Inverse Protein Folding Problem via Quadratic Programming

TL;DR

This paper introduces a quadratic programming approach to solve the inverse protein folding problem, predicting amino acid sequences from 3D structures by energy minimization and convex relaxation techniques.

Contribution

It formulates the inverse protein folding as a quadratic optimization problem and applies relaxation methods to efficiently predict amino acid sequences from tertiary structures.

Findings

Different relaxation techniques improve prediction accuracy

Quadratic programming effectively models the inverse folding problem

Experimental results demonstrate the method's viability

Abstract

This paper presents a method of reconstruction a primary structure of a protein that folds into a given geometrical shape. This method predicts the primary structure of a protein and restores its linear sequence of amino acids in the polypeptide chain using the tertiary structure of a molecule. Unknown amino acids are determined according to the principle of energy minimization. This study represents inverse folding problem as a quadratic optimization problem and uses different relaxation techniques to reduce it to the problem of convex optimizations. Computational experiment compares the quality of these approaches on real protein structures.