Experimentally Tuned Protein-RNA Rosetta Score Function using Bayesian Optimization
Bailey, J. S.; Phan, N.; Spina, S. C.; Getman, R. B.; Paulson, J. A.; Kimmel, B. R.
Show abstract
Protein-RNA complexes drive fundamental cellular processes such as transcription and translation. Despite the prevalence and importance of protein-RNA interactions, the field lacks reliable and accessible methods to quantify the energetic favorability of these interactions. We propose an experimentally tuned protein-RNA score function that can be directly implemented into ROSETTA. Fine-tuning these score functions for predictive tasks requires repeated evaluations on a set of protein-RNA complexes, which can be computationally expensive given the number of parameters to tune. We used Bayesian Optimization to efficiently improve the energetic agreement between ROSETTA and experimentation. We observe significant interactions for specific RNA subclasses, serving as further confirmation of the physical validity of the score function. Beyond protein-RNA interaction prediction, we establish a framework to efficiently fine-tune ROSETTA score functions for any protein-class interaction using Bayesian Optimization. TOC FIGURE O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=100 SRC="FIGDIR/small/739244v1_ufig1.gif" ALT="Figure 1"> View larger version (18K): org.highwire.dtl.DTLVardef@700559org.highwire.dtl.DTLVardef@6f4ca6org.highwire.dtl.DTLVardef@11157c0org.highwire.dtl.DTLVardef@1981456_HPS_FORMAT_FIGEXP M_FIG C_FIG
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Neural Network-Derived Potts Models for Structure-Based Protein Design using Backbone Atomic Coordinates and Tertiary Motifs 96%
- SMOG 2 and OpenSMOG: Extending the limits of structure-based models 95%
- ExploreTurns: A web tool for the exploration, analysis, and classification of beta turns and structured loops in proteins; application to beta-bulge and Schellman loops, Asx helix caps, beta hairpins and other hydrogen-bonded motifs 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.