Generative artificial intelligence performs rudimentary structural biology modeling.

Christopher Markosian, Wadih Arap, Renata Pasqualini, Michael B Mathews, Stephen K Burley, Alexander M Ille

Journal: Scientific reports 2024;14(1):19372

PMID: 39169047

Free Full Text on Nature Publishing Group View on PubMed

Abstract

Natural language-based generative artificial intelligence (AI) has become increasingly prevalent in scientific research. Intriguingly, capabilities of generative pre-trained transformer (GPT) language models beyond the scope of natural language tasks have recently been identified. Here we explored how GPT-4 might be able to perform rudimentary structural biology modeling. We prompted GPT-4 to model 3D structures for the 20 standard amino acids and an α-helical polypeptide chain, with the latter incorporating Wolfram mathematical computation. We also used GPT-4 to perform structural interaction analysis between the anti-viral nirmatrelvir and its target, the SARS-CoV-2 main protease. Geometric parameters of the generated structures typically approximated close to experimental references. However, modeling was sporadically error-prone and molecular complexity was not well tolerated. Interaction analysis further revealed the ability of GPT-4 to identify specific amino acid residues involved in ligand binding along with corresponding bond distances. Despite current limitations, we show the current capacity of natural language generative AI to perform basic structural biology modeling and interaction analysis with atomic-scale accuracy.

Address: School of Graduate Studies, Rutgers, The State University of New Jersey, Newark, NJ, USA.; Rutgers Cancer Institute, Newark, NJ, USA.; Division of Cancer Biology, Department of Radiation Oncology, Rutgers New Jersey Medical School, Newark, NJ, USA.; Research Collaboratory for Structural Bioinformatics Protein Data Bank, Institute for Quantitative Biomedicine, Rutgers, The State University of New Jersey, Piscataway, NJ, USA.; Department of Chemistry and Chemical Biology, Rutgers, The State University of New Jersey, Piscataway, NJ, USA.; Rutgers Cancer Institute, New Brunswick, NJ, USA.; Research Collaboratory for Structural Bioinformatics Protein Data Bank, San Diego Supercomputer Center, University of California-San Diego, La Jolla, San Diego, CA, USA.; School of Graduate Studies, Rutgers, The State University of New Jersey, Newark, NJ, USA.; Division of Infectious Disease, Department of Medicine, Rutgers New Jersey Medical School, Newark, NJ, USA.; Rutgers Cancer Institute, Newark, NJ, USA. [email protected].; Division of Cancer Biology, Department of Radiation Oncology, Rutgers New Jersey Medical School, Newark, NJ, USA. [email protected].; Rutgers Cancer Institute, Newark, NJ, USA. [email protected].; Division of Hematology/Oncology, Department of Medicine, Rutgers New Jersey Medical School, Newark, NJ, USA. [email protected].

DOI: 10.1038/s41598-024-69021-2

Link outs

Free resources

Full Text Sources:

Miscellaneous:

https://assays.cancer.gov/CPTAC-438

MeSH Terms: Artificial Intelligence, Models, Molecular, SARS-CoV-2, Humans, Coronavirus 3C Proteases, Protein Conformation, COVID-19, Amino Acids