//
sign in
Profile
by @danabra.mov
Profile
by @dansshadow.bsky.social
Profile
by @jimpick.com
AviHandle
by @danabra.mov
AviHandle
by @dansshadow.bsky.social
AviHandle
by @katherine.computer
EventsList
by @katherine.computer
ProfileHeader
by @dansshadow.bsky.social
ProfileHeader
by @danabra.mov
ProfileMedia
by @danabra.mov
ProfilePlays
by @danabra.mov
ProfilePosts
by @danabra.mov
ProfilePosts
by @dansshadow.bsky.social
ProfileReplies
by @danabra.mov
Record
by @atsui.org
Skircle
by @danabra.mov
StreamPlacePlaylist
by @katherine.computer
+ new component
ProfilePosts









Loading...
Excited to share our new paper in @JNCI_Now! We integrated GWAS data from 11 solid cancers with ~1,500 cell type annotations to pinpoint WHERE in the body cancer risk variants actually act. A thread ๐Ÿ‘‡ @peter-kraft.bsky.social
๐Ÿ“ฃ ๐–๐žโ€™๐ซ๐ž ๐ก๐ข๐ซ๐ข๐ง๐  ๐š ๐ฉ๐จ๐ฌ๐ญ๐๐จ๐œ ๐ข๐ง ๐ฉ๐จ๐ฉ๐ฎ๐ฅ๐š๐ญ๐ข๐จ๐ง & ๐ฌ๐ญ๐š๐ญ๐ข๐ฌ๐ญ๐ข๐œ๐š๐ฅ ๐ ๐ž๐ง๐ž๐ญ๐ข๐œ๐ฌ! ๐ŸŒ๐Ÿ“ˆ๐Ÿงฌ If youโ€™re finishing a PhD (or know someone who is) and want to work on complex trait biology + ๐‘Ÿ๐‘’๐‘Ž๐‘™-๐‘ค๐‘œ๐‘Ÿ๐‘™๐‘‘ ๐‘–๐‘š๐‘๐‘Ž๐‘๐‘ก, read on ๐Ÿ‘‡
โ€œ[G]enerative models generate numbers which are thought to represent real possibilites in the world. It is very tempting to change model inputs and then look at the result. A safe way to describe this is โ€˜in silico perturbationโ€™, but many use the word โ€˜counterfactual.โ€™ This is very dangerous.โ€
(Quotes lightly edited for space. Any errors on me. Do read the original post.)
โ€œMany valid, tested, robust, and clearly generalisable generative models will not correspond to the real world if you do this in silico perturbation. The presence of a robust and generalisable association model absolutely does not mean that interventions can be modeled.โ€
Kodama: genotype compression and matrix multiplication leveraging genetic relatedness www.biorxiv.org/content/10.6...
(Even โ€˜in silico perturbationโ€™ might be too strong. Maybe simply โ€˜simulationโ€™? Generative models capture more complexity [tuned to training data] than your typical biostats simulation [โ€˜now weโ€™re really going to get fancy and throw in 2nd order interactionsโ€™], but theyโ€™re still simulacra.)