GAMA Miguel Angel 🐦‍⬛🔑

🧵1/3 I created this free 37-hour course, distributed across 10 lectures, to introduce AI-based protein design. For more information about the course and its specific topics, please visit the official course page: miangoaren.github.io/teaching/prote…

Interested in molecular animation and in SF for #BPS2026? Stick around for the evening Structural Biology workshop (Rm 204/205/206) and my talk at 8:45pm (New Tools for Visualizing Dynamic Molecular Models) to learn about ProteinBlender! animation-lab.github.io/ProteinBlender/

Karma, karma, karma, karma, Karma chameleon 🦎 youtube.com/watch?v=h5WA79…

Storytime: During my bachelors, a PhD student with a huge ego treated me poorly, she was dismissive, never paid attention, etc. During the pandemic, she left her PhD, and a later review of her notes revealed she had been manipulating data and fabricating gels that never existed

We made FLIP2, a protein fitness benchmark spanning seven new datasets, including enzymes, protein-protein interactions, and light-sensitive proteins, as well as splits that measure generalization relevant to real-world protein engineering campaigns.

I used to think doctors were very intelligent/respected people. After 1yr in med school and many conversations with doctor friends, I now see them as very horny-unfaithful people who don’t miss any chance, even in a hospital bed. In MEX 🇲🇽this is referred as “la putería” or LP 😅

There is great excitement about the potential for AI to reshape science, but so far very little empirical evidence about how that is (or is not??) happening in real time. I'm excited to share a new working paper with @carolyn_sms about the impact of AlphaFold on science ->

The proteinologist community trying to follow up on the papers of OpenFold3 x.com/MoAlQuraishi/s… 31M complexes added to the AlphaFold DB x.com/pushmeet/statu… Proteina-Complexa testing 1M binders in the lab x.com/DidiKieran/sta… x.com/ManifoldBio/st…

Big news! Starting my lab as Ramón y Cajal PI at @IBVF_Sevilla in Seville 🌞, Spain, bridging microbial ecology, photosynthesis & plant biotech: from metagenomic and AI analyses 💻 to experiments in microbes & plants 🌊🧬🌱 Looking for PhD students & postdocs. DM or share!

📢 We’re launching Proteina-Complexa — and after the Jensen keynote mention, we definitely had to post this thread now ;) Atomistic binder design with generative pretraining + test-time compute, plus large-scale wet-lab validation. Project page: research.nvidia.com/labs/genair/pr… 🧵 1/n

🧵 We ran the largest head-to-head benchmark of protein binder design methods in the wet lab. Project page: research.nvidia.com/labs/genair/pr… 1 million designs. 127 targets. RFdiffusion, BindCraft, BoltzGen, and Proteina-Complexa — all tested side by side.👇

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: github.com/unslothai/unsl… Blog and Guide: unsloth.ai/docs/new/studio Available now on Hugging Face, NVIDIA, Docker and Colab.

@ATinyGreenCell Also, this new pipe looks really interesting x.com/mionoyui/statu… I’ve also curated a few design workflows in this list of tools. #protein-design" target="_blank" rel="nofollow noopener">github.com/miangoar/AI-dr…

@ATinyGreenCell I think that BAGEL is a good choice :) x.com/jakublala/stat… It's a framework inspired by a protocol presented by the ESM team, where they used sampling methods like MCMC to optimize a specific design x.com/miangoar/statu… A more recent example x.com/jakublala/stat…

Any recommendations for an arbitrary de novo protein design tool that's ideally free? Every time I see de novo protein design it actually is antibody or binder design. I need it for things that have nothing to do with medicine. TYIA!

@SimonDBarnett @_DimensionCap @ChemVagabond @karpathy @modal Cool! Looking forward to reading that blog :) If possible, it would be great to see a Colab notebook using autoresearch applied to a tiny model like ESM2-8M.

@miangoar @_DimensionCap @ChemVagabond @karpathy @modal Agreed - we will walk through what we learned in our blog. Most important thing to us is not the absolute results (though they're becoming quite interesting as we let it run) - more important is our experience using it, pitfalls, etc.

Can't think of a better first X post for @_DimensionCap's newest research ~ Frank Gao (@ChemVagabond). We ran @karpathy's autoresearch framework using @modal this weekend ~ focusing on protein thermostability prediction. 50 experiments in and much more to come this week! 👇

Lab renovations are almost finished...

No. The massive unlock for biology comes from classical workflows, LLMs/agents and, remarkably, from high-quality data curated and freely shared by thousands of scientists around the world. Not all problems can be accelerated by machine learning. x.com/miangoar/statu…

At @GoogleDeepMind, we believe AI is the ultimate catalyst for science. 🧬 The best example of this has been the AlphaFold database (AFDB) of protein structure predictions which has been used free of cost by more than 3.3 millions researchers across the world! Today, in collaboration with @emblebi, @Nvidia and @SeoulNatlUni, we are expanding the database by adding millions of AI-predicted protein complex structures to the AlphaFold Database. To maximise global health impact, we’ve prioritised proteins that are important for understanding human health and disease, including homodimers from 20 of the most studied organisms, including humans, as well as the @WHO’S bacterial priority pathogens list. Read more here: embl.org/news/science-t…

A nice documentary about the history of neural networks (belief nets, AlexNet) from the perspective of Ilya Sutskever, covering the foundation of OpenAI, the rise of ChatGPT, ideological conflicts with Sam Altman and more. What Did Ilya See? youtube.com/watch?v=glWvwv…

I'm excited to announce some major updates to our ProteinEBM paper with Chenxi Ou and @sokrypton!