Microsoft releases quantum chemistry tool Skala

[hotblack]

Microsoft AI Research has made a tool called Skala available for everyone to use. It was previously an internal research project. Here’s the new Azure Skala page.

What is this all about? There’s some info this webpage about the DFT research project

Our mission is to enable predictive modeling of laboratory experiments by achieving chemically accurate electronic structure predictions with deep learning powered DFT, targeting errors below 1 kcal/mol, while retaining the computational efficiency of scalable semi-local DFT.

Most accessible is probably this blogpost about a paper they released in the summer

Breaking bonds, breaking ground: Advancing the accuracy of computational chemistry with deep learning

We are excited to share our first big milestone in solving a grand challenge that has hampered the predictive power of computational chemistry, biochemistry, and materials science for decades. By using a scalable deep-learning approach and generating an unprecedented quantity of diverse, highly accurate data, we have achieved a breakthrough in the accuracy of density functional theory (DFT), the workhorse method that thousands of scientists use every year to simulate matter at the atomistic level. Within the region of chemical space represented in our large training dataset, our model reaches the accuracy required to reliably predict experimental outcomes, as assessed on the well-known benchmark dataset W4-17. This removes a fundamental barrier to shifting the balance of molecule and material design from being driven by laboratory experiments to being driven by computational simulations. The implications for accelerating scientific discovery are far reaching, spanning applications from drugs to batteries and green fertilizers.

And here’s the paper:

Accurate and scalable exchange-correlation with deep learning, 2025, Luise et al

Abstract
Density Functional Theory (DFT) is the most widely used electronic structure method for predicting the properties of molecules and materials. Although DFT is, in principle, an exact reformulation of the Schrödinger equation, practical applications rely on approximations to the unknown exchange-correlation (XC) functional. Most existing XC functionals are constructed using a limited set of increasingly complex, hand-crafted features that improve accuracy at the expense of computational efficiency. Yet, no current approximation achieves the accuracy and generality for predictive modeling of laboratory experiments at chemical accuracy -- typically defined as errors below 1 kcal/mol.

In this work, we present Skala, a modern deep learning-based XC functional that bypasses expensive hand-designed features by learning representations directly from data. Skala achieves chemical accuracy for atomization energies of small molecules while retaining the computational efficiency typical of semi-local DFT. This performance is enabled by training on an unprecedented volume of high-accuracy reference data generated using computationally intensive wavefunction-based methods.

Notably, Skala systematically improves with additional training data covering diverse chemistry. By incorporating a modest amount of additional high-accuracy data tailored to chemistry beyond atomization energies, Skala achieves accuracy competitive with the best-performing hybrid functionals across general main group chemistry, at the cost of semi-local DFT. As the training dataset continues to expand, Skala is poised to further enhance the predictive power of first-principles simulations.

https://doi.org/10.48550/arXiv.2506.14665

And a video

 

[hotblack]

I found this interesting in general and thought others would. A scientific development with potentially relevant applications and also ties in with recent discussion of usefulness of AI/ML. I also think it’s an area @Jonathan Edwards is very familiar with!