# PROSPECT PTMs Precursor Charge Prediction: Peptide Charge-State Labels from ProteomeTools Mass Spectrometry

## Facts

- Provider: Wilhelmlab, Technical University of Munich
- License: CC-BY-4.0 (https://huggingface.co/datasets/Wilhelmlab/prospect-ptms-charge)
- Size: 7 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/Wilhelmlab/prospect-ptms-charge
- Access: public, readable without an account
- Category: Proteomics
- Source: https://huggingface.co/datasets/Wilhelmlab/prospect-ptms-charge
- Page: https://scigantic.com/archive/9387bccb-8567-5d29-b2ba-4175fb8df0e9
- Keywords: Proteomics, benchmark, Parquet, Hugging Face

## About

A benchmark for predicting the precursor charge state of a peptide in tandem mass spectrometry from its sequence, built by the Wilhelm lab (Technical University of Munich) from the PROSPECT PTMs datasets on Zenodo, which in turn come from the ProteomeTools synthetic peptide data on PRIDE. Each peptide carries three labels aggregated over all its observations: the most abundant charge state (one-hot), all observed charge states (k-hot) and the charge-state distribution (proportions); optional features encode post-translational modifications and experimental settings. Two configurations: default, with train, validation and test splits from the PROSPECT PTMs sets, and holdout, a test-only set from the PROSPECT Test-PTM dataset reserved for final benchmarking of PTM-aware models. Parquet, about 0.45 GB; load with datasets.load_dataset('Wilhelmlab/prospect-ptms-charge') or with the 'holdout' config. Complements the PROSPECT PTMs fragment intensity (MS2) and retention time (iRT) sets. Licensed CC BY 4.0 by Wilhelmlab, TUM; cite PROSPECT (Shouman et al., NeurIPS 2022) and ProteomeTools (Zolg et al., 2017).

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("Wilhelmlab/prospect-ptms-charge")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `data/test-00000-of-00001.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/9387bccb-8567-5d29-b2ba-4175fb8df0e9
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/9387bccb-8567-5d29-b2ba-4175fb8df0e9
- Over MCP: `get_schema_card` with id `9387bccb-8567-5d29-b2ba-4175fb8df0e9` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Proteomics datasets](https://scigantic.com/topics/proteomics)
