Scientific discovery and research is more important than trade, tariffs and terabytes. We’re in the most important time for funded research. I’d like to see the major AI platforms of the world unite to fund science.

A perpetual universal global fund for scientists is what’s needed today. Earth is in desperate need now more than ever to create frontier labs. With the new discoveries made by AI, it’s the scientists, most importantly, whom will need to handle these discoveries with practiced care.

🔗 Evolutionary and structural bioinformatics identifies GPR89 as a conserved member of the LIMR protein superfamily. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.cs... 📚 CSBJ: www.csbj.org #StructuralBiology #ComputationalBiology #Evolution #ProteinScience #AlphaFold

Scientific research and studies should be the first biggest focus for funding in Silicon Valley. AI without a scientist is a hammer without a hand.

A nanoluciferase-tagged Schmallenberg virus (SBV): an efficient tool for measuring and tracking viral infection dynamics. Published Open Access and fee-free in JMM using a Publish and read agreement: doi.org/10.1099/jmm.... #JMM #PublishAndRead

#BCNspiracy25 #DIVERSspiracy #updatespiracy#diversspiracyÓscar Huertas Rosales nos pone un éxito de la IA, la predicción de la conformación tridimensional de proteínas. Un problema muy difícil que está en camino de su solución (AlphaFold aún no resuelve el problema completo).

📣 New Podcast! "The AI Scientists Are Here (And They're Rewriting Everything)" on @Spreaker #ai #aiinscience #aimedicine #alphafold #artificialintelligence #autonomousai #breakthrough #deepmind #discovery #drugdiscovery #futureofscience #innovation #mindblown #research #scienceandtech #stem

Experiments must be in the loop. Automation helps, but the real bottleneck is choosing the right optimisation targets and defining what “good” looks like. AlphaFold succeeded because protein structures could be validated experimentally. Not all biological tasks have that luxury. 5/8

The second direction: post-AlphaFold biology. Architectures built specifically for molecules, not NLP models. To replicate AlphaFold’s impact, we need: • high-quality experimental benchmarks • sufficient data volume • new architectures • tight integration with wet-lab validation 5/8

For fun, I thought I'd compare different AlphaFold softwares on a random sample of 1000 proteins I'm working on. AlphaFold2/ColabFold is still the most accurate, but slowest and most buggy (the run randomly stopped at the 975th protein). Boltz is the best for speed.

The capabilities are real: • AlphaFold: 214M protein structures (Nobel Prize 2024) • Insilico Medicine: AI drug to Phase IIa in 30 months vs 4-6 years • IDx-DR: First FDA-approved autonomous AI diagnostic But here's what matters more: implementation.

Thanks! Through the NSF NAIRR pilot program we were paired with an industry partner to support our AI-related project. The program connected us with NVIDIA and they provided three months of access to a 256-GPU DGX cluster, which is where we ran all of the AlphaFold predictions.

Food for thought/discussion. 🧪

ICYMI: New online: AlphaSync is an enhanced AlphaFold structure database synchronized with UniProt

Thrilled to share that the final piece of my PhD work is now on bioRxiv! biorxiv.org/content/10.1... With support from @nvidia and the @NSF, we used AlphaFold to screen 1.6M+ protein pairs, revealing thousands of potential novel PPIs. All data can be viewed at predictomes.org/hp

🔗 Improving prediction accuracy in chimeric proteins with windowed multiple sequence alignment. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.cs... 📚 CSBJ: www.csbj.org #StructuralBiology #Biophysics #Bioinformatics #ProteinStructurePrediction #AlphaFold

Prof Ho's fellowship project will combine the capabilities of specialized scientific AI models like AlphaFold with more general AI models that can reason about science without understanding it deeply, building a stepping stone toward scientific artificial general intelligence.

Quantum isn't hype—it's buildable. Follow @TheTechWorldPod for AI/quantum breakdowns, no-buzz scripts. #AI #Quantum #WillowChip #AlphaFold spti.fi/dRbvXjf

New online: AlphaSync is an enhanced AlphaFold structure database synchronized with UniProt

Part of HTGAA Week 4 is to write a proposal on an In-silico Bacteriophage Engineering. My proposal: 'ArmoredPhage' 🛡️ My goal: Engineer a Thermostable MS2 Bacteriophage Using Protein Design Techniques. Check it out: djosergenomics.github.io/Armored-Phag... #HTGAA #synbio #AlphaFold #proteindesign

User annotations are visible on the 2D and 3D tracks, but they are only applied for the duration of the user session and not saved. The AlphaFold Database provides open access to over 240 million protein structure predictions. The resource is a collaboration between EMBL-EBI and Google DeepMind.

#alphafold www.pnas.org/doi/10.1073/...

Hi Anni, have you tried our bioinfirmatics AI assistant Pipette.bio? It can access AlphaFold predictions for a given protein, along with several other protein databases.

