De novo protein design has the potential to produce superior combinations of mechanical qualities and unique functionalities, boosting biological and engineering applications. Testing the enormous amount of potential amino acid sequences, in addition to the experimental expenses related to creating novel proteins with specific structural traits or properties, is still a difficult task.
Researchers have used attention-based diffusion models to effectively produce unique protein sequences with predetermined secondary structures in a work that was published in the journal Chem.
De novo protein design has the potential to produce superior combinations of mechanical qualities and unique functionalities, boosting biological and engineering applications. Testing the enormous amount of potential amino acid sequences, in addition to the experimental expenses related to creating novel proteins with specific structural traits or properties, is still a difficult task.
Researchers have used attention-based diffusion models to effectively produce unique protein sequences with predetermined secondary structures in a work that was published in the journal Chem.
The diffusion models were found to efficiently design proteins with secondary structure specifications and de novo amino acid sequences that have not been discovered previously.
The generative models provided robust results, even for imperfect-type inputs and unrealistic designs. As a result, the use of these models has the potential be expanded to generate proteins with other clinically and functionally relevant properties.
The per-residue secondary structure-based model was more accurate and yielded more diverse amino acid sequences, particularly for α-helical structures.
