Casanovo-TMT training corpus
training · DDA · 1 version · 1 paper
27,075,536 spectra from 2,146 Orbitrap Exploris 480 runs acquired in one laboratory, 85.6% of them TMTpro-labeled and many phosphopeptide-enriched, split by peptide 80/10/10. Not deposited yet: the paper says it will be released on publication.
| Kind | training |
| Acquisition | DDA |
27,075,536 spectra from 2,146 Orbitrap Exploris 480 runs acquired in one laboratory, 85.6% of them TMTpro-labeled and many phosphopeptide-enriched, split by peptide 80/10/10. Not deposited yet: the paper says it will be released on publication.
Versions
as described
Peptide-disjoint partitions as printed in the preprint.
spectra 27,075,536 · train 21,688,803 · validation 2,717,217 · test 2,669,516 · introduced by Casanovo-TMT: deep learning-based de novo sequencing of TMTpro-labeled peptides and phosphopeptides
No public address: this version is named in the literature but cannot be downloaded.
Trained on by (1)
- Casanovo-TMT: deep learning-based de novo sequencing of TMTpro-labeled peptides and phosphopeptides (2026) preprint as described
Methods on these papers (1)
- Casanovo-TMT 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.