1
|
Mazraedoost S, Žuvela P, Ulenberg S, Bączek T, Liu JJ. Cross-column density functional theory-based quantitative structure-retention relationship model development powered by machine learning. Anal Bioanal Chem 2024:10.1007/s00216-024-05243-7. [PMID: 38507043 DOI: 10.1007/s00216-024-05243-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2023] [Revised: 03/03/2024] [Accepted: 03/06/2024] [Indexed: 03/22/2024]
Abstract
Quantitative structure-retention relationship (QSRR) modeling has emerged as an efficient alternative to predict analyte retention times using molecular descriptors. However, most reported QSRR models are column-specific, requiring separate models for each high-performance liquid chromatography (HPLC) system. This study evaluates the potential of machine learning (ML) algorithms and quantum mechanical (QM) descriptors to develop QSRR models that can predict retention times across three different reversed-phase HPLC columns under varying conditions. Four machine learning methods-partial least squares (PLS) regression, ridge regression (RR), random forest (RF), and gradient boosting (GB)-were compared on a dataset of 360 retention times for 15 aromatic analytes. Molecular descriptors were calculated using density functional theory (DFT). Column characteristics like particle size and pore size and experimental conditions like temperature and gradient time were additionally used as descriptors. Results showed that the GB-QSRR model demonstrated the best predictive performance, with Q2 of 0.989 and root mean square error of prediction (RMSEP) of 0.749 min on the test set. Feature analysis revealed that solvation energy (SE), HOMO-LUMO energy gap (∆E HOMO-LUMO), total dipole moment (Mtot), and global hardness (η) are among the most influential predictors for retention time prediction, indicating the significance of electrostatic interactions and hydrophobicity. Our findings underscore the efficiency of ensemble methods, GB and RF models employing non-linear learners, in capturing local variations in retention times across diverse experimental setups. This study emphasizes the potential of cross-column QSRR modeling and highlights the utility of ML models in optimizing chromatographic analysis.
Collapse
Affiliation(s)
- Sargol Mazraedoost
- Intelligent Systems Laboratory, Department of Chemical Engineering, Pukyong National University, Busan, 48513, Republic of Korea
| | - Petar Žuvela
- Intelligent Systems Laboratory, Department of Chemical Engineering, Pukyong National University, Busan, 48513, Republic of Korea
| | - Szymon Ulenberg
- Department of Pharmaceutical Chemistry, Medical University of Gdańsk, Gen. J. Hallera 107, 80-416, Gdańsk, Poland
| | - Tomasz Bączek
- Department of Pharmaceutical Chemistry, Medical University of Gdańsk, Gen. J. Hallera 107, 80-416, Gdańsk, Poland
| | - J Jay Liu
- Intelligent Systems Laboratory, Department of Chemical Engineering, Pukyong National University, Busan, 48513, Republic of Korea.
- Institute of Cleaner Production Technology, Pukyong National University, (48513) 45, Yongso-Ro, Nam-Gu, Busan, South Korea.
