Developing optimal nonlinear scoring function for protein design

TL;DR

This paper introduces a novel nonlinear scoring function for protein design, capable of accurately distinguishing native protein sequences from decoys, outperforming linear methods and advancing the development of protein folding scoring functions.

Contribution

The paper proposes a mixture of nonlinear Gaussian kernel functions as a new approach to protein scoring, demonstrating superior discrimination of native sequences over linear methods.

Findings

Successfully discriminates 440 native proteins from 14 million decoys

Misclassifies only 13 native proteins out of 194 in blind tests

Outperforms existing linear scoring functions by 3-4 times in accuracy

Abstract

Motivation. Protein design aims to identify sequences compatible with a given protein fold but incompatible to any alternative folds. To select the correct sequences and to guide the search process, a design scoring function is critically important. Such a scoring function should be able to characterize the global fitness landscape of many proteins simultaneously. Results. To find optimal design scoring functions, we introduce two geometric views and propose a formulation using mixture of nonlinear Gaussian kernel functions. We aim to solve a simplified protein sequence design problem. Our goal is to distinguish each native sequence for a major portion of representative protein structures from a large number of alternative decoy sequences, each a fragment from proteins of different fold. Our scoring function discriminate perfectly a set of 440 native proteins from 14 million sequence decoys. We show that no linear scoring function can succeed in this task. In a blind test of unrelated proteins, our scoring function misclassfies only 13 native proteins out of 194. This compares favorably with about 3-4 times more misclassifications when optimal linear functions reported in literature are used. We also discuss how to develop protein folding scoring function.