Investigations of quantitative relationships between structure and color fastness of dyes are crucial in seeking novel dyes. For the first time, this work reported a classification model based on a quantitative structure–property relationship to predict color fastness to ironing of vat dyes. By performing binary classification analysis based on a support vector machine (SVM) and genetic algorithm, 56 vat dyes in the training set together with seven molecular descriptors were used to develop the classification model, which was validated with 59 vat dyes in the test set. The optimal SVM model (C = 208.465 and γ = 5.9692) possesses overall accuracy of 91.1% for the training set and 83.1% for the test set, which is more accurate than those from the binary logistic regression model (87.5% and 81.4%, respectively). Furthermore, the mechanism of molecular descriptors correlated with color fastness to ironing of vat dyes is discussed.
TimofeiSSchmidtWKuruncziL, et al.
A review of QSAR for dye affinity for cellulose fibres. Dyes Pigments2000;
47: 5–16.
2.
TeleginFShushinaIRanJH, et al.
Structure–property relationships for dyes of different nature. Adv Mater Res2013;
821–822: 488–492.
3.
KatritzkyARKuanarMSlavovS, et al.
Quantitative correlation of physical and chemical properties with chemical structure: utility for prediction. Chem Rev2010;
110: 5714–5789.
4.
KuruncziLFunar-TimofeiSBoraA, et al.
Application of the MTD-PLS method to heterocyclic dye–cellulose interactions. Int J Quantum Chem2007;
107: 2057–2065.
5.
PolanskiJGieleciakR, andWyszomirskiM.Comparative molecular surface analysis (CoMSA) for modeling dye−fiber affinities of the azo and anthraquinone dyes. J Chem Inf Comput Sci2003;
43: 1754–1762.
6.
PolanskiJGieleciakR, andWyszomirskiM.Mapping dye pharmacophores by the comparative molecular surface analysis (CoMSA): application to heterocyclic monoazo dyes. Dyes Pigments2004;
62: 61–76.
7.
ZhokhovaNIBaskinIIPalyulinVA, et al.
A study of the affinity of dyes for cellulose fiber within the framework of a fragment approach in QSPR. Russ J Appl Chem2005;
78: 1013–1017.
8.
XuXLuanFLiuH, et al.
Prediction of the maximum absorption wavelength of azobenzene dyes by QSPR tools. Spectrochim Acta A2011;
83: 353–361.
9.
FayetGJacqueminDWatheletV, et al.
Excited-state properties from ground-state DFT descriptors: a QSPR approach for dyes. J Mol Graph Model2010;
28: 465–471.
10.
AtabatiMZareiK, andMohsenniaM.Prediction of λmax of 1,4-naphthoquinone derivatives using ant colony optimization. Anal Chim Acta2010;
663: 7–10.
11.
XuJZhangHWangL, et al.
QSPR study of absorption maxima of organic dyes for dye-sensitized solar cells based on 3D descriptors. Spectrochim Acta A2010;
76: 239–247.
12.
XuJZhangHWangL, et al.
Artificial neural network-based QSPR study on absorption maxima of organic dyes for dye-sensitised solar cells. Mol Simulat2011;
37: 1–10.
13.
TabarakiRKhayamianT, andEnsafiA.Wavelet neural network modeling in QSPR for prediction of solubility of 25 anthraquinone dyes at different temperatures and pressures in supercritical carbon dioxide. J Mol Graph Model2006;
25: 46–54.
14.
TabarakiRKhayamianT, andEnsafiA.Solubility prediction of 21 azo dyes in supercritical carbon dioxide using wavelet neural network. Dyes Pigments2007;
73: 230–238.
15.
TarasovaABurdenFGasteigerJ, et al.
Robust modelling of solubility in supercritical carbon dioxide using Bayesian methods. J Mol Graph Model2010,
28: 593–597.
16.
PashaFMuddassarMChungHW, et al.
Hologram and 3D-quantitative structure toxicity relationship studies of azo dyes. J Mol Model2008;
14: 293–302.
17.
LiuHHanPWenY, et al.
Quantitative structure–electrochemistry relationship for variously-substituted 9, 10-anthraquinones using both an heuristic method and a radial basis function neural network. Dyes Pigments2010;
84: 148–152.
18.
VenkatramanVAlsbergBK.A quantitative structure–property relationship study of the photovoltaic performance of phenothiazine dyes. Dyes Pigments2015;
114: 69–77.
19.
LuanFXuX, andLiuH.Review of quantitative structure–activity/property relationship studies of dyes: recent advances and perspectives. Color Technol2013;
129: 173–186.
