babak-a.bsky.social
Chief Scientist at @exai.bio — I use computational biology, machine learning and large-scale datasets to improve human health
62 posts
1,077 followers
309 following
Prolific Poster
Conversation Starter
comment in response to
post
These are the phenotypes they claim to screen:
comment in response to
post
I developed accurate polygenic risk scores at 23andMe using its huge database and can attest to their limitations, I see this craze stemming from a deep ignorance about this topic.
@lpachter.bsky.social wrote an amazing piece on this back in 2021: liorpachter.wordpress.com/2021/04/12/t...
comment in response to
post
Pseudo-scientific charlatanism at its worst.
comment in response to
post
@erictopol.bsky.social definitely interesting and exciting! But could it be that the recovering patients who had the energy and the "want" to exercise were bound to have a better prognosis?
comment in response to
post
We’ve developed an accurate, fully automated, low-cost assay that requires only a small volume of blood and leverages RNA molecules and AI to push the boundaries of cancer diagnosis and care even further.
Congratulations to the amazing @exai.bio exonauts!
comment in response to
post
I highly recommend reading Hani's thread (linked above) for insights into our thought process and a high-level overview of the model.
comment in response to
post
How so? Other than 'reactiveness,' what stands out to you?
comment in response to
post
I am so sorry for your loss. It is truly heartbreaking.
comment in response to
post
How about iron deficiency @erictopol.bsky.social? I know people around me that had to go back to read meat due to severe anemia, females in particular.
comment in response to
post
Eric, JCI link is broken.
comment in response to
post
I think work emails can be guessed much more easily than personal emails: {first initial}{last name}@company.com and the like. I have added all variants as an alias and it is funny sometimes I receive multiple emails from the same person.