How artificial intelligence and machine learning will help cancer patient care and vaccine design

Artificial intelligence / machine learning involves the development of computer systems that perform tasks that would normally require human intelligence. AI / ML is used by people every day, for example, when using smart home devices or digital voice assistants. The use of AI / ML is also growing rapidly in biomedical research and healthcare. In a recent Viewpoint article, researchers at the Rutgers Cancer Institute of New Jersey and Rutgers New Jersey Medical School (NJMS) explored how AI / ML will complement existing approaches focused on genome sequence information. protein, including the identification of mutations in human tumors.

Stephen K. Burley, MD, DPhil, and colleagues published the study Dec. 2 in the New England Journal of Medicine.

What is the potential of AI / MI in cancer research and clinical practice?

We anticipate that the most immediate applications of computed structure modeling will focus on point mutations detected in human tumors (germline or somatic). Calculated structural models of frequently mutated oncoproteins (e.g., epidermal growth factor receptor, EGFR, shown in Figure 2B of the article) are already being used to help identify genes responsible for cancer, enabling the discovery treatment, explain drug resistance and inform treatment plans.

What are the biggest challenges for AI / ML in healthcare?

In broad terms, the core challenges would likely include AI / ML research and development, technology validation, efficient / equitable deployment and cohesive integration into existing health systems, and issues inherent in the regulatory environment as well as the complex problems of reimbursement of medical care.

How will this technology impact vaccine design, especially with regard to SARS-CoV-2?

Going beyond knowledge of 3D structure through entire proteomes (parts lists for biology and biomedicine), precise computer modeling will allow analyzes of clinically significant genetic changes manifested in 3D by individual proteins. For example, the SARS-CoV-2 delta variant of the spike protein of concern carries 13 amino changes. The experimentally determined 3D structures of advanced SARS-CoV-2 protein variants bound to various antibodies, all freely available from the Protein Database, can be used with calculated structural models of the new Advanced protein variant of concern to understand the potential impact of other amino acid changes. In ongoing work (not yet published), we used AI / ML approaches to understand the structure-function relationship of the spike protein of concern from the omicron variant of SARS-CoV-2 (with over 30 changes in amino acids), illustrating the practical and immediate application of this emerging technology.

What’s the next step to better use AI / ML in cancer research?

Development and equitable dissemination of user-friendly tools that cancer biologists can use to understand the proteins of three-dimensional structures involved in human cancers and how somatic mutations affect structure and function leading to uncontrolled proliferation of tumor cells.

Provided by the Rutgers Cancer Institute of New Jersey