{"success":true,"data":{"author":"Wilhelmlab, Technical University of Munich","bucketAccessType":"public","bucketName":"Wilhelmlab/prospect-ptms-charge","bucketPrefix":"","category":"Proteomics","cloudProvider":"huggingface","createdAt":"2026-11-19T15:09:28.020Z","description":"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).","displayTitle":"PROSPECT PTMs Precursor Charge Prediction: Peptide Charge-State Labels from ProteomeTools Mass Spectrometry","huggingFaceUrl":"https://huggingface.co/datasets/Wilhelmlab/prospect-ptms-charge","id":"9387bccb-8567-5d29-b2ba-4175fb8df0e9","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/Wilhelmlab/prospect-ptms-charge","objectCountEstimate":7,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/Wilhelmlab/prospect-ptms-charge","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Wilhelmlab/prospect-ptms-charge\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Wilhelmlab/prospect-ptms-charge\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Wilhelmlab, license:cc-by-4.0, size_categories:1M<n<10M, format:parquet, downloads=98"],"format":"mixed","generatedAt":"2026-11-19T15:21:58.266Z","layout":{"example":"data/test-00000-of-00001.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/test-00000-of-00001.parquet","truncatedAt":512}],"sampleObjects":["data/test-00000-of-00001.parquet","data/train-00000-of-00002.parquet","data/train-00001-of-00002.parquet","data/val-00000-of-00001.parquet","holdout/test-00000-of-00001.parquet"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ndataset_info:\n- config_name: default\n  features:\n  - name: modified_sequence\n    dtype: string\n  - name: raw_file\n    sequence: string\n  - name: scan_number\n    sequence: int64\n  - name: package\n    sequence: string\n  - name: most_abundant_charge_state\n    sequence: int64\n  - name: observed_charge_states\n    sequence: int64\n  - name: charge_state_dist\n    sequence: float64\n  splits:\n  - name: train\n    num_bytes: 771591307\n    num_examples: 1142537\n  - name: val\n    num_bytes: 220810369\n    num_examples: 328072\n  - name: test\n    num_bytes: 108923080\n    num_examples: 161588\n  download_size: 440448117\n  dataset_size: 1101324756\n- config_name: holdout\n  features:\n  - name: modified_sequence\n    dtype: string\n  - name: raw_file\n    sequence: string\n  - name: scan_number\n    sequence: int64\n  - name: package\n    sequence: string\n  - name: most_abundant_charge_state\n    sequence: int64\n  - name: observed_charge_states\n    sequence: int64\n  - name: charge_state_dist\n    sequence: float64\n  splits:\n  - name: test\n    num_bytes: 29980852\n    num_examples: 42028\n  download_size: 9257686\n  dataset_size: 29980852\nconfigs:\n- config_name: default\n  data_files:\n  - split: train\n    path: data/train-*\n  - split: val\n    path: data/val-*\n  - split: test\n    path: data/test-*\n- config_name: holdout\n  data_files:\n  - split: test\n    path: holdout/test-*\ntags:\n- proteomics\n- mass-spectrometry\n- charge-state\n---\n\n# PROSPECT PTMs - Precursor Charge Prediction\n\nA mass-spectrometry dataset for applied machine learning in proteomics, processed and split for the task of precursor charge prediction.\n\n## Dataset Details\n\n- **Curated by:** Wilhelmlab - Technical University of Munich - School of Life Sciences - Germany\n- **License:** CC-BY4.0\n\n### Dataset Sources\n\nThe data is based on the PROSPECT PTMs datasets hosted in Zenodo [3][4][5][6]. \n- **Repository:** https://github.com/wilhelm-lab/PROSPECT\n\n## Uses\n\nThe dataset is intended to be used for precursor charge state prediction given a peptide sequence. Optionally, addiional inputs can be used as features to encode PTMs or features describing the experimental setup.\n\n## Dataset Structure\n\nThe dataset has two configurations:\n- default: this is the train/val/test data that is based on all the Zenodo PROSPECT PTMs datasets [3][4][5]\n- holdout: this is the holdout datasets that can be eventually used to evaluate a model capable of processing PTMs. It is based on the PROSPECT Test-PTM dataset on Zenodo [6].\n\nUse one of the following lines to load the respective configuration:\n\n```python\n# main data for training and evaluation; contains train, val, tesst splits\nmain_dataset = load_dataset(\"Wilhelmlab/prospect-ptms-charge\")\n\n# holdout data for final benchmarking and model comparison; contains test split only\nholdout_dataset = load_dataset(\"Wilhelmlab/prospect-ptms-charge\", \"holdout\")\n```\n\n## Dataset Creation\n\n### Curation Rationale\n\nThe dataset is intended to serve as a reference benchmark dataset for precursor charge state prediction, processed, split, and ready-to-use for developing deep learning models for this specific task.\n\n\n### Source Data\n\nThe upstream source data is based on the ProteomeTools datasets available on PRIDE [1][2].\n\n#### Data Collection and Processing\n\n[More Information Needed]\n\n\n### Annotations\n\nThree labels are aggregated from the original data to enable different formulation of the precursor charge state prediction.\n\n- `most_abundant_charge_state` one-hot encoded version of the most dominant charge for the sequence\n- `observed_charge_states`: binarized vector (k-hot encoded) with all possible charge states\n- `charge_state_dist`: the proportions for different charge states for a given sequence based on all occurences in the original data\n\n#### Personal and Sensitive Information\n\nThe dataset does not contain any personal, sensitive, or private data.\n\n### Recommendations\n\nWe recommend using the holdout configuration for solely evaluation models at the end of the research iteration. \n\n## Citation\n\n**BibTeX:**\n\n[More Information Needed]\n\n**APA:**\n\n\n## Referenc","encoding":"utf8","key":"README.md","name":"README.md","size":5486,"truncated":true}],"sourceObjectKey":"data/test-00000-of-00001.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"Wilhelmlab/prospect-ptms-charge\")\nprint(ds)","starterSamplePath":"data/test-00000-of-00001.parquet","totalObjects":7},"summary":"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…","title":"PROSPECT PTMs Precursor Charge Prediction: Peptide Charge-State Labels from ProteomeTools Mass Spectrometry","updatedAt":"2026-11-19T19:04:04.194Z","visibility":"public","websiteUrl":"https://github.com/wilhelm-lab/PROSPECT"}}