
La 100cia no se hace, hay que hacerla. En mi caso, la hago en el @IBMB_CSIC. https://xitter.gq/t.co/KvnbcIy8ty
Joined September 2019
- Tweets220
- Following75
- Followers13
- Likes662
Supposing we get all this treatments next year, can you explain how to perform the massive amounts of pre-clinical and clinical tests required in less than 10 years?
You are already throwing massive amounts of money in "only" to reach in vitro success, mate.
Anthropic CEO predicts cancer, Alzheimer's, heart disease, mental illness will be cured in less than 10 years
ACCELERATE
5
Pregunta seria:
¿Cómo haces humor con un público seleccionadamente hostil que va a responder con un silencio sepulcral a cualquier chiste que intentes?
Me sabe mal por Broncano porque lo digo desde los inicios de La Vida Moderna, pero es la mayor cagada de toda su carrera. Con lo fácil que habría sido usar el humor, no tocar apenas temas y ventilarselo en 30-40 minutos, se ha querido hacer hora y media de entrevista-debate.
10
There’s a really pronounced divide between people who are on the AI side of things and people who are on the biology side of things. Even among people working in AI, the divide persists based on where they’re focused.
The AI side, adherents of scaling laws and the bitter lesson, believe that AI getting better means AI being more capable of novel discoveries in medicine (that go beyond discovering new drugs in well understood targets or speeding up dry lab work etc).
The biology people think the idea of a bitter lesson in biology is kind of ridiculous and that regardless of AI’s capabilities it’s going to be at least 5-10 years until you could hope to reliably simulate human toxicology in silico (right now AI/ML can’t even reliably simulate in vivo studies like binding affinities or functional assays).
Even the most AI pilled of them, who will list all the areas that AI can reduce the time spent on various areas, don’t think the concept of AI discovering novel targets or generating new understanding of causal biology is realistic in the near term. Most, in fact, will readily characterize the assumption that even an “ASI” level model could find cures hidden in our current understanding (without expanding that understanding with significantly more biological data) as patently false.
This was a big part of why we wanted to experience it ourselves by using AI for a (very) small portion of what it can do in biology. It was both mind blowing and revealed some poignant insights into how different the problem of making AI better at something like coding is to the problems of biology.
Even if it unlocked the ability to generate new molecules at a stunning pace, its simulation (in silico) of binding only had 49% accuracy. And if we wanted to improve that, we’d need to feed it back the data from the lab - data that took about 30x as long to get as it took to generate the molecules. And these were tests in a test tube (turn of phrase), imagine how long it would take if we wanted to improve the model with data that required recruiting humans and monitoring their reactions.
Human biology is very complex, and adding a drug - especially a novel drug and doubly so for a novel drug acting on a novel mechanism - means mapping interactions that have nth-order-effects that we don’t have the data to predict. Virtual cells have made advancements enabled by AI, but the perturbations equate to a small fraction of the possible.
This is before you even get into curing disease, especially uniquely human diseases. Brain function involves cellular identities that are unique to humans, meaning animal studies are of little use.
How long does it take to understand what the side effects of chronic administration of a drug in humans are? AI can speed up analyzing the data, or designing the trial or even getting it approved…but it can’t make a 6 month trial complete in 3 months.
I think its important to point out that significant advancements can be made in AI that contribute to biology, while also being realistic about how much it speeds up something as complex as curing a specific cancer or diseases of the brain.
"I don't know what models RFDiffusion5 will be built upon, but RFDiffusion6 will be built on Monte Carlo and energy functions."
rfd4-proteina.org/
23
Anthropic: We are going to relax the Claude safe guards, act responsibly, it can be used to make bioweapons.
Biologists:
Finally a more intuitive way to learn pLDDT/pAE? 😎
sokrypton.github.io/protein_…
(Character idea from @HannesStaerk & Alex Waldherr)
Why in the actual hell pharmaceutical companies have secret stashes of structural data?
An AI system trained on more than 20,000 protein structures from pharmaceutical companies outperforms AlphaFold-like models that use only public data
go.nature.com/4gTSLaA
16
This is the saddest thing I have read since Johnny Got His Gun.
I don’t think you understand what ChatGPT Voice unlocks
I went on a 4 hour hike yesterday. Through the northern California redwoods.
Got more work done in those 4 hours talking to Voice through my AirPods then I do in 8 hours at my desk
Work can be done ANYWHERE now
45 minute drive back using self driving? Now 45 minutes I can talk to Voice and work on side projects
20 minutes in the cafe? I can sit and talk to Voice and when I get home I have drafts on my computer for my newsletter for the next month
Being able to just use your voice to talk to a super intelligence that controls your computer is unlike anything we’ve ever experienced before
I don’t even care that the voice sounds human like, or you can interrupt it, or any of the wild advancements they made to the tech
It’s the fact that it can control my computer, meaning all I need to get incredible work done is talk through my AirPods anywhere in the world that is the major game changer for me
I don’t think people truly understand the implications of this yet
Why even have a desk or monitor anymore. Work can be done ANYWHERE now
The key is your set up:
1. Choose one device (preferably an always on desktop) as your main “headquarters” device all your work gets done on
2. Get the ChatGPT app on all your other devices (iPhone, iPad, laptops, Mac Minis)
3. Set up ‘connections’ in your settings so that all your ‘node’ devices can control your ‘headquarters’ device
4. Go legit anywhere in the world. Turn on Voice. Ask it to brief you on your projects, give you a recommended next step, then spin up new threads to do work
I really don’t think work looks the same moving forward.
