Computational Structural Biologist |
- Tweets 459
- Following 399
- Followers 673
- Likes 3,489
BindCraft2 - LICENSE
-Selling binders "you designed" with BindCraft2: allowed
-Selling access to BindCraft2 as a "hosted designer service": not allowed
github.com/PacesaLab/BindCra…
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/BindCra…
4
9
51
7,210
Using cms, we screened cyclic peptides (1st image) & binder (last image) in single & double-digit nM affinities. In both cases we dropped sc and preferred deltaG. Both showed promising in vitro and in vivo activity.
GPU-accelerated (CUDA) contact molecular surface (CMS), Lawrence & Colman shape complementarity (SC) for protein design.
Originally developed by Cao, code opensource by Brian. The original NumPy code is unchanged and utilize CPU. The GPU/CUDA version gives the same results while 36-165× faster per complex. cms-cuda is built on bcov77/py_contact_ms(github.com/ullahsamee/cms-cu…)
1
31
3,049
GPU-accelerated (CUDA) contact molecular surface (CMS), Lawrence & Colman shape complementarity (SC) for protein design.
Originally developed by Cao, code opensource by Brian. The original NumPy code is unchanged and utilize CPU. The GPU/CUDA version gives the same results while 36-165× faster per complex. cms-cuda is built on bcov77/py_contact_ms(github.com/ullahsamee/cms-cu…)
1
19
3,743
Visualization(cms/sc) experimental features in PyMOL
target surface = CMS per atom, white 0 → red ≥15 Ų
target surface = local fit: purple good · gray neutral · orange poor · white not in interface
Use it for binders screening if you're participating in @AnthropicAI protein design competition @amirshanehsaz
7
529
esmfold2 - i wanted to capture diffusion sampling coordinates for trajectory animation similar to @sokrypton at localfold.org/ so using Opus5.5 in 2-3 prompts, its not bad.
3
1
61
4,644
i_pDAE is Dunbrack’s ipSAE recipe with one ingredient swapped.
i_pDAE in BindCraft2(contact-masked TM-of-PAE), copies ipSAE’s three structural ideas - restrict the pairs, shrink d0d_0d_0 ,take the best residue in both directions - then replaces Dunbrack’s PAE cutoff with an 8 Å Cα contact cutoff.
So i_pDAE is ipSAE’s recipe with the gate changed from “does AF trust this pair?” to “are these two Cα atoms touching?
github.com/PacesaLab/BindCra…
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/BindCra…
1
2
62
5,709
sk retweeted
ColabFold2 Sneak Peak - integrates: alphafold3, openfold3, intellifold2, protenix2, boltz2, opendde, rosettafold3, chai1, esmfold2, openbind0 (thx Julia Buhmann), fully in Jax!
🗒️ Colab Notebook colab.research.google.com/gi…
🐍 pip install gist.github.com/sokrypton/75…
(2/3)
4
43
160
7,270
sk retweeted
I must be among an extremely small group of people (n=1?) that have both 1) trained a frontier LLM and 2) designed and synthesized custom viruses in a lab with my own two hands.
And I think that the takes on AI killing us all by creating dangerous viruses is total bogus.
573
1,909
14,436
1,934,507
sk retweeted
Not to throw shade but I’m not sure I buy the argument that this is an example of agents “reducing the burden of human expertise” when the prompt used to kick things off is like ten pages long and looks like this. How many humans on earth know all these methods? Maybe 5,000 tops?
2
10
141
10,669
sk retweeted
To me it seems silly everyone is trying to automate their tasks with LLMs. Wouldn't it make more sense to use LLMs to develop better workflows for their tasks that do not require calls to LLMs? 🤔
13
8
113
6,977
So human-written protocol prompts handed to Claude and the skew towards the 7 starred mandatory(design tools) was baked in upstream.
1
48
All those protein design startups and co-founded companies at UW are gone 😅
Many drugs work by binding to a specific target in the body and blocking or changing what it does. An important first step in the drug development process is designing a molecule that can bind tightly to its target. Traditionally, that's meant weeks or months of expert work per target, sifting through a large number of candidates to identify the few that work.
We wanted to test if Claude could successfully design novel protein binders from scratch (also called de novo design). With a protein design prompt written by a human expert, Claude autonomously designed protein binders against 14 out of 15 targets.
We then worked with Adaptyv Bio and Twist Bioscience, who independently built and tested the proteins Claude designed.
1
4
3,069
Found our forever style for protein structures. Color palette looks great, β-sheets are crisp, and it’s officially locked in for our preprint.
limewire.com/d/UV5o2#eGb8vTz…
3
5
72
4,221
Tell me you hate wasting time
Initially took me hours👇
Now just 15minutes
limewire.com/d/QbhcP#icWxiFo…
3
4
59
5,671
Mother of the ribbon diagram
One paper in 1981.
Changed how we see proteins.
If you haven’t read it, you’re late.
doi.org/10.1016/S0065-3233(0…
#compchem #phd
1
53
294
14,866
