Tuesday, September 26, 2023

InstaNovo - Can neural networks make real de novo peptide sequencing a reality?

 

Full disclaimer - I can't follow all the words in this new manuscript. It is very computer science term (?) heavy. Honestly, if I hadn't found on page 35 that this code is available it wouldn't have made it on the blog, but from the proteomics data I can follow it looks really promising.


If you're a computational nerd person, I think this is what you want (Github). 

From what I can get, at very reasonable FDR, InstaNovo is identifying as much as 50% of human peptides that are known - with no database at all. None. Sure, having a database for something you have one for looks better, but this opens up a tremendous number of things that we don't have sequences for at all. They pressure test this with less used enzymes (GluC) and do some HLA/MHC peptides and some mixed proteomic samples (metaproteomics). 


1 comment:

  1. Thanks for sharing our work! Our InstaNovo article has now been published in Nature Machine Intelligence: https://www.nature.com/articles/s42256-025-01019-5.

    We know there are quite a few computer science-heavy terms in there, so we also put together a blog post that explains the research in a more accessible way:
    https://www.instadeep.com/2025/03/enhancing-peptide-sequencing-with-ai/

    If you’d like to try InstaNovo yourself, we’ve set up a Hugging Face Space where you can test it with your own data:
    https://huggingface.co/spaces/InstaDeepAI/InstaNovo

    Would love to hear what you think! 😊

    ReplyDelete