iiinova — where your digital self keeps evolving

Reposted by Tim O'Donnell

Sergey Ovchinnikov @sokrypton.org · 09/07/2026

One thing that helped with was implementing a simulated gameplay. Have Claude run 100s of games, get feedback and update ai.js. It is still doing some silly things... but getting better. Perhaps a future direction would be to let multiple LLM compete with eachother by building better ai.js?🤠 (3/4)

251

Tim O'Donnell @timodonnell.bsky.social · 12/02/2026

I wanted to understand how much information is lost when tokenizing protein structures using bio2token. Claude code whipped up this viz amazingly well

120

Tim O'Donnell @timodonnell.bsky.social · 18/12/2025

Is there a way to bulk download the MSAs from AlphaFold DB? cc @ebi.embl.org

000

Reposted by Tim O'Donnell

jproney @jproney.bsky.social · 10/12/2025

I'm super excited to announce the first preprint of my PhD, together with Chenxi Ou and @sokrypton.org! ML has revolutionized protein modeling, but crucial challenges remain. For example, we can't reliably predict complicated protein structures without MSAs, which limits what we can design.

2326

Reposted by Tim O'Donnell

Matteo Cagiada @mcagiada.bsky.social · 12/11/2025

My first full contribution from my time in @opig.stats.ox.ac.uk is now out! Together with @fspoendlin.bsky.social (and with contributions from King Ifashe), we created FlAbDab and FTCRDab: two large-scale, open molecular dynamics datasets to study flexibility in immune receptors.

1156

Tim O'Donnell @timodonnell.bsky.social · 27/10/2025

One cool thing about BoltzGen is the flexibility of the conditioning information you can provide (e.g. "constrain the structure of these residues and also these but let their relative placement vary"). I'm really curious to see what the community does with it! github.com/HannesStark/...

github.com

GitHub - HannesStark/boltzgen

Contribute to HannesStark/boltzgen development by creating an account on GitHub.

151

Reposted by Tim O'Donnell

Brian Naughton @btnaughton.bsky.social · 27/10/2025

I’ve been testing BoltzGen a bit recently and while I haven’t done any experimental testing yet, the quality of the software is very clear. It installs, runs, logs everything, has tons of options. Very excited to test out the designs irl!

162

Tim O'Donnell @timodonnell.bsky.social · 09/05/2025

TCR-seq q: collaborator has ~10% of clones assigned to alleles IMGT says are "ORFs" like TRAJ44*01, TRBJ1-6*01 (this is 10x in mice). What can cause this? How likely are they productive TCRs? Maybe @jamieheather.bsky.social @victorgreiff.bsky.social @10xgenomics.bsky.social have ideas? 🙏

110

Tim O'Donnell @timodonnell.bsky.social · 13/02/2025

Newbie antibody design q: if I take a mouse IgG1 antibody and express its VH/VL on a human IgG1 constant framework, how likely is it to still bind the target? Does that kind of thing usually work?

000

Tim O'Donnell @timodonnell.bsky.social · 31/01/2025

I like how the deepseek r1 tech report includes an "ideas that didn't work" section (although it is admittedly very short). I wish more papers had that

010

Tim O'Donnell @timodonnell.bsky.social · 13/11/2024

Anyone receive the AF3 weights yet? (Applied on Mon, have not heard anything)

121

Tim O'Donnell @timodonnell.bsky.social · 08/11/2024

Missed this when it came out this summer - high doses of MHC II neoags in a peptide vaccine can be counterproductive due to a population of FOXP3− CD4+ regulatory cells that *kill* cDC1s. Big implications for peptide cancer vaccines if true www.nature.com/articles/s41...

nature.com

Neoantigen-specific cytotoxic Tr1 CD4 T cells suppress cancer immunotherapy - Nature

Type 1 regulatory T cells (Tr1) represent a major obstacle that compromises naturally occurring and therapeutically induced tumour-specific immunity.

163

Tim O'Donnell @timodonnell.bsky.social · 24/06/2024

I moved to Cambridge MA! If you're around and would like to meet up let me know. Looking forward to getting to know the community here

000

Tim O'Donnell @timodonnell.bsky.social · 08/05/2024

Say I have a deep learning model that runs on pairs of things M(a,b), and I want to distill it into three models X,Y,Z where Z(X(a), Y(b)) approximates M(a,b), and hopefully Z can be shallow and fast. Is that problem studied? What should I google?

000

Tim O'Donnell @timodonnell.bsky.social · 29/03/2024

Anyone know of a nice alphafold multimer batch inference script? I am doing an all against all run and would like to reuse MSAs etc. Running on an academic HPC cluster

223

Tim O'Donnell @timodonnell.bsky.social · 29/03/2024

Most memorable thing I've learned from #singlecellgenomicsday so far is from 2022... LIVE-SEQ does a "cytoplasmic biopsy" to profile RNA from a living cell without destroying it www.nature.com/articles/s41...

010

Tim O'Donnell @timodonnell.bsky.social · 28/03/2024

High quality benchmark of AlphaFold-Multimer and other tools on Ab/Ag complex structure prediction. Lots of room for improvement but the trope that AF can't do antibodies is not really right anymore after the late 2022 models update (v 2.3.0) www.biorxiv.org/content/10.1...

0104

Tim O'Donnell @timodonnell.bsky.social · 28/03/2024

I love the simplicity of this idea - 1992 paper showing how to use FFTs to do rigid body molecular docking efficiently www.pnas.org/doi/abs/10.1...

000

Tim O'Donnell @timodonnell.bsky.social · 28/03/2024

Ok going to try using this. Who should I follow?

480