| |
Collapse
|
2
|
Sun S, Cui B, Kong F, Zhang Z, Qiao Y, Zhang S, Zhang X, Sun C. Construction and application of a QSRR approach for identifying flavonoids. J Pharm Biomed Anal 2024; 240:115929. [PMID: 38147703 DOI: 10.1016/j.jpba.2023.115929] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 11/24/2023] [Accepted: 12/16/2023] [Indexed: 12/28/2023]
Abstract
A quantitative structure retention relationship (QSRR) method was developed to identify flavonoid isomers auxiliary using an ultra high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS) method based on the linear relationships between the Ln(k') values of flavonoids and their hydrogen bonding energy (XAH) and dissolution energy (ES). Chromatographic separation was achieved with a Hypersil GOLD C18 (100 mm × 2.1 mm, 1.9 µm) column and Agilent SB-C18 (2.1 ×50 mm, 1.8 µm) column on a Dionex Ultimate 3000 RSLC chromatograph. Compounds were eluted isocratically using a mobile phase containing 0.1% formic acid/water solution and methanol at a ratio of 55:45 (v/v). Mass spectrometry was performed in the negative and positive ionization modes on a Thermo Fisher Q Exactive Orbitrap mass spectrometer equipped with an electrospray ionization interface. The established QSRR model was Ln(k') = 5.6163 + 0.0469ES - 0.0984XAH, with a determination coefficient (R2) of 0.9981, adjusted determination coefficient (adjR2) of 0.9976, and corrected root mean square error of 0.0682. The determination coefficient of the leave-one-out (LOO) cross-validation (Q2LOO) was 0.9976, and the cross-verification root mean square error was 0.0754. Simulated samples containing 7 flavonoids were used to validate the feasibility of the method. The classical method (UHPLC-MS/MS combined the CD software and the mzCloud, mzVault and Chemspider databases) was used to identify the seven flavonoids in the simulated samples. This classic identification strategy cannot provide accurate identification results, which provided multiple identification results for each compound in the simulated samples. On the basis of the results, the 7 flavonoids were accurately identified by the established QSRR model, and the reference standards were used to validate it. The relative error of retention time(RE(tR)) between the model calculation and experimental results was less than 10%. This method effectively complements and improves the classical methods, that UHPLC-MS/MS combined the CD software and the mass spectra databases were used to identify flavonoids identification.
Collapse
Affiliation(s)
- Shiyuan Sun
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China
| | - Biyue Cui
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China
| | - Fanyu Kong
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China
| | - Zitong Zhang
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China
| | - Youfu Qiao
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China
| | - Shuting Zhang
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China; Shenyang Pharmaceutical University, P.O. Box 117004, China
| | - Xinran Zhang
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China.
| | - Changhai Sun
- College of Pharmacy, Jiamusi University, P.O. Box 154007, China.
| |
Collapse
|
3
|
Kumari P, Van Laethem T, Duroux D, Fillet M, Hubert P, Sacré PY, Hubert C. A multi-target QSRR approach to model retention times of small molecules in RPLC. J Pharm Biomed Anal 2023; 236:115690. [PMID: 37688907 DOI: 10.1016/j.jpba.2023.115690] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2023] [Revised: 08/28/2023] [Accepted: 08/29/2023] [Indexed: 09/11/2023]
Abstract
Quantitative structure-retention relationship models (QSRR) have been utilized as an alternative to costly and time-consuming separation analyses and associated experiments for predicting retention time. However, achieving 100 % accuracy in retention prediction is unrealistic despite the existence of various tools and approaches. The limitations of vast data availability and time complexity hinder the use of most algorithms for retention prediction. Therefore, in this study, we examined and compared two approaches for modelling retention time using a dataset of small molecules with retention times obtained at multiple conditions, referred to as multi-targets (five pH levels: 2.7, 3.5, 5, 6.5, and 8 at gradient times of 20 min of mobile phase). The first approach involved developing separate models for predicting retention time at each condition (single-target approach), while the second approach aimed to learn a single model for predicting retention across all conditions simultaneously (multi-target approach). Our findings highlight the advantages of the multi-target approach over the single-target modelling approach. The multi-target models are more efficient in terms of size and learning speed compared to the single-target models. These retention prediction models offer two-fold benefits. Firstly, they enhance knowledge and understanding of retention times, identifying molecular descriptors that contribute to changes in retention behaviour under different pH conditions. Secondly, these approaches can be extended to address other multi-target property prediction problems, such as multi-quantitative structure Property(X) relationship studies (mt-QS(X)R).
