Abstract
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 inhibit therapeutically relevant protein–protein interactions. During the course of the ICERM WiSDM workshop 2017, we combined the KFC2a protein–protein interaction hotspot prediction features with Rosetta scoring function terms and interface filter metrics. A two-way and three-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.
Original language | English |
---|---|
Title of host publication | Association for Women in Mathematics Series |
Publisher | Springer |
Pages | 177-197 |
Number of pages | 21 |
DOIs | |
State | Published - 2019 |
Publication series
Name | Association for Women in Mathematics Series |
---|---|
Volume | 17 |
ISSN (Print) | 2364-5733 |
ISSN (Electronic) | 2364-5741 |
Funding
The feature table and feature selection code are available by email to the corresponding author. We thank the Association for Women in Mathematics (AWM) and the Brown University Institute for Computational and Experimental Research in Mathematics (ICERM) for hosting the Women in Data Science and Mathematics (WiSDM) workshop. The Brown University Center for Computation and Visualization (CCV) and the Institute for Protein Design at the University of Washington provided computational resources used for this project. Participation by JM was sponsored by the National Science Foundation [NSF DMS 1160360]. The AWM Advance Program supported participation by FS, AL, YC, TW, and HC. Participation by TW was also supported by DIMACS. FS is generously funded by the Washington Research Foundation Institute for Protein Design Postdoctoral Innovation Fellowship. Acknowledgements The feature table and feature selection code are available by email to the corresponding author. We thank the Association for Women in Mathematics (AWM) and the Brown University Institute for Computational and Experimental Research in Mathematics (ICERM) for hosting the Women in Data Science and Mathematics (WiSDM) workshop. The Brown University Center for Computation and Visualization (CCV) and the Institute for Protein Design at the University of Washington provided computational resources used for this project. Participation by JM was sponsored by the National Science Foundation [NSF DMS 1160360]. The AWM Advance Program supported participation by FS, AL, YC, TW, and HC. Participation by TW was also supported by DIMACS. FS is generously funded by the Washington Research Foundation Institute for Protein Design Postdoctoral Innovation Fellowship.