A large-scale unified deep learning model for peptide mass spectrum interpretation trained on multimodal data

Abstract

Deep learning has advanced mass spectrometry data interpretation, yet most models remain feature extractors rather than unified scoring frameworks. We present pUniFind, a large-scale multimodal foundational model in proteomics that integrates open end-to-end peptide-spectrum scoring with open, zero-shot de novo sequencing. Trained on over 100 million open search-derived spectra, pUniFind aligns spectral and peptide modalities through cross-modality prediction alongside other carefully designed pretraining tasks. Consequently, further benefiting from its open scoring capability, pUniFind outperforms traditional engines across diverse datasets, notably achieving a 42.6% increase in identified peptides in immunopeptidomics. We propose two de novo sequencing workflows to support different applications. For modification-rich de novo sequencing, pUniFind identifies 60% more peptide–spectrum matches than existing de novo methods despite a 300 times larger search space. For regular de novo sequencing, pUniFind recovers an additional 38.5% of peptides, including 1,891 that map to the genome but are absent from reference proteomes. Crucially, it achieves this while preserving full fragment ion coverage and maintaining high consistency with database-search-based methods. Furthermore, a quality control module based on deep learning-derived features increases the consistency of results with RNA-Seq evidence from 65.4% to 85.0%. These results establish a unified, scalable deep learning framework for proteomic analysis, offering improved sensitivity, modification coverage, and interpretability. pUniFind is a large-scale deep learning model for proteomics that unifies peptide–spectrum scoring and open de novo sequencing. Trained on over 100 million spectra, it substantially improves peptide identification and modification discovery.