Machine learning‐based genetic evolution of antitumor proteins containing unnatural amino acids by integrating chemometric modeling and cytotoxicity analysis

Abstract

Antitumor proteins (ATPs) are small oligoproteins or peptides that have been recognized as new and promising therapeutics against a variety of human tumors and cancers. In order to extend the structural diversity space of ATPs, the unnatural amino acids were incorporated into naturally occurring ATPs by using a chemometrics‐based genetic evolution strategy. Based on hundreds of ATPs derived from animals, plant and microbes statistical regression models were developed, optimized, and validated with a systematic combination of 5 widely used machine learning methods and 3 sophisticated unnatural amino acid descriptors. The best regression predictor was employed to guide genetic evolution of a large oligoprotein population. In the evolution procedure, a number of unnatural amino acids with desired physicochemical properties were introduced, resulting in an evolution‐improved population, from which few oligoprotein candidates with top scores, containing 1 to 3 unnatural amino acids, and having diverse structures were successfully prepared, and their antitumor potency against 2 cancer cell lines was analyzed with biological assays. It was found that the high‐activity ATPs are preferentially structured in partial α‐helix or β‐sheet with an alternative sequence pattern of polar, charged, and hydrophobic amino acids, while the intrinsically disordering oligoproteins usually have low or no antitumor activity against tested cancer cell lines.

Identification and Characterization of a Novel Protein ASP-3 Purified from Arca subcrenata and Its Antitumor Mechanism

“…The amino acids are usually polar, charged, and hydrophobic. Similarly, phenylalanine and leucine, as well as other hydrophobic amino acids accounted for more in the protein sequences [37]. The FTIR spectrum results indicated that there was a certain percentage of α-helix conformation in ASP-3.…”

High‐throughput statistical screening of antiinfective peptides from natural antibacterial protein repertoire: Chemometric prediction, molecular modeling, and susceptibility analysis

“…Amino acid descriptors were utilized as local descriptors to peptide sequence were derived from various physicochemical properties of 20 amino acids by using principal component analysis (PCA) . With amino acid descriptor characterization, the number of variables for a peptide is proportional to the peptide length, and thus, all the collected 12‐mer AIPs in the sample set would have the same number of variables generating from the characterization . The molecular structures of peptides were built and minimized with TINKER force field .…”

“…36 With amino acid descriptor characterization, the number of variables for a peptide is proportional to the peptide length, and thus, all the collected 12-mer AIPs in the sample set would have the same number of variables generating from the characterization. 37 The molecular structures of peptides were built and minimized with TINKER force field. 38 The structures were imported into CODESSA to generate more than 500 constitutional, topological, geometrical, charge-related, and thermodynamical descriptors.…”