PepSpecBench is a unified benchmark that standardizes preprocessing, uses backbone-disjoint splits to prevent leakage, and adds multi-species plus perturbation tests for peptide MS/MS prediction models.
A multi-species benchmark for training and validating mass spectrometry proteomics machine learning models.Scientific Data, 11(1):1259
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction
PepSpecBench is a unified benchmark that standardizes preprocessing, uses backbone-disjoint splits to prevent leakage, and adds multi-species plus perturbation tests for peptide MS/MS prediction models.