Prediction of protein p <i>K</i> _a with representation learning

2022/01/01 by Hatice Gökcan, Olexandr Isayev · 1 voice
Computer Science · Materials Science · Biochemistry, Genetics and Molecular Biology · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Protein Structure and Dynamics

paper · pdf · doi:10.1039/d1sc05610g

Abstract

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.

Citations

• Less is more: Sampling chemical space with active learning

Discussions

• We explicitly did not look at protein pKa because IMHO @olexandr.bsky.social already published a good model using their ANI-2x potential. doi.org/10.1039/D1SC... [bsky, 10 points, 1 comments]

Related

• Very fast empirical prediction and rationalization of protein pK_a values
• Estimation of Distribution Algorithm for Protein Structure Prediction
• Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
• Combination of digital signal processing and assembled predictive models facilitates the rational design of proteins
• Accessible, uniform protein property prediction with a scikit-learn based toolset AIDE