Tim O'Donnell
@timodonnell
Followers
583
Following
792
Media
13
Statuses
294
https://t.co/NK4GR3BDjg
Cambridge, MA
Joined February 2008
🚀 Just released: Protein Hunter on GitHub! https://t.co/78TfdNO6i4 Now supports Boltz and Chai with more models coming soon! Use it to: 1️⃣ Design binders from scratch 2️⃣ Optimize your own designs 🔗 Boltz: https://t.co/7X9id9uDsL 🔗 Chai: https://t.co/P5w2TvoXYI
4
58
263
OpenFold3-preview (OF3p) is out: a sneak peek of our AF3-based structure prediction model. Our aim for OF3 is full AF3-parity for every modality. We now believe we have a clear path towards this goal and are releasing OF3p to enable building in the OF3 ecosystem. More👇
3
66
221
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!
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..
1
4
77
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..
20
268
985
🧵1/ We @tahoe_ai just published a new post on the Tahoe blog—a story of how we used Tahoe-100M, the world’s largest drug-perturbed single-cell dataset, to find compounds that upregulate MHC-I and make tumors more visible to the immune system. Here’s how 🧬🔍👇
5
43
221
Protein templates are finally supported in Boltz-2! Next up: updating BoltzDesign1 to use Boltz2 for template-based motif scaffolding and more
Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀
1
22
169
Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀
49
411
2K
Despite a lot of cool work in the last few years on high throughput TCR/epitope mapping assays, there's still only ~30 pMHCs where we have at least 100 known binding paired-chain TCRs. Where is all the data? Is it locked up in companies?
0
0
3
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
2
2
11
A shared neoantigen vaccine combined with immune checkpoint blockade for advanced metastatic solid tumors: phase 1 trial interim results https://t.co/eoKz3Q4IF4
@gritstonebio therapeutic vaccine data in KRAS mutant solid tumors. The overall response rate was 0%! @NatureMedicine
nature.com
Nature Medicine - In an interim analysis of a phase 1/2 trial, a heterologous prime boost vaccine comprised of a chimpanzee adenovirus and self-amplifying mRNA that encodes neoantigens derived from...
7
26
94
I'm looking for a list of human AIRE-dependent transcripts, ideally curated from multiple studies rather than a single analysis. Anyone know of such a thing?
0
2
3
We’re really excited to announce that we’re releasing code for running RFdiffusion! The code is released under an open source license and is free for anyone to use.
Today we're making RF Diffusion, our guided diffusion model for protein design with potential applications in medicine, vaccines & advanced materials, free to use. The software has proven much faster and more capable than prior protein design tools. https://t.co/lhkhBZNzYc
9
98
359
Found it buried here https://t.co/k7a868s37B . Thanks for your attention :)
0
0
2
Has strelka version 1 (the somatic variant caller from Illumina) disappeared from the internet? I'm looking for a file called 'strelka_workflow-1.0.14.tar.gz', which used to be downloadable from Illumina ftp but no longer. Anyone have this file?
1
1
3
Catch is that F486P requires *two* nucleotide mutations to the same codon, which is rare event even for RNA virus like SARS-CoV-2: https://t.co/FjfKbqQzIw That's why it took so long for variants to start fixing F486P.
One reason this mutation is so surprising is that it requires a 2-nucleotide change. Each amino acid is encoded by three nucleotides, & the vast majority of mutations (>99.99% I’d guess) involve just one nucleotide change. Two-nuc mutations are exceedingly rare. 2/16
3
82
438
Anyone know what the V940 is? The trial only seems to mention mRNA-4157
0
0
1
Strongest indication yet that personalized neoag cancer vaccines can work. It is open label though (and small - 157 patients, they needed a one-tailed p-value to get significance) so time will tell
2
2
15
In addition to newer work on protein design, I'll be continuing to work on cancer vaccines and tumor immunity + contributing OSS via @OpenVax . Get in touch if you'd like to explore a project together!
0
0
6
Some professional news - after 8+ years at Mount Sinai, I've switched to an independent consulting model for my work. A huge thank you to @BhardwajLab @lasersonlab @hammer_lab @iskander @neoviral and all the inspiring people I worked with at @IcahnMountSinai !
2
3
32
Voices: We asked @victorgreiff @timodonnell @Francesca_Fin_ @saireddy911, Eline Luning Prak, Aleksandra Walczak & Thierry Mora what are the current driving questions are in immune repertoire research.
cell.com
Adaptive immune receptors (AIRs: B cell receptors [BCRs] and/or T cell receptors [TCRs]) can recognize nearly any antigen by incredibly diverse AIR repertoires (AIRRs). AIRs are crucial to fighting...
0
17
31