Jeroen Van Goey

Thanks 🙏🏼 Much appreciated!

GitHub - bittremieuxlab/denovo_benchmarks Contribute to bittremieuxlab/denovo_benchmarks development by creating an account on GitHub.

You can submit your work to github.com/bittremieuxl... to see how it compares to the rest of the field. I still would be interested to read at least a preprint.

Can you share the code repository? I would be interested to look into it. I'm working on InstaNovo, another de novo peptide sequencing tool.
www.nature.com/articles/s42...

Welcome to InstaNovo website Discover InstaNovo, an AI-powered transformer model for de novo peptide sequencing. Boost your proteomics research with cutting-edge tool!

Fully open source and available now, explore Winnow today:

💻 Read the blog here: bit.ly/3Lq335a

📃 See the paper: bit.ly/43go0FG

📕 Explore the codebase: bit.ly/3JLWqcM

Winnow: Calibrated confidence and FDR control for de novo sequencing

Missed out on the recent announcement of Winnow, a new method for estimating false discovery rate in de novo peptide sequencing? 🧮

Catch up on our blog and learn how we're helping to uncover new discoveries with improved peptide recall and more accurate error estimates. 🔍

#TeamMassSpec #Proteomics

Protein Language Model-Aligned Spectra Embeddings for De Novo Peptide Sequencing

https://www.biorxiv.org/content/10.1101/2025.10.01.679857v1

Protein Language Model-Aligned Spectra Embeddings for De Novo Peptide Sequencing www.biorxiv.org/cont...

---
#proteomics #prot-preprint

Our new preprint on "de novo peptide sequencing rescoring and FDR estimation with Winnow" is out!
#TeamMassSpec #Proteomics
arxiv.org/abs/2509.24952

Figure 1

Figure 2

Figure 3

Figure 4

De novo peptide sequencing rescoring and FDR estimation with Winnow [new]
Improves de novo peptide sequencing by calibrating confidence scores with neural networks and estimating false discovery rates without decoy databases.

Mabona, Daniel, Knudsen, Catzel, Eloff, Schoof, Carranza, Jenkins, Van Goey, Kalogeropoulos: De novo peptide sequencing rescoring and FDR estimation with Winnow https://arxiv.org/abs/2509.24952 https://arxiv.org/pdf/2509.24952 https://arxiv.org/html/2509.24952

De novo peptide sequencing rescoring and FDR estimation with Winnow arxiv.org/abs/2509.2...

---
#proteomics #prot-preprint

We hope Winnow can become a standard tool to make de novo sequencing results easier to interpret. Feedback is very welcome! We’d love to hear from researchers and practitioners who might want to try Winnow in their own pipelines.

A great collaboration with @tpjenkins.bsky.social and Konstantinos at DTU Bioengineering.

winnow-fdr Score calibration and false discovery estimation for de novo peptide sequencing.

🐍 Download the code from PyPI:
pypi.org/project/winn...

De novo peptide sequencing - a InstaDeepAI Collection We’re on a journey to advance and democratize artificial intelligence through open source and open science.

🗞️ Download the pretrained model:
huggingface.co/collections/...

GitHub - instadeepai/winnow: Confidence control and FDR estimation for de novo peptide sequencing Confidence control and FDR estimation for de novo peptide sequencing - instadeepai/winnow

💻 Explore our repo:
github.com/instadeepai/...

De novo peptide sequencing rescoring and FDR estimation with Winnow Machine learning has markedly advanced de novo peptide sequencing (DNS) for mass spectrometry-based proteomics. DNS tools offer a reliable way to identify peptides without relying on reference databas...

Winnow is available today:
📃 Check out our preprint:
arxiv.org/abs/2509.24952

✨ Key features of Winnow:
- DNS score calibration and rescoring
- Lightweight, non-parametric false discovery rate estimation
- Common metrics such as PEP and q-value
- Pretrained general model for zero-shot estimation with InstaNovo
- Extensible framework

Winnow supports these discoveries by improving peptide recall while simultaneously providing accurate error estimates.

That could mean identifying peptides that drive immune responses in diseases like cancer, tracing protein interactions in complex microbial communities, or even sequencing ancient proteins from fossil samples.

Why does this matter? De novo sequencing tools like InstaNovo don’t just recover known biology. They can uncover what’s new and hidden.

Over the past 9 months we developed Winnow. It provides a principled and robust method to estimate false discovery rate in de novo peptide sequencing, where the lack of reference databases makes traditional error control strategies impossible.

A few years ago we set out to build a cutting-edge de novo peptide sequencing model. That became InstaNovo, which set a new benchmark for peptide sequencing.
bsky.app/profile/tpje...

De novo peptide sequencing rescoring and FDR estimation with Winnow

🚀 New research from the InstaNovo team at
@instadeep.bsky.social: Winnow, our method for estimating false discovery rate in de novo peptide sequencing.

Work of my first PhD student, Sam, who fully stumbled down the de novo rabbithole!

Limitations of de novo sequencing in resolving sequence ambiguity De novo peptide sequencing enables peptide identification from fragmentation spectra without relying on sequence databases. However, incomplete spectra create ambiguity, making unambiguous identificat...

Exciting news: Preprint on the limitations of current de novo peptide sequencing models on dealing with sequence ambiguity is now out! It focuses on how current models deal with sequence ambiguity, and when and where they go wrong.

Check it out here: www.biorxiv.org/content/10.1...

Limitations of de novo sequencing in resolving sequence ambiguity https://www.biorxiv.org/content/10.1101/2025.08.19.671052v1

We’re excited to unveil the first #DLI2025 lineup of tutorials and practicals:

✨ Machine Learning Foundations
✨ Generative Models & LLMs for African languages

All tutorial content will also be available online after the Indaba. Don’t miss out, subscribe here 👉 lnkd.in/eCgXRqsV

A look back at the incredible learning from yesterday! Our attendees got to dive deep into some of the most exciting fields in AI through our parallel tutorial sessions.
A huge thank you to our expert presenters for sharing their knowledge: Luis Serrano, Dr. Arnu Pretorius and Yousra Farhan.

Following a day of deep-dive tutorials, attendees at #DLI2025 got to put their knowledge to the test in practical, hands-on sessions!