Document Type
Article
Version Deposited
Published Version
Open Access Funding Source
Other
Publication Date
8-21-2024
Publication Title
Nano Letters
DOI
10.1021/acs.nanolett.4c02568
Abstract
Modern nanotechnology has generated numerous datasets from in vitro and in vivo studies on nanomaterials, with some available on nanoinformatics portals. However, these existing databases lack the digital data and tools suitable for machine learning studies. Here, we report a nanoinformatics platform that accurately annotates nanostructures into machine-readable data files and provides modeling toolkits. This platform, accessible to the public at https://vinas-toolbox.com/, has annotated nanostructures of 14 material types. The associated nanodescriptor data and assay test results are appropriate for modeling purposes. The modeling toolkits enable data standardization, data visualization, and machine learning model development to predict properties and bioactivities of new nanomaterials. Moreover, a library of virtual nanostructures with their predicted properties and bioactivities is available, directing the synthesis of new nanomaterials. This platform provides a data-driven computational modeling platform for the nanoscience community, significantly aiding in the development of safe and effective nanomaterials.
Recommended Citation
Nano Lett. 2024, 24, 33, 10228–10236
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Comments
© 2024 The Authors. Published by American Chemical Society.