In ACS biomaterials science & engineering ; h5-index 39.0
We developed a method for efficiently activating functional peptides with a large structural contribution using the peptide-searching method with machine learning. The physicochemical properties of the amino acids were employed as variables. As a model peptide, we used GHWYYRCW, which is a functional peptide that inhibits α-amylase derived from human pancreatic juice. First, training data were acquired. A total of 153 peptides were prepared in which 1 amino acid in GHWYYRCW was replaced to construct a 1-amino acid substitution coverage peptide library. The inhibitory activity of each peptide against α-amylase and α-glucosidase was evaluated. Second, random forest (RF) regression analysis was performed using 120 variables, and the enzyme inhibitory activity of the peptide was related to the physicochemical properties. The constructed model had many features describing the charge of the amino acid (isoelectric point and pK2). Then, high inhibitory (HI) peptides were predicted using a library of peptides with 2- or 3-amino acid substitution as test data, which were called HI2 and HI3 peptides. As results, the first or seventh amino acid of the HI2 peptide was replaced with Arg, Trp, or Tyr. We found that all 30 HI2 peptides had significantly higher activity than the original sequence (100%) and 26 of the 30 HI3 peptides were significantly active (86.7%). However, the actual inhibitory activity of the HI3 peptides was improved to a lesser extent. The docking simulation clarified that the CDOCKER energy decrease was roughly correlated with the inhibitory activity. The machine learning-based predictive model was a promising tool for design of substituted peptides with high activity values, and it was assumed that the advanced model that forecasts the interaction index such as the CDOCKER energy substituting for the inhibitory activity would be used to design HI peptides, even in the case of the HI3 peptides.
Yamashita Haruki, Fujitani Masaya, Shimizu Kazunori, Kanie Kei, Kato Ryuji, Honda Hiroyuki
amino acid index, data mining, peptide array, physicochemical property, screening system