310.ai

End2End AI Protein Design

[310.ai @310ai__]

Thanks to the @AMD team, 310AI’s MP5 drops soon.

[kooshiar @kooshiar]

Thanks @LisaSu for talking about MP4

Only 12d before release of our most revolutionary model MP5

[kooshiar @kooshiar]

Thanks @LisaSu for talking about MP4

Only 12d before release of our most revolutionary model MP5

[kooshiar @kooshiar]

Full report: https://t.co/trJlKtbPXm

[kooshiar @kooshiar]

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.

[Kathy Y. Wei, Ph.D. @KathyYWei1]

In our interview with Nature, we explore how AI is learning to design real, functional proteins at 310ai:
https://t.co/ZNlOTaIRn8

[kooshiar @kooshiar]

https://t.co/KMuEXxhqF2 text2protein model MP4 got featured in Nature's article on GenAI+protein https://t.co/3acKIdiQKp

[kooshiar @kooshiar]

#ScientificBreakthrough: AI-designed protein targets heart failure mechanism. First demonstration of a new, lab-verified protein designed to target cellular energy depletion in heart failure.
Experimental validation confirms successful synthesis, improved stability, and confirmed ATP binding affinity.

[310.ai @310ai__]

#Update: 310ai’s Copilot now generates highly precise #antibody designs. Enter your plain text and receive predicted antibody structures in seconds.

You can find the sample script in the link below:
https://t.co/Mba3C8rDQD

[310.ai @310ai__]

Copilot speeds up protein analysis with AI tools for folding, docking, and binding site detection. With just a few clicks, you can design variants, compare structures, and share 3D visuals in no time.

[310.ai @310ai__]

After obtaining the results of your research on Copilot, click the share button and export the 3D visualization of the #protein as an animated GIF.

[310.ai @310ai__]

#AF2BIND is a lightweight and efficient notebook designed for rapid inference on #AlphaFold2 outputs. After loading your protein into Copilot, click #FindPockets in the action box, and within seconds, the binding pockets will be displayed.

[310.ai @310ai__]

AI can help you anticipate your next moves after loading a molecule, guiding you on how to perform #docking and analyze the results for optimal interactions.

[310.ai @310ai__]

After loading your protein, open the Actions box and select #Diversify. Copilot will apply AI-driven models to generate and suggest novel protein designs in a short time.

[310.ai @310ai__]

On Copilot, you can open the Actions box and, by clicking the #FoldSeek button, quickly perform accurate and sensitive comparisons of large protein structure sets, supporting monomer and multimer searches.

[310.ai @310ai__]

Instantly visualize and design with just a click on the sequence.

[kooshiar @kooshiar]

AI-Generated Proteins Achieve 84% Expression Success in the Lab.

https://t.co/HebMePuWNU

[310.ai @310ai__]

Seamlessly go from idea to result with 310 Copilot + @adaptyvbio

1️⃣ Describe the protein you want in words.
2️⃣ Use AI to bring your vision to life.
3️⃣ Send to the lab and get results!

Example: https://t.co/KTDZScGREP

[Kathy Y. Wei, Ph.D. @KathyYWei1]

Fold ""HAPPY HALLCWEEN FRCM THREE TEN AI AS THE SEASCN CF FALLING LEAVES STARTS WE ARE CELEDRATING THE SPIRIT CF INNCVATICN THAT LEADS TC NCDEL PRISES IN PRCTEIN DESIGN WE ARE CCMMITTED TC MAKING MCLECVLE PRCGRAMMING A REALITY"

https://t.co/TZviSZEdUV

[Kathy Y. Wei, Ph.D. @KathyYWei1]

Numbers always tell an interesting story.

• RoseTTAFold from David Baker’s lab: 9 out of 32 authors are women, representing 28% female authorship.
• AlphaFold from DeepMind: 4 out of 34 authors are women, making up only 12% female authorship.

[310.ai @310ai__]

If the Protein Data Bank (PDB) hadn’t been established, #AlphaFold wouldn’t have achieved its groundbreaking success or contributed to a #NobelPrize. A huge shout-out to all the scientists who, over the years, have made the PDB a vital resource for future discoveries.