
not accurate fold as @sokrypton but 27B quant4 will lose to 10T model😅

Computational Structural Biologist |

not accurate fold as @sokrypton but 27B quant4 will lose to 10T model😅

Can also predict structure - Qwen3.8-27B-Q4 quants i tried with and i assume bf16 will be better.
Given Claude Fable 5.2 can predict protein sequence, I was curious if it can predict structure. I gave it a relatively simple prompt: "predict contacts, 2ndary struct, use dynamic prog. and linear alg. to predict structure" It was able to predict fold of ubiquitin correctly 🤯

Claude Mythos Preview (18/60) hit rate, a LLM running those tools, its "not a specialized protein design model" like RFD4-Proteina, RFdiffusion or Latent-X etc. As a peer-reviewer i don't need that kinda comparison, so i removed it from that graph and now it make sense. But then here's my question: Why was the experimental sample size so much larger for your method(rfd4-proteina)? Also What if you increase the sample size for all other methods?
Reading group today. RFD4-Proteina: 158 of 188 designed binders bound TrkA below 1 µM. Next best method: 18 of 60. Nate Corley and @DidiKieran will present rfd4-proteina.org/ On Zoom 2pm ET / 8pm CET: hannes-stark.com/starkly-spe…

We can now design all kinds of fancy de novo proteins. But can we produce them at scale, at a reasonable cost, and without extensive optimization? That’s what got this project started. Our preprint is now out! Much of the work was led by Selena @sesameandrea and Kaori. 1/8
Our preprint is out on bioRxiv! We measured monomeric protein yield in E. coli at scale and built predictors to help guide protein design. Huge thanks to all my co-authors and collaborators! 1/6 biorxiv.org/content/10.64898…


Today we are excited to release Artios, a fully open source system for designing functional de novo enzymes. Enzymes present a new frontier for de novo protein design models due to the challenge of coordinating precise chemistry, rather than binding a target. Enzymes are life’s biological machines and by designing them we can truly start to engineer biology. We believe these fundamental capabilities should be built in the open and shared with the community to progress science faster. 🧵 1/6

Public preview of BioEmu2! @MSFTResearch AI for Science’s new foundation model for biomolecular structure, dynamics and function. Open weights, MIT license. github.com/microsoft/bioemu2 Movie: BioEmu2-simulated binding of intrinsically disordered peptide PUMA to MCL-1 receptor. 🧵⬇️

Nice! Others are; -LenioBio -GeneScript -SinoBiological
Today we are launching RootPath BinderVerse, a cloud lab for AI-designed binders. Sequence in, binding data out in as few as 3 days, gene synthesis time included! Antibodies and Fab fragments made with CHO cells (TAT from 6 days) and CAR-Ts made with primary T cells (TAT from 10 days) can also be created from your binder sequences and tested. Trustable data at lightning speed -- Learn more at binderverse.rootpath.com

I also remember MP3/MP4 from @310ai__ doing this two years ago
I also remember Pinal doing this almost a year ago: github.com/westlake-repl/Den…

ipSAEmin - i see it everywhere, each new paper, preprint or tool in binder design. I haven't been able to find a single study demonstrating that it correlates with affinity
✨Introducing Prompteina: all-atom protein design directly from natural language✨ - Control diverse protein properties through a single text prompt - Higher predicted binding confidence than baselines - First experimentally validated de novo binders reported for GM2A 🧵

Introducing AlphaProtein Novo, a pipeline for de novo enzyme design! In collaboration with @francesarnold's group, we developed AP Novo and used it to get SoTA "novel-scaffold" activity on 2 benchmark reactions and create enzymes to synthesize the pharmaceutical motif piperidine and degrade the environmental toxin DEHP. Work led by @ZvxyWu @ZiqiLi0513 with teammates @alexechu_ @kelly_ruijie @schulluc @jacobjinkelly @rosaliags @davidla @solserpens @j_reisenbauer, @pengliu_group, Josh, Thomas, Amy, Tristan, Harshnira, and others. It was a joy and privilege to work with you all! Preprints and code: biorxiv.org/content/10.64898… biorxiv.org/content/10.64898… github.com/google-deepmind/a…

Biosecurity is too important for security theater. In a quick test with Raygun, we found that DeepMind's SynthIDBio watermark signal could be washed out while preserving the predicted structure. We don’t think protein sequence watermarks buy much biosecurity.

This is the worst idea since NFTs
Very happy to announce that our team @GoogleDeepmind has pushed the boundaries of generative biology, achieving the successful synthesis of AI-designed proteins that are both functional and watermarked. This proof-of-concept watermarking of the building blocks of life is enabled by SynthID Bio, our new protein watermarking method. It is designed to safeguard the new era of AI-powered generative biology and strengthen global biosecurity. You can read my thoughts here on why watermarking AI-designed proteins is an important research breakthrough: x.com/pushmeet/status/210531…

An interesting achievement but this statement is laughable. A strength of this field is how comprehensively the metadata create a paper trail that traces the DNA of a reading frame to EM/Xray-resolved polypeptides. We should be grateful this isn’t something we need to worry about
Pushmeet Kohli @pushmeet Sep 30 Article Safeguarding the AI Era of Biology: Watermarking the Building Blocks of Life Today, we announced SynthID Bio, a method to watermark and detect AI-designed proteins, the building blocks of life. We believe this is the first time humanity has successfully synthesised AI-designed


Assume --- three of your group members - Designed binders - Using different techniques/tools - For folding they used Boltz → Protenix → ColabFold - For interface scoring/ranking somewhat similar metrics. You/PI: "can you guys also rank and check with i_pDAE, in BindCraft2. I just want to see how our binders rank/look" -One of them simply clones the repo👇& sets it up in 3 min using uv. -They paste the folded binders from Boltz → Protenix → AF2/ColabFold into one folder and run one command: "python ipdae.py designs/" -By the time they finish their coffee☕️, the results are ready. -One ranked CSV file, best binders(0-1 i_pDAE scores) first. For every seed/structures user get (i_pDAE, i_pDAE_median, Contact_Pairs, interface_Binder_Residues/interface_Target_Residues). -Plain-text report. -PyMOL views with F1–F3: ipdae_view.pml stores three scenes on the F1, F2 & F3 keys. i_pDAE values/colors/residues/surfaces in pymol/clip👇: 🔴 Deep Red (0.8–1.0): High confidence (PAE <0.5Å) 🌸 Light Red (0.6–0.8): Confident ⚪ White (0.4–0.6): Moderate / mixed 🩵 Light Blue (0.2–0.4): Uncertain 🔵 Deep Blue (0–0.2): Interface contact, unknown placement 🩶 Grey (-1): Off-interface (unscored) Dropping it tomorrow. github.com/ullahsamee/i_pDAE

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…