Early detection
up close

Reliable detection of cancer at earlier stages has the potential to decrease global cancer mortality and suffering.

The GRAIL approach

GRAIL is poised to detect cancer early by combining high-intensity sequencing of unprecedented breadth and depth with the techniques of modern data science. Through what we believe to be one of the largest clinical study programs ever pursued in genomic medicine, GRAIL is creating vast datasets to develop evidence supporting our products.

Seeking cancer signals in the blood

An increasing body of evidence suggests tumors release cell-free nucleic acids (cfNAs) into the bloodstream. cfNAs are small fragments of DNA and RNA, and reflect the genomic features of the tumor from which they originated. cfNAs are thought to be a direct measure of cancer and can be detectable in the bloodstream of people with cancer, potentially even before symptoms present.

The breadth of cancer’s complexity

Our understanding of cancer has been greatly enhanced through Initiatives elucidating the genomic and molecular biology of tumors. The Cancer Genome Atlas (TCGA)1 project, for example, has established that cancers are extremely heterogeneous.

The complexity of tumors suggests that measurements that capture the breadth of the heterogeneous cancer genome represent the most comprehensive and direct signature of disease biology. GRAIL’s unique ability to sequence broadly across the genome allows us to discover the millions of unique patterns that define cancer.

Because cfNAs are a more direct measure of cancer, and represent the genomic diversity of cancer throughout the body, cfNA-based tests have the potential to be highly specific and sensitive for early cancer detection.

1. https://cancergenome.nih.gov/

Separating the signal from the noise

The fraction of tumor-derived cfNA in the bloodstream compared to cfNA from non-cancerous cells is very small, necessitating the ability to distinguish faint signals of early tumors from an overwhelming background of genomic material.

GRAIL is using the latest data science tools to query cfNAs at depth and detect cancer signals.

We feed our large clinical and sequencing data sets into our bioinformatics and machine learning algorithms to distinguish with high accuracy the true invasive cancer signals from a sea of background biological noise.

The scale of GRAIL’s
data set

From the laboratory to the clinic, GRAIL aims to produce the highest-quality data and transform it into actionable information for healthcare providers. Our high-intensity sequencing assays and population-scale clinical studies seek to create datasets of significant scale in modern clinical medicine.

We are deploying the latest tools of data science, including powerful approaches from machine learning such as neural networks. We intend to apply such methods to the unmet clinical problem of classifying individuals according to the presence and type of cancer.

Our commitment to scientific rigor

GRAIL is committed to developing a deep understanding of cancer biology. We are building an atlas characterizing the landscape of cell-free nucleic acids in thousands of individuals with and without cancer that will help validate our early detection products.

We are generating scientific and clinical evidence through clinical studies enrolling tens of thousands of participants in what we believe are some of the largest cancer-related studies to date.