Respiratory physician from Australia working in Cambridge with interests in pulmonary infection, bronchiectasis and lung transplant. Wannabe Data Scientist.
Can bacteria save out planet? They metabolise plastic, break down oil slicks, thrive in boiling acid, and outwit our strongest antibiotics. And there are 10^30 of them to help.
All we need is to learn to talk to them: A new LLM speaks their language!
💥 Excited to introduce Bacformer 🦠 - the first foundation model for bacterial genomics. Bacformer represents genomes as sequences of ordered proteins, learning the “grammar” of how genes are arranged, interact and evolve.
Preprint 📝: https://t.co/NmxA68rLqC
🧵 1/n
💥 Excited to introduce Bacformer 🦠 - the first foundation model for bacterial genomics. Bacformer represents genomes as sequences of ordered proteins, learning the “grammar” of how genes are arranged, interact and evolve.
Preprint 📝: https://t.co/NmxA68rLqC
🧵 1/n
@ThoraxBMJ@DavidT_Arnold Such basic and critical information. That,
In 2024, we treat pleural infections, abscess and pneumonia without information on antibiotic concentrations in the relevant space is embarrassing to our field and an academic scandal.
Thank you for the work!
NEWS
Bronx medical school, the Albert Einstein College of Medicine, is now tuition-free thanks to a $1 billion gift from Dr. Ruth Gottesman, a former professor.
Gottesman, whose late husband was an early investor with Warren Buffett, has made it a condition of the gift that the college NOT change its name—an unusual requirement in a world where much smaller gifts often come with the requirement that the colleges be named after the donor.
Most students at the Einstein College of Medicine graduate with $200,000 in debt; they will now be free of that burden.
https://t.co/SOekmWV8d4
We need a language to describe clinically important effects. The p-value tells us how certain we can be of the result, NOT the 'signficance'.
⚡️ “Statistical significance must go” by @_MiguelHernan
https://t.co/4DVPdpPnoW ⚡️ “Statistical significance must go” @_MiguelHernan
Pragmatic trials are designed to help patients and doctors make better decisions. Exclusive reliance on intention-to-treat defeats that purpose.
So we’re crowdsourcing guidelines for #causalinference from pragmatic trials.
Join us at👉🏼https://t.co/Eck3bQ0R2z
@_MiguelHernan
@jordy_bc@EpiEllie Jordy, I'm about to start a PhD in Toronto in epidemiology of Lung Transplant. Do you know anyone at UToronto who works on causal inference?