Ariel Ben-Sasson

The IPD is looking to hire a full time on site Public Information Specialist! wd5.myworkdaysite.com/en-US/recruiti…

One command install: > brew tap Arielbs/claude-usage-monitor github.com/Arielbs/claude… &&brew install --cask claude-usage-monitor > GitHub: github.com/Arielbs/claude…

#claudecode has been the most transformative day-to-day tool in science & engineering recently, #protein engineering in my case... Hitting quota became both my hobby and my "please not now" moment, so I've let #claudecode build a little menu bar app for MacBooks to track itself.

@ssiddhant_ @PyRosetta @RosettaCommons @cursor_ai Thanks, of course, or even much easier to directly install it as your local npm server. 📦 NPM: lnkd.in/gtaiFZGy

@Arielbs100 @PyRosetta @RosettaCommons @cursor_ai Just adding it here for easy access: github.com/Arielbs/rosett…

Rosetta MCP server #Rosetta, #RosettaScripts, @PyRosetta , and @RosettaCommons docs are now accessible as modular components in agentic workflows. Translate XML scripts into PyRosetta code, let your agent reason on mover functionality, and more in your MCP enabled @cursor_ai IDE

You can find it here: 🔗 GitHub: lnkd.in/gXib8Mtp 📦 NPM: lnkd.in/gtaiFZGy

@DidiKieran @biotite_python Thanks @DidiKieran! @biotite_python is awesome and it's great to see platform tools like Atomworks being built on top of it

AtomWorks is out! Building upon @biotite_python, we built for a toolkit for all things biomolecules and trained RF3 with it. All open-source, test it via `pip install atomworks`! AtomWorks: github.com/RosettaCommons… RF3: github.com/RosettaCommons… Paper: tinyurl.com/y2w4z65b 1/6

@KeystoneSymp (Non-scientific update!) Broke my high-altitude (3,000 meters) 10K snow-run record today here in Keystone! Only minutes after presenting our work in the “Machine Learning for Protein Design” session. 🚀❄️🏃‍♂️ #ProteinDesign #MachineLearning #KeystoneSymposia

I’m excited to give a Short Talk about protein compression and drugs generation at @KeystoneSymp #MachineLearning Applied to Macro#MolecularStructure and Function, this March! Looking forward to meet old and new friends and colleagues and explore emerging research in Keystone!

📢Excited to introduce NanoCas -our new mini CRISPR system that can reach tissues previously out of reach! By shrinking CRISPR to 1/3 its normal size, we can now edit genes in muscle, heart & brain that were difficult to access before. Summary & link to paper:

@olexandr @lnkldt I don't understand this argument. Preclinical + clinical trials duration is a minimum of 6 years. De novo designed proteins became practical during 2022. Why would you expect an approved drug based on that technology before late 2028 or after?

@lnkldt Show me FDA approved drugs 😉

Wow… real AI in drug discovery shots fired 😎 chemistryworld.com/opinion/robots… “It sounds like someone trying to sell a new car model by pointing out that its windows roll up and down much more quickly” #compchem

Best read of the day - innovative design, and great science to generate large virus-like protein cages by breaking symmetry 🎉 nature.com/articles/s4158… nature.com/articles/s4158… nature.com/articles/s4146… Quinton Dowling, @lsmin0152 @kribler @KingLabIPD @UWproteindesign

@ZiboChen That's so cool Zibo, I was waiting to see this work published!

Excited to finally share Perceptein, a PERCEPtron made of proTEINs: science.org/doi/10.1126/sc…

1/🧬 Excited to share PLAID, our new approach for co-generating sequence and all-atom protein structures by sampling from the latent space of ESMFold. This requires only sequences during training, which unlocks more data and annotations: bit.ly/plaid-proteins 🧵

Chai-1 has always been available for commercial use via our server. Today, we're also making Chai-1(r) code and weights available under an Apache 2.0 license, which permits broad commercial use. github.com/chaidiscovery/…

@adam_broerman Congrats Adam! And coworks. Great step in advancing multi state de novo protein design!

Excited to announce our new #proteindesign strategy for allosterically controlling the kinetics of protein-protein interactions! Read on for cool applications in cytokine signaling, biosensing, and protein circuits. biorxiv.org/content/10.110…

@BiologyAIDaily Great work and important, is github repo to be released ?

pLDDT-Predictor: High-Speed Protein Screening Using Transformer and ESM2 • pLDDT-Predictor introduces a fast and accurate tool for protein structure quality assessment, predicting pLDDT scores from sequences using Transformer architecture combined with ESM2 embeddings. • The model bridges the gap between high-throughput screening and computational cost by providing near-AlphaFold2 accuracy in milliseconds, allowing the screening of over 100 proteins per second on a single GPU. • It leverages ESM2 embeddings to capture evolutionary and structural information from sequences, feeding them into a Transformer model to predict pLDDT scores efficiently. • Compared to AlphaFold2 and ESMFold, which require minutes to hours per protein, pLDDT-Predictor completes its prediction in an average of 0.007 seconds per sequence. • The model shows strong performance on benchmark datasets, achieving a Pearson correlation of 0.78 with AlphaFold2-generated pLDDT scores and minimizing errors with an MSE of 84.8. • Its scalable design and use of distributed data parallel (DDP) training across multiple GPUs ensure fast processing and minimal training time, supporting large-scale protein engineering and drug discovery efforts. • Future directions include addressing performance on very long protein sequences and expanding the model to predict other structural quality metrics. 📜Paper: arxiv.org/abs/2410.21283 #ProteinEngineering #Bioinformatics #StructuralBiology #AlphaFold #HighThroughput #MachineLearning #AIforBiology

@andrewwhite01 Antibodies can do so many things, but that’s only a fraction of what is possible.

Why is everyone working on de novo miniprotein binders again? Do they create drugs or do something antibodies cannot do?

@rohitsingh8080 Congrats @rohitsingh8080 for the excellent work! Beyond the natural vs. de novo protein design debate, this work could deepen our understanding of minimal sequence-function relationships, with exciting implications for creating (at @ZipBio_Inc as well) compact #bio-therapeutics.

De novo protein design is great, but nature has millions of proteins- why not repurpose them? Introducing Raygun, a new approach to protein design. It allows you to miniaturize, magnify or modify any protein. We synthesized miniaturized variants of eGFP and mCherry! 1/

We are not a cult... Anymore