Collapse
Affiliation(s)
- Priyanka Kumari
- Department of Pharmacy, Laboratory of Pharmaceutical Analytical Chemistry, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium; Laboratory for the Analysis of Medicines, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium.
| | - Thomas Van Laethem
- Department of Pharmacy, Laboratory of Pharmaceutical Analytical Chemistry, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium; Laboratory for the Analysis of Medicines, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium
| | - Diane Duroux
- ETH AI Center, OAT X11, Andreasstrasse 5, 8092 Zürich
| | - Marianne Fillet
- Laboratory for the Analysis of Medicines, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium
| | - Phillipe Hubert
- Department of Pharmacy, Laboratory of Pharmaceutical Analytical Chemistry, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium
| | - Pierre-Yves Sacré
- Department of Pharmacy, Laboratory of Pharmaceutical Analytical Chemistry, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium
| | - Cédric Hubert
- Department of Pharmacy, Laboratory of Pharmaceutical Analytical Chemistry, University of Liège (ULiege), CIRM, Quartier Hopital (B36 Tower 4), Avenue Hippocrate, 4000 Liège, Belgium.
| |
Collapse
|
4
|
Chen X, Yang Z, Xu Y, Liu Z, Liu Y, Dai Y, Chen S. Progress and prediction of multicomponent quantification in complex systems with practical LC-UV methods. J Pharm Anal 2023; 13:142-155. [PMID: 36908853 PMCID: PMC9999300 DOI: 10.1016/j.jpha.2022.11.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2022] [Revised: 11/24/2022] [Accepted: 11/28/2022] [Indexed: 12/12/2022] Open
Abstract
Complex systems exist widely, including medicines from natural products, functional foods, and biological samples. The biological activity of complex systems is often the result of the synergistic effect of multiple components. In the quality evaluation of complex samples, multicomponent quantitative analysis (MCQA) is usually needed. To overcome the difficulty in obtaining standard products, scholars have proposed achieving MCQA through the "single standard to determine multiple components (SSDMC)" approach. This method has been used in the determination of multicomponent content in natural source drugs and the analysis of impurities in chemical drugs and has been included in the Chinese Pharmacopoeia. Depending on a convenient (ultra) high-performance liquid chromatography method, how can the repeatability and robustness of the MCQA method be improved? How can the chromatography conditions be optimized to improve the number of quantitative components? How can computer software technology be introduced to improve the efficiency of multicomponent analysis (MCA)? These are the key problems that remain to be solved in practical MCQA. First, this review article summarizes the calculation methods of relative correction factors in the SSDMC approach in the past five years, as well as the method robustness and accuracy evaluation. Second, it also summarizes methods to improve peak capacity and quantitative accuracy in MCA, including column selection and two-dimensional chromatographic analysis technology. Finally, computer software technologies for predicting chromatographic conditions and analytical parameters are introduced, which provides an idea for intelligent method development in MCA. This paper aims to provide methodological ideas for the improvement of complex system analysis, especially MCQA.
Collapse
Affiliation(s)
- Xi Chen
- Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, 100700, China
| | - Zhao Yang
- Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, 100700, China
| | - Yang Xu
- Key Lab of Separation Science for Analytical Chemistry, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian, 116023, China
| | - Zhe Liu
- Key Lab of Separation Science for Analytical Chemistry, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian, 116023, China
| | - Yanfang Liu
- Key Lab of Separation Science for Analytical Chemistry, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian, 116023, China
| | - Yuntao Dai
- Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, 100700, China
- Corresponding author.
| | - Shilin Chen
- Institute of Chinese Materia Medica, China Academy of Chinese Medical Sciences, Beijing, 100700, China
- Institute of Herbgenomics, Chengdu University of Traditional Chinese Medicine, Chengdu, 611137, China
- Corresponding author. Institute of Herbgenomics, Chengdu University of Traditional Chinese Medicine, Chengdu, 611137, China.
