1
|
Martínez-Trespalacios JA, Polo-Herrera DE, Félix-Massa TY, Hernandez-Rivera SP, Hernandez-Fernandez J, Colpas-Castillo F, Castro-Suarez JR. QCL Infrared Spectroscopy Combined with Machine Learning as a Useful Tool for Classifying Acetaminophen Tablets by Brand. Molecules 2024; 29:3562. [PMID: 39124967 PMCID: PMC11313707 DOI: 10.3390/molecules29153562] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2024] [Revised: 07/18/2024] [Accepted: 07/23/2024] [Indexed: 08/12/2024] Open
Abstract
The development of new methods of identification of active pharmaceutical ingredients (API) is a subject of paramount importance for research centers, the pharmaceutical industry, and law enforcement agencies. Here, a system for identifying and classifying pharmaceutical tablets containing acetaminophen (AAP) by brand has been developed. In total, 15 tablets of 11 brands for a total of 165 samples were analyzed. Mid-infrared vibrational spectroscopy with multivariate analysis was employed. Quantum cascade lasers (QCLs) were used as mid-infrared sources. IR spectra in the spectral range 980-1600 cm-1 were recorded. Five different classification methods were used. First, a spectral search through correlation indices. Second, machine learning algorithms such as principal component analysis (PCA), support vector classification (SVC), decision tree classifier (DTC), and artificial neural network (ANN) were employed to classify tablets by brands. SNV and first derivative were used as preprocessing to improve the spectral information. Precision, recall, specificity, F1-score, and accuracy were used as criteria to evaluate the best SVC, DEE, and ANN classification models obtained. The IR spectra of the tablets show characteristic vibrational signals of AAP and other APIs present. Spectral classification by spectral search and PCA showed limitations in differentiating between brands, particularly for tablets containing AAP as the only API. Machine learning models, specifically SVC, achieved high accuracy in classifying AAP tablets according to their brand, even for brands containing only AAP.
Collapse
Affiliation(s)
- José A. Martínez-Trespalacios
- Mechanical Engineering Program, School of Engineering, Universidad Tecnológica de Bolívar, Parque Industrial y Tecnológico Carlos Vélez Pombo, Cartagena 130001, Colombia; (J.A.M.-T.); (J.H.-F.)
| | - Daniel E. Polo-Herrera
- Chemistry Program, Department of Natural and Exact Sciences, San Pablo Campus, University of Cartagena, Cartagena 130015, Colombia; (D.E.P.-H.); (F.C.-C.)
| | - Tamara Y. Félix-Massa
- Center for Chemical Sensors and Chemical Imaging and Surface Analysis Center, Department of Chemistry, University of Puerto Rico, Mayaguez, PR 00681, USA; (T.Y.F.-M.); (S.P.H.-R.)
| | - Samuel P. Hernandez-Rivera
- Center for Chemical Sensors and Chemical Imaging and Surface Analysis Center, Department of Chemistry, University of Puerto Rico, Mayaguez, PR 00681, USA; (T.Y.F.-M.); (S.P.H.-R.)
| | - Joaquín Hernandez-Fernandez
- Mechanical Engineering Program, School of Engineering, Universidad Tecnológica de Bolívar, Parque Industrial y Tecnológico Carlos Vélez Pombo, Cartagena 130001, Colombia; (J.A.M.-T.); (J.H.-F.)
- Chemistry Program, Department of Natural and Exact Sciences, San Pablo Campus, University of Cartagena, Cartagena 130015, Colombia; (D.E.P.-H.); (F.C.-C.)
- Department of Natural and Exact Science, Universidad de la Costa, Barranquilla 080002, Colombia
| | - Fredy Colpas-Castillo
- Chemistry Program, Department of Natural and Exact Sciences, San Pablo Campus, University of Cartagena, Cartagena 130015, Colombia; (D.E.P.-H.); (F.C.-C.)
| | - John R. Castro-Suarez
- Área Básicas Exactas, Universidad del Sinú, Seccional Cartagena, Cartagena 130015, Colombia
| |
Collapse
|
2
|
Wang L, Li X, Wang Y, Ren X, Liu X, Dong Y, Ma J, Song R, Wei J, Yu AX, Fan Q, Shan D, Yao J, She G. Rapid discrimination and screening of volatile markers for varietal recognition of Curcumae Radix using ATR-FTIR and HS-GC-MS combined with chemometrics. JOURNAL OF ETHNOPHARMACOLOGY 2021; 280:114422. [PMID: 34274441 DOI: 10.1016/j.jep.2021.114422] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/23/2021] [Revised: 07/10/2021] [Accepted: 07/13/2021] [Indexed: 06/13/2023]
Abstract
ETHNOPHARMACOLOGICAL RELEVANCE Curcumae Radix (Yujin) has a long medicinal use history in China, which is used to cure diseases like jaundice, cholelithiasis caused by dampness-heat of gallbladder and liver, and so on. It comes from the dried tuberous roots of C. kwangsiensis (Guiyujin), C. longa (Huangyujin), C. phaeocaulis (Lvyujin) and C. wenyujin (Wenyujin). Though there are differences in chemical compositions and pharmacological activities among the four species of Yujin, they have not been differentiated well in clinical application due to their similar morphological characterizations. AIM OF THE STUDY In this study, the four species of Yujin were rapidly and accurately discriminated. The potential volatile markers for varietal recognition were identified. MATERIALS AND METHODS Attenuated total reflection fourier transformed infrared (ATR-FTIR) spectroscopy combined with chemometrics was used to rapidly discriminate the four species of Yujin. Headspace-gas chromatography-mass spectrometry (HS-GC-MS) technology coupled with chemometrics was employed to characterize volatile profiling, differentiate species and select potential markers for varietal recognition of Yujin. RESULTS By applying PCA (principal components analysis) and HCA (hierarchical cluster analysis), HS-GC-MS realized complete differentiation of the four species of Yujin, while ATR-FTIR only recognized Guiyuijin. Back propagation neural network (BP-NN), KNN (K-nearest neighbor) and LDA (linear discriminant analysis) models based on spectral data achieved 100% discriminant accuracies. Support vector machines (SVM), KNN and PLS-DA (partial least square discriminant analysis) models based on volatile compounds also realized 100% discriminant accuracies. Additionally, the potential volatile markers for varietal recognition of Yujin were screened using PLS-DA, including 2 for Guiyujin, 6 for Lvyujin, 9 for Wenyujin and 13 for Huangyujin. CONCLUSIONS The present study developed reliable methods for the varietal discrimination and volatile compounds characterization of Yujin, which will provide references for its quality control and clinical efficacy.
Collapse
Affiliation(s)
- Le Wang
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China; School of Pharmacy, Minzu University of China, 27 Zhongguancun South Avenue, Beijing, China.
| | - Xiang Li
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Yu Wang
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Xueyang Ren
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Xiaoyun Liu
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Ying Dong
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Jiamu Ma
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Ruolan Song
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Jing Wei
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - AXiang Yu
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Qiqi Fan
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Dongjie Shan
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Jianling Yao
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| | - Gaimei She
- School of Chinese Materia Medica, Beijing University of Chinese Medicine, Fangshan District, Beijing, China; Beijing Key Laboratory for Quality Evaluation of Chinese Materia Medica, China.
| |
Collapse
|