Kathy Y. Wei, Ph.D.
@KathyYWei1
CSO http://310.ai. AI/ML protein design expert. According to ChatGPT: writing the future of biology — one protein at a time :)
AI Designing Functional Proteins from Plain Text Prompts?@Nature "I told AI to make me a protein. Here’s what it came up with" 1. Scientists are developing a new generation of AI tools that can translate plain language instructions into protein designs and other biological…
Proteins are the new yarnballs?
Alright, last one, now need to get back to real work... 😸
Alright, last one, now need to get back to real work... 😸
Definitely not as cute as the cat force, but still a fun roller coaster ride through a xtal of a novel sequence! Thanks to NimaAI. Prompt: Nima, please make it look cool 😎
We’re making a few intentional changes to our US-based Rosetta conferences next year to better support our growing community. We want to hear what you think. Learn more about the changes: rosettacommons.org/2025/06/26/loo… Share your thoughts: docs.google.com/forms/d/e/1FAI…
First CASP... now Machine Learning in Structural Biology (MLSB)... sad to see workshop getting cut by Neurips. 😭
Unfortunately, the MLSB Workshop @ NeurIPS (@workshopmlsb) was rejected this year. Feedback from the deciding committee indicates it was a coin flip decision, with 283 proposals & a number related to “computational biology” More on the future of MLSB soon…
Thanks @LisaSu for talking about MP4 Only 12d before release of our most revolutionary model MP5
Thanks to the @AMD team, 310AI’s MP5 drops soon.
Thanks @LisaSu for talking about MP4 Only 12d before release of our most revolutionary model MP5
Is creative AI the best AI 🤔?
Our AI model MP4 designed 93 GLP-1R agonists. 67% outperformed the native peptide in experimental testing. To our surprise, the more creative the AI got, the greater the activity gains.
Matterworks would like to thank our #ASMS2025 poster collaborators: @JNJNews, @dsmfirmenich, @corteva, @bruker, @310ai__, @thermosci, and Metalytics. 🔎 For a full list of our posters, visit (hubs.la/Q03pxTYV0) Thank you to all the organizers for an excellent program.
Can citizen scientists design real drugs? Check out Drugit: nature.com/articles/s4146…
RareFold predicts and designs proteins with noncanonical AAs. With EvoBindRare, we designed linear & cyclic peptide binders with high affinity & novel binding modes, validated in wet lab. A step toward next-gen therapeutics. 📄 biorxiv.org/content/10.110… 💻 github.com/patrickbryant1…
You can now design binders with 49 different amino acids of both linear and cyclic topologies. We also made it a lot more efficient, for the validated target we only used 1 GPU vs 24 with our previous model. Try it: github.com/patrickbryant1…
RareFold predicts and designs proteins with noncanonical AAs. With EvoBindRare, we designed linear & cyclic peptide binders with high affinity & novel binding modes, validated in wet lab. A step toward next-gen therapeutics. 📄 biorxiv.org/content/10.110… 💻 github.com/patrickbryant1…
Even in the era of AlphaFold, can't help but get super excited at a beautiful xtal! Thanks @adaptyvbio
I told AI to make me a protein. Here's what it came up with - Nature nature.com/articles/d4158… #MachineLearning
I told AI to make me a protein. Here’s what it came up with nature.com/articles/d4158…