Innocent Byiringiro
@inno250.bsky.social
PhD student. 🌱genome engineering/🌱 epigenetic engineering/protein design…PLSC/UMD
Reposted by Innocent Byiringiro
ProteinMPNN trained exclusively on proteins from thermophiles, with some experimental validation www.biorxiv.org/content/10.1...
HyperMPNN ‒ A general strategy to design thermostable proteins learned from hyperthermophiles
Stability is a key factor to enable the use of recombinant proteins in therapeutic or biotechnological applications. Deep learning protein design approaches like ProteinMPNN have shown strong performa...
www.biorxiv.org
December 2, 2024 at 11:26 AM
ProteinMPNN trained exclusively on proteins from thermophiles, with some experimental validation www.biorxiv.org/content/10.1...
Reposted by Innocent Byiringiro
Nice paper from Jenn Prescher and colleagues on tags for bioluminescence imaging of RNAs. www.nature.com/articles/s41...
A modular platform for bioluminescent RNA tracking - Nature Communications
Studying RNA dynamics in vivo often relies on fluorogenic approaches, but these can be hampered by factors such as limited sensitivity and sample autofluorescence. Here, the authors describe an ultras...
www.nature.com
December 2, 2024 at 11:54 PM
Nice paper from Jenn Prescher and colleagues on tags for bioluminescence imaging of RNAs. www.nature.com/articles/s41...
Reposted by Innocent Byiringiro
Major breakthrough in AI-assisted protein engineering! This is highly significant, as it enables the rapid design & evolution of protein activity using few-shot active learning. EVOLVEpro is achieving up to 100-fold improvements in protein properties and functions! 🤯 www.science.org/doi/10.1126/...
Rapid in silico directed evolution by a protein language model with EVOLVEpro
Directed protein evolution is central to biomedical applications but faces challenges like experimental complexity, inefficient multi-property optimization, and local maxima traps. While in silico met...
www.science.org
November 23, 2024 at 1:58 AM
Major breakthrough in AI-assisted protein engineering! This is highly significant, as it enables the rapid design & evolution of protein activity using few-shot active learning. EVOLVEpro is achieving up to 100-fold improvements in protein properties and functions! 🤯 www.science.org/doi/10.1126/...