Moshir

AI for biology and health at Harvard Medical School | PhD in Statistical physics and Machine Learning @uniGoettingen

[Moshir @moshirbte]

Great to be at the 50th edition of the #MLSS in Tübingen, a week done, one to go. Lots of amazing lectures on causality, explainability in genAI & learning theory. Discussing ideas to explore causal learning for large-scale health data and foundation models. @bschoelkopf @MPI_IS

[Suhas Mahesh @suhasm]

New @techreview piece where @ericschmidt and I discuss why agents, not AlphaFold, are the likely template for the future of science (link follows)

[Moshir @moshirbte]

@tigerstatdoc Congratulations! Great work and great thread. On to read the detailed manuscript.

[Moshir @moshirbte]

Very tragic indeed. I remember our great brief conversation during my time at @embl as a young undergraduate which inspired me a lot.

[Steven Salzberg 💙💛 @StevenSalzberg1]

Very sad news: Peer Bork, a wonderful scientist, has long been one of the leaders of our field (genomics and bioinformatics) and he was far too young to be gone. https://t.co/oeaptUww96

[Debora Marks @deboramarks]

Announcing our new protein design server https://t.co/nHeMlJVba2:
• End-to-end protein design for everyone!
• Analyze your generated library interactively and on 3D structures
• Export codon-optimized DNA sequences for experimental testing.
Developed in collaboration between @deboramarks, @thomas_a_hopf, @SteineggerM, Simon d'Oelsnitz, Chris Sander, Artem Gazizov,@haysunny_hi, Milot Mirdita, Sergio Garcia Busto, Jake Reardon

[Moshir @moshirbte]

Scaling laws demonstrate scale invariant mechanisms which are as fundamental in biology as in physics. Wonder if we will discover more of these from the large amount of data-sets that we have been generating in biology for training AI algorithms.

[Peter Fedichev @fedichev]

As you know I'm obsessed with power laws in biology, which is a biological consequence of fundamental principles, like energy conservation from the first law of thermodynamics. Geoffrey West showed how highly optimized biological networks—think blood vessels or respiratory systems—lead to allometric scaling. Specifically, the energy production per unit of body mass (mass-specific metabolic rate) scales as body mass (M) to the power of -0.25. This is part of what's known as Kleiber's law (or as we've dubbed it in our research, the Kleiber-West law), where whole-body basal metabolic rate scales as M^{0.75}. It's why elephants burn energy more efficiently per gram than mice, but mice live fast and die young.

What's interesting, is that this same scaling pops up in something as everyday as sleep. Across mammals, daily sleep duration follows a similar power law: it decreases with body size as roughly M^{-0.25}. Smaller animals like shrews might snooze 15+ hours a day, while giants like whales get by on just a few.

This is a clue that sleep is deeply tied to metabolism. Nervous systems are energy hogs, guzzling up to 20% of our body's oxygen despite making up only 2% of our mass. In smaller creatures, those fractal-like distribution networks deliver more oxygen per cell, letting their brains run "hotter" with faster firing rates and higher energy demands. But this revved-up metabolism exhausts resources quicker, creating energy deficits that sleep likely evolved to fix. Essentially, tinier mammals burn through their neural fuel faster and need more downtime to replenish.

In this view, sleep isn't just rest—it's an ancient fix for the energy trade-offs imposed by Kleiber-West scaling, ensuring that high-metabolism critters don't fry their circuits. Sure, sleep does fancy stuff today. In humans and other mammals, it consolidates memories by pruning unnecessary synapses during REM phases and clears brain toxins via the glymphatic system, which ramps up during non-REM sleep to flush out waste like beta-amyloid.

The relation of sleep and metabolism may have evidence from evolutionary history. The emergence of anaerobic metabolism could be tied the Great oxygenation event, 2B years ago. The next oxidation event (Neoproterozoic Oxygenation Event , 750M years ago) set the stage for Cambrian explosion leading to emergence of neural systems across species. And we had never had enough oxygen ever since.

The link to a great Nature paper by @RafSarnataro et al, and some practical implication of that study are in the next comment. As usual, please like and repost - this is cool science (thank you @Alexey_Kadet for bringing this up)

1/2

[Moshir @moshirbte]

#GLP1 #Migraine #HealthInnovation #RepurposingDrugs #TranslationalResearch #ChronicPain #FutureOfMedicine

[Moshir @moshirbte]

Another surprising use for GLP-1 drugs?

This new, very preliminary study caught my attention: Liraglutide, typically used for diabetes and obesity, significantly reduced migraine days — without relying on weight loss.

It’s a striking example of how medications developed for one

[Moshir @moshirbte]

purpose can open doors in entirely different areas. GLP-1 applications just keep expanding.

A reminder that the boundaries of medicine are constantly shifting — and why cross-disciplinary research matters.

https://t.co/IO66Vf5g7S

[Ruben Weitzman @ruben_weitzman]

🚨ICML Paper Alert🚨
What if finding the right protein homologs wasn't a slow search, but a learned part of the model itself?
We introduce 𝐏𝐫𝐨𝐭𝐫𝐢𝐞𝐯𝐞𝐫, an end-to-end framework that learns to retrieve the most useful homologs for self-supervised reconstruction! (1/12)

[Moshir @moshirbte]

@SuryaGanguli @KempnerInst Missed it, do you have a recorded link ?

[Noor Youssef @nooryoussef03]

🚨 New in @ImmunityCP !
EVE-Vax, an AI model that anticipates future viral evolution and designs antigens to proactively test vaccines + therapeutics—before variants even emerge.
We envision this work will help make future-proofed vaccines and therapeutics.
👇 (1/7)

[Moshir @moshirbte]

@airindia flight from Zurich to Delhi got cancelled. Mismanagement here. No meals provided in the last 6 hours. No possibility of getting food here. No rebooking information provided. Need to reach Delhi ASAP. Please rebook on the first flight to Delhi.

[Moshir @moshirbte]

@willcb @MorganStanley Are you narrowly looking for ML/AI PhDs or Theoretical Physics (with some ML research exp) also welcome ?

[Moshir @moshirbte]

@MLSTjournal

[Moshir @moshirbte]

1/n 🚀 New paper out in @MacTjournal with @psollich at @uniGoettingen. 🧵👇[https://t.co/RDS0neFLDy]. Physics-inspired machine learning detects ‘unknown unknowns’ in networks. TL:DR

#MachineLearning #NetworkScience #PhysicsInspiredAI #Research #TimeSeries #EGFR #AI

[Moshir @moshirbte]

10/n Read here: [https://t.co/RDS0neFLDy]

[Moshir @moshirbte]

9/n Want to dive deeper? The paper includes open-access materials and code to explore the method further. Let’s push the boundaries of network science together.