Probabilistic Assessment of a Pentapeptide Composition Influence on Its Stability

Abstract

The influence of the arrangement of amino acid residues in a pentapeptide on its stability is being studied. A forecast of pentapeptide stability is made using the gradient boosting method, which allows one to evaluate the influence of each feature on the stability of the pentapeptide. Combinations of amino acid arrangements in the pentapeptide have been identified that make a significant contribution to its stability. It has been shown that the use of such combinations reduces the amount of data required to obtain a reliable prediction of pentapeptide stability.