GRAIL

GRAIL aims to develop a blood test to detect cancer early before symptoms appear, when it can be cured. To achieve this, the company will build intelligent models to surface clinically actionable insights from vast amounts of tumor genome data obtained through high-intensity sequencing (ultra-broad and ultra-deep sequencing). GRAIL is deploying, at scale, the latest tools of data science, including powerful approaches from machine learning such as hierarchical neural networks. Its intends to apply such methods to the ultimate problem of classifying patients according to the presence, type, and severity of cancer, and in all steps of our data-generating pipeline.