Luminescent properties of new 2,2-, 2,3- and 3,3-CH2-bis(BODIPY)s dyes: Structural and solvation effects

Antina, L. A.; Ksenofontov, Alexander A.; Kalyagin, Alexander A.; Антина, Е. В.; Berezin, Mikhail Y.; Khodov, Ilya A.

doi:10.1016/j.saa.2019.03.117

Cited by 20 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this article, we overcame the limitations of this model to predict the band maximum positions of BODIPYs absorption by including nearly new 9000 measurements. We also verified the prediction ability of this model on an external dataset of 26 BODIPYs synthesized and characterized by our scientific team [12][13][14] including three new BODIPYs.…”

Section: Introductionmentioning

confidence: 62%

“…While the performance of the model slightly decreased for both 5CV and test sets, the change in the accuracy was not significant. This result could be due to the fact that only a limited number of BODIPYs exhibit effective solvatochromism [12,36]. For example, some structures synthesized in our laboratory were measured at about 19 solvents.…”

Section: Resultsmentioning

confidence: 99%

“…Additional testing of the models was done with the spectral data for BODIPYs previously synthesized in our laboratory [12][13][14]. These data consisted of 173 absorption measurements at 19 solvents for 23 BODIPYs (TS2 set) and did not have any molecules in common with the training sets.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Deep neural network model for highly accurate prediction of BODIPYs absorption

Ksenofontov

Lukanov

Bocharov

et al. 2022

Spectrochimica Acta Part A: Molecular and Biomolecular Spectros

Self Cite

View full text Add to dashboard Cite

A possibility to accurately predict the absorption maximum wavelength of BODIPYs was investigated. We found that previously reported models had a low accuracy (40-57 nm) to predict BODIPYs due to the limited dataset sizes and/or number of BODIPYs (few hundreds). New models developed in this study were based on data of 6000-plus fluorescent dyes (including 4000-plus BODIPYs) and the deep neural network architecture. The high prediction accuracy (five-fold cross-validation room mean squared error (RMSE) of 18.4 nm) was obtained using a consensus model, which was more accurate than individual models. This model provided the excellent accuracy (RMSE of 8 nm) for molecules previously synthesized in our laboratory as well as for prospective validation of three new BODIPYs. We found that solvent properties did not significantly influence the model accuracy since only few BODIPYs exhibited solvatochromism. The analysis of large prediction errors suggested that compounds able to have intermolecular interactions with solvent or salts were likely to be incorrectly predicted. The consensus model is freely available at https://ochem.eu/article/134921 and can help the other researchers to accelerate design of new dyes with desired properties.

show abstract

Section: Introductionmentioning

confidence: 62%

Section: Resultsmentioning

confidence: 99%