Predicting protein stability and solubility changes upon mutations: data perspective. Issue 22 (3rd September 2020)

• Record Type: Journal Article
• Authors: Mazurenko, Stanislav
• Is Part Of: ChemCatChem. Volume 12:Issue 22(2020)
• Page Start: 5590
• Page End: 5598
• Publication Date: 2020-09-03
• Subjects: Database -- Machine learning -- Protein design -- Protein engineering -- Protein modifications; Catalysis -- Periodicals; 541.39505
• DOI: 10.1002/cctc.202000933
• Languages: English
• ISSNs: 1867-3880

Abstract

Abstract: Understanding mutational effects on protein stability and solubility is of particular importance for creating industrially relevant biocatalysts, resolving mechanisms of many human diseases, and producing efficient biopharmaceuticals, to name a few. For in silico predictions, the complexity of the underlying processes and increasing computational capabilities favor the use of machine learning. However, this approach requires sufficient training data of reasonable quality for making precise predictions. This minireview aims to summarize and scrutinize available mutational datasets commonly used for training predictors. We analyze their structure and discuss the possible directions of improvement in terms of data size, quality, and availability. We also present perspectives on the development of mutational data for accelerating the design of efficient predictors, introducing two new manually curated databases FireProt DB and SoluProtMut DB for protein stability and solubility, respectively. Abstract : In silico predictions have become an integral part of successful biocatalyst design. Modern computational analysis for protein engineering applies machine learning to predict changes in protein stability and solubility on introducing mutations. Here we summarize state‐of‐the‐art for the most critical part of the approach: mutational datasets used for training and validation.