| |
Collapse
|
5
|
Piekuś-Słomka N, Zapadka M, Kupcewicz B. Methoxy and methylthio-substituted trans-stilbene derivatives as CYP1B1 inhibitors – QSAR study with detailed interpretation of molecular descriptors. ARAB J CHEM 2022. [DOI: 10.1016/j.arabjc.2022.104204] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
|
6
|
Šegan S, Jevtić I, Tosti T, Penjišević J, Šukalović V, Kostić-Rajačić S, Milojković-Opsenica D. Determination of lipophilicity and ionization of fentanyl and its 3‑substituted analogs by reversed-phase thin-layer chromatography. J Chromatogr B Analyt Technol Biomed Life Sci 2022; 1211:123481. [DOI: 10.1016/j.jchromb.2022.123481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Revised: 09/12/2022] [Accepted: 09/20/2022] [Indexed: 11/30/2022]
|
7
|
Lee C, Hee Lim J, Young Cho A, Yoon W, Yun H, Won Kang J, Lee J. Molecular Structures of Flavonoid Co-Formers for Cocrystallization with Carbamazepine. J IND ENG CHEM 2022. [DOI: 10.1016/j.jiec.2022.11.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022]
|
8
|
Kovačević S, Karadžić Banjac M, Anojčić J, Podunavac-Kuzmanović S, Jevrić L, Nikolić A, Savić M, Kuzminac I. Chemometrics of anisotropic lipophilicity of anticancer androstane derivatives determined by reversed-phase ultra high performance liquid chromatography with polar aprotic and protic modifiers. J Chromatogr A 2022; 1673:463197. [DOI: 10.1016/j.chroma.2022.463197] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Revised: 06/01/2022] [Accepted: 06/01/2022] [Indexed: 10/18/2022]
|
9
|
Umair M, Sultana T, Xiaoyu Z, Senan AM, Jabbar S, Khan L, Abid M, Murtaza MA, Kuldeep D, Al‐Areqi NAS, Zhaoxin L. LC-ESI-QTOF/MS characterization of antimicrobial compounds with their action mode extracted from vine tea ( Ampelopsis grossedentata) leaves. Food Sci Nutr 2022; 10:422-435. [PMID: 35154679 PMCID: PMC8825723 DOI: 10.1002/fsn3.2679] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2021] [Revised: 10/10/2021] [Accepted: 10/20/2021] [Indexed: 12/23/2022] Open
Abstract
Vine tea (Ampelopsis grossedentata) is a tea plant cultivated south of the Chinese Yangtze River. It has anti-inflammatory properties and is used to normalize blood circulation and detoxification. The leaves of vine tea are the most abundant source of flavonoids, such as dihydromyricetin and myricetin. However, as the main bioactive flavonoid in vine tea, dihydromyricetin was the main focus of previous research. This study aimed to explore the antibacterial activities of vine tea against selected foodborne pathogens. The antimicrobial activity of vine tea extract was evaluated by the agar well diffusion method. Cell membrane integrity and bactericidal kinetics, along with physical damage to the cell membrane, were also observed. The extract was analyzed using a high-performance liquid chromatography-diode array detector (HPLC-DAD), and the results were confirmed using a modified version of a previously published method that combined liquid chromatography and electrospray-ionized quadrupole time-of-flight mass spectrometry (LC-ESI-QTOF/MS). Cell membrane integrity and bactericidal kinetics were determined by releasing intracellular material in suspension and monitoring it at 260 nm using an ultraviolet (UV) spectrophotometer. A scanning electron microscope (SEM) was used to detect morphological alterations and physical damage to the cell membrane. Six compounds were isolated successfully: (1) myricetin (C15H10O8), (2) myricetin 3-O-rhamnoside (C21H20O12), (3) 5,7,8,3,4-pentahydroxyisoflavone (C15H10O7), (4) dihydroquercetin (C15H12O7), (5) 6,8-dihydroxykaempferol (C15H10O8), and (6) ellagic acid glucoside (C20H16O13). Among these bioactive compounds, C15H10O7 was found to have vigorous antimicrobial activity against Bacillus cereus (AS11846) and Staphylococcus aureus (CMCCB26003). A dose-dependent bactericidal kinetics with a higher degree of absorbance at optical density 260 (OD260) was observed when the bacterial suspension was incubated with C15H10O7 for 8 h. Furthermore, a scanning electron microscope study revealed physical damage to the cell membrane. In addition, the action mode of C15H10O7 was on the cell wall of the target microorganism. Together, these results suggest that C15H10O7 has vigorous antimicrobial activity and can be used as a potent antimicrobial agent in the food processing industry.
