Sign in

Thomas Litfin

@tlitfin.bsky.social
538 followers 55 following 5 posts
PostsRepliesMedia
Reposted by Thomas Litfin
Martin Pacesa @martinpacesa.bsky.social · 21/09/2026
ʙɪɴᴅᴄʀᴀꜰᴛ2 is out, and we're not waiting for the paper. The full code drops today, free for academic and industry use. We're releasing it early so you can start designing right now, and bring its full power to the current Adaptyv competition. github.com/PacesaLab/Bi...
4292142
Reposted by Thomas Litfin
Milot Mirdita @milot.bsky.social · 16/09/2026
ColabFold 1.6.3 is out! 2.5x faster, pip-installable, ipSAE+pDockQ2 scores. Thanks Choonghwan Lee, Marielle Russo, Gyuri Kim 🐍pip install colabfold[alphafold] CF2 Sneak Peak with AF3/Boltz/Protenix/ESMFold2… 🐍pip install "colabfold[alphafold3]@git+https://github.com/sokrypton/ColabFold@af3-preview"
29736
Thomas Litfin @tlitfin.bsky.social · 03/09/2026
Was great to work with @joshuamhardy.bsky.social and David Ladd on this nice update! Very happy to maintain consistent 'in silico' pass rates across multiple versions!
020
Reposted by Thomas Litfin
Australian BioCommons @ausbiocommons.bsky.social · 05/06/2026
World-leading Aussie science fighting #AntimicrobialResistance! PhD student George Bouras added 17M bacterial protein predictions to the #AlphaFold database. This was made possible by a partnership between BioCommons & @pawseycentre.bsky.social to containerise #ColabFold on Setonix. Read more 🔗
biocommons.org.au
World-leading Australian science: 17M protein structures added to the AlphaFold Database to accelerate the fight against antimicrobial resistance  — Australian BioCommons
Australian researcher, George Bouras, has recently contributed an extraordinary 17 million protein predictions to the AlphaFold Protein Structure Database. This work was possible thanks to the availability of the ColabFold tool on Setonix AMD, the result of collaboration between BioCommons and the P
0177
Reposted by Thomas Litfin
Peter Škrinjar @peterskrinjar.bsky.social · 11/05/2026
Now published in NSMB! Paper: doi.org/10.1038/s415... Full PDF: rdcu.be/fhBtI Overview of additions since the preprint👇 (1/5)
doi.org
Evaluating generalization in protein–ligand cofolding methods - Nature Structural & Molecular Biology
This work introduces the Runs N’ Poses dataset for benchmarking deep learning methods on the protein–ligand complex prediction task. It shows that current methods rely on memorization, challenging the...
23915
Reposted by Thomas Litfin
Australian BioCommons @ausbiocommons.bsky.social · 08/05/2026
Excited to welcome Dr Cameron Gilchrist (Korea Basic Science Institute) to our next Structural Biology Community Meeting! 🧬💻 They’ll be presenting: "Multiple protein structure alignment with FoldMason." 🗓️ Wed 20 May. All welcome! Agenda & join link: www.biocommons.org.au/events/struc...
031
Reposted by Thomas Litfin
EMBL-EBI @ebi.embl.org · 16/03/2026
You asked, we listened. Millions of AI-predicted protein complex structures are now available in the #AlphaFold Database. This spans homodimers from 20 of the most studied species, including humans, as well as the World Health Organization’s priority pathogens list. www.ebi.ac.uk/about/news/t...
816087
Reposted by Thomas Litfin
Torsten Schwede @torstenschwede.bsky.social · 13/03/2026
Is #AI hitting a plateau in structure prediction? Help us find out at CASP17! 🧪🧬 Calling for Targets: Immune Complexes, protein - ligand complexes, RNA/DNA, conformational ensembles, membrane proteins, viral origins, and large complexes. The Rule of Thumb: If AF3 can’t model it, we want it.
The Critical Assessment of Structure Prediction (CASP) experiment is calling for prediction targets: Immune Complexes, Organic Ligand-Protein Complexes, Nucleic Acids and Complexes, Conformational Ensembles, Difficult Protein Structures and Complexes. 
Rule of Thumb: If AlphaFold3 can generate a high-quality model, it is likely not a CASP-grade challenge. If it struggles, we want it.
24935
Reposted by Thomas Litfin
Mohammed AlQuraishi @moalquraishi.bsky.social · 13/03/2026
New OpenFold3 preview out! (OF3p2) It closes the gap to AlphaFold3 for most modalities. Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
124490
Reposted by Thomas Litfin
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 10/02/2026
Isomorphic Labs Drug Design Engine (IsoDDE), a unified computational drug-design system Announcement: www.isomorphiclabs.com/articles/the... Report: storage.googleapis.com/isomorphicla...
1318
Reposted by Thomas Litfin
Martin Steinegger 🇺🇦 @martinsteinegger.bsky.social · 30/01/2026
FoldMason is out now in @science.org. It generates accurate multiple structure alignments for thousands of protein structures in seconds. Great work by Cameron L. M. Gilchrist and @milot.bsky.social. 📄 www.science.org/doi/10.1126/... 🌐 search.foldseek.com/foldmason 💾 github.com/steineggerla...
science.org
Multiple protein structure alignment at scale with FoldMason
Protein structure is conserved beyond sequence, making multiple structural alignment (MSTA) essential for analyzing distantly related proteins. Computational prediction methods have vastly extended ou...
4302147
Reposted by Thomas Litfin
Martin Pacesa @martinpacesa.bsky.social · 22/01/2026
Here are the success rates of de novo pipelines based on which designs I could actually identify the methods for.
22312
Reposted by Thomas Litfin
Max Fürst @maxfus.bsky.social · 16/12/2025
New preprint🚨 Imagine (re)designing a protein via inverse folding. AF2 predicts the designed sequence to a structure with pLDDT 94 & you get 1.8 Å RMSD to the input. Perfect design? What if I told u that the structure has 4 solvent-exposed Trp and 3 Pro where a Gly should be? Why to be wary🧵👇
46524
Reposted by Thomas Litfin
James Fraser @fraserlab.com · 29/12/2025
I'm really excited to break up the holiday relaxation time with a new preprint that benchmarks AlphaFold3 (AF3)/“co-folding” methods with 2 new stringent performance tests. Thread below - but first some links: A longer take: fraserlab.com/2025/12/29/k... Preprint: www.biorxiv.org/content/10.6...
fraserlab.com
Know when to co-fold'em
This is the official web page for the James Fraser Lab at UCSF.
57230
Thomas Litfin @tlitfin.bsky.social · 31/10/2025
🧶🧬 We present LMi4Boltz: www.biorxiv.org/content/10.1... Boltz-2 is an excellent open source alternative to AlphaFold3. However, high VRAM use restricts modeling large complexes. Using careful memory management, we increase the Boltz-2 size limit by >60% while maintaining execution speed.
Figure comparing runtime and VRAM utilization between Boltz-2 (baseline), and LMI4Boltz (+memory, and +chunk).
Main plot: runtime (y-axis) versus token count (x-axis), showing that all methods scale similarly, with +memory and +chunk handling larger token counts.
Inset scatterplot: PDB test lDDT scores from Boltz-2 versus LMI4Boltz, showing a strong linear correlation (values near y = x).
Right panels:
– Top bar chart: maximum tokens processable on a 24 GB GPU increase from 1596 (Boltz-2) to 2356 (+memory) and 2660 (+chunk).
– Bottom bar chart: H200 runtime for 1596 tokens remains comparable across methods.
1258