Data · dataset · 2026
AI-ready LC-MS/MS Dataset for Pesticide Residue Analysis
Listed in ScienceDB
Liquid chromatography tandem mass spectrometry (LC-MS/MS) is the core technology for pesticide residue analysis.
Description
The AI driven mass spectrometry intelligent analysis method highly relies on high-quality, standardized, and metadata complete training datasets. However, existing publicly available pesticide mass spectrometry data generally suffer from problems such as format heterogeneity, uneven spectrum quality, severe metadata loss, and lack of unified preprocessing processes.
The construction process of this dataset has established an end-to-end, reproducible workflow for constructing pesticide LC-MS/MS datasets, covering eight core modules: pesticide targeted screening, multi-source data integration, spectral cleaning and deduplication, metadata standardization, quality filtering, hierarchical partitioning, multi-dimensional feature engineering, and baseline model validation. The study integrated 15 public data sources including GNPS, MassiVE, MoNA, and MassBank, with 91420 original spectra.
Read the rest (3 more)
After multi-level quality control, two versions of the dataset were obtained: the strict version (7527 spectra, 3197 compounds), which is characterized by high quality and low redundancy and is suitable for model training with high data accuracy requirements; The extended version (21292 spectra, 3224 compounds) retains more differences in experimental conditions and is suitable for data augmentation and large-scale pre training.
The dataset covers 8 pesticide functional categories and is compatible with mainstream high-resolution mass spectrometry platforms such as QTOF and Orbitrap. SMILES、InChIKey、 The completeness of core metadata such as molecular formula exceeds 98%. This study constructed a feature system consisting of 32 physical and chemical descriptors, 2214 dimensional molecular fingerprints, and 30 dimensional spectral features, and systematically validated the dataset using five classification models.
The accuracy of XGBoost and LightGBM classification models both reached 81.5%.
Links
Where it is published
- DOI doi.org/10.57760/sciencedb.35414 ↗
DOI / persistent id · from scidb cn
Catalogue records · 1
- OAI-PMH record scidb.cn/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=10.57760%2… ↗
metadata API · from scidb cn
Topics
- From keywords
- Earth & Environmental Science · Engineering · Humanities · Life Sciences · Social Science
- Inferred from text
- Crop and pasture production 68% · Mass spectrometry 75%
Provenance · 1 source records, 11 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| ScienceDB | 10.57760/sciencedb.35414 | 12 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| concepts[field].anzsrc:group:3004 | enrichment · scidb cn | taxonomy-embedding@1.0.0 | title+keywords+description (68%) |
| concepts[field].local:field:earth-environmental | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:engineering | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:humanities | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:life-sciences | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[field].local:field:social-science | mapping · scidb cn | connector:scidb_cn@1.0.0 | |
| concepts[modality].local:modality:mass-spectrometry | enrichment · scidb cn | keyword-concept-rules@1.0.0 | title+description (75%) |
| description | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/description |
| license_text | source · scidb cn | connector:scidb_cn@1.0.0 | |
| publication_date | source · scidb cn | connector:scidb_cn@1.0.0 | |
| title | source · scidb cn | connector:scidb_cn@1.0.0 | /metadata/dc/title |