Collapse
Affiliation(s)
- Muhammad Umair
- College of Food Science and TechnologyNanjing Agriculture UniversityNanjingChina
| | - Tayyaba Sultana
- College of Public AdministrationNanjing Agriculture UniversityNanjingChina
| | - Zhu Xiaoyu
- College of Food Science and TechnologyNanjing Agriculture UniversityNanjingChina
| | - Ahmed M. Senan
- College of Food Science and TechnologyNanjing Agriculture UniversityNanjingChina
| | - Saqib Jabbar
- Food Science Research Institute (FSRI)National Agricultural Research CentreIslamabadPakistan
| | - Labiba Khan
- Food Science Research Institute (FSRI)National Agricultural Research CentreIslamabadPakistan
| | - Muhammad Abid
- Institute of Food and Nutritional SciencesPir Mehr Ali Shah, Arid Agriculture University RawalpindiRawalpindiPakistan
| | - Mian Anjum Murtaza
- Institute of Food Science and NutritionUniversity of SargodhaSargodhaPakistan
| | - Dhama Kuldeep
- Division of PathologyICAR‐Indian Veterinary, Research InstituteIzatnagarIndia
| | - Niyazi A. S. Al‐Areqi
- Department of ChemistryFaculty of Applied ScienceTaiz UniversityTaizRepublic of Yemen
| | - Lu Zhaoxin
- College of Food Science and TechnologyNanjing Agriculture UniversityNanjingChina
| |
Collapse
|
10
|
Aćimović MG, Cvetković MT, Stanković Jeremić JM, Pezo LL, Varga AO, Čabarkapa IS, Kiprovski B. Biological activity and profiling of
Salvia sclarea
essential oil obtained by steam and hydrodistillation extraction methods via chemometrics tools. FLAVOUR FRAG J 2021. [DOI: 10.1002/ffj.3684] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Affiliation(s)
| | - Mirjana T. Cvetković
- Department of Chemistry Institute of Chemistry, Technology and Metallurgy University of Belgrade Belgrade Serbia
| | - Jovana M. Stanković Jeremić
- Department of Chemistry Institute of Chemistry, Technology and Metallurgy University of Belgrade Belgrade Serbia
| | - Lato L. Pezo
- Institute of General and Physical Chemistry University of Belgrade Belgrade Serbia
| | - Ana O. Varga
- Institute of Food Technology University of Novi Sad Novi Sad Serbia
| | | | | |
Collapse
|
11
|
Chen D, Huang X, Fan Y. Thermodynamics-Based Model Construction for the Accurate Prediction of Molecular Properties From Partition Coefficients. Front Chem 2021; 9:737579. [PMID: 34589468 PMCID: PMC8473701 DOI: 10.3389/fchem.2021.737579] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Accepted: 08/20/2021] [Indexed: 11/17/2022] Open
Abstract
Developing models for predicting molecular properties of organic compounds is imperative for drug development and environmental safety; however, development of such models that have high predictive power and are independent of the compounds used is challenging. To overcome the challenges, we used a thermodynamics-based theoretical derivation to construct models for accurately predicting molecular properties. The free energy change that determines a property equals the sum of the free energy changes (ΔGFs) caused by the factors affecting the property. By developing or selecting molecular descriptors that are directly proportional to ΔGFs, we built a general linear free energy relationship (LFER) for predicting the property with the molecular descriptors as predictive variables. The LFER can be used to construct models for predicting various specific properties from partition coefficients. Validations show that the models constructed according to the LFER have high predictive power and their performance is independent of the compounds used, including the models for the properties having little correlation with partition coefficients. The findings in this study are highly useful for applications in drug development and environmental safety.
