Metastatic clear cell renal cell carcinoma is treated with therapies that target the tumor blood vessels and/or with immune checkpoint inhibitors (ICIs) that use the body's immune system to fight the cancer. However, none of these treatments uniformly benefit all patients and many patients suffer from lot of side effects from these drugs. Different drugs target different molecular pathways and benefit different groups of patients. We therefore need markers that can be used in the clinic and tell us if the patient will respond to one group of drugs or not (ICI or those that target blood vessels).

Recently, data from a clinical trial showed that a set of gene expression signature could predic...

Read More

Metastatic clear cell renal cell carcinoma is treated with therapies that target the tumor blood vessels and/or with immune checkpoint inhibitors (ICIs) that use the body's immune system to fight the cancer. However, none of these treatments uniformly benefit all patients and many patients suffer from lot of side effects from these drugs. Different drugs target different molecular pathways and benefit different groups of patients. We therefore need markers that can be used in the clinic and tell us if the patient will respond to one group of drugs or not (ICI or those that target blood vessels).

Recently, data from a clinical trial showed that a set of gene expression signature could predict if patients would be susceptible to drugs that target blood vessels or respond better to a combination drug regime that included ICI. These results have now been validated in an independent large clinical trial. However, similar to most prior studies that have tried to identify markers for respond to drug therapy rely on a small region of tumor. Because tumors vary from region to region most studies have failed to identify markers that can capture this variability.

In this proposal, we will use artificial intelligence and apply it to the digital images from routinely used tumor sections to predict the gene expression signature. This will allow us to evaluate the gene expression without the need for expensive and time-consuming studies like sequencing. We will evaluate the entire tumor to consider the tumor variability.

If successful, our efforts will lead to the first clinically applicable predictive biomarker in renal cell carcinoma. This will enable appropriate allocation of drugs to the patients who will show treatment benefit and not be given to those patients who will not benefit and thus minimize toxicity. This program could be applied to other cancers.

Read Less