AI Makes Inroads In Treating Cancer

"Biomedical startups are using artificial intelligence to predict the response patients will have to cancer treatments, aiming to increase the success of drugs in clinical trials and tailor therapies to individuals.

As data accumulate from clinical trials and fields such as gene and protein research, AI is helping scientists sift through large volumes of information to uncover signatures that correlate with response -- or resistance -- to treatment. Startups are using it to predict which drugs are likely to work in clinical studies and create tests to help doctors choose treatments.

Venture firms are banking on the expertise of founders -- and their ability to get access to the data needed to develop highly predictive tests. 

Several companies have raised significant funding, including Artera, which disclosed $90 million in venture funding in March; Vivodyne, which launched with $38 million in November, and Enable Medicine, which revealed a $60 million financing last year.

Artera, better known as ArteraAI, in September 2022 launched a test designed to aid treatment decisions for prostate-cancer patients. To train its algorithms, the company used clinical-trial data for tens of thousands of patients across dozens of solid tumors, including prostate cancer, said co-founder and Chief Executive Andre Esteva.

ArteraAI's test is performed on digitized pathology slides, which are made from a biopsy of the patient's tumor. Using this information, and clinical variables such as the patient's age and levels of the protein prostate-specific antigen, ArteraAI provides prognostic information, for instance, on the likelihood the disease will spread or might return later, as well as predictive information on treatments likely to be effective, said Esteva.

The list price for the test is $3,873 and out-of-pocket costs depend on the patient's insurance, according to the company, which intends to launch additional tests for other cancers, Esteva said.

Tel Aviv-based Pangea Biomed is partnering with drugmakers seeking help with questions such as which cancers to target with treatments in clinical trials, according to CEO Tuvik Beker.

Targeted cancer drugs are designed to treat patients with a specific gene mutation. Patients are tested for these mutations to determine whether they are likely to benefit. But this testing doesn't tell the whole story, Beker said.

Many other genes are also involved in a patient's response, he said. Pangea, which has raised $12 million in venture capital, examines interaction patterns of many other related genes to predict if a drug will work or not. While its revenue now comes from partnerships with pharmaceutical companies, Pangea eventually aims to make its technology available to clinicians to aid treatment decisions for patients, Beker said.

Menlo Park, Calif.-based Enable Medicine, which uses AI to generate insights in biology and medicine, recently analyzed RNA sequencing and other data to identify features associated with response to a form of cancer immunotherapy, known as checkpoint inhibition. People who didn't respond to the treatment had increased interaction between immune cells known as CD68+ macrophages and CD8+ T cells, according to the company.

Armed with this information, researchers can explore questions such as why these interactions correlate with a lack of response and what might be done to reverse that, CEO Sunil Bodapati said." [1]

1.  AI Makes Inroads In Treating Cancer. Gormley, Brian.  Wall Street Journal, Eastern edition; New York, N.Y.. 29 Dec 2023: B.4.