We next turned to AlphaFold to understand how MTR interacts with its binding partners. AlphaFold of MTR with its rescue partner MTRR threw a surprise our way: AF3 suggested two regions of interaction with one newly suggested that deviated from the previously known interaction with MTRR’s FMN domain.

AlphaFold Database users can now temporarily integrate and visualise their own protein annotations, making the resource a more interactive and personalised platform for structural bioinformatics analysis. www.ebi.ac.uk/about/news/u... #AlphaFold

AlphaFold is pretty legit! I would say amino acid/nucleotide sequences are some of the best use cases. But in general the AI hype is dumb. If you don't tell me*how* you use AI in the pitch I'm assuming you shoehorned it in unnecessarily.

We dream of simulated proteins, trust worthy AI and technology that heals and gives more than it takes.

OpenFold3 🎯

If Linux (for OS) is any model, OpenFold3 wants to become the standard for structural biology in academia & industry alike. Ambitious—but necessary. #OpenSource https://www.maffulli.net/2025/10/30/openfold3-open-source-replacement-alphafold/ #ai

Brian Weitzner, co-founder of OpenFold, discusses the collaborative effort to develop software and AI tools to predict the 3D structure of proteins, how its open licensing model ensures broad accessibility, and how it stacks up against AlphaFold. thebioreport.podbean.com/e/an-ai-coll...

OpenFold3: Open-source protein structure AI aims to match AlphaFold! Has anyone tried it yet? 🙌 www.nature.com/articles/d41... github.com/aqlaboratory... #microsky #bioinformatics 🧪 🧬 🖥️ ✨

Once you use AlphaFold to invent a new drug, it still has to be brought to market using pharma company infrastructure, not a server farm.

Yes 50

Human betterment will advance when biotechnological systems begin to read the body’s informational structure as an active language. Proteins, signals, and genetic loops can become co-authors in regenerative design through high-fidelity molecular modeling.

When AI begins to simulate enzymatic catalysis at atomic resolution, biology transitions from observation to design. Protein structures cease to be static outputs and become programmable frameworks for therapeutic and environmental repair.

This is going to be one of the biggest, most important features of AlphaFold @alphafold.bsky.social if further improved! Glycobiochemistry needs this bestfriend! #glycotime academic.oup.com/glycob/artic...

Open-source protein structure AI aims to match AlphaFold The system, called OpenFold3. OpenFold3 uses proteins’ amino acid sequences to map their 3D structures and model how they interact with other molecules, such as drugs or DNA. The tool still doesn’t have the same functionality as […]

Open-source protein structure AI aims to match AlphaFold www.nature.com/articles/d41... Why open source is important for AI sovereignty and more, from a discussion at the @mediamuseum.bsky.social blog.scienceandmediamuseum.org.uk/how-britain-...

L'IA open source de structure protéique vise à égaler AlphaFold

This kind of consortium-led effort — academic + industry + nonprofit — shows how open collaboration can deliver foundational infrastructure for biology and AI, not just apps. 🤝 #OpenSource https://www.maffulli.net/2025/10/30/openfold3-open-source-replacement-alphafold/

AlphaFold DB v6 is here! 🚀 Heads up on key updates: 🔹 Website now only serves v6 🔹 New URL format!! 🔹 Dual API active for 9 months (retirement: 25-06-2026) Use the AlphaFold API for reliable access. Time to update those bookmarks & scripts!

Any news of alphaproteo ? It's been over a year and since then, nothing. #alphafold deepmind.google/discover/blo...

This reminded me of what Dame Janet Thornton said about AlphaFold. It's a help to protein research, but not a substitute for protein researchers. youtu.be/lxgaILSZEbU?...

I love AlphaFold—but please include PAE (Predicted Aligned Error) plots for every “interaction.” Pretty PDBs ≠ proof. If the PAE doesn’t show an interface, it ain’t one. Show the plots. Structural biology's reputation is on the line.

Let's differentiate between GenAI and machine learning (ML). Alphafold is ML. I'm personally familiar with several applications of ML that are transformational for biochemistry, drug development, and healthcare. ML is great at mining huge datasets for patterns. I don't know anything about GenAI.

AlphaFold heads to the clinic. DeepMind says three therapies for rare genetic diseases start trials in October 2025. With 200 million protein structures predicted by 2023, timelines could fall from 5 years to under 1, with cost savings. Big potential and big questions.

This paper is incredible; IMO large-scale, unbiased data is our best chance to get beyond the relatively small set of sequences that AlphaFold loves

Is the alphafold database performing really poorly, and Uniprot alphafold links broken for everyone, or just me? I've tried clearing my cache, but any tips @ebi.embl.org?

Excited to share our new @narjournal.bsky.social paper! Using ReLo and AlphaFold, we described a network of interactions between Drosophila piRNA pathway factors suggesting new links how they coordinate to ensure transposon silencing and genome integrity. academic.oup.com/nar/article/...