Lightnews — Scholar-powered news

LightNews

Tine Claeys

@tineclaeys.bsky.social

670 followers 270 following 51 posts

Postdoc in computational proteomics @CompOmics @VIBLifeSciences - turning public data into tissue biomarkers with ML, AI, and a mission to make proteomics truly reusable

Posts Media Videos Starter Packs

Tine Claeys @tineclaeys.bsky.social · Aug 27

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

samvpy.bsky.social @samvpy.bsky.social · Aug 27

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

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

www.biorxiv.org

Tine Claeys @tineclaeys.bsky.social · Aug 15

Check our website: psi-ai.org
Looking forward to where this will take us!
A huge thanks to all attendees and of course to my co-chairs Samuel Wein and @ralf.gabriels.dev

Tine Claeys @tineclaeys.bsky.social · Aug 15

The AI-working group of the Proteomics Standards Initiative officially launched! #AI is increasingly present within #proteomics, we want to support the community to get the most out of their data and models. For this, we need your input #TeamMassSpec
Rewatch the kickoff event: tinyurl.com/37cz9bnj

Aug14_Kickoff.mp4

Managed Nextcloud - powered by hosting.de

cloud.samwein.com

Tine Claeys @tineclaeys.bsky.social · Jul 23

Metadata from the paper is often too incomplete to reuse the dataset without extra tools, even raw file species mapping is a disaster! Authors need better reporting guidelines so at least the paper is complete, or they need to make an SDRF (preferably both).

Tine Claeys @tineclaeys.bsky.social · Jul 22

I fully agree as well, that is the endgoal! That would however require then also treating it as pub with (i) enforcable metadata and peerreview/validation; (ii) doi for citations; (iii) impact metrics for grants.
Maybe the rise of clinical datasets might push this?

Tine Claeys @tineclaeys.bsky.social · Jul 22

repository.jpostdb.org/entry/JPST00...

jPOSTrepo (Japan ProteOme STandard Repository)

jPOSTrepo (Japan ProteOme STandard Repository) is a new data repository of sharing MS raw/processed data

repository.jpostdb.org

Tine Claeys @tineclaeys.bsky.social · Jul 22

Authors need to inform repositories that their paper got published, right? PRIDE has built-in automatic checks in case the authors would forget. Having a bunch of public datasets that don't link back to a paper is also not ideal. Unless there is proper metadata I'd suppose?

Tine Claeys @tineclaeys.bsky.social · Jul 22

Never know that there were so many ''condoms'' involved in studying open reading frames, the more you know 🤷‍♀️

Tine Claeys @tineclaeys.bsky.social · Jul 22

Yes, enjoyong the amazing british weather, luckily there's tea 😉 I'm flying back directly after the conference but will keep it in mind for future EBI visits 🤗

Tine Claeys @tineclaeys.bsky.social · Jul 22

Up before sunrise and a little nervous, it’s my first keynote ever!
Speaking tonight at #ISMB2025 in the CompMS track about making proteomics AI ready. Expect metadata, MLMarker, and a lot of public data love. See you there!
@iscb.bsky.social

Reposted by Tine Claeys

Yasset Perez-Riverol @ypriverol.bsky.social · Jul 11

🚀 Attention DIA/DDA proteomics users! Whether you're using #DIA-NN, #MaxQuant, #quantms, or any tool that outputs mzIdentML and mzML, the NEW pmultiqc v0.0.29 is here!

💡 Create stunning, shareable HTML reports for your collaborators in seconds.

✨ Try pmultiqc.quantms.org Examples👇
#Proteomics #QC

Tine Claeys @tineclaeys.bsky.social · Jun 25

ProteomicsML is absolutely awesome to get hands-on with the ML learning part and learn the classical pitfalls

Tine Claeys @tineclaeys.bsky.social · Jun 25

Depends on where you want to start in your data process (raw files, PSMs, identifications?)
I'd say that AI-readiness is 75% preprocessing and getting all data in the same format plus scalability of your scripts. There are some good packages like psmutils and pyopenMS but depends on your specifics.

Tine Claeys @tineclaeys.bsky.social · Jun 23

Mark is the cutest octopus which will guide you through #AI driven biomarker identification in your proteomics sample (preprint: www.biorxiv.org/content/10.1...
Pretty clear that @compomics.com is thé best team to do science and have fun with 🙌

www.biorxiv.org

Tine Claeys @tineclaeys.bsky.social · Jun 23

Last weeks #EuPA2025 was a blast! From receiving the Bioinformatics Award for my #metadata and community efforts with getting the opportunity to present my work, to building sandcastles in the shape of the logo of my newest tool MLMarker.

Tine Claeys @tineclaeys.bsky.social · Jun 23

Mark is the cutest octopus which will guide you through #AI driven biomarker identification in your proteomics sample (preprint: www.biorxiv.org/content/10.1...
Pretty clear that @compomics.com is thé best team to do science and have fun with 🙌

www.biorxiv.org

Tine Claeys @tineclaeys.bsky.social · Jun 23

Last weeks #EuPA2025 was a blast! From receiving the Bioinformatics Award for my #metadata and community efforts with getting the opportunity to present my work, to building sandcastles in the shape of the logo of my newest tool MLMarker.

Reposted by Tine Claeys

Ralf Gabriels @ralf.gabriels.dev · Jun 18

Really liking @tineclaeys.bsky.social's metaphor on metadata:
It's like the philosopher's stone, turning your experimental data into gold and giving it the elixir of life.

