Jan H. Jensen

New highlight: Classical solution of the FeMo-cofactor model to chemical accuracy and its implications www.compchemhighlights.org/2026/02/clas... #compchem

Coupled Cluster con MōLe: Molecular Orbital Learning for Neural Wavefunctions Density functional theory (DFT) is the most widely used method for calculating molecular properties; however, its accuracy is often insufficient for quantitative predictions. Coupled-cluster (CC) theo...

Coupled Cluster con MōLe: Molecular Orbital Learning for Neural Wavefunctions arxiv.org/abs/2602.20232 #compchem

Sampling a GDB-20 Database of 32 Trillion Drug-Like Molecules by Generative Artificial Intelligence | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

Perhaps. But will they ask the right questions?

A Reinforcement Learning-guided Genetic Algorithm Integrating Medicinal Chemistry-inspired Molecular Transformations | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

#compchem

Does AI already have human-level intelligence? The evidence is clear The vision of human-level machine intelligence laid out by Alan Turing in the 1950s is now a reality. Eyes unclouded by dread or hype will help us to prepare for what comes next.

Goddness, there's lots to say about this. Good to see the case pro laid out in detail. I wonder if Nature will be publishing the counter-argument too?
www.nature.com/articles/d41...

tmQM-RDF Dataset: a Knowledge Graph Representing Transition Metal Complexes Transition Metal Complexes (TMCs) have wide-ranging practical utility in chemistry, with possible applications that range from catalysis to medicinal chemistry. The study of TMCs and their properties ...

tmQM-RDF Dataset: a Knowledge Graph Representing Transition Metal Complexes #compchem
arxiv.org/abs/2602.07091

#RobSelects paper of the week #ACSCentSci: Systematic statistical analysis of 66,000 organic reactions from high-throughput experiments representative of pharmaceutical drug discovery. #orgchem https://doi.org/10.1021/acscentsci.5c02031

Structure-free generation of transition state conformations with Bayesian flow networks | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

El Agente Estructural: An Artificially Intelligent Molecular Editor We present El Agente Estructural, a multimodal, natural-language-driven geometry-generation and manipulation agent for autonomous chemistry and molecular modelling. Unlike molecular generation or edit...

Agente Estructural: An Artificially Intelligent Molecular Editor
arxiv.org/abs/2602.04849 #compchem

SOT-RM: An equivariant shortcut and optimal transportation-based flow model for exploring chemical reaction mechanisms | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

FragmentFlow: Scalable Transition State Generation for Large Molecules Transition states (TSs) are central to understanding and quantitatively predicting chemical reactivity and reaction mechanisms. Although traditional TS generation methods are computationally expensive...

FragmentFlow: Scalable Transition State Generation for Large Molecules
arxiv.org/abs/2602.02310 #compchem

Not 100% sure whether becoming *my* new colleague is a win or a threat, 😂 but the amazing PSDA group at AstraZeneca is looking for new faces to join a clever, fun, and interdisciplinary team! I… | Nes... Not 100% sure whether becoming *my* new colleague is a win or a threat, 😂 but the amazing PSDA group at AstraZeneca is looking for new faces to join a clever, fun, and interdisciplinary team! I believ...

AstraZeneca is hiring in Predictive Science, Digital, and Automation and you even get my face on your screen. Being real, this is an awesome department to work in though #chemjobs #UKchemjobs #EUchemjobs www.linkedin.com/posts/nessac...

Paths to cheminformatics: Q&A with Rajarshi Guha - Journal of Cheminformatics Journal of Cheminformatics -

link.springer.com/article/10.1...

YouTube video by Welch Labs Can humans make AI any better?

"We want AI agents that can discover like we can, not which contain what we have discovered."
youtu.be/2hcsmtkSzIw?...

A New LLM System for Synthesis Planning

A look at the new MOSAIC paper on an LLM-based system to try to help with predicting synthetic chemical lab procedures:

New highlight: Predicting Enantioselectivity via Kinetic Simulations on Gigantic Reaction Path Networks www.compchemhighlights.org/2026/01/pred... #compchem

Predicting Enantioselectivity via Kinetic Simulations on Gigantic Reaction Path Networks | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

Now out in JACS! 🎉 : "Computing Solvation Free Energies of Small Molecules with Experimental Accuracy"! It's been a pleasure to collaborate on this with Harry Moore (@jhmchem.bsky.social) & Gábor Csányi pubs.acs.org/doi/10.1021/...

A 3D, Structure-Based, Deep Learning Approach for Predicting the Regioselectivity of Transition-Metal Catalysis | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

#chemsky #compchemsky

Reaching for Transition-Metal Chemical Accuracy by Adding Ladders to Fifth-Rung Density Functionals | ChemRxiv chemrxiv.org/doi/full/10.... #compchem

Beyond the Training Domain: Robust Generative Transition State Models for Unseen Chemistry Transition states (TSs) govern the rates and outcomes of chemical reactions, making their accurate prediction a central challenge in computational chemistry. Although recent machine-learning models ac...

Beyond the Training Domain: Robust Generative Transition State Models for Unseen Chemistry
arxiv.org/abs/2601.16469 #compchem

The new ChemRxiv website is now live! Come and check out the new platform at chemrxiv.org

#RobSelects paper of the week #ChemicalScience: Real-space analysis and visualization of steric repulsion based on the Pauli kinetic energy excess. #compchem https://doi.org/10.1039/D5SC07952G

Toward On-the-Fly Prediction of Reaction Energetics for High-Throughput Screening Machine learning is increasingly used to predict reaction properties such as barrier heights, reaction energies, rates, or yields, as well as the underlying molecular geometries, including transition ...

Toward On-the-Fly Prediction of Reaction Energetics for High-Throughput Screening | ChemRxiv - doi.org/10.26434/che... #compchem

Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model Implicit solvent models (ISMs) promise to deliver the accuracy of explicit solvent simulations at a fraction of the computational cost. However, despite decades of development, their accuracy has rema...

Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model
arxiv.org/abs/2601.05388 #compchem

#chemjobs

ONE MORE WEEK TO GO !
Please apply and let people know of this opportunity !

#chemjobs Come be my colleague in 2026 ! New position in the Department of Chemistry at the University of Florida. AST/ASO/FULL PROF in Artificial Intelligence for Quantum Chemistry.

explore.jobs.ufl.edu/en-us/job/53...