Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing

TL;DR

RankNovo is a universal deep reranking framework that significantly improves de novo peptide sequencing accuracy by leveraging multiple models, novel metrics, and a list-wise approach, demonstrating state-of-the-art performance and strong generalization.

Contribution

It introduces RankNovo, the first deep reranking framework for peptide sequencing that uses list-wise modeling, axial attention, and new metrics, advancing the accuracy and robustness of de novo sequencing.

Findings

Outperforms base models used for candidate generation.

Sets new state-of-the-art benchmark results.

Exhibits strong zero-shot generalization to unseen models.

Abstract

De novo peptide sequencing is a critical task in proteomics. However, the performance of current deep learning-based methods is limited by the inherent complexity of mass spectrometry data and the heterogeneous distribution of noise signals, leading to data-specific biases. We present RankNovo, the first deep reranking framework that enhances de novo peptide sequencing by leveraging the complementary strengths of multiple sequencing models. RankNovo employs a list-wise reranking approach, modeling candidate peptides as multiple sequence alignments and utilizing axial attention to extract informative features across candidates. Additionally, we introduce two new metrics, PMD (Peptide Mass Deviation) and RMD (residual Mass Deviation), which offer delicate supervision by quantifying mass differences between peptides at both the sequence and residue levels. Extensive experiments demonstrate that RankNovo not only surpasses its base models used to generate training candidates for reranking pre-training, but also sets a new state-of-the-art benchmark. Moreover, RankNovo exhibits strong zero-shot generalization to unseen models whose generations were not exposed during training, highlighting its robustness and potential as a universal reranking framework for peptide sequencing. Our work presents a novel reranking strategy that fundamentally challenges existing single-model paradigms and advances the frontier of accurate de novo sequencing. Our source code is provided on GitHub.