Collapse
Affiliation(s)
- Deliang Chen
- Jiangxi Key Laboratory of Organo-Pharmaceutical Chemistry, Chemistry and Chemical Engineering College, Gannan Normal University, Ganzhou, China
| | - Xiaoqing Huang
- Jiangxi Key Laboratory of Organo-Pharmaceutical Chemistry, Chemistry and Chemical Engineering College, Gannan Normal University, Ganzhou, China
| | - Yulan Fan
- Jiangxi Key Laboratory of Organo-Pharmaceutical Chemistry, Chemistry and Chemical Engineering College, Gannan Normal University, Ganzhou, China
| |
Collapse
|
12
|
QSRR modelling aimed on the HPLC retention prediction of dimethylamino- and pyrrolidino-substitued esters of alkoxyphenylcarbamic acid. CHEMICAL PAPERS 2021. [DOI: 10.1007/s11696-020-01470-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
13
|
Kensert A, Collaerts G, Efthymiadis K, Desmet G, Cabooter D. Deep Q-learning for the selection of optimal isocratic scouting runs in liquid chromatography. J Chromatogr A 2021; 1638:461900. [PMID: 33485027 DOI: 10.1016/j.chroma.2021.461900] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2020] [Revised: 01/07/2021] [Accepted: 01/09/2021] [Indexed: 10/22/2022]
Abstract
An important challenge in chromatography is the development of adequate separation methods. Accurate retention models can significantly simplify and expedite the development of adequate separation methods for complex mixtures. The purpose of this study was to introduce reinforcement learning to chromatographic method development, by training a double deep Q-learning algorithm to select optimal isocratic scouting runs to generate accurate retention models. These scouting runs were fit to the Neue-Kuss retention model, which was then used to predict retention factors both under isocratic and gradient conditions. The quality of these predictions was compared to experimental data points, by computing a mean relative percentage error (MRPE) between the predicted and actual retention factors. By providing the reinforcement learning algorithm with a reward whenever the scouting runs led to accurate retention models and a penalty when the analysis time of a selected scouting run was too high (> 1h); it was hypothesized that the reinforcement learning algorithm should by time learn to select good scouting runs for compounds displaying a variety of characteristics. The reinforcement learning algorithm developed in this work was first trained on simulated data, and then evaluated on experimental data for 57 small molecules - each run at 10 different fractions of organic modifier (0.05 to 0.90) and four different linear gradients. The results showed that the MRPE of these retention models (3.77% for isocratic runs and 1.93% for gradient runs), mostly obtained via 3 isocratic scouting runs for each compound, were comparable in performance to retention models obtained by fitting the Neue-Kuss model to all (10) available isocratic datapoints (3.26% for isocratic runs and 4.97% for gradient runs) and retention models obtained via a "chromatographer's selection" of three scouting runs (3.86% for isocratic runs and 6.66% for gradient runs). It was therefore concluded that the reinforcement learning algorithm learned to select optimal scouting runs for retention modeling, by selecting 3 (out of 10) isocratic scouting runs per compound, that were informative enough to successfully capture the retention behavior of each compound.
Collapse
Affiliation(s)
- Alexander Kensert
- University of Leuven (KU Leuven), Department for Pharmaceutical and Pharmacological Sciences, Pharmaceutical Analysis, Herestraat 49, 3000 Leuven, Belgium
| | - Gilles Collaerts
- University of Leuven (KU Leuven), Department for Pharmaceutical and Pharmacological Sciences, Pharmaceutical Analysis, Herestraat 49, 3000 Leuven, Belgium
| | - Kyriakos Efthymiadis
- Vrije Universiteit Brussel, Department of Computer Science, Artificial Intelligence Lab, Pleinlaan 9, 1050 Brussel, Belgium
| | - Gert Desmet
- Vrije Universiteit Brussel, Department of Chemical Engineering, Pleinlaan 2, 1050 Brussel, Belgium
| | - Deirdre Cabooter
- University of Leuven (KU Leuven), Department for Pharmaceutical and Pharmacological Sciences, Pharmaceutical Analysis, Herestraat 49, 3000 Leuven, Belgium.
