YouTube video by Dan Grib

YouTube video by 3Blue1Brown

2026 RDKit User Group Meeting (in person and online)

Regioselectivity models are of key importance to the implementation of C–H functionalisations in synthetic route planning. In structure- and fragment-based drug discovery (SBDD/FBDD), ligand-target affinity is enhanced by elaborating weak hits into potent ...

Electronic-structure calculations in solution often require explicit solvent to describe hydrogen bonding, ion pairing, charge transfer, and solvent reorganization. However, preparing explicit-solvent...

A predictive model capable of generalizing to previously unseen Buchwald–Hartwig chemical space is built to enable rapid, in silico optimization, reducing reaction scouting time from weeks to minutes.

YouTube video by AiChemist-MSCA-DN

There is hardly anyone doing electronic structure calculations on molecules who has not used the famous B3LYP functional. Many will even know that the "B" in B3LYP stands for Becke, but how many know ...

Predicting which products can be made from a set of building blocks underpins library design, analogue generation, and synthesis-constrained generative modelling. Reaction templates encoded as SMARTS patterns are the standard tool for this forward ...

Transfer learning offers a promising route to accelerate Bayesian optimization (BO) by reusing knowledge acquired during related optimization tasks. In chemical reaction optimization, this most natura...

Finding exact solutions to the quantum many-body problem is computationally intractable (QMA-hard). Traditional approximations for electrons in an atom or molecule -- density functional theory and wav...

This work presents thermoMLIP, a machine-learning-interatomic-potential-based workflow for efficient conformer optimization and thermochemistry prediction across organic chemical space. By combining M...

Computational kinetic modeling relies on accurate transition-state geometries and activation barriers. While machine learning models trained on ab initio data have shown promise for transition-state s...

Machine learning has emerged as a powerful approach for molecular property prediction and drug discovery. However, the black-box nature of many machine learning models limits their interpretability, trustworthiness, and adoption in interdisciplinary ...

Applying generative molecular design requires both chemical knowledge to turn a scientific aim into a computable objective and technical skill to configure and run the workflow that pursues it. Here, ...

She was not burned out from writing code. She had barely written any in eight months. She was burned out from reading it. From being the…

The Novo Nordisk Foundation Center for Protein Design at the University of Copenhagen seeks to appoint two new group leaders in de novo protein design from 1 February 2027 or as soon as possible thereafter. These positions will be at the Assistant or Associate Professor level and associated with the Department of Biology (Faculty of Science) or the Department of Drug Design and Pharmacology (Faculty of Health and Medical Sciences).

AI progress creates more work for humans, not less

Bowen Deng, Bohan Li, Matthew Cox, Hoje Chun, Juno Nam, Artur Lyssenko, Sathya Edamadaka, Jurgis Ruza, Xiaochen Du, Nofit Segal, Jesus Diaz ...

Accurate generation of intricate 3D molecular structures is a fundamental challenge in computational chemistry. Transition states (TS), the transient structures that dictate reaction kinetics, exempli...

Efficient and reliable identification of transition states (TS) is critical for reaction modelling. Among the available approaches, the combination of double-ended TS search with eigenvector-following...