Open Materials 2024 dataset enables machine learning models to surpass previous standards, achieving F1 scores above 0.9 and 20 meV per atom accuracy in inorganic materials.
- 18 cites
Moving in Nature Computational Science.
Rebuilt
Open Materials 2024 dataset enables machine learning models to surpass previous standards, achieving F1 scores above 0.9 and 20 meV per atom accuracy in inorganic materials.
NEP89 delivers high-accuracy, computationally efficient atomistic simulations across 89 elements, enabling large-scale studies previously limited by resource demands.
Newest first · last 60 days
Spurious model comparisons are prevalent in biomedical AI, with nearly two-thirds of studies using invalid tests that inflate false-positive rates.
Local pseudopotentials enhance the efficiency and accuracy of neural network-based quantum Monte Carlo for large, complex systems, including the Fe4S4 cluster.
TDiMS descriptor outperforms existing methods by accurately capturing nonlocal intramolecular interactions with 20% higher predictive accuracy in property prediction tasks.
Agentic AI system RepurAgent outperforms baseline models by generating more novel, credible drug candidates across multiple stages of drug repurposing, including in leukemia, COVID-19, and rare diseases.
Surface and bulk defect characteristics critically influence the photoelectrochemical performance of Ta(3)N(5) photoanodes, with surface properties varying significantly by precursor chemistry.
Journals this month
Moving areas, week to 3 Oct 2026