The Potential of Neural Network Potentials DOI Creative Commons
Timothy T. Duignan

ACS Physical Chemistry Au, Journal Year: 2024, Volume and Issue: 4(3), P. 232 - 241

Published: March 21, 2024

In the next half-century, physical chemistry will likely undergo a profound transformation, driven predominantly by combination of recent advances in quantum and machine learning (ML). Specifically, equivariant neural network potentials (NNPs) are breakthrough new tool that already enabling us to simulate systems at molecular scale with unprecedented accuracy speed, relying on nothing but fundamental laws. The continued development this approach realize Paul Dirac's 80-year-old vision using mechanics unify physics providing invaluable tools for understanding materials science, biology, earth sciences, beyond. era highly accurate efficient first-principles simulations provide wealth training data can be used build automated computational methodologies, such as diffusion models, design optimization scale. Large language models (LLMs) also evolve into increasingly indispensable literature review, coding, idea generation, scientific writing.

Language: Английский

Connectivity Optimized Nested Line Graph Networks for Crystal Structures DOI Creative Commons
Robin Ruff, Patrick Reiser,

Jan Stühmer

et al.

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(3), P. 594 - 601

Published: Jan. 1, 2024

Graph neural networks (GNNs) have been applied to a large variety of applications in materials science and chemistry. We report nested line-graph network achieving state-of-the-art performance multiple benchmarks.

Language: Английский

Citations

15
Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity DOI Creative Commons
Johan Fredin Haslum,

Charles-Hugues Lardeau,

Johan Karlsson

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: April 24, 2024

Abstract Identifying active compounds for a target is time- and resource-intensive task in early drug discovery. Accurate bioactivity prediction using morphological profiles could streamline the process, enabling smaller, more focused compound screens. We investigate potential of deep learning on unrefined single-concentration activity readouts Cell Painting data, to predict across 140 diverse assays. observe an average ROC-AUC 0.744 ± 0.108 with 62% assays achieving ≥0.7, 30% ≥0.8, 7% ≥0.9. In many cases, high performance can be achieved only brightfield images instead multichannel fluorescence images. A comprehensive analysis shows that Painting-based robust assay types, technologies, classes, cell-based kinase targets being particularly well-suited prediction. Experimental validation confirms enrichment compounds. Our findings indicate models trained combined small set data points, reliably library while maintaining hit rates scaffold diversity. This approach has reduce size screening campaigns, saving time resources, primary complex

Language: Английский

Citations

15
Rise of machine learning potentials in heterogeneous catalysis: Developments, applications, and prospects DOI
Seokhyun Choung,

Wongyu Park,

Jinuk Moon

et al.

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 494, P. 152757 - 152757

Published: June 2, 2024

Language: Английский

Citations

15
Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study DOI Creative Commons
Sadman Sadeed Omee, Nihang Fu, Rongzhi Dong

et al.

npj Computational Materials, Journal Year: 2024, Volume and Issue: 10(1)

Published: July 4, 2024

Abstract In real-world materials research, machine learning (ML) models are usually expected to predict and discover novel exceptional that deviate from the known materials. It is thus a pressing question provide an objective evaluation of ML model performances in property prediction out-of-distribution (OOD) different training set. Traditional performance through random splitting dataset frequently results artificially high-performance assessments due inherent redundancy typical material datasets. Here we present comprehensive benchmark study structure-based graph neural networks (GNNs) for extrapolative OOD prediction. We formulate five categories problems three datasets MatBench study. Our extensive experiments show current state-of-the-art GNN algorithms significantly underperform tasks on average compared their baselines study, demonstrating crucial generalization gap realistic tasks. further examine latent physical spaces these identify sources CGCNN, ALIGNN, DeeperGATGNN’s more robust than those best (coGN coNGN) as case perovskites dataset, insights improve performance.

Language: Английский

Citations

15
The Potential of Neural Network Potentials DOI Creative Commons
Timothy T. Duignan

ACS Physical Chemistry Au, Journal Year: 2024, Volume and Issue: 4(3), P. 232 - 241

Published: March 21, 2024

In the next half-century, physical chemistry will likely undergo a profound transformation, driven predominantly by combination of recent advances in quantum and machine learning (ML). Specifically, equivariant neural network potentials (NNPs) are breakthrough new tool that already enabling us to simulate systems at molecular scale with unprecedented accuracy speed, relying on nothing but fundamental laws. The continued development this approach realize Paul Dirac's 80-year-old vision using mechanics unify physics providing invaluable tools for understanding materials science, biology, earth sciences, beyond. era highly accurate efficient first-principles simulations provide wealth training data can be used build automated computational methodologies, such as diffusion models, design optimization scale. Large language models (LLMs) also evolve into increasingly indispensable literature review, coding, idea generation, scientific writing.

Language: Английский

Citations

14