Multi-Objective Design of DNA-Stabilized Nanoclusters Using Variational Autoencoders With Automatic Feature Extraction
ACS Nano · 01.10.2024 · 18 (39) · 26997-27008
DOI: 10.1021/acsnano.4c09640 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Nano, online erschienen am 17.09.2024. Verfasst von Elham Sadeghi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University at Albany-SUNY, Albany, New York 12222, United States. Hauptthemen laut MEDLINE: DNA, Silver, Metal Nanoparticles. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: 'la Caixa' Foundation, Chan Zuckerberg Initiative, Division of Chemical, Bioengineering, Environmental, and Transport Systems.
Abstract (Originalsprache)
DNA-stabilized silver nanoclusters (AgN-DNAs) have sequence-tuned compositions and fluorescence colors. High-throughput experiments together with supervised machine learning models have recently enabled design of DNA templates that select for AgN-DNA properties, including near-infrared (NIR) emission that holds promise for deep tissue bioimaging. However, these existing models do not enable simultaneous selection of multiple AgN-DNA properties, and require significant expert input for feature engineering and class definitions. This work presents a model for multiobjective, continuous-property design of AgN-DNAs with automatic feature extraction, based on variational autoencoders (VAEs). This model is generative, i.e., it learns both the forward mapping from DNA sequence to AgN-DNA properties and the inverse mapping from properties to sequence, and is trained on an experimental data set of DNA sequences paired with AgN-DNA fluorescence properties. Experimental testing shows that the model enables effective design of AgN-DNA emission, including bright NIR AgN-DNAs with 4-fold greater abundance compared to training data. In addition, Shapley analysis is employed to discern learned nucleobase patterns that correspond to fluorescence color and brightness. This generative model can be adapted for a range of biomolecular systems with sequence-dependent properties, enabling precise design of emerging biomolecular nanomaterials.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science, University at Albany-SUNY, Albany, New York 12222, United States.
- Department of Materials Science and Engineering, University of California, Irvine, California 92697, United States.
- Department of Chemistry, University of California, Irvine, California 92697, United States.
- Department of Chemical and Biomolecular Engineering, University of California, Irvine, California 92697, United States.
- Department of Physics and Astronomy, University of California, Irvine, California 92697, United States.
ORCID-Profile: Elham Sadeghi, Peter Mastracco, Stacy M Copp, Petko Bogdanov
Förderung
- 'la Caixa' Foundation
- Chan Zuckerberg Initiative
- Division of Chemical, Bioengineering, Environmental, and Transport Systems
- Division of Materials Research
- Office of the President, University of California
Zitieren
APA
Sadeghi, E., Mastracco, P., Gonzàlez-Rosell, A., Copp, S. M., & Bogdanov, P. (2024). Multi-Objective Design of DNA-Stabilized Nanoclusters Using Variational Autoencoders With Automatic Feature Extraction. ACS Nano, 18(39), 26997-27008. https://doi.org/10.1021/acsnano.4c09640
Vancouver
Sadeghi E, Mastracco P, Gonzàlez-Rosell A, Copp SM, Bogdanov P. Multi-Objective Design of DNA-Stabilized Nanoclusters Using Variational Autoencoders With Automatic Feature Extraction. ACS Nano. 2024;18(39):26997-27008. doi:10.1021/acsnano.4c09640
BibTeX
@article{Sadeghi2024,
author = {Sadeghi, Elham and Mastracco, Peter and Gonzàlez-Rosell, Anna and Copp, Stacy M and Bogdanov, Petko},
title = {Multi-Objective Design of DNA-Stabilized Nanoclusters Using Variational Autoencoders With Automatic Feature Extraction},
journal = {ACS Nano},
year = {2024},
volume = {18},
number = {39},
pages = {26997--27008},
doi = {10.1021/acsnano.4c09640}
}
EUVIMED