Tine Claeys
@tineclaeys.bsky.social
Postdoc in computational proteomics @CompOmics @VIBLifeSciences - turning public data into tissue biomarkers with ML, AI, and a mission to make proteomics truly reusable
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
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
PSI-AI
psi-ai.org
August 15, 2025 at 10:48 AM
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
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
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).
July 23, 2025 at 11:11 AM
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).
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?
Maybe the rise of clinical datasets might push this?
July 22, 2025 at 7:31 PM
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?
Maybe the rise of clinical datasets might push this?
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?
July 22, 2025 at 6:23 PM
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?
Never know that there were so many ''condoms'' involved in studying open reading frames, the more you know 🤷♀️
July 22, 2025 at 2:37 PM
Never know that there were so many ''condoms'' involved in studying open reading frames, the more you know 🤷♀️
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 🤗
July 22, 2025 at 10:28 AM
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 🤗
ProteomicsML is absolutely awesome to get hands-on with the ML learning part and learn the classical pitfalls
June 25, 2025 at 5:05 PM
ProteomicsML is absolutely awesome to get hands-on with the ML learning part and learn the classical pitfalls
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.
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.
June 25, 2025 at 4:00 PM
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.
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.
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 🙌
Pretty clear that @compomics.com is thé best team to do science and have fun with 🙌
www.biorxiv.org
June 23, 2025 at 8:03 PM
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 🙌
Pretty clear that @compomics.com is thé best team to do science and have fun with 🙌
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 🙌
Pretty clear that @compomics.com is thé best team to do science and have fun with 🙌
www.biorxiv.org
June 23, 2025 at 8:01 PM
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 🙌
Pretty clear that @compomics.com is thé best team to do science and have fun with 🙌
And you get the cutest mascotte octopus. His name is Mark! He'll guide you Clippy-wise through your analyses 🙌
June 16, 2025 at 12:32 PM
And you get the cutest mascotte octopus. His name is Mark! He'll guide you Clippy-wise through your analyses 🙌