The Proteome Landscape of the Kingdoms of Life
benchmark · DDA · 3 versions · 9 papers
| Kind | benchmark |
| Acquisition | DDA |
| Organisms | Arabidopsis thaliana (mouse-ear cress), Bos taurus (bovine), Caenorhabditis elegans, Danio rerio (zebrafish) (brachydanio rerio), Dictyostelium discoideum (slime mold), Drosophila melanogaster (fruit fly), Escherichia coli, Gallus gallus (chicken), Homo sapiens (human), Mus musculus (mouse), Rattus norvegicus (rat), Saccharomyces cerevisiae (baker’s yeast), Sus scrofa domesticus (domestic pig), Triticum aestivum (wheat), Vitis vinifera (grape) |
A cross-kingdom proteomics survey, deposited as two accessions and reused as a generalisation test across species.
Versions
as deposited
released 2019-08-01
Where it lives:
capped de novo test (dIon)
Run-disjoint, multi-species de novo test corpus from PXD019483: 70 species, at most 100,000 spectra per species. Filter the species column for the per-species evaluations.
test 4,926,232 · 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/kingdoms de_novo/kingdoms
representation benchmark (dIon)
Run-disjoint validation and test populations for spectrum retrieval and pair discrimination, not peptidoform-disjoint. Distinct from dIon’s capped de novo test.
validation 658,738 · test 4,112,590 · 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#representation_benchmarks/kingdoms representation_benchmarks/kingdoms
Deposited by (1)
- dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra (2026) preprint capped de novo test (dIon), representation benchmark (dIon)
Used by (8)
- Learning from tandem mass spectra at scale with a self-supervised foundation model for proteomics (2026) preprint as deposited
- π-HelixNovo2: Making Accurate Online De Novo Peptide Sequencing Available to All (2026) peer-reviewed as deposited
- A large-scale unified deep learning model for peptide mass spectrum interpretation trained on multimodal data (2026) peer-reviewed as deposited
- π-MSNet: A billion-scale, AI-ready living proteomics data portal (2026) preprint as deposited
- De novo peptide sequencing rescoring and FDR estimation with Winnow (2025) preprint as deposited
- π-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing (2024) preprint as deposited
- Accurate de novo peptide sequencing using fully convolutional neural networks (2023) peer-reviewed as deposited
- PepNet: A Fully Convolutional Neural Network for De novo Peptide Sequencing (2022) preprint as deposited
Methods on these papers (8)
- InstaNovo-FM algorithm
- PepNet algorithm
- Winnow post-processor
- dIon algorithm
- pUniFind algorithm
- π-HelixNovo2 algorithm
- π-MSNet adjacent
- π-PrimeNovo 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.