Machine learning overcomes human bias in the discovery of self-assembling peptides

• Published in: Nature chemistry Vol. 14; no. 12; pp. 1427 - 1435
• Main Authors: Batra, Rohit, Loeffler, Troy D., Chan, Henry, Srinivasan, Srilok, Cui, Honggang, Korendovych, Ivan V., Nanda, Vikas, Palmer, Liam C., Solomon, Lee A., Fry, H. Christopher, Sankaranarayanan, Subramanian K. R. S.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.12.2022; Nature Publishing Group
• Subjects: 631/45/611; 639/925/357/341; Amino Acids; Analytical Chemistry; Artificial intelligence; Bias; Biochemistry; Catalysis; Chemistry; Chemistry and Materials Science; Chemistry/Food Science; Computer applications; Design; Human bias; Humans; Hydrogels - chemistry; Inorganic Chemistry; INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Learning algorithms; Machine Learning; Molecular dynamics; Molecular Dynamics Simulation; molecular self-assembly; Organic Chemistry; Pentapeptides; Peptides; Peptides - chemistry; Physical Chemistry; Search engines; Self-assembly; Tissue engineering; Workflow
• ISSN: 1755-4330; 1755-4349; 1755-4349
• DOI: 10.1038/s41557-022-01055-3

Peptide materials have a wide array of functions, from tissue engineering and surface coatings to catalysis and sensing. Tuning the sequence of amino acids that comprise the peptide modulates peptide functionality, but a small increase in sequence length leads to a dramatic increase in the number of peptide candidates. Traditionally, peptide design is guided by human expertise and intuition and typically yields fewer than ten peptides per study, but these approaches are not easily scalable and are susceptible to human bias. Here we introduce a machine learning workflow—AI-expert—that combines Monte Carlo tree search and random forest with molecular dynamics simulations to develop a fully autonomous computational search engine to discover peptide sequences with high potential for self-assembly. We demonstrate the efficacy of the AI-expert to efficiently search large spaces of tripeptides and pentapeptides. The predictability of AI-expert performs on par or better than our human experts and suggests several non-intuitive sequences with high self-assembly propensity, outlining its potential to overcome human bias and accelerate peptide discovery. Peptide design remains a challenge owing to the large library of amino acids. Rational design approaches, although successful, result in a peptide design bias. Now it has been shown that AI techniques can be used to overcome such bias and discover unusual peptides as efficiently as humans.