Jordan Cahoon retweeted
Labor of love here, more than a year in the making 👇
Jordan Cahoon retweeted
🚨 Introducing the SAIL Therapeutic Actionability AI Challenge! 🚨
Patients with rare genetic diseases (~450M worldwide!) often face decades-long journeys to find therapies. Less than 10% of rare diseases have an FDA approved therapeutic. We believe AI can transform this experience.
We're launching the SAIL Therapeutic Actionability AI Challenge, which asks teams to build AI that turns a genetic diagnosis into a report of actionable treatment options.
@SAILhealth @GoogleAI @NEJM_AI @huggingface 1/4
Jordan Cahoon retweeted
🚨Introducing the SAIL Therapeutic Actionability AI Challenge🚨
~450M people have a rare disease, often facing decades-long journeys to find therapies. <10% of rare diseases have an FDA-approved one.
We think AI can help close this gap.
Submit your model by Jan 5.
Details 👇
Jordan Cahoon retweeted
[1/5] Our paper “Clinically Grounded Privacy Evaluation of Medical LMs” received the Social Impact Award at #EMNLP2026! 🎉
We probe LMs trained on patient notes with realistic adversary knowledge & measure leakage that has real-world consequences and is attributable to training.
1/ As LLMs are integrated into our health systems, how can we efficiently evaluate whether evolving systems can reliably retrieve the information clinicians need?
Excited to share our new preprint: A Living Benchmark for Information Retrieval from Electronic Health Records.
8/ Interested in using BRIE and exploring the corpus? We will release BRIE, the accompanying de-identified clinical notes spanning patients’ care, clinician annotations, and model responses. Stay tuned!
1
2
303
9/ This was truly a team effort across collaborators. Huge thanks to my amazing advisor @Emily_Alsentzer, @drnigam , @jasonafries, @clssfr, @davidjhwu, @atfisherMD, @salonikumarmd, @KameronBlack633, @bridgetilin12, @lucyyin78, @JamJX, and more!
Preprint: arxiv.org/abs/2609.30205
Jordan Cahoon retweeted
📢New from @itscahoon @CharlestonCWKC & co
📰Imputation accuracy across global human populations
cell.com/ajhg/abstract/S0002…
Jordan Cahoon retweeted
🎉Congratulations @CharlestonCWKC
📰Inverted genomic regions between reference genome builds in humans impact imputation accuracy and decrease the power of association testing
#ASHG23
cell.com/hgg-advances/fullte…
Jordan Cahoon retweeted
🎉We are THRILLED to recognize & celebrate this year's winners of the @HGGAdvances Award for Outstanding Early Career Publication: @genetisaur & @CharlestonCWKC #ASHG23
Jordan Cahoon retweeted
In case you need some weekend reading, very proud of the new preprint from our group, Spearheaded by the superb recent PhD, Caoqi Fan, on leveraging the genealogical trees to better infer the demographic histories of human populations!
biorxiv.org/content/10.1101/…
Jordan Cahoon retweeted
Our paper on estimating the expected number of African and European genealogical ancestors for a typical African American (born btwn 1960-1965) is out in this month's issue of GENETICS. Stay tuned for a thread and a series of excellent write-ups from GENETICS, USC, and Stanford.
The July GENETICS cover image of a double-helix drill bit forged in 1820 by enslaved blacksmith Solomon Williams accompanies a study from J.A. Mooney et al. on the genetic and genealogical history of African Americans from the 17th century to the 1960s. academic.oup.com/genetics/ar…

ALT The July GENETICS cover image of a double-helix drill bit forged in 1820 by enslaved blacksmith Solomon Williams accompanies a study from J.A. Mooney et al. on the genetic and genealogical history of African Americans from the 17th century to the 1960s. The artifact is on loan from the National Park Service, Cane River Creole National Historical Park; photo courtesy of Smithsonian National Museum of African American History and Culture.
Jordan Cahoon retweeted
Imputation Efficacy Across Global Human Populations biorxiv.org/content/10.1101/…
I am excited to share my first pre-print as part of my research in @CharlestonCWKC’s lab. Interested in learning about which populations impute well with the TOPMed reference panel? Read the🧵
biorxiv.org/content/10.1101/…
The bottom line: we must sequence more underrepresented individuals to increase inclusivity in GWAS.🌎
1
1
227
Huge thanks to my co-authors @camellia_rui, Echo Tang, Chris Simmons, Jalen Langie, @imyingchulo, and @chen_cmh! 🙌This work could not have been done without their tremendous help!
Welcoming any and all feedback on our work!
biorxiv.org/content/10.1101/…
2
247
















