Interpretable Small-Sample Deep Learning with Approximate Attribution Enhancement for Atomically Precise Gold Nanoclusters Synthesis
Molecules · 12.08.2026 · 31 (16) · 2808
DOI: 10.3390/molecules31162808 ↗Kurz gefasst
Fachartikel in der Zeitschrift Molecules, online erschienen am 12.08.2026. Verfasst von Ziyue You und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Communication Engineering, Jilin University, Changchun 130022, China. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council, Jilin Province Science and Technology Department, Jilin University.
Abstract (Originalsprache)
Small experimental datasets make synthesis-condition modelling particularly sensitive to overfitting and data leakage. Here, a graph convolutional neural network (GCNN) was coupled with approximate attribution enhancement (AAE) and evaluated on 54 gold-nanocluster synthesis records using a strict fold-local pipeline. All preprocessing, supervised representation learning, augmentation, model selection, and calibration were confined to each training fold, and metrics were calculated only on untouched original records. The strongest no-augmentation model achieved a Matthews correlation coefficient (MCC) of 0.729. With 20,000 fold-local AAE samples, Logistic Regression reached an accuracy of 0.864, an F1 score of 0.862, and an MCC of 0.758. The corresponding MCC values decreased to 0.579, 0.526, and 0.652 under leave-one-ligand-out, leave-one-publication-out, and leave-region-out evaluation, respectively, indicating that extrapolation beyond represented chemistry remained more difficult than random-fold interpolation. Feature, label-weight, augmentation-baseline, covariance, calibration, and stability analyses consistently identified ligand aromaticity, temperature, and HAuCl4 concentration as the most influential factors. An interpretable analysis of a 34-record aqueous Au25 subset further produced condition rules and a pH–temperature map, while nine literature formulations provided an external audit within the represented domain. The results position AAE as a local regularisation strategy for data-limited synthesis modelling rather than as a source of new chemical information.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Communication Engineering, Jilin University, Changchun 130022, China.
- Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583, Singapore.
- State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China.
- School of Physics, Changchun University of Science and Technology, Changchun 130022, China.
- Key Laboratory of Bionic Engineering, Ministry of Education, Jilin University, Changchun 130022, China.
- Institute of Structured and Architected Materials, Liaoning Academy of Materials, Shenyang 110167, China.
ORCID-Profile: Ziyue You, Yitong Qin, Yubing Gao, Zhengzhi Mu, Fu Liu, Shuzhi Sam Ge
Förderung
- China Scholarship Council
- Jilin Province Science and Technology Department
- Jilin University
- Ningbo Science and Technology Bureau
- Ningbo Major Science and Technology Tackling Project under the Science and Technology Innovation 2025 Major Special Project
- Natural Science Foundation of Jilin Province
Zitieren
APA
You, Z., Qin, Y., Gao, Y., Mu, Z., Liu, F., & Ge, S. S. (2026). Interpretable Small-Sample Deep Learning with Approximate Attribution Enhancement for Atomically Precise Gold Nanoclusters Synthesis. Molecules, 31(16), 2808. https://doi.org/10.3390/molecules31162808
Vancouver
You Z, Qin Y, Gao Y, Mu Z, Liu F, Ge SS. Interpretable Small-Sample Deep Learning with Approximate Attribution Enhancement for Atomically Precise Gold Nanoclusters Synthesis. Molecules. 2026;31(16):2808. doi:10.3390/molecules31162808
BibTeX
@article{You2026,
author = {You, Ziyue and Qin, Yitong and Gao, Yubing and Mu, Zhengzhi and Liu, Fu and Ge, Shuzhi Sam},
title = {Interpretable Small-Sample Deep Learning with Approximate Attribution Enhancement for Atomically Precise Gold Nanoclusters Synthesis},
journal = {Molecules},
year = {2026},
volume = {31},
number = {16},
pages = {2808},
doi = {10.3390/molecules31162808}
}
EUVIMED