COMPAS-4: A Data Set of (BN)1 Substituted Cata-Condensed Polybenzenoid Hydrocarbons─Data Analysis and Feature Engineering pubs.acs.org/doi/10.1021/ac… Sabyasachi Chakraborty Renana Poranne #JCIM Vol65 Issue11 #ChemicalInformation

Check out my latest article: Symmetry by Design: Wyckoff Transformer linkedin.com/pulse/symmetry… via LinkedIn

Outstanding work by grad students Atreyee, Atreyee Majumdar and Surajit, Surajit Das (of TIFR Hyderabad) "Unlocking Inverted Singlet-Triplet Gap in Alternant Hydrocarbons with Heteroatoms" now published in Chemical Science pubs.rsc.org/en/content/art…

Ryota Ryota Tomioka and Cecilia Cecilia Clementi. Work done at Microsoft Research AI for Science! Check out the full paper here: science.org/doi/10.1126/sc…

🚨 Just published in J. Am. Chem. Soc.! 🚨 What happens to the pH of #water when it’s squeezed into a space thinner than a nanometer?🤔 👉 doi.org/10.1021/jacs.5… In our latest study, we show that sub-nanometer confinement suppresses #water autoionization, raising its pKw by more than

🧪🔬 Synthesis experts! Our team at Google DeepMind is hiring a scientist to establish and lead an AI-driven laboratory for materials discovery. The team is working to combine our AI capabilities with automated experimentation to discover novel functional materials. 1/

We show how photoredox catalysis can bypass Kasha’s rule, enabling reactions from higher excited states. This work, led by the exceptional Björn Pfund, offers new insights into photochemical reactivity. Published in J. Am. Chem. Soc.: bit.ly/3IysmjX

Our development of machine-learned transferable coarse-grained models in now on Nat Chem! doi.org/10.1038/s41557… I am so proud of my group for this work! Particularly first authors Nick Charron, Klara Bonneau, Aldo S. Pasos-Trejo, Andrea Guljas.

I'm happy to share the recording of a lecture I gave in Prague in May 2025: "Towards Understanding of Scaling, Emergence and Transformers." slideslive.com/39043090/towar…

I have a dream that one day thermodynamics, like calculus, will be taught to sons and daughters of many people. 😀 docs.google.com/document/d/1Ix…

Andrey, Momir, and Sandra published a paper in JCTC Papers about the "Bridging the Gap between Variational and Perturbational DFT-Based Methods for Calculating Excited States" Swiss National Science Foundation University of Zurich Check it here: pubs.acs.org/doi/full/10.10…

Yes I think of rational design of materials at the atomistic scale as a keystone problem: Once you unlock it the possibilities are endless and will set off a cascade of breakthroughs throughout the sciences and engineering.

Locating transition states is often a #compchem challenge. We find that geodesics (shortest length paths) on ML PES can yield excellent initial geometries for transition state optimization on DFT PES (even compared to pure DFT frozen string method/FSM!). Preprint below!

“Why would you test on the training set?”

Please share: Apply for PhD position in theoretical chemistry for our ERC Synergy 2DPolyMembrane on simulating ion transport in atom-thin 2D polymer & graphene based membranes. Deadline 15.8. Start asap verw.tu-dresden.de/StellAus/stell… #phdjobs #chemtwitter #PhDposition #compchem

Our new paper in Comms Chem paper explores how small modifications in drug molecules affect properties that influence their efficacy and the role molecular simulation can play in elucidating these effects: rdcu.be/eznSi

I had a blast presenting our work with Catherine Mollart and Michelle Ernst on #COF and #MOF at the vdW/L Discussions! Thank you Alex and Mirela TCPUniLu for having me!

“On a log-log plot, my grandmother fits on a straight line.” -Physicist Fritz Houtermans There's a lot of truth to this. log-log plots are often abused and can be very misleading 1/5

Do you use chemical #ML to discover #molecules and #materials? Don’t miss the 2nd Chemical Compound Space Conference next March. We had fantastic time organising the 1st one last year, no doubt the 2nd will deliver! Early-bird register till 15.11. ccsc2026.github.io//

Unabashed self-promotion: Super hyped about my paper with Giorgio Domenichini finally coming out in JCP! We applied the Verlet algorithm trick to anti-symmetric alchemical perturbations and it seems to work great! It leads to what we call 'alchemical diastereomers' (for lack of a