TY - JOUR
T1 - Virtual Molecular Projections and Convolutional Neural Networks for the End-to-End Modeling of Nanoparticle Activities and Properties
AU - Russo, Daniel P.
AU - Yan, Xiliang
AU - Shende, Sunil
AU - Huang, Heng
AU - Yan, Bing
AU - Zhu, Hao
N1 - Funding Information:
X.Y. and B.Y. were supported by the National Key R&D Program of China (2016YFA0203103), the National Natural Science Foundation of China (91543204 and 91643204), and the introduced innovative R&D team project under “The Peal River Talent Recruitment Program” of Guangzhou Province (2019ZT08L387).
Funding Information:
X.Y. and B.Y. were supported by the National Key R&D Program of China (2016YFA0203103), the National Natural Science Foundation of China (91543204 and 91643204), and the introduced innovative R&D team project under "The Peal River Talent Recruitment Program" of Guangzhou Province (2019ZT08L387).
Publisher Copyright:
© 2020 American Chemical Society.
PY - 2020/10/20
Y1 - 2020/10/20
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85096662019&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096662019&partnerID=8YFLogxK
U2 - 10.1021/acs.analchem.0c02878
DO - 10.1021/acs.analchem.0c02878
M3 - Article
AN - SCOPUS:85096662019
SN - 0003-2700
VL - 92
SP - 13971
EP - 13979
JO - Analytical Chemistry
JF - Analytical Chemistry
IS - 20
ER -