🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Brian Gordon My pet theory: - these are domains where matching is valuable. You want to talk to people about books/movies/papers you’ve both seen. - assume everyone sees n works per year out of N total - probability two people have seen the same work is roughly (n/N)^2 if sampling randomly

Really pleased to share what I have been working on for 2 months: 🇬🇧 UK SovAI are today announcing our £8m seed investment into OpenBind - A consortium that will actually make AI for drug discovery great by generating 500k experiment protein-ligand complexes!! Explainer 🧵 (1/n)

This is really cool. I’m interested to see whether Basecamp can get this sort of revenue sharing model to work. A lot of the value of AI is driven by the people creating the underlying data!

Super comprehensive guide to fundraising for science orgs - from startups to FROs. Great job Andy Coravos!

This should be required reading by all graduate students and postdocs | A brief guide to statistical analysis of grouped data in preclinical research nature.com/articles/s4225…

novonordiskfonden.dk/en/news/new-da…

holy shit, it’s here! deepmind just released AlphaGenome. an AI model that reads 1 million bases of DNA and predicts how any mutation changes molecular function not just in single genes but across the entire regulatory genome. DNA is code, and you are software 1/

Excited to launch our AlphaGenome API goo.gle/3ZPUeFX along with the preprint goo.gle/45AkUyc describing and evaluating our latest DNA sequence model powering the API. Looking forward to seeing how scientists use it! Google DeepMind

What determines who a phage can infect? We tackled this question for temperate phages of Klebsiella — a bacterial pathogen — using a genome-wide association study (GWAS) and a massive protein testing effort. 👇 A thread!

New Renaissance Philanthropy programme with ARIA to provide ambitious individuals the freedom to pursue and test their biggest scientific ideas that are too risky or bold for others to support 💥 Learn more and apply below 👇👇

New preprint with Benjamin Lang, Kriwacki Lab, John Christodoulou, and M. Madan Babu ! biorxiv.org/content/10.110… Protein Dynamics at Different Timescales Unlock Access to Hidden Post-Translational Modification Sites #bioinformatics #compchem #folding #proteindynamics

Yesterday, the Centre for British Progress team's away day was at Docklands Park where we got to see a Concorde. When shown a video of its last flight set to Don't Stop Me Now by Queen, I cried.* Concorde is a testimony to British ambition and progress, which is why I want to revisit its

Just one more reminder that the NMR ensembles deposited in the PDB != dynamics of a protein... The ensemble represents *uncertainty* due to lack of experimental data when solving a structure from NMR. Using ensembles to benchmark ML/AI models of dynamics isn't a good idea.

this is a great read by jack morris. gives such a fresh perspective on what really matters. TLDR: with every "new" architecture, we unlocked a new source of data to use at scale. it was the large amount of data we unlocked that boosted performance not the architecture itself,

A periodic reminder to leave behind simplistic & naive notions.

The past few years of "AI for life sciences" has been all about the models: AF3, NNPs, PLMs, binder generation, docking, co-folding, ADMET, &c. But Chai-2, and lots of related work, shows us that the vibes are shifting. Models themselves are becoming just a building block; the

What Are Virtual Cells? centuryofbio.com/p/virtual-cell Two months ago, I started working on an essay to answer this question. The goal was to cover a few of the recent research results. Simple as that! Instead, I went down a rabbit hole exploring ideas around cellular simulation

I think we also need alphafold for lipids. A lot of applied research around mRNA delivery mechanisms is bottlenecked around better understanding LNPs. Some applications that would be super useful - lipid-protein interactions, membrane interactions, 3d structure prediction

Fungi jam in the corner. 😯 special sensors read electrical impulses in the caps, and then turn into commands for motors. some studies have prove mycelial networks are known to be able to communicate information along their networks much like neurons do in a human brain.

It’s out. Proud and tired. gov.uk/government/pub…