PepGo: a deep learning and tree search-based model forde novopeptide sequencing

Identifying peptide sequences from tandem mass spectra is a fundamental problem in proteomics. Unlike search-based methods that rely on matching spectra to databases,de novopeptide sequencing determines peptides directly from mass spectra without any prior information. However, the design of models and algorithms forde novopeptide sequencing remains a challenge. Manyde novoapproaches leverage deep learning but primarily focus on the architecture of neural networks, paying less attention to search algorithms. We introduce PepGo, ade novopeptide sequencing model that integrates Transformer neural networks with Monte Carlo Tree Search (MCTS). PepGo predicts peptide sequences directly from mass spectra without databases, even without prior training. We show that PepGo surpasses existing methods, achieving state-of-the-art performance. To our knowledge, this is the first approach to combine deep learning with MCTS forde novopeptide sequencing, offering a powerful and adaptable solution for peptide identification in proteomics research.