New Machine Learning Method Automates Selection of Active Spaces in Quantum Chemistry Calculations
Researchers have developed RLEASE, a reinforcement learning method that automatically selects which orbitals to include in multireference electronic-structure calculations, a task that traditionally requires expert intuition and extensive trial-and-error. The method uses a neural network trained on inexpensive Hartree-Fock descriptors and optimizes orbital selection by comparing results to reference calculations. This approach could enable high-throughput quantum chemistry workflows by eliminating the need for molecule-specific retraining or expensive pilot calculations.
RLEASE (Reinforcement Learning Efficient Active Space Engine) addresses a fundamental bottleneck in computational chemistry: selecting the active space—the set of orbitals most important for accurate multireference calculations. The method combines a neural network that predicts per-orbital diagnostic scores from inexpensive Hartree-Fock descriptors with a learned threshold policy optimized via proximal policy optimization. The reward signal comes from comparing sc-NEVPT2 energies computed with selected active spaces against DMRG reference energies. Despite training on only a small set of molecules and geometries, RLEASE generalizes to chemically diverse systems, producing compact active spaces and competitive potential-energy surfaces compared to established entropy-based methods. The approach requires only inexpensive orbital descriptors and neural-network inference at deployment, making it suitable for high-throughput workflows without molecule-specific retraining.
What's missing
The study does not discuss computational cost comparisons with traditional active-space selection methods, limitations of the approach for very large molecules or systems with unusual electronic structures, or how performance scales with molecular size and complexity.
What different sources said
- arXiv physicsCenter
RLEASE: Reinforcement Learning Efficient Active Space Engine
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.