Research ResourceCancer

A machine learning approach for somatic mutation discovery

See allHide authors and affiliations

Science Translational Medicine  05 Sep 2018:
Vol. 10, Issue 457, eaar7939
DOI: 10.1126/scitranslmed.aar7939

Calling it like the algorithm sees it

Somatic mutation calling is essential for the proper diagnosis and treatment of most cancer patients. Wood et al. developed a machine learning approach called Cerebro that increased the accuracy of calling validated somatic mutations in tumor samples from cancer patients. Cerebro outperformed six other mutation detection methods by better distinguishing technical sequencing artifacts. An analysis of non–small cell lung cancer and melanoma patient samples revealed that Cerebro more accurately classified patients according to their immunotherapy response, suggesting that the authors’ mutation calling approach could favorably affect patient care.

View Full Text

Stay Connected to Science Translational Medicine