Get the latest tech news

Hallucination of closed repeat proteins containing central pockets (2023)


Here, the authors constructed a deep-learning approach to design closed repeat proteins with central binding pockets—a step towards designing proteins to specifically bind small molecules.

c, Representative design trajectory showing the optimization of predicted local distance difference test (pLDDT, teal) and cyclic loss (dark blue) over 300 steps, with dashed lines indicating our selected score cutoffs. Linna An, Derrick R. Hicks, Dmitri Zorine, Justas Dauparas, Basile I. M. Wicky, Lukas F. Milles, Alexis Courbet, Asim K. Bera, Hannah Nguyen, Alex Kang, Lauren Carter & David Baker Linna An, Derrick R. Hicks, Dmitri Zorine, Justas Dauparas, Basile I. M. Wicky, Lukas F. Milles, Alexis Courbet, Asim K. Bera, Hannah Nguyen, Alex Kang, Lauren Carter & David Baker

Get the Android app

Or read this on Hacker News

Read more on:

Photo of hallucination

hallucination

Photo of central pockets

central pockets

Related news:

News photo

Hospitals use a transcription tool powered by a hallucination-prone OpenAI model

News photo

Google’s DataGemma AI is a statistics wizard

News photo

Exclusive: Alembic debuts hallucination-free AI for enterprise data analysis and decision support