Standard

Predicting fluorescence to singlet oxygen generation quantum yield ratio for BODIPY dyes using QSPR and machine learning. / Чеботаев, Платон Платонович; Буглак, Андрей Андреевич; Sheehan, Aimee ; Филатов, Михаил А.

In: Physical Chemistry Chemical Physics, Vol. 26, No. 38, 18.09.2024, p. 25131-25142.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

BibTeX

@article{e0e6b133e7724a4d9ba725a46a678751,
title = "Predicting fluorescence to singlet oxygen generation quantum yield ratio for BODIPY dyes using QSPR and machine learning",
abstract = "Functional dyes that are capable of both bright fluorescence and efficient singlet oxygen generation are crucial for theranostic techniques, which integrate fluorescence imaging and photodynamic therapy (PDT). The development of new functional dyes for theranostics is often costly and time-consuming due to laborious synthesis and post-synthetic screening of large libraries of compounds. In this work, we describe machine learning methods suitable for simultaneous prediction of fluorescence and photosensitizing ability of heavy-atom-free boron dipyrromethene (BODIPY) compounds. We analysed the ratio between fluorescence quantum yield (ΦFl) and singlet oxygen quantum yield (ΦΔ) for over 70 BODIPY structures in polar (acetonitrile) and non-polar (toluene) solvents, which mimic hydrophilic and hydrophobic cell environments, respectively. QSPR models were developed based on more than 5000 calculated molecular descriptors, including quantum chemical and topological descriptors. We applied multiple linear regression (MLR), support vector regression (SVR), and random forest regression (RFR) methods for model building and optimization. The resulting models demonstrated robust statistical parameters (R2 = 0.73-0.91) for both polar and non-polar media. The relative contributions of the descriptors to the models were assessed, identifying Eig03_EA(dm), F01[C-N], and TDB06p as the most influential. These results demonstrate that QSPR machine learning methods are effective in predicting key photochemical parameters of BODIPY photosensitizers, thereby potentially streamlining the development of theranostic agents.",
keywords = "QSPR, BODIPY, quantum yield, fluorescence, singlet oxygen",
author = "Чеботаев, {Платон Платонович} and Буглак, {Андрей Андреевич} and Aimee Sheehan and Филатов, {Михаил А.}",
year = "2024",
month = sep,
day = "18",
doi = "10.1039/D4CP02471K",
language = "English",
volume = "26",
pages = "25131--25142",
journal = "Physical Chemistry Chemical Physics",
issn = "1463-9076",
publisher = "Royal Society of Chemistry",
number = "38",

}

RIS

TY - JOUR

T1 - Predicting fluorescence to singlet oxygen generation quantum yield ratio for BODIPY dyes using QSPR and machine learning

AU - Чеботаев, Платон Платонович

AU - Буглак, Андрей Андреевич

AU - Sheehan, Aimee

AU - Филатов, Михаил А.

PY - 2024/9/18

Y1 - 2024/9/18

N2 - Functional dyes that are capable of both bright fluorescence and efficient singlet oxygen generation are crucial for theranostic techniques, which integrate fluorescence imaging and photodynamic therapy (PDT). The development of new functional dyes for theranostics is often costly and time-consuming due to laborious synthesis and post-synthetic screening of large libraries of compounds. In this work, we describe machine learning methods suitable for simultaneous prediction of fluorescence and photosensitizing ability of heavy-atom-free boron dipyrromethene (BODIPY) compounds. We analysed the ratio between fluorescence quantum yield (ΦFl) and singlet oxygen quantum yield (ΦΔ) for over 70 BODIPY structures in polar (acetonitrile) and non-polar (toluene) solvents, which mimic hydrophilic and hydrophobic cell environments, respectively. QSPR models were developed based on more than 5000 calculated molecular descriptors, including quantum chemical and topological descriptors. We applied multiple linear regression (MLR), support vector regression (SVR), and random forest regression (RFR) methods for model building and optimization. The resulting models demonstrated robust statistical parameters (R2 = 0.73-0.91) for both polar and non-polar media. The relative contributions of the descriptors to the models were assessed, identifying Eig03_EA(dm), F01[C-N], and TDB06p as the most influential. These results demonstrate that QSPR machine learning methods are effective in predicting key photochemical parameters of BODIPY photosensitizers, thereby potentially streamlining the development of theranostic agents.

AB - Functional dyes that are capable of both bright fluorescence and efficient singlet oxygen generation are crucial for theranostic techniques, which integrate fluorescence imaging and photodynamic therapy (PDT). The development of new functional dyes for theranostics is often costly and time-consuming due to laborious synthesis and post-synthetic screening of large libraries of compounds. In this work, we describe machine learning methods suitable for simultaneous prediction of fluorescence and photosensitizing ability of heavy-atom-free boron dipyrromethene (BODIPY) compounds. We analysed the ratio between fluorescence quantum yield (ΦFl) and singlet oxygen quantum yield (ΦΔ) for over 70 BODIPY structures in polar (acetonitrile) and non-polar (toluene) solvents, which mimic hydrophilic and hydrophobic cell environments, respectively. QSPR models were developed based on more than 5000 calculated molecular descriptors, including quantum chemical and topological descriptors. We applied multiple linear regression (MLR), support vector regression (SVR), and random forest regression (RFR) methods for model building and optimization. The resulting models demonstrated robust statistical parameters (R2 = 0.73-0.91) for both polar and non-polar media. The relative contributions of the descriptors to the models were assessed, identifying Eig03_EA(dm), F01[C-N], and TDB06p as the most influential. These results demonstrate that QSPR machine learning methods are effective in predicting key photochemical parameters of BODIPY photosensitizers, thereby potentially streamlining the development of theranostic agents.

KW - QSPR

KW - BODIPY

KW - quantum yield

KW - fluorescence

KW - singlet oxygen

UR - https://www.mendeley.com/catalogue/b9809309-6a20-39d6-b5f6-a9c74e1cdc8f/

U2 - 10.1039/D4CP02471K

DO - 10.1039/D4CP02471K

M3 - Article

VL - 26

SP - 25131

EP - 25142

JO - Physical Chemistry Chemical Physics

JF - Physical Chemistry Chemical Physics

SN - 1463-9076

IS - 38

ER -

ID: 125311552