A new AI model called COMPASS uses tumour gene expression data to predict which patients will respond to cancer immunotherapy drugs immune checkpoint inhibitors.
Cancer immunotherapy drugs known as immune checkpoint inhibitors (ICIs) can be miracle drugs for cancer patients, curing some and turning deadly disease into a manageable chronic condition in others. But these drugs work for only a subset of patients, with few indications why - a knowledge gap that has detrimental effects on patient prognosis, clinical trial recruitment, and research that could lead to new therapies.
A new artificial intelligence model called COMPASS, developed by Harvard Medical School (pictured) researchers and their colleagues and detailed in a recently published paper in Nature Medicine, improves prediction of which patients are most likely to respond to ICIs. Using data from patients treated in the past, the model outperformed the best existing approaches by 8.5%. It makes its predictions based on patients’ tumour gene activity and provides a rationale for its output.
If these results are validated in a future clinical trial, COMPASS could lead to better personalised medicine for cancer patients, more efficient trial enrolment for new therapies, and new drug targets for researchers to explore.
“ICIs are an exciting therapeutic modality that has transformed cancer treatment over the past decade by engaging the immune system to fight cancer cells and destroy them. By leveraging cutting-edge AI capabilities, we can identify who would be most likely to respond to a particular ICI before that patient receives the drug,” said study senior author Marinka Zitnik, Associate Professor of Biomedical Informatics in the Blavatnik Institute at Harvard Medical School.
ICIs target proteins on the surface of tumour cells or T cells, including PD-L1, PD-1, and CTLA-4. These proteins can act as an invisibility cloak, shielding cancer cells from immune attack. ICIs disrupt this interaction, reopening cancer cells to being recognised and destroyed by the immune system.
For some patients with specific cancer types, ICIs have extended survival far beyond what was considered possible in the past. However, clinical trials have shown that only 10 - 40% of patients find success with ICIs, depending on their cancer type. Nonresponders not only risk sometimes serious side effects but also waste time receiving noneffective treatment while their cancers progress.
Some machine learning approaches and biomarkers have been used to help predict which patients are most likely to respond to ICIs. For example, response has been associated with an immune-inflamed tumour microenvironment - marked by tumour infiltration of immune cells - while nonresponders’ tumours are often so-called immune deserts. But a significant number of patients respond to these drugs in unexpected ways, negatively impacting the reliability of these predictions.
“Understanding who will respond to ICIs is not a minor knowledge gap,” said Zitnik, who is also associate faculty at the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University. “It is one of the central unsolved problems in oncology.”
Zitnik and her colleagues developed COMPASS to help solve this problem. The model makes ICI response predictions by analysing the activity of nearly 16,000 genes with known roles in immune cell states, tumour-microenvironment interaction, and signalling pathways.
COMPASS was designed with what’s known as concept bottleneck transformer architecture: Rather than spitting out black-box predictions with no explanation, it provides human-interpretable results, delivering rationale for its outputs.
The researchers trained COMPASS using data from 10,184 tumours across 33 cancer types derived from the Cancer Genome Atlas, a public database containing genetic sequence and molecular data from primary cancer and matched normal samples. With this data, the AI program ‘learned’ what gene activity correlated with responders and nonresponders to different types of ICIs.
The team then fine-tuned this training using the results from 16 clinical trials that tested the effects of different ICI regimens on seven cancer types. To evaluate the model’s success, they removed individual clinical trials from this fine-tuning one by one and asked COMPASS to predict ICI responders and nonresponders in the missing trial.
Their results showed that COMPASS outperformed the best existing approach for predicting ICI response by nearly 10% on average. This boost in accuracy held true under a variety of conditions, including for different cancer types, ICI drugs, gene transcript sequencing platforms, and biopsy sites.
Because the results were interpretable, the team could explain unexpected results among ICI response outliers. For example, the gene expression of some nonresponders with immune-inflamed tumours correlated with processes that impeded immune response. Conversely, the gene expression signatures of responders with immune-desert tumours often suggested biological processes that encouraged other types of immune activity.
- Shen W, Moon I, Nguyen TH, et al. Generalizable AI predicts immunotherapy outcomes across cancers and treatments. Nat Med. Published online July 3, 2026. doi:10.1038/s41591-026-04502-7