Abstract
De novo peptide sequencing directly identifies peptides from mass spectrometry data, playing a critical role in discovering novel proteins and analyzing complex biological samples without reliance on existing databases. To address challenges in both speed and accuracy, a transformer-based model, TSARseqNovo, incorporates two key innovations: a Semi-Autoregressive decoder for parallel prediction of multiple amino acids and a Masking Refinement decoder for refining low-confidence predictions. These features significantly enhance sequencing efficiency and accuracy. Evaluations on the Nine-Species, Aggregated, and Glycoproteomic datasets, demonstrate that TSARseqNovo outperforms state-of-the-art models, including CasaNovo, NovoB, InstaNovo + , and π-HelixNovo. Specifically, TSARseqNovo achieves up to a 2-fold speed increase over CasaNovo and π-HelixNovo, and approximately 10-fold over NovoB and InstaNovo + , while also showing substantial improvements in peptide prediction precision, especially for long peptides. These advancements position TSARseqNovo as a powerful tool for accelerating high-throughput proteomics research and addressing increasingly complex biological questions.