Spectralis
post-processor · CNN
Spectralis: post-processor · CNN. AA-gapped convolutional layer
AA-gapped convolutional layer
| Kind | post-processor |
| Deep learning | yes |
| Acquisition | DDA |
| Family | CNN |
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.
Trained on
Evaluated on
- A deep proteome and transcriptome abundance atlas of 29 healthy human tissues (as deposited) · 2023 preprint, 2024 peer-reviewed
- Nine-species benchmark (version not stated) · 2024 peer-reviewed
- Nine-species benchmark (original (DeepNovo, 2017)) · 2024 peer-reviewed
Also used, purpose not recorded
- Casanovo data set and model weights (as deposited) · 2024 peer-reviewed
Benchmarks
- denovo_benchmarks: median peptide-level average precision 0.729 over 86 datasets, median rank 9 of 15 (version bm-1.0.0).
Both are mass-based matches on the tool’s most recent run. What these numbers mean.
Papers describing it (2)
- Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing (2023, bioRxiv, preprint)
- Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing (2024, Nature Communications, peer-reviewed)