sk
@compchemm
Followers
460
Following
3K
Media
72
Statuses
335
Computational Structural Biologist |
Joined April 2017
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👇
2
61
198
OpenFold3-preview now available The final OpenFold3 model is still in development Report: https://t.co/pp89s3QJd1 Code: https://t.co/QrHNvU6HdB Documentation: https://t.co/3EeG8lmZTK
0
1
16
OpenFold3(OF3) version 1.0.0 – available at NVIDIA NIM https://t.co/df4GGhiCNk Trained on: ~13M complexes datasets - 20M sample crops training #compchem #AcademicTwitter
0
0
0
Why @GeminiApp @GoogleAIStudio not integrating Google Scholar???
We’re building tools to support research in the life sciences, from early discovery through to commercialization. With Claude for Life Sciences, we’ve added connectors to scientific tools, Skills, and new partnerships to make Claude more useful for scientific work.
0
0
0
I recall working on a paper that was planned for submission to Nature - and then we got into the pettiest debate over authorship with colleagues from another university - and in that moment I realized I needed to leave academia and work for startups. Nothing worthwhile was going
What radicalized *you*??
31
27
634
A complete list of Molecular Dynamics Research groups worldwide - perfect for anyone looking for any positions https://t.co/AEMYL5LLSt
0
18
81
#ScientificBreakthrough: AI-designed protein targets heart failure mechanism. First demonstration of a new, lab-verified protein designed to target cellular energy depletion in heart failure. Experimental validation confirms successful synthesis, improved stability, and
75
320
823
🔥 Benchmark Alert! MotifBench sets a new standard for evaluating protein design methods for motif scaffolding. Why does this matter? Reproducibility & consistent evaluation have been lacking—until now. Paper: https://t.co/i2Lk3YZ24N | Repo: https://t.co/Xoun67eE9P A thread ⬇️
5
41
136
Full-atom MPNN (FAMPNN) - a sequence design method that explicitly models both sequence identity and sidechain conformation. https://t.co/0m4jQpigpK code: https://t.co/XayonzBNSL
2
34
118
CyclicBoltz1, fast and accurately predicting structures of cyclic peptides and complexes containing non-canonical amino acids using ... https://t.co/hHMZHCXwNV
#biorxiv_bioinfo
biorxiv.org
Cyclic peptides exhibit favourable properties making them promising candidates as therapeutics. While the design and modeling of peptides in general has seen rapid advances since the advent of modern...
2
20
76
Bindcraft is killing it! 🤩
0
15
171
Here are the 10 binders from me and Lennart that got selected for testing, all expressed, top left was 5th best ranked binder. We only went for beta sheeted proteins we designed for round 1, no additional optimisation.
PROTEIN DESIGN COMPETITION ROUND 2 The long awaited results are here -- and they don’t disappoint! 📈 We doubled the number of proteins we tested in our lab from 200 to 400! 🧬 Out of those 400 proteins, 378 expressed (95% expression rate!) 🚀 Out of those 378 expressed
6
17
160
AF3 has clearly not solved the antibody-antigen prediction problem seeing the #CASP16 results…
4
12
102
🧬✨Excited to share our online demo " Natural language → De Novo Protein design" Live demo: http://113.45.254.183:8888/ The demo version Pinal is 1.2B.🔬 You try very detailed textual prompt up to 500 words. https://t.co/f8b7vxzOQS
Toward De Novo Protein Design from Natural Language: Propose Pinal, a 2-stage generative framework, avoiding end-to-end text-protein generation. Design an optimal sampler to integrate both stages. Outperform ESM3 when prompting with text. #ProteinDesign
https://t.co/f8b7vxzOQS
11
50
296
Our experience with #alphafold3 🤖 (code recently released) and some of our most recent #cryoEM 🔬 structures (thread below) https://t.co/SmX8i15Zwa
https://t.co/hwJUlkwhye
5
96
398
After showing that AF2 can be used to design very large proteins by performing #RSO, I am happy to share another fun project we did: the #af2cycler @sokrypton @hendrik_dietz
https://t.co/xMSVFH7oF1
biorxiv.org
Recent advances in computational protein design have enabled the creation of novel proteins for a variety of purposes. The capability for producing custom-shape high-quality backbones for very large...
3
46
150
The #AlphaFold 3 model code and weights are now available for academic use. We @GoogleDeepMind are excited to see how the research community continues to use AlphaFold to address open questions in biology and new lines of research. https://t.co/kVB9hWJZTI
github.com
AlphaFold 3 inference pipeline. Contribute to google-deepmind/alphafold3 development by creating an account on GitHub.
We love the excitement & results from the community on AlphaFold 3 and are doubling the AF Server daily job limit to 20. Happy to also share that we're working on releasing the AF3 model (incl weights) for academic use, which doesn’t depend on our research infra, within 6 months.
21
260
1K