π-MNovo

algorithm

π-MNovo: algorithm. De novo sequencer adapted to microbial spectra, addressing the fact that existing models were trained largely on non-microbial proteomic data. Built on a purpose-made…

De novo sequencer adapted to microbial spectra, addressing the fact that existing models were trained largely on non-microbial proteomic data. Built on a purpose-made resource of over 10 million annotated spectra from 72 cultured microbial isolates, each digest split into five high-pH reversed-phase fractions for deeper peptide sampling, and paired with evidence-guided candidate selection. Reports 66.30% complete-peptide recall on a seven-species benchmark, 6.9-21.7% relative above four published models, and recovered 1,587 reference-matched peptides from spectra pFind left unidentified.

Kind algorithm
Deep learning yes
Acquisition DDA

Code

Live stars, open issues and last-push figures are on the Code activity chart.

Data

What the papers describing this method trained it on and reported its results on, as each paper states it. A version is named only where the paper names one.

Evaluated on

Also used, purpose not recorded

Paper describing it

Authors (12)

Jingwen Ye, Xin Zhang (NCPSB), Boyan Sun, Tianze Ling, Zhendong Liang, Jingyi Dong, Yuan Zheng, Hui Jin, Liming Jin, Zikai Hao, Leyuan Li, Cheng Chang

Seen in the charts

Back to the full map

Back to top