4 docs tagged with "de novo design"

MP3 is a transformer-based AI model for molecule programming that can be used for redesign, diversification, or de novo (from scratch) design of protein sequences.

MP4 is a general transformer-based text2protein AI model for molecule programming. It is capable of redesigning (fixed or variable length) based on a given input sequence or completely de novo design based on input text describing protein function. Over 1,000 de novo text2protein examples designed by MP4 can be found in a repo here. And over 6,000 text2enzyme examples covering Enzyme Commission (EC) space designed by MP4 can be found here.

Protein design involves creating proteins with specific functions by manipulating their amino acid sequences. This process allows scientists to develop a range of applications, such as anti-cancer drugs (e.g., antibodies), gene editing tools (e.g., Cas9), laundry detergents (e.g., amylases), and digestible milk (e.g., lactases). While protein engineering typically refers to small modifications of natural proteins, protein design encompasses more extensive alterations. De novo protein design specifically refers to creating sequences from scratch.

ProtGPT2 is an AI transformer method for unconditional de novo protein sequence generation.