Congrats with the EuPA Bioinformatics Award, Tine!

#EuPA2025

Reposted by Tine Claeys

Yasset Perez-Riverol @ypriverol.bsky.social · Jun 18

🚨 Has PRIDE helped your research?

Take 15 mins to tell funders why open data matters!
📊 Fill out the EMBL-EBI 2025 survey 👉
www.surveymonkey.com/r/QGFMBH8?ch...

Your feedback helps keep PRIDE open, FAIR & impactful.
🙏 Please share!
#FAIR #OpenData #Proteomics #MassSpectrometry #PRIDE

This link will take you to a page that’s not on LinkedIn

Tine Claeys @tineclaeys.bsky.social · Jun 16

And you get the cutest mascotte octopus. His name is Mark! He'll guide you Clippy-wise through your analyses 🙌

Tine Claeys @tineclaeys.bsky.social · Jun 16

MLMarker is live! This ML-tool predicts tissue similarity and uncovers biomarkers from your proteomics data. It was trained on public data of healthy human tissues.
Preprint & app: www.biorxiv.org/content/10.1...
Let's chat at #EuPA2025 - Award session (Wednesday) & poster session (Thursday)!

www.biorxiv.org

Reposted by Tine Claeys

CompOmics @compomics.com · Jun 16

From PTMs to proteins, from metadata to metaproteomics. CompOmics has got you covered at #EuPA2025!

Plenary talk

Lennart Martens
Rise of the Robots – definitely artificial, somewhat intelligent

Keynote lecture

Tim Van Den Bossche
Improving metaproteomics data analysis with the Ghent Metaproteomics Toolbox

Oral presentations

Harikrishnan Ramadasan
Bridging expert curation and LLMs for automated metadata extraction in lesSDRF 2.0

Robbe Devreese
Collisional cross-section prediction for peptides and small molecules: covering all bases (and bridging the gap?)

Robbin Bouwmeester
Challenges and opportunities in modification searches for DIA proteomics

Educational session

Lennart Martens
No more surprises: AI predictions in MS DDA and DIA data interpretation

Robbin Bouwmeester
A deep dive into limitations of modification searching for DIA data

Caroline Jachmann
Fantastic PTMs and how (not?) to find them using msqrob2PTM -
a real-life journey

Poster presentations

Enrico Massignani
Overcoming challenges in non-canonical protein searches with OpenProt and ionbot

Pathmanaban Ramasamy
Assessing the relation between protein phosphorylation, AlphaFold3 models and conformational variability

Toon Callens
Advancing tissue prediction using read-based DNA methylation modelling towards a multi-omics integration

Tine Claeys
MLMarker: Data-driven discovery of tissue similarity and biomarkers

Alireza Nameni
Enhancing peptide-spectrum match identification with non-linear models in Mokapot: Assessing complexity, overfitting, and false discovery rates

Tim Van Den Bossche
The Metaproteomics Initiative: An international community by and for metaproteomics researchers

Award presentations

Tine Claeys
Bioinformatics Award

Tim Van Den Bossche
Vision & Commitment Award

Tine Claeys @tineclaeys.bsky.social · Jun 13

We are working on an AI based metadata extraction pipeline from papers, supplementary files and mass spectra. Come to @harirmds.bsky.social's talk at #EuPA2025 for the newest and hottest results!

EuBIC-MS @eubic-ms.org · Jun 13

Join us in Saint-Malo for the #EuBIC-MS session at #EuPA2025!
After a short introduction, we have three exciting talks lined up, as well as an interactive discussion on open issues in computational proteomics.

@eupaproteomics.bsky.social @uszkoreitju.bsky.social @harirmds.bsky.social

EuBIC-MS session at EuPA 2025
Tuesday June 17, 10:15 - 12:00, Room Vauban 1

Ralf Gabriels
Introducing EuBIC-MS
10:15 - 10:30

Julian Uszkoreit
O85 - What can we gain - a comparison of common search engines and post-processing methods
10:30 - 10:45

Yannic Chen
O84 - Benchmarking Database Search Engines for DDA-based Immunopeptidomics
10:45 - 11:00

Harikrishnan Ramadasan
O86 - Bridging expert curation and LLMs for automated metadata extraction in lesSDRF 2.0
11:00 - 11:15

Interactive discussions on open challenges in computational proteomics
11:15 - 12:00

Reposted by Tine Claeys

robbin @robbinbouwmeester.bsky.social · Jun 4

New in DeepLC! Ability to deal with wild, weird, and wobbly LC setups or peptide modifications. This ability is possible with transfer learning; where only a minimal amount of training peptides are needed for accurate retention time predictions.

www.biorxiv.org/content/10.1...

DeepLC introduces transfer learning for accurate LC retention time prediction and adaptation to substantially different modifications and setups

While LC retention time prediction of peptides and their modifications has proven useful, widespread adoption and optimal performance are hindered by variations in experimental parameters. These varia...

www.biorxiv.org

Reposted by Tine Claeys

Yasset Perez-Riverol @ypriverol.bsky.social · Jun 4

🎉 Big news from the @pride-ebi.bsky.social Team! 🎉

We’re officially in #ASMS2025 mode and kicking things off with a major milestone:

🚀 Introducing PRIDE-AP – the first Affinity Proteomics archive!
🔗 www.ebi.ac.uk/pride/archiv...

A new home for your #Olink and #SomaScan and other non-MS data.👇

PRIDE - PRoteomics IDEntifications Database