Predicting cancer drug combinations with AI test

Predicting cancer drug combinations with AI test
© iStock/apomares

Scientists have created a prototype test that can predict which cancer drug combinations are likely to work for patients in less than two days.

The innovative development utilises Artificial Intelligence (AI) to analyse large-scale protein data from tumour samples and is capable of predicting patients’ responses to cancer drug combinations more accurately than what is currently possible.

Genetic analysis of tumours can reveal mutations that are fuelling cancer growth, but genomics alone does not provide sufficiently accurate predictions to select cancer drug combinations.

The research team was led by a National Institute for Health Research (NIHR) Professor and was conducted at The Institute of Cancer Research (ICR) in London. The study has been published in the journal Molecular Cancer Therapeutics and was funded by NIHR, Wellcome, Cancer Research UK, and ICR.

Predicting the response of cancer drug combinations

The team conducted ‘proteomic’ analyses; this examines the changes in 52 important proteins and how they interact with each other in response to cancer drug treatments. Researchers trained machine learning algorithms to define the key protein changes that predict cancer drug responses.

The algorithm was utilised to predict how sensitive cells were to individual cancer drugs. The AI technology could predict individual cancer drug responses more accurately than genetic features, such as mutations in key genes EGFR, KRAS, and PIK3CA – these are the three genetic markers currently employed clinically to predict drug responses in lung cancer.

Researchers examined this approach further to predict sensitivity to cancer drug combinations – utilising 21 different, two-drug combinations in lung cancer cells with different gene faults, such as mutations in EGFR and KRAS.

Personalised predictions for cancer patients

Of the 252 total cancer drug combinations, 128 showed a level of synergy, meaning their combined effect exceeded the effect of each individual drug added together. The AI test correctly identified the top five ranked combinations 57% of the time and the top 10 ranked combinations 83% of the time.

Furthermore, the test successfully identified cancer drug combinations that previously showed promise and uncovered new possible combinations, such as vemurafenib and capivasertib; the test discovered a potentially effective combination for non-small cell lung cancer cell lines with no mutations in EGFR or KRAS.

This is the first prototype test that has the potential to offer personalised predictions of cancer drug combinations that are likely to work for different individuals. Researchers at the ICR believe the novel technology could be crucial in overcoming cancer evolution and treatment resistance, by allowing doctors to analyse how drugs work when combined.

Udai Banerji, study lead, NIHR Research Professor, Professor of Molecular Cancer Pharmacology at ICR, and Consultant Medical Oncologist at The Royal Marsden NHS Foundation Trust said: “Our test provides proof of concept for using AI to analyse changes in the way information flows within cancer cells and makes predictions about how tumours are likely to respond to combinations of drugs.

“With a rapid turnaround time of less than two days, the test has the potential to guide doctors in their judgements on which treatments are most likely to benefit individual cancer patients. It is an important step to move forward from our current focus on using genetic mutations to predict response.

“Our findings show that our innovative approach is feasible and makes more accurate predictions than genetic analysis for patients with non-small cell lung cancer. Before this test can enter the clinic and guide personalised treatment, we will need to further validate our findings – for example, by carrying out a study where we run the test in patients already getting a treatment to check if the predictions are correct.”

Subscribe to our newsletter


Please enter your comment!
Please enter your name here