CNN
4 methods · 2020–2024
CNN: Convolutional networks without a recurrent decoder, reading the spectrum as a signal over the m/z axis. Used where the output is a score or a local call rather than a sequence emitted left to right.
Convolutional networks without a recurrent decoder, reading the spectrum as a signal over the m/z axis. Used where the output is a score or a local call rather than a sequence emitted left to right.
The earliest of its 4 methods is RANovo (2020); 3 more have followed.
| Methods | 4 |
| Papers describing them | 6 |
| Authors | 24 |
| Active | 2020-12-13 to 2024-01-02 |
| Deep learning | 4 of 4 |
| Kinds | algorithm (2), adjacent, post-processor |
| Acquisition | DDA (4) |
Methods (4)
Oldest first, by the paper that describes each one.
- RANovo (2020): A residual network with an attention mechanism for de novo peptide sequencing.
- PepNet (2022): Temporal convolutional network
- Spectralis (2023): AA-gapped convolutional layer
- GlycanFinder (2023): Glycopeptide sequencing
How they score
1 of the 4 has been run on denovo_benchmarks, which ranks 14 tools over 86 datasets. The family’s best median rank is 8.
- Spectralis: median peptide-level average precision 0.729, median rank 8 of 14
Read these next to the rest of the field, not on their own: what the numbers mean.
Papers describing them (6)
- A residual network for de novo peptide sequencing with attention mechanism (2020, 2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV), peer-reviewed)
- PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing (2022, Research Square, preprint)
- Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing (2023, bioRxiv, preprint)
- Glycopeptide database search and de novo sequencing with PEAKS GlycanFinder enable highly sensitive glycoproteomics (2023, Nature Communications, peer-reviewed)
- Accurate de novo peptide sequencing using fully convolutional neural networks (2023, Nature Communications, peer-reviewed)
- Deep learning-driven fragment ion series classification enables highly precise and sensitive de novo peptide sequencing (2024, Nature Communications, peer-reviewed)