Albany 2019: 20th Conversation - Abstracts

category image Albany 2019
Conversation 20
June 11-15 2019
Adenine Press (2019)

Feature Selection in Biomolecular Models

Protein-protein interactions regulate many essential biological processes and play an important role in health and disease. The process of experimentally characterizing protein residues that contribute the most to protein-protein interaction affinity and specificity is laborious. Thus, developing models that accurately characterize hotspots at protein-protein interfaces provides important information about how to drug therapeutically relevant protein-protein interactions. In this work, we combined the KFC2a protein-protein interaction hotspot prediction features with Rosetta scoring function terms and interface filter metrics. A 2-way and 3-way forward selection strategy was employed to train support vector machine classifiers, as was a reverse feature elimination strategy. From these results, we identified subsets of KFC2a and Rosetta combined features that show improved performance over KFC2a features alone. The forward selection algorithm also helped elucidate the biophysical principles that determine whether a given amino acid is a binding hot spot.

Julie Mitchell

Biosciences Division
Oak Ridge National Laboratory
Oak Ridge TN

Email: mitchelljc@ornl.gov