Publications by authors named "Hugh Yeh"
Article Synopsis
- The text discusses a new framework called BioM3 that allows for the design of proteins using natural language prompts, integrating text and protein representation in a novel way.
- This framework operates in three stages: aligning protein and text representations, refining text embeddings, and generating protein sequences using a specific model.
- BioM3 has shown impressive results in various protein-related tasks and successfully generates proteins with characteristics similar to naturally occurring ones, validated through experimental tests.
Masked inverse folding with sequence transfer for protein representation learning.
Protein Eng Des Sel
January 2023
Self-supervised pretraining on protein sequences has led to state-of-the art performance on protein function and fitness prediction. However, sequence-only methods ignore the rich information contained in experimental and predicted protein structures. Meanwhile, inverse folding methods reconstruct a protein's amino-acid sequence given its structure, but do not take advantage of sequences that do not have known structures.
View Article and Find Full Text PDFAn amendment to this paper has been published and can be accessed via a link at the top of the paper.
View Article and Find Full Text PDFHere, we report a rapid CRISPR-Cas9-mediated gene knock-in strategy that uses Cas9 ribonucleoprotein and 5'-modified double-stranded DNA donors with 50-base-pair homology arms and achieved unprecedented 65/40% knock-in rates for 0.7/2.5 kilobase inserts, respectively, in human embryonic kidney 293T cells.
View Article and Find Full Text PDF