NIST peptide tandem mass spectral libraries
training · 2 versions · 6 papers
NIST’s consensus libraries of annotated peptide spectra, per organism and per instrument, used as training data by spectrum-to-sequence models since PepNet.
| Kind | training |
| Organisms | Homo sapiens and other species |
| Home | https://chemdata.nist.gov/dokuwiki/doku.php?id=peptidew:cdownload |
NIST’s consensus libraries of annotated peptide spectra, per organism and per instrument, used as training data by spectrum-to-sequence models since PepNet.
Versions
H. sapiens Orbitrap HCD
NIST’s human Orbitrap HCD library. DpNovo trains on its ‘Library 1 (best)’, 398,373 spectra.
No public address: this version is named in the literature but cannot be downloaded.
synthetic HCD
NIST’s HCD library of synthetic peptides, which PepNet names beside its human HCD library.
No public address: this version is named in the literature but cannot be downloaded.
Trained on by (5)
- π-HelixNovo2: Making Accurate Online De Novo Peptide Sequencing Available to All (2026) peer-reviewed synthetic HCD
- PowerNovo: de novo peptide sequencing via tandem mass spectrometry using an ensemble of transformer and BERT models (2024) peer-reviewed version not stated
- Accurate de novo peptide sequencing using fully convolutional neural networks (2023) peer-reviewed synthetic HCD
- DpNovo: A DEEP LEARNING MODEL COMBINED WITH DYNAMIC PROGRAMMING FOR DE NOVO PEPTIDE SEQUENCING (2023) thesis H. sapiens Orbitrap HCD
- PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing (2022) preprint synthetic HCD
Evaluated on by (3)
- PowerNovo2: A generative flow-based approach to non-autoregressive de novo peptide sequencing (2026) peer-reviewed version not stated
- PowerNovo: de novo peptide sequencing via tandem mass spectrometry using an ensemble of transformer and BERT models (2024) peer-reviewed version not stated
- DpNovo: A DEEP LEARNING MODEL COMBINED WITH DYNAMIC PROGRAMMING FOR DE NOVO PEPTIDE SEQUENCING (2023) thesis version not stated
Methods on these papers (5)
- DpNovo algorithm
- PepNet algorithm
- PowerNovo algorithm
- PowerNovo2 algorithm
- π-HelixNovo2 algorithm
Taken from the describing links only, so a paper that merely ran a tool on this data does not make that tool a method of it.