20.
De GiorgiMRCarpignanoR.Design of dyes of high technical properties for silk by a chemometric approach. Dyes Pigments1996;
30: 79–88.
21.
De GiorgiMRCarpignanoR, andCernianiA.Structure optimization in a series of thiadiazole disperse dyes using a chemometric approach. Dyes Pigments1998,
37: 187–196.
22.
XiaYZhangH.13C NMR chemical shift prediction of diverse chemical; compounds. SAR QSAR Environ Res2019;
30: 477–490
23.
ChenXDangLYangH, et al.
Machine learning-based prediction of toxicity of organic compounds towards fathead minnow. RSC Adv2020;
10: 36174–36180.
24.
LiuYYuX, andChenJ.Quantitative structure–property relationship of distribution coefficients of organic compounds. SAR QSAR Environ Res2020;
31: 585–596.
25.
YangXXiao G, andHeY.World Dyes-2000. Shenyang: National Dyestuff Industry Information Center, 2001, pp.1–134. (In Chinese.)
26.
KhanKBadernaDCappelliC, et al.
Ecotoxicological QSAR modeling of organic compounds against fish: application of fragment based descriptors in feature analysis. Aquat Toxicol2019;
212: 162–174.
27.
KhanKRoyK.Ecotoxicological QSAR modelling of organic chemicals against Pseudokirchneriella subcapitata using consensus predictions approach. SAR QSAR Environ Res2019,
30(9): 665–681.
28.
Talete srl. DRAGON (software for molecular descriptor calculation), version 6.0, 2012.
29.
YuXYi X, andYangH. Quantitative structure–activity relationship models of monomers reactivity. Chinese J Struct Chem2019;
38: 1867–1873.
30.
KhanKBenfenatiE, andRoyK.Consensus QSAR modeling of toxicity of pharmaceuticals to different aquatic organisms: ranking and prioritization of the DrugBank database compounds. Ecotox Environ Safe2019;
168: 287–297.
VoAHVleetTRVGuptaRR, et al.
An overview of machine learning and big data for drug toxicity evaluation. Chem Res Toxicol2020;
33: 20–37.
33.
MudnoorCVChakrabortyJN.Evaluation of dyeing characteristics of cotton with vat dyes using alkaline lipase and Fe (II) salt. Fiber Polym2020;
21: 1061–1070.
34.
KhatriMAhmedFShaikhI, et al.
Dyeing and characterization of regenerated cellulose nanofibers with vat dyes. Carbohyd Polym2017;
174: 443–449.
35.
SchüürmannGFunar-TimofeS.Multilinear regression and comparative molecular field analysis (CoMFA) of azo dye−fiber affinities. 2. Inclusion of solution-phase molecular orbital descriptors. J Chem Inf Comput Sci2003;
43: 1502–1512.
36.
CaoCZLinYB.Correlation between the glass transition temperature and repeating unit structure for high molecular weight polymers. J Chem Inf Comput Sci2003;
43: 643–650.
37.
GuillaumontDNakamuraS.Calculation of the absorption wavelength of dyes using time-dependent density-functional theory (TD-DFT). Dyes Pigments2000;
46: 85–92.
38.
TimofeiSFabianWMF.Comparative molecular field analysis of heterocyclic monoazo dye−fiber affinities. J Chem Inf Comput Sci1998;
38: 1218–1222.
39.
YuX.Prediction of chemical toxicity to Tetrahymena pyriformis with four descriptor models. Ecotox Environ Safe2020;
190: 110146.
40.
YuX.Quantitative structure–toxicity relationships of organic chemicals against Pseudokirchneriella subcapitata. Aquat Toxicol2020;
224: 105496.
41.
YuXXuLZhuY, et al.
Correlation between 13C NMR chemical shifts and complete sets of descriptors of natural coumarin derivatives. Chemometr Intell Lab Syst2019;
184: 167–174.
42.
ValaMVyñuchalJTomanP, et al.
Novel, soluble diphenyl-diketo-pyrrolopyrroles: experimental and theoretical study. Dyes Pigments2010;
84: 176–182.
43.
MahmoodURashidSAliSI, et al.
3D-QSPR method of computational technique applied on red reactive dyes by using CoMFA strategy. Int J Mol Sci2011;
12: 8862–8877.
44.
YuXWangYYangH, et al.
Prediction of the binding affinity of aptamers against the influenza virus. SAR QSAR Environ Res2019;
30: 51–62.
