Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence

[Image: see text] DNA can stabilize silver nanoclusters (Ag(N)-DNAs) whose atomic sizes and diverse fluorescence colors are selected by nucleobase sequence. These programmable nanoclusters hold promise for sensing, bioimaging, and nanophononics. However, DNA’s vast sequence space challenges the desi...

Descripción completa

Detalles Bibliográficos
Autores principales: Mastracco, Peter, Gonzàlez-Rosell, Anna, Evans, Joshua, Bogdanov, Petko, Copp, Stacy M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2022
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9620400/
https://www.ncbi.nlm.nih.gov/pubmed/36124941
http://dx.doi.org/10.1021/acsnano.2c05390
_version_ 1784821330810503168
author Mastracco, Peter
Gonzàlez-Rosell, Anna
Evans, Joshua
Bogdanov, Petko
Copp, Stacy M.
author_facet Mastracco, Peter
Gonzàlez-Rosell, Anna
Evans, Joshua
Bogdanov, Petko
Copp, Stacy M.
author_sort Mastracco, Peter
collection PubMed
description [Image: see text] DNA can stabilize silver nanoclusters (Ag(N)-DNAs) whose atomic sizes and diverse fluorescence colors are selected by nucleobase sequence. These programmable nanoclusters hold promise for sensing, bioimaging, and nanophononics. However, DNA’s vast sequence space challenges the design and discovery of Ag(N)-DNAs with tailored properties. In particular, Ag(N)-DNAs with bright near-infrared luminescence above 800 nm remain rare, placing limits on their applications for bioimaging in the tissue transparency windows. Here, we present a design method for near-infrared emissive Ag(N)-DNAs. By combining high-throughput experimentation and machine learning with fundamental information from Ag(N)-DNA crystal structures, we distill the salient DNA sequence features that determine Ag(N)-DNA color, for the entire known spectral range of these nanoclusters. A succinct set of nucleobase staple features are predictive of Ag(N)-DNA color. By representing DNA sequences in terms of these motifs, our machine learning models increase the design success for near-infrared emissive Ag(N)-DNAs by 12.3 times as compared to training data, nearly doubling the number of known Ag(N)-DNAs with bright near-infrared luminescence above 800 nm. These results demonstrate how incorporating known structure–property relationships into machine learning models can enhance materials study and design, even for sparse and imbalanced training data.
format Online
Article
Text
id pubmed-9620400
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-96204002022-11-01 Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence Mastracco, Peter Gonzàlez-Rosell, Anna Evans, Joshua Bogdanov, Petko Copp, Stacy M. ACS Nano [Image: see text] DNA can stabilize silver nanoclusters (Ag(N)-DNAs) whose atomic sizes and diverse fluorescence colors are selected by nucleobase sequence. These programmable nanoclusters hold promise for sensing, bioimaging, and nanophononics. However, DNA’s vast sequence space challenges the design and discovery of Ag(N)-DNAs with tailored properties. In particular, Ag(N)-DNAs with bright near-infrared luminescence above 800 nm remain rare, placing limits on their applications for bioimaging in the tissue transparency windows. Here, we present a design method for near-infrared emissive Ag(N)-DNAs. By combining high-throughput experimentation and machine learning with fundamental information from Ag(N)-DNA crystal structures, we distill the salient DNA sequence features that determine Ag(N)-DNA color, for the entire known spectral range of these nanoclusters. A succinct set of nucleobase staple features are predictive of Ag(N)-DNA color. By representing DNA sequences in terms of these motifs, our machine learning models increase the design success for near-infrared emissive Ag(N)-DNAs by 12.3 times as compared to training data, nearly doubling the number of known Ag(N)-DNAs with bright near-infrared luminescence above 800 nm. These results demonstrate how incorporating known structure–property relationships into machine learning models can enhance materials study and design, even for sparse and imbalanced training data. American Chemical Society 2022-09-20 2022-10-25 /pmc/articles/PMC9620400/ /pubmed/36124941 http://dx.doi.org/10.1021/acsnano.2c05390 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Mastracco, Peter
Gonzàlez-Rosell, Anna
Evans, Joshua
Bogdanov, Petko
Copp, Stacy M.
Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence
title Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence
title_full Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence
title_fullStr Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence
title_full_unstemmed Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence
title_short Chemistry-Informed Machine Learning Enables Discovery of DNA-Stabilized Silver Nanoclusters with Near-Infrared Fluorescence
title_sort chemistry-informed machine learning enables discovery of dna-stabilized silver nanoclusters with near-infrared fluorescence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9620400/
https://www.ncbi.nlm.nih.gov/pubmed/36124941
http://dx.doi.org/10.1021/acsnano.2c05390
work_keys_str_mv AT mastraccopeter chemistryinformedmachinelearningenablesdiscoveryofdnastabilizedsilvernanoclusterswithnearinfraredfluorescence
AT gonzalezrosellanna chemistryinformedmachinelearningenablesdiscoveryofdnastabilizedsilvernanoclusterswithnearinfraredfluorescence
AT evansjoshua chemistryinformedmachinelearningenablesdiscoveryofdnastabilizedsilvernanoclusterswithnearinfraredfluorescence
AT bogdanovpetko chemistryinformedmachinelearningenablesdiscoveryofdnastabilizedsilvernanoclusterswithnearinfraredfluorescence
AT coppstacym chemistryinformedmachinelearningenablesdiscoveryofdnastabilizedsilvernanoclusterswithnearinfraredfluorescence