| |
Collapse
|
14
|
Zuo T, Zhang C, Li W, Wang H, Hu Y, Yang W, Jia L, Wang X, Gao X, Guo D. Offline two-dimensional liquid chromatography coupled with ion mobility-quadrupole time-of-flight mass spectrometry enabling four-dimensional separation and characterization of the multicomponents from white ginseng and red ginseng. J Pharm Anal 2020; 10:597-609. [PMID: 33425454 PMCID: PMC7775852 DOI: 10.1016/j.jpha.2019.11.001] [Citation(s) in RCA: 44] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2019] [Revised: 09/05/2019] [Accepted: 11/01/2019] [Indexed: 02/07/2023] Open
Abstract
Inherent complexity of plant metabolites necessitates the use of multi-dimensional information to accomplish comprehensive profiling and confirmative identification. A dimension-enhanced strategy, by offline two-dimensional liquid chromatography/ion mobility-quadrupole time-of-flight mass spectrometry (2D-LC/IM-QTOF-MS) enabling four-dimensional separations (2D-LC, IM, and MS), is proposed. In combination with in-house database-driven automated peak annotation, this strategy was utilized to characterize ginsenosides simultaneously from white ginseng (WG) and red ginseng (RG). An offline 2D-LC system configuring an Xbridge Amide column and an HSS T3 column showed orthogonality 0.76 in the resolution of ginsenosides. Ginsenoside analysis was performed by data-independent high-definition MSE (HDMSE) in the negative ESI mode on a Vion™ IMS-QTOF hybrid high-resolution mass spectrometer, which could better resolve ginsenosides than MSE and directly give the CCS information. An in-house ginsenoside database recording 504 known ginsenosides and 58 reference compounds, was established to assist the identification of ginsenosides. Streamlined workflows, by applying UNIFI™ to automatedly annotate the HDMSE data, were proposed. We could separate and characterize 323 ginsenosides (including 286 from WG and 306 from RG), and 125 thereof may have not been isolated from the Panax genus. The established 2D-LC/IM-QTOF-HDMSE approach could also act as a magnifier to probe differentiated components between WG and RG. Compared with conventional approaches, this dimension-enhanced strategy could better resolve coeluting herbal components and more efficiently, more reliably identify the multicomponents, which, we believe, offers more possibilities for the systematic exposure and confirmative identification of plant metabolites.
