AI Engineer, Patent owner of Artificial Intelligence-assisted methodology for Medical Discovery. Tweets are mine/not medical advice or endorsements.
Joined May 2009
- Tweets2.4K
- Following3K
- Followers5K
- Likes3.7K
Pinned Tweet
1) Using a state-of-the art #AI committee (=multiple reasoning #AI engines investigating the same problem) we have two new #MECFS and #LongCOVID research targets being confirmed : a) Phosphoinositide-controlled membrane identity b) The role of RAB Proteins and prenylation.
Efthymios Kalafatis retweeted
I just spoke to an 8th-semester medical student.
Not a SINGLE class on ME/CFS.
A neurological disease affecting potentially 70 MILLION people worldwide, yet future doctors aren’t even taught about it.
This isn’t just an educational gap. It’s a medical scandal.
1/ Based on research proposals listed by @weandmecfs in collaboration with @s4me_info forum, I performed a ranking based on a #AI framework reasoning consisting of multiple #AI engines. This, I believe will be the future of research proposal evaluation, along with humans
3/ Unfortunately, @s4me_info forum does not allow posting #AI content related to #MECFS. My opinion as a patient / researcher : This is a very unfortunate decision. The truly groundbreaking aspect (quoting @cstroeckw) below would be allowing #AI to help us as well.
4/ So someone with an expertise in #AI to research #MECFS cannot contribute to @s4me_info along with other patients because of this limitation at the time of writing. I would be very interested to hear @weandmecfs foundation's opinion on this and hopefully more patient opinions.
1/ My father had to be rushed to the hospital 3 days ago because of pain in the stomach. 86 years old, he is a real fighter, doing better now (Thank God). He was found to have cholecystitis because of a 2cm gallstone. Two points to say regarding #MECFS :
5/ 2nd point : Ι am 57 years old. I had to rush to the hospital without any help. I had to run to see the doctors, do the paperwork, wait for hours for several tests to take place. Then, get on with my work, do errands non stop until late night. 2 days, 10 hours of sleep in total
Efthymios Kalafatis retweeted
BREAKING: The U.S. government, Google, Meta & Zuckerberg-backed @biohub are launching a $1.8B push to build the data layer for AI biology.
The goal is to create the largest open, AI-ready biological dataset ever assembled, giving models the data needed to better predict how biology works & ultimately help treat disease.
The coalition is massive:
› Biohub committed $500M
› DOE is investing $500M+ across measurement, modeling & compute
› NIH is bringing $500M+ of federally funded datasets & repositories
› Meta, Google DeepMind & @IsomorphicLabs are jointly investing another $300M
This is effectively an infrastructure buildout for AI biology.
Instead of just building bigger models, they’re attacking one of the biggest bottlenecks in biology AI today, generating standardized, high-quality biological data at massive scale & making it openly available to researchers.
$1.8B committed to turning biology into something AI can increasingly model, predict & engineer.
1/ I have been working on understanding better the reasoning abilities of several LLMs independently and when working in tandem.. I think that our knowledge for #MECFS will progress at unprecedented rates. I also wonder whether we could investigate further the recovery stories..
2/ of patients. Do we have an estimate on how many people recovered from #LongCOVID or #MECFS ? @ahandvanish do we have relevant info (regarding #LongCOVID) on this ? Having data from this cohort could significantly help us accelerate our research in my opinion.
Efthymios Kalafatis retweeted
Support link is artizen.fund/index/p/open-po…
Project link is pots.erinmagennis.com
1/ We have a new research target been confirmed from previous analyses on #MECFS using #machinelearning and #networkanalysis methods named PGC-1α / PPARGC1A (see below - arrow). It was identified in 2017, as shown below. All annotations via circles show confirmations so far :
4/ The study by Hunter et . al could be -in my opinion- groundbreaking because of the 3D chromatin method it uses. PGC-1a is a master metabolic regulator and its downregulation leads to impaired mitochondrial quality control, low OXPHOS, impaired Fatty Acid Oxidation capacity
5/ Here is a list of the previously identified concepts. Using a computational approach to research #MECFS could have advanced our understanding in key areas by a median of 7 years earlier :
