Author:
Ille Alexander M.,Markosian Christopher,Burley Stephen K.,Mathews Michael B.,Pasqualini Renata,Arap Wadih
Abstract
Generative artificial intelligence (AI) is increasingly used by researchers in numerous fields, including the biological sciences. To date, the most commonly used tool grounded in this technology is Chat Generative Pre-trained Transformer (ChatGPT). While ChatGPT is typically applied for natural language text generation, other application modes include coding and mathematical problem-solving. We have recently reported the ability of ChatGPT to interpret the central dogma of molecular biology and the genetic code. Here we explored how ChatGPT might be able to perform rudimentary structural biology modelling. We prompted ChatGPT to model 3D structures for the 20 standard amino acids as well as an α-helical polypeptide chain, with the latter involving incorporation of the Wolfram plugin for advanced mathematical computation. For amino acid modelling, distances and angles between atoms of the generated structures in most cases approximated to experimentally determined values. For α-helix modelling, the generated structures were comparable to that of an experimentally determined α-helical structure. However, both amino acid and α-helix modelling were sporadically error-prone and molecular complexity was not well tolerated. Despite current limitations, we show the capacity of generative AI to perform basic structural biology modelling with atomic-scale accuracy. These results provide precedent for the potential use of generative AI in structural biology as this technology continues to advance.
Publisher
Cold Spring Harbor Laboratory