Abstract | ||
---|---|---|
Predicting how a point mutation alters a protein's stability can guide drug design initiatives which aim to counter the effects of serious diseases. Mutagenesis studies give insights about the effects of amino acid substitutions, but such wet-lab work is prohibitive due to the time and costs needed to assess the consequences of even a single mutation. Computational methods for predicting the effects of a mutation are available, with promising accuracy rates. In this work we study the utility of several machine learning methods and their ability to predict the effects of mutations. We in silico generate mutant protein structures, and compute several rigidity metrics for each of them. Our approach does not require costly calculations of energy functions that rely on atomic-level statistical mechanics and molecular energetics. Our metrics are features for support vector regression, random forest, and deep neural network methods. We validate the effects of our in silico mutations against experimental Delta Delta G stability data. We attain Pearson Correlations upwards of 0.69. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3107411.3107492 | BCB |
Keywords | Field | DocType |
Machine Learning,Protein Structure,Mutation,Support Vector Regression,Random Forest,Deep Neural Network,Rigidity Analysis | Mutant protein,Force field (chemistry),Computer science,Point mutation,Support vector machine,Artificial intelligence,Bioinformatics,Random forest,Artificial neural network,Machine learning,In silico,Mutation | Conference |
ISBN | Citations | PageRank |
978-1-4503-4722-8 | 2 | 0.43 |
References | Authors | |
9 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roshanak Farhoodi | 1 | 17 | 2.77 |
Max Shelbourne | 2 | 2 | 0.43 |
Rebecca Hsieh | 3 | 3 | 0.80 |
Nurit Haspel | 4 | 60 | 14.11 |
Brian Hutchinson | 5 | 137 | 13.23 |
Filip Jagodzinski | 6 | 71 | 14.83 |