I wrote a short post about the danger of AI in biology as a response to a post in HN that downplayed the risk posed by AI, narrowing it down to “AI designed viruses”. I think it missed the point.
substack.com/home/post/p-217…
22
LiorZ retweeted
In 1965, Margaret Dayhoff published the Atlas of Protein Sequence and Structure, which collated the 65 proteins whose amino acid sequences were then known.
Inspired by that Atlas, today we are releasing the Dayhoff Atlas of protein sequence data and protein language models.
Starting a SaaS business in the space of drug design or discovery? think again!
This is my latest post on a blog I started not long ago.
liorz.github.io/blog/posts/s…
1
82
LiorZ retweeted
🚀 𝗦𝗼𝗹𝘃𝗜𝗧 by Enzymit is now open source on GitHub!
🎉 SolvIT is a GNN based protein solubility prediction model with state-of-the-art accuracy.
🔗 Explore: GitHub [github.com/Enzymit/SolvIT] | PNAS: 10.1073/pnas.2313809121
LiorZ retweeted
.@enzymit raises $10 million Series A for cell-free bio-production technology.
The Israeli startup is building a cell-free production platform that aims to make bioproduction faster, simpler, cost-effective, and scalable.
calcalistech.com/ctechnews/a…
LiorZ retweeted
💸 Can software-only protein design companies succeed in biotech? or is it all a hype?
Read the full analysis of our CEO Gideon Lapidoth:
medium.com/enzymit-log/thoug…
LiorZ retweeted
Introducing Genie 2, our latest protein design model! Genie 2 sets a new state of the art on key design metrics and supports motif scaffolding, including that of multiple motifs with undefined geometric relationships, a feature new to protein diffusion models. (1/5)
If you believe that the complete lack of source code access for AlphaFold3 does not align with the principles of scientific progress, then please consider signing this letter.
We were incredibly disappointed with the lack of code or executable accompanying the publication of AF3 in @Nature . This contradicts scientific principles of the ability to evaluate, use, and build upon existing work. zenodo.org/records/11179894
500
LiorZ retweeted
If you watch one thing today…
A lot has been and can be said about @joerogan but I gotta hand it to him for actually listening and having some integrity.
This is an important video.
LiorZ retweeted
Register today for this free @SynBioBeta event: synbiobeta.zoom.us/webinar/r…
Do you know someone who is doing exceptional work in the field of protein design and/or modeling? Please nominate them to give a talk at BPDMC! We host speakers at any career stage, and self nominations are also accepted.
forms.gle/ZZ258AhNu7uJhUUG7
LiorZ retweeted
Poster call! Are you an early-career researcher using #imagingtechnologies or #proteintools in #neurobiology? We’re now accepting abstracts for #IPILightingUp, a symposium in June. Find out more & submit your abstract! proteininnovation.org/lighti…
LiorZ retweeted
THEY SAID WE COULDN'T DO IT........well, no one actually said that. But in our updated manuscript with @CasperGoverde, @GoldbachNico, and @befcorreia we show you can now design soluble analogues of membrane proteins with preserved functional features!
biorxiv.org/content/10.1101/…
RFDiffusion All-atom is out (Both code, and peer reviewed paper)
This is another one of those transformative moments in a series of scientific breakthroughs that took place in the last years in comp protein design.
Paper: science.org/doi/10.1126/scie…
Code: github.com/baker-laboratory/…
93
Our paper is out in #PNAS!
in short, we show that under simple assumptions AlphaFold reliably graft protein segments onto a homologous template.
We demonstrated our method on enzymes, molecules that are notoriously sensitive to backbone perturbations. pnas.org/doi/10.1073/pnas.23…
Structural basis of assembly and torque transmission of the bacterial flagellar motor. Dam'n, Nature is impressive.
cell.com/cell/fulltext/S0092…
1
69
Multi-indicator Comparative Evaluation for Deep Learning-Based Protein Sequence Design Methods
A comparison between different sequence design methods. Would love to see this kind of comparison done with experimental part as well
academic.oup.com/bioinformat…
3
92

















