An in-silico method for identifying aggregation rate enhancer and mitigator mutations in proteins

摘要: Newly synthesized polypeptides must pass stringent quality controls in cells to ensure appropriate folding and function. However, mutations, environmental stresses aging can reduce efficiencies of these controls, leading accumulation protein aggregates, amyloid fibrils plaques. In-vitro experiments have shown that even single amino acid substitutions drastically enhance or mitigate aggregation kinetics. In this work, we collected a dataset 220 unique mutations 25 proteins classified them as enhancers mitigators on the basis their effect rate. The data were analyzed via machine learning identify features capable distinguishing between rate mitigators. Our initial Support Vector Machine (SVM) model separated such with an overall accuracy 69%. When local secondary structures at mutation sites considered, accuracies further improved by 13-15%. machine-learnt are distinct for each structure class sites. Protein stability flexibility changes important α-helices. β-strand propensity, polarity charge become when occur β-strands ability form structure, helical tendency propensity lying coils. These results been incorporated into sequence-based algorithm (available http://www.iitm.ac.in/bioinfo/aggrerate-disc/) predicting whether will protein's This find several applications towards understanding human diseases, enable in-silico optimization biopharmaceuticals enzymes biophysical attributes de novo design bio-nanomaterials.