A sensor array for the discrimination of polycyclic aromatic hydrocarbons using conjugated polymers and the inner filter effect

Abstract

Natural and anthropogenic activities result in the production of polycyclic aromatic hydrocarbons (PAHs), persistent pollutants that negatively impact the environment and human health. Rapid and reliable methods for the detection and discrimination of these compounds remains a technological challenge owing to their relatively featureless properties, structural similarities, and existence as complex mixtures. Here, we demonstrate that the inner filter effect (IFE), in combination with conjugated polymer (CP) array-based sensing, offers a straightforward approach for the quantitative and qualitative profiling of PAHs. The sensor array was constructed from six fluorescent fluorene-based copolymers, which incorporate side chains with peripheral 2-phenylbenzimidazole substituents that provide spectral overlap with PAHs and give rise to a pronounced IFE. Subtle structural differences in copolymer structure result in distinct spectral signatures, which provide a unique "chemical fingerprint" for each PAH. The discriminatory power of the array was evaluated using linear discriminant analysis (LDA) and principal component analysis (PCA) in order to discriminate between 16 PAH compounds identified as priority pollutants by the US Environmental Protection Agency (EPA). This array is the first multivariate system reliant on the modulation of the spectral signatures of CPs through the IFE for the detection and discrimination of closely related polynuclear aromatic species.

Fig. 1. (a) Synthesis of P1–P6. (b) Normalized excitation and emission spectra of P2 overlaid with normalized anthracene absorption ([anthracene] = 10 μM; [P2] = 15 mg L^–1), providing the basis for an IFE. (c) Fluorescence spectra of P2 (15 mg L^–1) upon titration with anthracene (0–9.4 mM) in N,N-dimethylformamide (DMF) (λ_exc = 374 nm).

Fig. 2. Normalized UV-vis absorption spectra of P2 (solid line, [P2] = 15 mg L^–1) compared to P6 (dashed line, [P6] = 15 mg L^–1) overlaid with the normalized absorption spectra of (a) two- and three-membered PAHs, (b) four- and five-membered PAHs, and (c) five- and six-membered PAHs in DMF ([PAHs] = 10 μM). Wavelength dependence of ε for (d) two- and three-membered PAHs, (e) four- and five-membered PAHs, and (f) five- and six-membered PAHs in DMF. Extinction coefficients at λ_max for each PAH are annotated. (g) The structures of all 16 PAHs identified by the EPA as priority pollutants.

Fig. 3. (a) Fluorescence titration profiles of P1–P4 upon the addition of aliquots of anthracene, acenaphthylene, and pyrene in DMF (λ_exc = 374 nm/λ_em = 418 nm). (b) Wavelength dependence of the molar extinction coefficient for anthracene, acenaphthylene, and pyrene. The colors indicate the PAH involved.

Fig. 4. (a) Two-dimensional plot of the LDA scores for the attempted differentiation of 16 PAHs with P1–P6. The plot was generated using 114 instrumental variables and captures 78.0% of the total information in the raw dataset. The inset shows a representative tight intra-cluster spacing of 12 replicate samples of indeno[1,2,3-cd]pyrene ([PAH] = 500 μM). (b) Zoomed-in LDA scores plot from (a) for 14 PAHs, displaying low inter-cluster spacing between those PAHs. (c) LDA loadings plot for the differentiation of 16 PAHs shown in (a), indicating the relative contributions of each instrumental variable to the first two LDA factors. Colored squares: contributions from fluorescence measurements. Colored circles: contributions from absorbance measurements.

Fig. 5. (a) The two-dimensional plot of the LDA scores for the differentiation of 16 PAHs with polymers P1–P6 ([PAH] = 500 μM; [P1–P6] = 15 mg L^–1). This plot was generated using the most important instrumental variables (79 in total) and captures 53.4% of the total information contained in the raw dataset. (b) LDA loadings plot for the differentiation of 16 PAHs shown in (a), indicating the relative contributions of each instrumental variable to the first two LDA factors. Colored squares: contributions from fluorescence measurements. Colored circles: contributions from absorbance measurements.

Fig. 6. (a) LDA scores plot for the attempted differentiation of 16 PAHs in the absence of polymers at [analyte] = 500 μM. (b) Two-dimensional loadings plot for factors F1 and F2 in the linear discriminant analysis of 16 PAHs without polymers. Inset: UV-vis absorption spectra of naphthalene, fluorene, acenaphthene, and phenanthrene.

Fig. 7. Emission decay of P2 (15 mg L^–1) before and after addition of anthracene (500 μM) in DMF. Inset: UV-vis absorption spectra of P2, anthracene, of a mixture of P2 and anthracene, compared to a simulated spectrum of this mixture calculated from the sum of the individual experimental spectra.