Casanovo digestion enzyme bias data
deposit · DDA · 2 versions · 4 papers
| Kind | deposit |
| Acquisition | DDA |
Data supporting “Accounting for digestion enzyme bias in Casanovo”.
Versions
as deposited
released 2024-06-28 · introduced by Accounting for Digestion Enzyme Bias in Casanovo
Where it lives:
- DOI · 10.5281/zenodo.12587317
MSKB-final (dIon)
Casanovo’s official MassIVE-KB train/test partition, processed to Lance, with a small validation set carved from training by canonical peptidoform (seed 42). A 196,979-spectrum charge 1-4 subset of the test split is kept for comparisons with Casanovo.
train 1,989,996 · validation 10,004 · test 200,000 · released 2026-10-09 · introduced by dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra
Where it lives:
- Hugging Face · alfred-n/dIon-datasets#de_novo/corpora/MSKB-final de_novo/corpora/MSKB-final
Deposited by (2)
Each of these introduced a DIFFERENT version, listed beside it; a deposit itself happens once.
- dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra (2026) preprint MSKB-final (dIon)
- Accounting for Digestion Enzyme Bias in Casanovo (2024) peer-reviewed as deposited
Used by (2)
- Learning Fragmentation Physics or Exploiting Sequence Priors? Benchmarking Bias in Deep Learning Models for De Novo Peptide Sequencing (2026) preprint as deposited
- Protein Language Model-Aligned Spectra Embeddings for De Novo Peptide Sequencing (2025) preprint as deposited
Methods on these papers (4)
- Casanovo algorithm
- PLMNovo algorithm
- Prior-vs-physics benchmark for DL de novo sequencing benchmark
- dIon 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.