New preprint #Frame2seq using a structure-conditioned masked language models for protein sequence design. Outperforms #ProteinMPNN and over six times faster.
https://www.biorxiv.org/content/10.1101/2023.12.15.571823v1
https://nitter.1d4.us/DenizAkpinaro/status/1735701746201112639#m
#AI generates #proteins with exceptional binding strengths.
#bioengineering #ProteinMPNN #RFdiffusion
https://phys.org/news/2023-12-ai-generates-proteins-exceptional-strengths.html
A new study in Nature reports an AI-driven advance in biotechnology with implications for drug development, disease detection, and environmental monitoring. Scientists at the Institute for Protein Design at the University of Washington School of Medicine used software to create protein molecules that bind with exceptionally high affinity and specificity to a variety of challenging biomarkers, including human hormones.
Using X-ray crystallography at the Advanced Light Source (ALS), research scientist Banumathi Sankaran at the Berkeley Center for Structural Biology (BCSB) has helped confirm the successful design of proteins that toggle between two different shapes in response to biological triggers.
Berkeley Lab #ProteinDesign #MachineLearning #StructuralBiology #Science #RoseTTAFold #ProteinMPNN #AlphaFold2
Elly Poretsky
CellBioNews
LBNL BioSci
Phil Leung