Jonas Verhellen
banner
jonasverhellen.bsky.social
Jonas Verhellen
@jonasverhellen.bsky.social
Theoretical physicist with a PhD in neuroscience. Postdoc in protein-protein interactions. Into art, science, and innovation.

Currently: Copenhagen 🇩🇰

Previously: Oslo 🇳🇴, London 🇬🇧, Brussels 🇧🇪
Reposted by Jonas Verhellen
Are you curious to see what my team and I are up to? Check out our group website here: peptide-discovery.ethz.ch
Homepage
peptide-discovery.ethz.ch
November 21, 2024 at 2:28 PM
Reposted by Jonas Verhellen
Our team is looking for a visual journalist to report, design and code stories with us. You'll be able to learn from our skilled colleagues. I joined this team in 2021 and have continued to learn ever since. It's definitely a great work environment. Learn more about it or apply here: bit.ly/4kG33L6
June 9, 2025 at 2:58 PM
Made it to @intconfchemstr.social.edu.nl.ap.brid.gy just in time for the Mike Lynch Award (after about 6 hours of public transport).
June 1, 2025 at 4:11 PM
Reposted by Jonas Verhellen
Academic freedom in the United States has found itself periodically under siege, but the current attacks from the federal government raise a new level of alarm. nyer.cm/u405qvQ
May 25, 2025 at 3:01 PM
Big news! I've received a DKK 2.97 million postdoc grant from the Lundbeck Foundation to kick off my independent research at the University of Copenhagen!

lundbeckfonden.com/news/young-t...

#neuroscience #postdoc #LundbeckFoundation #mentalhealth
May 4, 2025 at 2:05 PM
I was very happy to discover Copenhagen has a statue for @janhjensen.bsky.social! 🦉🦉🦉
April 7, 2025 at 3:50 PM
Reposted by Jonas Verhellen
Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)
NeurIPS participation in Europe
We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...
docs.google.com
March 30, 2025 at 6:04 PM
Reposted by Jonas Verhellen
Learn more about #NordicAIR at our new website: nordicpartnership.ai (3/3)
Home | Nordic Partnership
nordicpartnership.ai
February 26, 2025 at 12:42 PM
Reposted by Jonas Verhellen
Introducing olmOCR, our open-source tool to extract clean plain text from PDFs!

Built for scale, olmOCR handles many document types with high throughput. Run it on your own GPU for free—at over 3000 token/s, equivalent to $190 per million pages, or 1/32 the cost of GPT-4o!
February 25, 2025 at 5:04 PM
Reposted by Jonas Verhellen
Come work with me!
We are looking to bring on more top talent to our language modeling workstream at @ai2.bsky.social building the open ecosystem. We are hiring:
* Research scientists
* Senior research engineers
* Post docs (Young investigators)
* Pre docs

