π-MSNet: A large-scale, AI-ready and continuously reprocessed proteomics data resource

Abstract

Artificial intelligence (AI) is reshaping proteomics workflows, delivering remarkable gains in both peptide identification sensitivity and quantitative performance. However, the potential of deep learning models in proteomics has not been fully exploited due to the scarcity of large-scale, high-quality and consistently labeled datasets. Here, we present {pi}-MSNet, a large-scale, AI-ready and continuously reprocessed mass spectrometry (MS) data resource. Using a uniform identification and quality control workflow, it comprises over 737 million peptide-spectrum matches (PSMs) obtained from 2.16 billion MS2 spectra, and 11 million precursors from 45,583 LC-MS/MS runs across 12 instrument types and 55 diverse species. Through community collaboration, the data are shared via international, interactive, and continuously reprocessed web resources. {pi}-MSNet provides an AI-ready data framework for efficient training and systematic benchmarking of multiple models across four representative tasks (e.g., MS2 prediction, retention time prediction, collisional cross sections prediction, and de novo peptide sequencing). In particular, by retraining multiple models on {pi}-MSNet, we achieved consistent performance improvements over their original versions. These improved models were subsequently integrated into the {pi}-MSNet agent to enable interactive, deployment-free use. Through SDRF (Sample and Data Relationship Format) metadata, open-source cloud analysis workflow, and a community-driven interactive data portal that supports continuous data submission, {pi}-MSNet serves as a continuously updating, AI-ready resource for reproducible benchmarking, robust model training, and accelerated AI innovation in proteomics.