Designed active-site library reveals thousands of functional GFP variants
Weinstein, J. Y.; Aldaravi, C. M. G.; Lipsh-Sokolik, R.; Hoch, S. Y.; Liebermann, D.; Nevo, R.; Weissman, H.; Petrovich-Kopitman, E.; Margulies, D.; Ivankov, D.; McCandlish, D.; Fleishman, S. J.
Show abstract
Mutations in a protein active site can lead to dramatic and useful changes in protein activity. The active site, however, is extremely sensitive to mutations due to a high density of molecular interactions, drastically reducing the likelihood of obtaining functional multipoint mutants. We introduce an atomistic and machine-learning-based approach, called htFuncLib, to design a sequence space in which mutations form low-energy combinations that mitigate the risk of incompatible interactions. We applied htFuncLib to the GFP chromophore-binding pocket, and, using fluorescence readout, recovered >16,000 unique designs encoding as many as eight active-site mutations. Many designs exhibit substantial and useful diversity in functional thermostability (up to 96 {degrees}C), fluorescence lifetime, and quantum yield. By eliminating incompatible active-site mutations, htFuncLib generates a large diversity of functional sequences. We envision that htFuncLib will be useful for one-shot optimization of activity in enzymes, binders, and other proteins.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Accuracy and data efficiency in deep learning models of protein expression 97%
- Generalizable and scalable protein stability prediction with rewired protein generative models 96%
- A Multiplexed Bacterial Two-Hybrid for Rapid Characterization of Protein-Protein Interactions and Iterative Protein Design 96%
Similar papers in this journal
- The amino acid sequence determines protein abundance through its conformational stability and reduced synthesis cost. 96%
- Learning deep representations of enzyme thermal adaptation 95%
- COLLAPSE: A representation learning framework for identification and characterization of protein structural sites 94%
Similar papers in this journal
- Direct prediction of intrinsically disordered protein conformational properties from sequence 95%
- Engineered allostery in light-regulated LOV-Turbo enables precise spatiotemporal control of proximity labeling in living cells 94%
- Reliability and accuracy of single-molecule FRET studies for characterization of structural dynamics and distances in proteins 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.