20
No debería sorprendernos que cualquier destino del mundo, si se llena de turistas, se va a llenar de comercios-trampa y estafitas del tres al cuarto.
Se llame el sitio Benidorm, Praga, Kyoto o la puñetera base de Gabriel de Castilla en la Antártida, si se diera el caso.
This quoted post is unavailable.
361
Ha salido Nuccio Ordine en las PAU de Lengua Castellana de este año.
Me congratula profundamente.
24
Wow.
Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology.
The new model delivers state of the art performance on protein interactions, especially antibodies, a critical modality for therapeutics.
We have designed and validated miniprotein binders and single chain antibodies across five therapeutic targets that are important in cancer and immunology. We are seeing very high success rates, and affinities at levels consistent with therapeutic activity.
We’re also releasing an atlas of 6.8 billion proteins, and 1.1 billion predicted structures.
ESMFold2 is built on a state of the art language model that has been trained on billions of protein sequences.
A world model of protein biology emerges through language modeling.
We’ve used the techniques of mechanistic interpretability developed to understand large language models to understand the concepts ESM uses to represent proteins.
The model’s representation space has a compositional organization of features across scales, levels of complexity, and abstraction, that reflects and mirrors the understanding of protein biology developed through a century of empirical science.
This understanding emerges without prior knowledge, just from language modeling of protein sequences.
Language models are becoming a powerful substrate to understand and program biology.
The design of protein interactions is one of the most fundamental problems in biophysics, and has critical implications for the discovery of new medicines. A simple gradient based search with the model was able to discover high-affinity protein binders.
I'm excited by the potential this has to accelerate basic science and the understanding of proteins. And especially for the new avenues it opens up for therapeutic design and medicine.
42
Soy un nostálgico de Acinetobacter, no puedo evitarlo.
Sigo los estudios que van saliendo como quien mira highlights de Zidane mientras se le cae una lagrimilla.
Thrilled to share our new paper in @CellBiomat and @CellPressNews.
We report D-GK17, a protease-resistant inverso peptide derived from human LL-37 with potent antimicrobial, antibiofilm, and immunomodulatory activity against multidrug-resistant Acinetobacter baumannii.
Our preclinical results suggest that D-GK17 is stable, active, and a promising candidate for combating antimicrobial resistance.
Great teamwork by Shanthini Kalimuthu, Yiu Yan Leung, @HKUniversity, @MICROLab_UofA, @UAlberta, @mdt_torres, @Penn, @PennBioeng, @PennEngineers, @PennMedicine, @PennChemistry, @CBE_Penn, @PennMicro, @PennPsych, and @PennSAS!
Link to paper: sciencedirect.com/science/ar…
1
41
Mario López-Martín retweeted
Congratulations from Microbiology Society to the 2026 Prize Medal Winner, Professor Paul Williams!
#Microbio26
Mario López-Martín retweeted
Prize Medal 2026 Lecture by Professor Paul Williams, 'Bacterial cell-cell communication: mechanisms and exploitation'. Begins at 18:30 in the Auditorium. Learn more about their work: microb.io/3PTIi44
#Microbio26
Mario López-Martín retweeted
I'm rebuilding AlphaFold2 from scratch in pure PyTorch.
No frameworks on top of PyTorch. No copy-paste from DeepMind's repo. Just nn.Linear, einsum, and the 60-page supplementary paper.
The project is called minAlphaFold2, inspired by Karpathy's minGPT. The idea is simple: AlphaFold2 is one of the most important neural networks ever built, and there should be a version of it that a single person can sit down and read end-to-end in an afternoon.
Where it stands today:
- ~3,500 lines across 9 modules
- Full forward pass works: input embedding → Evoformer → Structure Module → all-atom 3D coordinates
- Every loss function from the paper (FAPE, torsion angles, pLDDT, distogram, structural violations)
- Recycling, templates, extra MSA stack, ensemble averaging — all implemented
- 50 tests passing
- Every module maps 1-to-1 to a numbered algorithm in the AF2 supplement
The Structure Module was the most satisfying part to build. Invariant Point Attention is genuinely beautiful — it does attention in 3D space using local reference frames so the whole thing is SE(3)-equivariant, and the math fits in about 150 lines of PyTorch.
What's next:
- Build the data pipeline (PDB structures + MSA features)
- Write the training loop
- Train on a small set of proteins and see what happens
The repo is public. If you've ever wanted to understand how AlphaFold2 actually works at the level of individual tensor operations, this is meant for you.
Repo: github.com/ChrisHayduk/minAl…
This is a supercool study about RsaM in P. fuscovaginae, an ortholog of the AbaM of Acineto, carried out by researcher at @ICGEB
It really questions how these regulators work and I feel it opens even more questions about how these QS architectures work.
biorxiv.org/content/10.64898…
1
1
25
And the mechanism of action and exact ecological role remains a mistery, of course.
Hope we see this little mistery fully solved soon, giving this huge step forward :)
1
15





















