Researchers at the Institute of Cancer Research in London were able to harness artificial intelligence (AI) to recognize patterns in gene sequences and molecular data from breast cancer, which revealed 5 new types of the disease matched with different personalized treatments.
Although breast cancer tumors, known as luminal A tumors, have the best cure rates, patients within these groups respond differently to standard-of-care treatments, such as tamoxifen, or newer treatments, such as immunotherapy.
In a previous study, the researchers used AI to uncover 5 different types of bowel cancer. Oncologists are now evaluating their application in clinical trials in hopes of being to apply the AI algorithm to many types of cancer and to provide information for each about their sensitivity to treatment, likely paths of evolution, and how to combat drug resistance.
In order to do this, the researchers applied the AI-trained computer software to an array of data available on the genetics, molecular, and cellular make-up of primary luminal A breast tumors, along with data on patient survival.
Patients with an inflammatory cancer type had immune cells present in their tumors and high levels of the PD-L1 protein, which suggested that they would respond to immunotherapies, according to the current study. Another group of patients had triple-negative tumors, which do not respond to standard hormone treatments, but various indicators suggest they might respond to immunotherapy.
Additionally, patients with tumors that contained a specific change in chromosome 8 had worse survival than other groups treated with tamoxifen and tended to relapse much earlier—an average of 42 months compared with 83 months in patients who had a different tumor type that contained many stem cells. The study authors suggested that these patients may benefit from an additional or new treatment to delay or prevent late relapse.
The study authors noted that the markers identified did not challenge the overall classification of breast cancer but did reveal additional differences within the current sub-divisions of the disease, with important implications for treatment.
Pawan Poudel, Gift Nyamundanda, Yatish Patil, Maggie Chon U Cheang, Anguraj Sadanandam. Heterocellular gene signatures reveal luminal-A breast cancer heterogeneity and differential therapeutic responses. npj Breast Cancer, 2019; 5 (1) DOI: 10.1038/s41523-019-0116-8. https://www.nature.com/articles/s41523-019-0116-8. Accessed August 5, 2019.