Tag
ProtStructQA introduces an executable benchmark for protein structural question answering that compiles natural language queries into a typed DSL program to evaluate LLMs on precise 3D measurements, revealing a capability-dependent denotation threshold where chain-of-thought becomes strongly beneficial above a certain model scale.
ESMFold2 is an open-source AI model for protein structure prediction that achieves state-of-the-art performance on protein interactions and antibodies, with a massive structure database (ESM Atlas).
Dr. Steven Mascall shares his personal story from neural network research in 1988 to building the AI Steve system, and developing an app for commemorating loved ones and friends, as well as a food health app, emphasizing dopamine-driven curiosity and the arrival of the era of the super individual.
This PhD thesis introduces deep learning methods for protein complex prediction and design, including GLINTER for contact prediction, ESMPair for homolog pairing, and RedNet for binder design.
This article reflects on the five-year impact of AlphaFold since its 2020 breakthrough, highlighting its role as a global scientific tool used by millions of researchers and its recognition with the 2024 Nobel Prize in Chemistry.
Researchers used AlphaFold and cryo-EM to map the structure of the apoB100 protein, which forms bad cholesterol, marking a significant breakthrough in understanding heart disease.
DeepMind's AI tools (including Gemini) reduce the time to analyze bacterial protein structures from years to 6 minutes, and generate unexpected drug design ideas, accelerating the discovery of new antimicrobial drugs, potentially getting ahead of antibiotic resistance.