. Our mission is to pave the way for drug discovery by providing the most innovative chemicals with the highest-level quality for a reasonable price.
Our Catalog Products
We deliver an extensive portfolio of products, including Building Blocks,Catalysts&Ligands,Synthetic Reagents,Material Science and ADC Linkers&Protac,.ChemScene now have over 600000 Building Blocks & Intermediates in our catalog and more than 70000 of them are in stock.
For details, please refer to the ChemScene website:https://www.chemscene.com