job-boards.greenhouse.io/thealleninst...
The Allen Institute for AI
job-boards.greenhouse.io
February 25, 2025 at 1:07 AM
Happy Valentine's day! And for all of us who need some extra love today - especially the NIH folks - here's a happy oxytocin molecule! 💞🧪
February 14, 2025 at 6:09 PM
Reposted by Jonas Verhellen
1 week left to apply for this fully funded #compchem PhD opportunity part of the EU Marie Curie Doctoral Network, “CATALOOP”
🗓 Deadline: 31/01/2025
📥 How to Apply: submit your application via the university portal shorturl.at/nHyAo
We are seeking an outstanding #PhD candidate to join our team (www.duartegroupchem.org)! If you know potential candidates interested in combining #ML and #compchem reaction modelling for catalyst design, please share this opportunity with them!
🗓 Deadline: 31/01/25
📥 Application: shorturl.at/nHyAo
January 23, 2025 at 7:53 AM
Reposted by Jonas Verhellen
New preprint from my group: Enhancing Chemical Synthesis Planning: Automated Quantum Mechanics-Based Regioselectivity Prediction for C-H Activation with Directing Groups doi.org/10.26434/che... #compchem
January 16, 2025 at 6:31 AM
Reposted by Jonas Verhellen
Active-learning ML approach for catalytic free-energy calculations by Liu et al.: An MLP “committee” and constrained MD refine data, capturing reaction pathways 10^6× faster than ab initio. Their scheme ensures robust coverage of transitions and near-DFT precision. pubs.acs.org/doi/10.1021/...
CatFlow: An Automated Workflow for Training Machine Learning Potentials to Compute Free Energies in Dynamic Catalysis
Dynamic effects of catalysts play a crucial role in catalytic reactions, necessitating the incorporation of statistical sampling and understanding of the impact of dynamic structures in free energy calculations. However, the complexity of catalytic systems poses challenges in effectively exploring the vast configurational space effectively. In this work, we propose CatFlow, an automated workflow for training machine learning potentials (MLPs) to compute free energies of catalytic reactions. CatFlow combines constrained molecular dynamics (MD) simulation with concurrent training of MLPs and sequential calculation of free energies with well trained MLPs. By rapidly generating reliable MLPs, CatFlow facilitates rigorous free energy calculations, enabling the determination of the reaction profiles in an end-to-end manner. We showcased the capabilities of CatFlow by investigating the activation of O2 catalyzed by Pt clusters and demonstrated the effects of phase transition on the activities of the catalytic reaction. CatFlow offers an efficient and automated solution for studying the catalytic elementary reaction processes. It reduces the need for human intervention and provides researchers with a powerful tool to investigate free energies of dynamic catalysis.
pubs.acs.org
January 1, 2025 at 5:08 PM
Reposted by Jonas Verhellen
Please forward to good candidates jobportal.ku.dk/videnskabeli...
Two PhD or Postdoc positions in computational off-target analysis of siRNA and small peptides
jobportal.ku.dk
December 27, 2024 at 7:10 AM
I used to share this video on the other place every year at Christmas ... time for a new tradition. Happy holidays BlueSky!

youtu.be/Etflv7R6NKA?...
Studio 60 O Holy Night
YouTube video by Oceandreams313
youtu.be
December 25, 2024 at 10:08 PM
Reposted by Jonas Verhellen

Come join us on an exciting joint PhD project on ML for protein function with @kailalab.bsky.social -- We are looking for a strong quantitative candidate with prior experience in ML. The position is based in Gothenburg and is fully funded for 5 years.

www.chalmers.se/en/about-cha...
Vacancies
www.chalmers.se
December 23, 2024 at 8:17 AM
🔬 More #SciComm! 🔬

This week’s figure shows how severe mental disorders affect the entire body.
🧠 While these disorders are known for their impact on brain functioning (blue), patients are also disproportionately affected by physical diseases (red). Details 👇!
December 20, 2024 at 8:45 AM
🔬 Hello, BlueSky! Time for some more #SciComm! 🔬

Last week’s (procrastination 🙈) figure illustrates the frequency spectrum of genetic risk factors for Schizophrenia: common variants (blue), protein truncating variants (red), and copy number variations (green). More 👇!
December 9, 2024 at 9:55 AM
🔬 Hello, BlueSky! Time for some #SciComm! 🔬

This week’s figure illustrates the onset and progression of schizophrenia, integrating symptom intensity (blue line), environmental and genetic risk factors (red boxes), and key disease milestones (white boxes) as they unfold across age.
November 29, 2024 at 12:17 PM
Reposted by Jonas Verhellen
Still believe that at the core of every exceptional research group are researchers who are both bright and kind and who value teamwork.

#chemsky
November 13, 2024 at 9:08 AM
Cannot overstate how stellar of a job @amelierocks.bsky.social did the past three days! An absolute masterclass. Calm, composed, always human. 💯👏
European RosettaCon has been phenomenal! Congratulations to the poster ptesentation winners and thanks @amelierocks.bsky.social for organizing!
November 13, 2024 at 12:40 PM
🚀 Excited to announce that "Bayesian Illumination: Inference and Quality-Diversity Accelerate Generative Molecular Models" is now available! Key takeaway: Bayesian Illumination is 100x more effective than either genetic algorithms or deep generative models. 📊
June 28, 2024 at 1:25 PM
Over the summer, I wrote a blog post series based on my PHD thesis. ✍️ So, whether you are a fellow academic, a curious mind, or simply looking to expand your knowledge, check it out! I'll be republishing announcements here from time to time. ✨

Link: jonas-verhellen.github.io/blog-thesis-...
October 7, 2023 at 5:21 PM