Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow DOI Creative Commons
Son Gyo Jung, Guwon Jung, Jacqueline M. Cole

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 23, 2024

Machine learning (ML) methods provide a pathway to accurately predict molecular properties, leveraging patterns derived from structure–property relationships within materials databases. This approach holds significant importance in drug discovery and design, where the rapid, efficient screening of molecules can accelerate development new pharmaceuticals chemical for highly specialized target application. Unsupervised self-supervised applied graph-based or geometric models have garnered considerable traction. More recently, transformer-based language emerged as powerful tools. Nevertheless, their application entails computational resources, owing need an extensive pretraining process on vast corpus unlabeled data sets. To this end, we present semisupervised strategy that harnesses substructure vector embeddings conjunction with ML-based feature selection workflow various properties. We evaluate efficacy our modeling methodology across diverse range sets, encompassing both regression classification tasks. Our findings demonstrate superior performance compared most existing state-of-the-art algorithms, while offering advantages terms balancing model accuracy requirements. Moreover, provides deeper insights into interactions are essential interpretability. A case study is conducted lipophilicity molecules, exemplifying robustness strategy. The result underscores meticulous analysis over mere reliance predictive high degree algorithmic complexity.

Language: Английский

Phase Stability and Transitions in High-Entropy Alloys: Insights from Lattice Gas Models, Computational Simulations, and Experimental Validation DOI Creative Commons
Łukasz Łach

Entropy, Journal Year: 2025, Volume and Issue: 27(5), P. 464 - 464

Published: April 25, 2025

High-entropy alloys (HEAs) are a novel class of metallic materials composed five or more principal elements in near-equimolar ratios. This unconventional composition leads to high configurational entropy, which promotes the formation solid solution phases with enhanced mechanical properties, thermal stability, and corrosion resistance. Phase stability plays critical role determining their structural integrity performance. study provides focused review HEA phase transitions, emphasizing lattice gas models predicting behavior. By integrating statistical mechanics thermodynamic principles, enable accurate modeling atomic interactions, segregation, order-disorder transformations. The combination computational simulations (e.g., Monte Carlo, molecular dynamics) experimental validation XRD, TEM, APT) improves predictive accuracy. Furthermore, advances data-driven methodologies facilitate high-throughput exploration compositions, accelerating discovery optimized superior Beyond applications, HEAs demonstrate potential functional domains, such as catalysis, hydrogen storage, energy technologies. brings together theoretical modeling—particularly approaches—and form unified understanding behavior high-entropy alloys. highlighting mechanisms behind transitions implications for material performance, this work aims support design optimization real-world applications aerospace, systems, engineering.

Language: Английский

Citations

0

Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow DOI Creative Commons
Son Gyo Jung, Guwon Jung, Jacqueline M. Cole

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 23, 2024

Machine learning (ML) methods provide a pathway to accurately predict molecular properties, leveraging patterns derived from structure–property relationships within materials databases. This approach holds significant importance in drug discovery and design, where the rapid, efficient screening of molecules can accelerate development new pharmaceuticals chemical for highly specialized target application. Unsupervised self-supervised applied graph-based or geometric models have garnered considerable traction. More recently, transformer-based language emerged as powerful tools. Nevertheless, their application entails computational resources, owing need an extensive pretraining process on vast corpus unlabeled data sets. To this end, we present semisupervised strategy that harnesses substructure vector embeddings conjunction with ML-based feature selection workflow various properties. We evaluate efficacy our modeling methodology across diverse range sets, encompassing both regression classification tasks. Our findings demonstrate superior performance compared most existing state-of-the-art algorithms, while offering advantages terms balancing model accuracy requirements. Moreover, provides deeper insights into interactions are essential interpretability. A case study is conducted lipophilicity molecules, exemplifying robustness strategy. The result underscores meticulous analysis over mere reliance predictive high degree algorithmic complexity.

Language: Английский

Citations

2