Virtual Molecular Projections and Convolutional Neural Networks for the End-to-End Modeling of Nanoparticle Activities and Properties

Daniel P. Russo, Xiliang Yan, Sunil Shende, Heng Huang, Bing Yan, Hao Zhu

Research output: Contribution to journalArticlepeer-review

16 Scopus citations

Abstract

Digitalizing complex nanostructures into data structures suitable for machine learning modeling without losing nanostructure information has been a major challenge. Deep learning frameworks, particularly convolutional neural networks (CNNs), are especially adept at handling multidimensional and complex inputs. In this study, CNNs were applied for the modeling of nanoparticle activities exclusively from nanostructures. The nanostructures were represented by virtual molecular projections, a multidimensional digitalization of nanostructures, and used as input data to train CNNs. To this end, 77 nanoparticles with various activities and/or physicochemical property results were used for modeling. The resulting CNN model predictions show high correlations with the experimental results. An analysis of a trained CNN quantitatively showed that neurons were able to recognize distinct nanostructure features critical to activities and physicochemical properties. This "end-to-end"deep learning approach is well suited to digitalize complex nanostructures for data-driven machine learning modeling and can be broadly applied to rationally design nanoparticles with desired activities.

Original languageEnglish (US)
Pages (from-to)13971-13979
Number of pages9
JournalAnalytical Chemistry
Volume92
Issue number20
DOIs
StatePublished - Oct 20 2020
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry

Fingerprint

Dive into the research topics of 'Virtual Molecular Projections and Convolutional Neural Networks for the End-to-End Modeling of Nanoparticle Activities and Properties'. Together they form a unique fingerprint.

Cite this