Protein Language Model-Aligned Spectra Embeddings for De Novo Peptide Sequencing
preprint · bioRxiv · 2025
| Date | 2025-10-03 |
| Type | preprint |
| Venue | bioRxiv |
| Publisher | Cold Spring Harbor Laboratory |
| Contribution | algorithm |
| DOI | 10.1101/2025.10.01.679857 |
| Citations (OpenAlex) | 0 |
Abstract
We consider the problem of de novo peptide sequencing in tandem mass spectrometry, where the goal is to predict the underlying peptide sequence given a spectrum’s fragment peaks and precursor information. We present PLMNovo, a constrained learning framework that leverages pre-trained protein language models (PLMs) to guide the training process. In particular, we cast peptide-spectrum matching as a constrained optimization problem that enforces alignment between spectrum and peptide embeddings produced by a spectrum encoder and a PLM, respectively. We use a Lagrangian primal-dual algorithm to train the spectrum encoder and the peptide decoder by solving the proposed constrained learning problem, while optionally fine-tuning the pre-trained PLM. Through numerical experiments on established benchmarks, we demonstrate that PLMNovo outperforms several state-of-the-art deep learning-based de novo sequencing algorithms.
Methods and tools
- PLMNovo: Casts peptide-spectrum matching as a constrained optimisation that aligns the spectrum encoder’s embeddings with those of a pre-trained protein language model, and trains encoder and decoder with a Lagrangian primal-dual algorithm, optionally fine-tuning the language model.
Data used
- Casanovo digestion enzyme bias data — as deposited · 10.5281/zenodo.12587317
Cites (20)
- Limitations of de novo sequencing in resolving sequence ambiguity (2025) both
- A transformer model for de novo sequencing of data independent acquisition mass spectrometry data (2025) both
- MassNet: billion-scale AI-friendly mass spectral corpus enables robust de novo peptide sequencing (2025) both
- Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing (2025) both
- Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing (2025) semanticscholar
- Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing (2025) both
- InstaNovo enables diffusion-powered de novo peptide sequencing in large-scale proteomics experiments (2025) both
- π-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing (2025) crossref
- Accounting for Digestion Enzyme Bias in Casanovo (2024) crossref
- Transforming de novo peptide sequencing by explainable AI (2024) crossref
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model (2024) both
- π-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing (2024) semanticscholar
- Accurate de novo peptide sequencing using fully convolutional neural networks (2023) both
- Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model (2023) both
- The impact of noise and missing fragmentation cleavages on de novo peptide identification algorithms (2022) both
- De novo mass spectrometry peptide sequencing with a transformer model (2022) both
- Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices (2021) both
- Deep Learning in Proteomics (2020) both
- De novo peptide sequencing by deep learning (2017) both
- De novo Peptide Sequencing (2016) both