Research Projects

At CCG, we believe that expanding clinical and genomic data has the potential to enable oncologists to make smarter decisions about which drug to use in which circumstance. To power our analytics, we carry out research at the cutting edge of machine learning and cancer genomics to power our precision oncology software.

SomaticNET

Neural network evaluation of tumor variants

Differences in our DNA underlie many aspects of human health; from rare genetic diseases to cancer. In this project, we build a new class of software for detecting DNA variants. Based on the same principles behind facial recognition, our technique can identify cancer variants with unparalleled accuracy. We hope that releasing this software for non-commercial use will lead to more successful targeted therapy and personalized cancer medicine.

PRIOR

Predicting Incidence of Relapse

Despite recent advances in the field of cancer therapy, first line treatments still fail for two out of three cancer patients. In this study, we show development of an open source tool to allow machine learning researchers to work on cancer genomic datasets. We use this tool to predict how effective treatment will be, with accuracies of >80%.