Abstract | ||
---|---|---|
Rosetta is one of the leading algorithms for protein structure prediction today. It is a Monte Carlo energy minimization method requiring many random restarts to find structures with low energy. In this paper we present a resampling technique for structure prediction of small alpha/beta proteins using Rosetta. From an ini- tial round of Rosetta sampling, we learn properties of the energy landscape that guide a subsequent round of sampling toward lower-energy structures. Rather than attempt to fit the full energy landscape, we use feature selection methods—both L1-regularized linear regression and decision trees—to identify structural features that give rise to low energy. We then enrich these structural features in the second sampling round. Results are presented across a benchmark set of nine small al- pha/beta proteins demonstrating that our methods seldom impair, and frequently improve, Rosetta's performance. |
Year | Venue | Keywords |
---|---|---|
2007 | NIPS | monte carlo,feature selection,protein structure prediction,energy minimization,decision tree,linear regression,energy landscape |
Field | DocType | Citations |
Data mining,Protein structure prediction,Monte Carlo method,Feature selection,Computer science,Artificial intelligence,Sampling (statistics),Resampling,Energy landscape,Machine learning,Linear regression,Energy minimization | Conference | 5 |
PageRank | References | Authors |
0.41 | 2 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ben Blum | 1 | 5 | 0.41 |
Michael I. Jordan | 2 | 31220 | 3640.80 |
David Kim | 3 | 2727 | 105.59 |
Rhiju Das | 4 | 37 | 7.66 |
Phil Bradley | 5 | 37 | 4.22 |
David Baker | 6 | 5 | 0.41 |