InstaNovo enables diffusion-powered de novo peptide sequencing in large-scale proteomics experiments
peer-reviewed · Nature Machine Intelligence · 2025
| Date | 2025-04-01 |
| Type | peer-reviewed |
| Venue | Nature Machine Intelligence |
| Publisher | Nature Machine Intelligence |
| Contribution | algorithm |
| DOI | 10.1038/s42256-025-01019-5 |
| Citations (OpenAlex) | 40 |
| Venue 2-year citedness | 19.94 |
Preprint version: De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments (2023-08-30, bioRxiv)
Abstract
Mass spectrometry-based proteomics focuses on identifying the peptide that generates a tandem mass spectrum. Traditional methods rely on protein databases but are often limited or inapplicable in certain contexts. De novo peptide sequencing, which assigns peptide sequences to spectra without prior information, is valuable for diverse biological applications; however, owing to a lack of accuracy, it remains challenging to apply. Here we introduce InstaNovo, a transformer model that translates fragment ion peaks into peptide sequences. We demonstrate that InstaNovo outperforms state-of-the-art methods and showcase its utility in several applications. We also introduce InstaNovo+, a diffusion model that improves performance through iterative refinement of predicted sequences. Using these models, we achieve improved therapeutic sequencing coverage, discover novel peptides and detect unreported organisms in diverse datasets, thereby expanding the scope and detection rate of proteomics searches. Our models unlock opportunities across domains such as direct protein sequencing, immunopeptidomics and exploration of the dark proteome.
Methods and tools
- InstaNovo: Knapsack beam search
- InstaNovo+: Multinomial diffusion
Cites (18)
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model (2024) both
- NovoBench: Benchmarking Deep Learning-based De Novo Peptide Sequencing Methods in Proteomics (2024) semanticscholar
- Introducing π-HelixNovo for practical large-scale de novo peptide sequencing (2024) crossref
- Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model (2023) both
- Introducing PandaNovo for practical large-scale de novo peptide sequencing (2023) semanticscholar
- Comprehensive evaluation of peptide de novo sequencing tools for monoclonal antibody assembly (2023) both
- DPST: De Novo Peptide Sequencing with Amino-Acid-Aware Transformers (2022) both
- DePS: An improved deep learning model for de novo peptide sequencing (2022) semanticscholar
- Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices (2021) both
- Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning (2019) both
- Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry (2018) both
- A potential golden age to come—current tools, recent use cases, and future avenues for de novo sequencing in proteomics (2018) both
- De novo peptide sequencing by deep learning (2017) both
- Evaluating de novo sequencing in proteomics: already an accurate alternative to database-driven peptide identification? (2017) both
- Lessons in de novo peptide sequencing by tandem mass spectrometry (2015) both
- De Novo Peptide Sequencing and Identification with Precision Mass Spectrometry (2007) both
- PepNovo: de novo peptide sequencing via probabilistic network modeling (2005) both
- PEAKS: powerful software for peptide de novo sequencing by tandem mass spectrometry (2003) crossref
Cited by (19)
- Reference-free protein sequencing by consensus assembly of redundant de novo peptide reads (2026) both
- Prime-DiffNovo: Accurate Peptide De Novo Sequencing via Non-autoregressive Generation and Diffusion Refinement (2026) crossref
- InstaNovo-P: a de novo peptide sequencing model for phosphoproteomics (2026) crossref
- False discovery rate control for trustworthy AI-based de novo peptide sequencing (2026) crossref
- Learning Fragmentation Physics or Exploiting Sequence Priors? Benchmarking Bias in Deep Learning Models for De Novo Peptide Sequencing (2026) crossref
- DLDN-Bench: A Benchmark Framework for Deep Learning de Novo Peptide Sequencing in Proteomics (2026) crossref
- Zero-shot de novo peptide sequencing with open posttranslational modification discovery (2026) crossref
- Lactation-stage specific protein shifts in koala milk mirror the joey’s growth needs (2026) crossref
- Characterisation of pouch secretions from breeding Tasmanian devils (2026) crossref
- Generalizable Direct Protein Sequencing With InstaNexus (2026) both
- AbNovoBench: a resource and benchmarking platform for monoclonal antibody de novo sequencing (2026) crossref
- Modanovo: A Unified Model for Post-translational Modification-Aware De Novo Sequencing Using Experimental Spectra From In Vivo and Synthetic Peptides (2025) both
- Modanovo: A Unified Model for Post-Translational Modification-Aware de Novo Sequencing Using Experimental Spectra from In Vivo and Synthetic Peptides (2025) both
- Limitations of de novo sequencing in resolving sequence ambiguity (2025) crossref
- Generalizable direct protein sequencing with InstaNexus (2025) crossref
- Diffusion Decoding for Peptide De Novo Sequencing (2025) semanticscholar
- A transformer model for de novo sequencing of data independent acquisition mass spectrometry data (2025) crossref
- MassNet: billion-scale AI-friendly mass spectral corpus enables robust de novo peptide sequencing (2025) crossref
- InstaNovo-P: A de novo peptide sequencing model for phosphoproteomics (2025) crossref