Collapse
Affiliation(s)
- Tiantian Zuo
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Chunxia Zhang
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Weiwei Li
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Hongda Wang
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Ying Hu
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Wenzhi Yang
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Li Jia
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Xiaoyan Wang
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Tianjin Key Laboratory of TCM Chemistry and Analysis, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Xiumei Gao
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
| | - Dean Guo
- Tianjin State Key Laboratory of Modern Chinese Medicine, Tianjin University of Traditional Chinese Medicine, 312 Anshanxi Road, Tianjin, 300193, China
- Shanghai Research Center for Modernization of Traditional Chinese Medicine, National Engineering Laboratory for TCM Standardization Technology, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, 501 Haike Road, Shanghai, 201203, China
| |
Collapse
|
15
|
Prediction of Retention Time of Morphine and Its Derivatives Without Using Computer-Encoded Complex Descriptors. Chromatographia 2020. [DOI: 10.1007/s10337-020-03975-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
16
|
Passarin PBS, Lourenço FR. Modeling an in silico platform to predict chromatographic profiles of UV filters using ChromSimulator. Microchem J 2020. [DOI: 10.1016/j.microc.2020.105002] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
|
17
|
Zhang X, Yang S, Srivastava G, Chen MY, Cheng X. Hybridization of cognitive computing for food services. Appl Soft Comput 2020. [DOI: 10.1016/j.asoc.2019.106051] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
18
|
Buszewski B, Žuvela P, Sagandykova G, Walczak-Skierska J, Pomastowski P, David J, Wong MW. Mechanistic Chromatographic Column Characterization for the Analysis of Flavonoids Using Quantitative Structure-Retention Relationships Based on Density Functional Theory. Int J Mol Sci 2020; 21:E2053. [PMID: 32192096 PMCID: PMC7139519 DOI: 10.3390/ijms21062053] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2020] [Revised: 03/12/2020] [Accepted: 03/13/2020] [Indexed: 11/16/2022] Open
Abstract
This work aimed to unravel the retention mechanisms of 30 structurally different flavonoids separated on three chromatographic columns: conventional Kinetex C18 (K-C18), Kinetex F5 (K-F5), and IAM.PC.DD2. Interactions between analytes and chromatographic phases governing the retention were analyzed and mechanistically interpreted via quantum chemical descriptors as compared to the typical 'black box' approach. Statistically significant consensus genetic algorithm-partial least squares (GA-PLS) quantitative structure retention relationship (QSRR) models were built and comprehensively validated. Results showed that for the K-C18 column, hydrophobicity and solvent effects were dominating, whereas electrostatic interactions were less pronounced. Similarly, for the K-F5 column, hydrophobicity, dispersion effects, and electrostatic interactions were found to be governing the retention of flavonoids. Conversely, besides hydrophobic forces and dispersion effects, electrostatic interactions were found to be dominating the IAM.PC.DD2 retention mechanism. As such, the developed approach has a great potential for gaining insights into biological activity upon analysis of interactions between analytes and stationary phases imitating molecular targets, giving rise to an exceptional alternative to existing methods lacking exhaustive interpretations.
Collapse
Affiliation(s)
- Bogusław Buszewski
- Department of Environmental Chemistry and Bioanalytics, Faculty of Chemistry, Gagarina 7, 87-100 Torun, Poland;
- Interdisciplinary Centre for Modern Technologies, Nicolaus Copernicus University, Wileńska 4, 87-100 Torun, Poland; (J.W.-S.); (P.P.)
| | - Petar Žuvela
- Department of Chemistry, National University of Singapore, 3 Science Drive 3, Singapore 117543, Singapore; (P.Ž.); (J.D.)
| | - Gulyaim Sagandykova
- Department of Environmental Chemistry and Bioanalytics, Faculty of Chemistry, Gagarina 7, 87-100 Torun, Poland;
- Interdisciplinary Centre for Modern Technologies, Nicolaus Copernicus University, Wileńska 4, 87-100 Torun, Poland; (J.W.-S.); (P.P.)
| | - Justyna Walczak-Skierska
- Interdisciplinary Centre for Modern Technologies, Nicolaus Copernicus University, Wileńska 4, 87-100 Torun, Poland; (J.W.-S.); (P.P.)
| | - Paweł Pomastowski
- Interdisciplinary Centre for Modern Technologies, Nicolaus Copernicus University, Wileńska 4, 87-100 Torun, Poland; (J.W.-S.); (P.P.)
| | - Jonathan David
- Department of Chemistry, National University of Singapore, 3 Science Drive 3, Singapore 117543, Singapore; (P.Ž.); (J.D.)
| | - Ming Wah Wong
- Department of Chemistry, National University of Singapore, 3 Science Drive 3, Singapore 117543, Singapore; (P.Ž.); (J.D.)
| |
Collapse
|
19
|
Mapari S, Camarda KV. Use of three-dimensional descriptors in molecular design for biologically active compounds. Curr Opin Chem Eng 2020. [DOI: 10.1016/j.coche.2019.11.011] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|