Back

Orthrus: an AI-powered, cloud-ready, and open-source hybrid approach for metaproteomics

Chiang, Y.; Collins, M. J.

2024-11-15 bioinformatics
10.1101/2024.11.15.623814 bioRxiv
Show abstract

While metaproteomics provides invaluable insight into microbial communities and functions, significant bioinformatics challenges persist due to data complexity and the limitations of database searching. We introduce Orthrus, a hybrid approach combining transformer-based de novo sequencing (Casanovo) and database searching with rescoring (Sage+Mokapot). Benchmarking against PEAKS(R)11, MaxQuant, and MetaNovo, Orthrus demonstrates high peptide outputs, taxonomic diversity, and proteome coverage. Orthrus is Python-based and accessible to all via Google Colaboratory.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.