With greater than 200 forms of cancer and each cancer individually unique, ongoing efforts to develop precision oncology treatments remain daunting. Most of the main focus has been on developing genetic sequencing assays or analyses to discover mutations in cancer driver genes, then attempting to match treatments that may match against those mutations.
But many, if not most, cancer patients don’t profit from these early targeted therapies. In a brand new study published on April 18, 2024, within the journal Nature Cancer, first writer Sanju Sinha, Ph.D., assistant professor within the Cancer Molecular Therapeutics Program at Sanford Burnham Prebys, with senior authors Eytan Ruppin, M.D., Ph.D., and Alejandro Schaffer, Ph.D., on the National Cancer Institute, a part of the National Institutes of Health (NIH) — and colleagues — describe a first-of-its-kind computational pipeline to systematically predict patient response to cancer drugs at single-cell resolution.
Dubbed PERsonalized Single-Cell Expression-Based Planning for Treatments in Oncology, or PERCEPTION, the brand new artificial intelligence-based approach dives deeper into the utility of transcriptomics — the study of transcription aspects, the messenger RNA molecules expressed by genes that carry and convert DNA information into motion.
“A tumor is a fancy and evolving beast. Using single-cell resolution can allow us to tackle each of those challenges,” says Sinha. “PERCEPTION allows for the usage of wealthy information inside single-cell omics to grasp the clonal architecture of the tumor and monitor the emergence of resistance.” (In biology, omics refers back to the sum of constituents inside a cell.)
Sinha says, “The power to observe the emergence of resistance is essentially the most exciting part for me. It has the potential to permit us to adapt to the evolution of cancer cells and even modify our treatment strategy.”
Sinha and colleagues used transfer learning — a branch of AI — to construct PERCEPTION.
“Limited single-cell data from clinics was our biggest challenge. An AI model needs large amounts of knowledge to grasp a disease, not unlike how ChatGPT needs huge amounts of text data scraped from the web.”
PERCEPTION uses published bulk-gene expression from tumors to pre-train its models. Then, single-cell data from cell lines and patients, though limited, was used to tune the models.
PERCEPTION was successfully validated by predicting the response to monotherapy and combination treatment in three independent, recently published clinical trials for multiple myeloma, breast and lung cancer.
In each case, PERCEPTION accurately stratified patients into responder and non-responder categories. In lung cancer, it even captured the event of drug resistance because the disease progressed, a notable discovery with great potential.
Sinha says that PERCEPTION just isn’t ready for clinics, however the approach shows that single-cell information will be used to guide treatment. He hopes to encourage the adoption of this technology in clinics to generate more data, which will be used to further develop and refine the technology for clinical use.
“The standard of the prediction rises with the standard and quantity of the information serving as its foundation,” says Sinha. “Our goal is to create a clinical tool that may predict the treatment response of individual cancer patients in a scientific, data-driven manner. We hope these findings spur more data and more such studies, sooner somewhat than later.”
Additional authors on the study include Rahulsimham Vegesna, Sumit Mukherjee, Ashwin V. Kammula, Saugato Rahman Dhruba, Nishanth Ulhas Nair, Peng Jiang, Alejandro Schäffer, Kenneth D. Aldape and Eytan Ruppin, National Cancer Institute (NCI); Wei Wu, Lucas Kerr, Collin M. Blakely and Trever G. Biovona, University of California, San Francisco; Mathew G. Jones and Nir Yosef, University of California, Berkeley; Oleg Stroganov and Ivan Grishagin, Rancho BioSciences; Craig J. Thomas, National Institutes of Health; and Cyril H. Benes, Harvard University.
This research was supported partially by the Intramural Research Program of the NIH; NCI; and NIH grants R01CA231300, R01CA204302, R01CA211052, R01CA169338 and U54CA224081.
