Jan H. Jensen

🚀 Our Mini-Symposium on Molecular Machine Learning returns for its 8th Edition! 🤖 💻

🔗Register here: uni-ms.zoom-x.de/webinar/regi...

🗓 Date: January 15th, 2026
🕒 Time: 3:00 PM (UTC+1)
💻 Location: Online | Free of charge

#MachineLearning #Chemistry #DataScience #SPP2363

I always do 1024 bit ECFP4 + RF with default settings. This gives me a good idea of what performance I can expect for this data sets. It's typically within 10-15% of the best model I end up using.

Lecturer (assistant professor equiv) in synthetic medicinal chemistry or #AI enabled medicinal chemistry at University of Manchester (UK) ref: BMH-030275 | closing: 26-Jan-2026 #MedChem #ChemBiol #SynChem #cheminformatics #UKChemJobs #ChemJobs #chemsky 🧪
www.jobs.manchester.ac.uk/Job/JobDetai...

Inverse Design of Frustrated Lewis Pairs for Direct Catalytic CO2 Hydrogenation: Refining and Expanding Design Rules Frustrated Lewis pairs (FLPs), composed of reactive combinations of Lewis acids (LAs) and bases (LBs) offer a metal-free platform for catalyzing a wide range of chemical transformations. Designing the...

Inverse Design of Frustrated Lewis Pairs for Direct Catalytic CO2 Hydrogenation: Refining and Expanding Design Rules | ChemRxiv - doi.org/10.26434/che... #compchem

The ideal candidate has experience in
Quantum chemistry calculations (especially reactivity)
Programming (especially Python)
Cheminformatics software (especially RDKit)

Start date in early 2026

I’m hiring

1-year postdoc position in computational chemistry at the University of Copenhagen

The research is focusing on automated reaction prediction in collaboration with two major Pharma companies (see e.g. doi.org/10.1002/anie...)

Please share #compchem

EurIPA! 🍻

Doing More with Less: Accurate and Scalable Ligand Free Energy Calculations by Focusing on the Binding Site Predicting how chemical modifications affect drug binding is central to rational drug design. Free Energy Perturbation (FEP) calculations provide accurate estimates of these binding affinity changes, ...

Doing More with Less: Accurate and Scalable Ligand Free Energy Calculations by Focusing on the Binding Site | ChemRxiv - doi.org/10.26434/che... #compchem

Check out this post by @dereklowe.bsky.social where he uses our new method from our recent @jacs.acspublications.org paper! Thanks for trying it out!

robert downey jr. is wearing a suit and tie and making a funny face . ALT: robert downey jr. is wearing a suit and tie and making a funny face .

People who use "reply all" to admonish a person for using "reply all" ...

The largest fundamental science agency in Europe will save €1.4 million annually by breaking free from Clavariate Analytics' huge databases of references and citations.

"We have worked for free to lock ourselves collectively into a paid system", one head of the CNRS explains - but no more! 🎉

The CNRS is breaking free from the Web of Science From January 1st 2026, the CNRS will cut access to one of the largest commercial bibliometric databases, Clarivate Analytics'

CNRS cancels Web of Science in order to focus on qualitative evaluation and promoting the development of open databases.

www.cnrs.fr/en/update/cn...

New(ish*) preprint: Computational prediction of C-H hydricities and their use in predicting the regioselectivity of electron rich C-H functionalisation reactions doi.org/10.26434/che... #compchem

*I rewrote about half the text

New highlight: From Random Determinants to the Ground State www.compchemhighlights.org/2025/11/from... #compchem

Schematic of an evolutionary algorithm for generating new organic molecules, with crystal structure prediction integrated into the fitness function calculation.

I'm excited to share the latest paper from our team, just published in Nature Communications: rdcu.be/eRTSs

"Exploring organic chemical space for materials discovery using crystal structure prediction-informed evolutionary optimisation"

#compchemsky #chemsky

1/n

A new preprint from our team @unisouthampton.bsky.social

Can machine learning predict the space group preference of organic molecules?

