(p. A15) So often the future shows up when you’re looking for something else. In 2013, DNA sequencing company Illumina bought Verinata Health and began offering noninvasive prenatal testing. Using a pregnant woman’s blood, a now-$500 DNA test can spot Down syndrome and other chromosomal conditions. Since then, the use of very invasive needle-to-the-womb amniocentesis testing has dropped.
But that’s not the story here. Of the first 100,000 women tested, 10 (or 0.01%) had unusual chromosome patterns. The fetus was fine, but in each case, the mother had cancer of differing types.
. . .
So Illumina spun out a new company named Grail in Menlo Park, Calif., to do what’s known as Circulating Cell-free Genome Atlas studies. Running DNA sequencing on regular blood samples, Grail generates hundreds of gigabytes of data per person—the well-known A-T-G-C nucleotides, but also the “methylation status,” or whether a particular DNA site’s function is turned on or off (technically, whether or not it represses gene transcription).
. . .
. . . , Grail’s chief medical officer Josh Ofman tells me, “cancer may show up as thousands of methylation changes, a much richer signal to teach machine learning algorithms to find cancer” vs. a single site. “There are 30 million methylation sites in the entire human genome on 100,000 DNA fragments. Grail looks at a million of them.” It takes industrial-grade artificial intelligence to find patterns in all this data, something a human eye would never see.
. . .
Grail is detecting the signature of actual cancer cells in your blood. According to validation data published in the Annals of Oncology, the test can find 50 different types, more than half of all known cancers.
. . .
Grail has raised almost $2 billion, including from Bill Gates and Jeff Bezos. Isn’t that interesting? Though much maligned as fat cats sitting on piles of gold coins and monopolists out to control the world, Messrs. Gates and Bezos are investing in technology—this is not philanthropy—that may save you or a relative’s life someday.
Innovation comes through surprises. This is a big one. And while worrywarts brood over artificial intelligence and robot overlords, early detection of cancer is really what machine learning is meant for. This is the Holy Grail.
For the full commentary, see:
(Note: ellipses added.)
(Note: the online version of the commentary has the date July 5, 2020, and has the same title as the print version.)