{"success":true,"data":{"author":"Wilhelmlab, Technical University of Munich","bucketAccessType":"public","bucketName":"Wilhelmlab/Prosit-2025-lac-ms2","bucketPrefix":"","category":"Proteomics","cloudProvider":"huggingface","createdAt":"2026-11-19T15:09:28.054Z","description":"Annotated tandem mass spectra prepared by the Wilhelm lab (Technical University of Munich) to train Prosit-style deep learning models that predict fragment ion intensities from peptide sequences, extended to lysine lactylation (Klac). The data combine the PROSPECT dataset with spectra of a Klac peptide library, with upstream data from the ProteomeTools synthetic peptide datasets on PRIDE. Fragment annotation follows the expert-system rules in the PROSPECT paper, and the raw intensity vector of each spectrum is stored in the intensities_raw column. Train, validation and test splits are spread over 63 Parquet files (about 2.2 GB) and load with datasets.load_dataset('Wilhelmlab/Prosit-2025-lac-ms2'). Supports MS2 spectrum prediction for unmodified and lactylated peptides. Licensed CC BY 4.0 by Wilhelmlab, TUM; cite PROSPECT (Shouman et al., NeurIPS 2022) and ProteomeTools (Zolg et al., Nature Methods 2017).","displayTitle":"Prosit lac 2025 Fragment Ion Intensity (MS2) Training Data: Lactylated and Unmodified Peptide Spectra from PROSPECT and ProteomeTools","huggingFaceUrl":"https://huggingface.co/datasets/Wilhelmlab/Prosit-2025-lac-ms2","id":"5cf0c649-61ba-5108-ae5a-49298cbd8f0a","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/Wilhelmlab/Prosit-2025-lac-ms2","objectCountEstimate":65,"probeStatus":"ok","referenceUrl":"https://huggingface.co/datasets/Wilhelmlab/Prosit-2025-lac-ms2","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"Wilhelmlab/Prosit-2025-lac-ms2\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"Wilhelmlab/Prosit-2025-lac-ms2\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=Wilhelmlab, license:cc-by-4.0, size_categories:10M<n<100M, format:parquet, downloads=113"],"format":"mixed","generatedAt":"2026-11-19T15:21:58.317Z","layout":{"example":"data/test-00000-of-00007.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/test-00000-of-00007.parquet","truncatedAt":512}],"sampleObjects":["data/test-00000-of-00007.parquet","data/test-00001-of-00007.parquet","data/test-00002-of-00007.parquet","data/test-00003-of-00007.parquet","data/test-00004-of-00007.parquet"],"sidecars":[{"bytes":"---\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-*\ndataset_info:\n  features:\n  - name: raw_file\n    dtype: string\n  - name: scan_number\n    dtype: int64\n  - name: method_nbr\n    dtype: int64\n  - name: precursor_charge_onehot\n    list: int64\n  - name: collision_energy_aligned_normed\n    dtype: float64\n  - name: intensities_raw\n    list: float64\n  - name: package\n    dtype: string\n  - name: modified_sequence\n    dtype: string\n  - name: instrument_type\n    dtype: int64\n  splits:\n  - name: train\n    num_bytes: 21109297226\n    num_examples: 13392664\n  - name: val\n    num_bytes: 6099758523\n    num_examples: 3869384\n  - name: test\n    num_bytes: 3229770922\n    num_examples: 2047190\n  download_size: 2230490329\n  dataset_size: 30438826671\nlicense: cc-by-4.0\n---\n\n# Prosit lac 2025 - Fragment Ion Intensity Prediction (MS2)\n\nA mass-spectrometry dataset for applied machine learning in proteomics, annotated, processed and split for the task of fragment ion intensity 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 dataset and on the Klac ChemIntelligence Library.\n- **Repository:** https://github.com/wilhelm-lab/PROSPECT\n\n## Uses\n\nThe dataset is intended to be used for fragment ion intensity prediction given a peptide sequence. \n\nUse the following lines to load the data (train/val/test):\n\n```python\n# main data for training and evaluation; contains train, validation, test splits\nmain_dataset = load_dataset(\"Wilhelmlab/Prosit-2025-lac-ms2\")\n```\n\n\n## Dataset Creation\n\n### Curation Rationale\n\nThe dataset is intended to serve as a reference benchmark dataset for fragment ion intensity 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\nThe annotations are based on an expert system [7] with a set of rules listed in the PROSPECT paper [8]. The vector of intensities is collected in one column named `intensities_raw`.\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## References\n\n[1] Daniel P Zolg, Mathias Wilhelm, Karsten Schnatbaum, Johannes Zerweck, Tobias Knaute, Bernard Delanghe, Derek J Bailey, Siegfried Gessulat, Hans-Christian Ehrlich, Maximilian Weininger, et al. Building proteometools based on a complete synthetic human proteome. Nature methods, 14(3):259–262, 2017.\n\n[2] Nadin Neuhauser, Annette Michalski, Jürgen Cox, and Matthias Mann. Expert system for computer-assisted annotation of ms/ms spectra. Molecular & Cellular Proteomics, 11(11):1500– 1509, 2012.\n\n[3] Omar Shouman, Wassim Gabriel, Victor-George Giurcoiu, Vitor Sternlicht, and Mathias Wil- helm. PROSPECT: Labeled tandem mass spectrometry dataset for machine learning in pro- teomics. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems, volume 35, pages 32882–32896. Curran Associates, Inc., 2022.\n\n\n## Dataset Card Contact\n\nmathias.wilhelm@tum.de\n\nWilhelmlab, TU Munich, School of Life Sciences, Germany.","encoding":"utf8","key":"README.md","name":"README.md","size":3668,"truncated":false}],"sourceObjectKey":"data/test-00000-of-00007.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"Wilhelmlab/Prosit-2025-lac-ms2\")\nprint(ds)","starterSamplePath":"data/test-00000-of-00007.parquet","totalObjects":65},"summary":"Annotated tandem mass spectra prepared by the Wilhelm lab (Technical University of Munich) to train Prosit-style deep learning models that predict fragment ion intensities from…","title":"Prosit lac 2025 Fragment Ion Intensity (MS2) Training Data: Lactylated and Unmodified Peptide Spectra from PROSPECT and ProteomeTools","updatedAt":"2026-11-19T19:09:55.953Z","visibility":"public","websiteUrl":"https://github.com/wilhelm-lab/PROSPECT"}}