Work by Hannah Gittins exploring random forest and graph neural network models to predict space group preferences of organic molecules.
doi.org/10.26434/che...

it's online, but I don't believe it is public. If it's recorded and made generally available, then I'll post it here.

Later today I'll give a talk entitled "Using QM and ML to predict the regioselectivity of C-H functionalisation reactions". Here are the slides: www.dropbox.com/scl/fi/7l2hf... #compchem

molSimplify 2.0: Improved Structure Generation for Automating Discovery in Inorganic Molecular and Reticular Chemistry ABSTRACT: We provide an overview of core molSimplify functionality and recent updates that enhance its capabilities for automated molecular and materials modeling. We describe the mol3D and atom3D cla...

molSimplify 2.0: Improved Structure Generation for Automating Discovery in Inorganic Molecular and Reticular Chemistry | ChemRxiv - doi.org/10.26434/che... #compchem

Rapid generation of transition-state conformer ensembles via constrained distance geometry The consideration of transition state (TS) conformer ensembles is required to accurately model a reaction, and thus plays a key role in computational catalyst design. While CREST and GOAT are establis...

Rapid generation of transition-state conformer ensembles via constrained distance geometry | ChemRxiv - doi.org/10.26434/che... #compchem

A General Pythonic Framework for DFT-in-DFT and WF-in-DFT Embedding High-level quantum mechanical (QM) simulations provide accurate electronic information of chemical systems but scale unfavourably with system size, making calculations of applied systems challenging. ...

A General Pythonic Framework for DFT-in-DFT and WF-in-DFT Embedding | ChemRxiv - doi.org/10.26434/che... #compchem

From Random Determinants to the Ground State Accurate quantum many-body calculations often depend on reliable reference states or good human-designed ansätze, yet these sources of knowledge can become unreliable in hard problems like strongly co...

From Random Determinants to the Ground State
arxiv.org/abs/2511.14734 #compchem

Exploring Transition Metal Complexes with Large Language Models Here we use a large language model for the exploration of chemical space of transition metal complexes (TMCs), fine-tuning the open-source Llama-3.2-1B model with a variation of the SMILES string repr...

Exploring Transition Metal Complexes with Large Language Models | ChemRxiv - doi.org/10.26434/che... #compchem

Toward lab-ready AI synthesis plans with protection strategies and route scoring AI-driven synthesis planning tools are developed to automatically create synthesis routes and thereby aid chemists in making novel molecules. However, these tools frequently produce reaction trees wit...

Toward lab-ready AI synthesis plans with protection strategies and route scoring | ChemRxiv - doi.org/10.26434/che... #compchem

a close up of a red and white logo for coca cola ALT: a close up of a red and white logo for coca cola

WooHoo! @chemrxiv.org has just crossed 10,000 papers (preprints) in the Theoretical and computational chemistry section! #compchem This is the largest section so far...

chemrxiv.org/engage/chemr...

A Software Framework for Physics- and AI-Driven Homogeneous Catalyst Design and Reactivity Optimization Identifying molecular catalysts that simultaneously exhibit high selectivity, high turnover frequency, and robust stability remains a major challenge in homogeneous catalysis. Traditionally, catalyst ...

A Software Framework for Physics- and AI-Driven Homogeneous Catalyst Design and Reactivity Optimization | ChemRxiv - doi.org/10.26434/che... #compchem

#RobSelects paper of the week #J_A_C_S: Frustrated Lewis pair catalyst for coupling formate esters with vinyl and aryl organoboranes. #catalysis https://doi.org/10.1021/jacs.5c17878

This week's #RDKit blog post looks at LOBSTER, a nice molecular superposition data set that came out last year. Now that everything's loaded into a database using lwreg, I can start playing with the data in future posts.
greglandrum.github.io/rdkit-blog/p...

Toward lab-ready AI synthesis plans with protection strategies and route scoring AI-driven synthesis planning tools are developed to automatically create synthesis routes and thereby aid chemists in making novel molecules. However, these tools frequently produce reaction trees wit...

Toward lab-ready AI synthesis plans with protection strategies and route scoring | ChemRxiv - doi.org/10.26434/che... #compchem