Home A supervised machine-learning approach for the efficient development of a multi method (LC-MS) for a large number of drugs and subsets thereof: focus on oral antitumor agents
Article
Licensed
Unlicensed Requires Authentication

A supervised machine-learning approach for the efficient development of a multi method (LC-MS) for a large number of drugs and subsets thereof: focus on oral antitumor agents

  • Niklas Kehl ORCID logo , Arne Gessner ORCID logo , Renke Maas ORCID logo , Martin F. Fromm ORCID logo and R. Verena Taudte ORCID logo EMAIL logo
Published/Copyright: August 23, 2023
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Clinical Chemistry and Laboratory Medicine (CCLM)
From the journal Clinical Chemistry and Laboratory Medicine (CCLM) Volume 62 Issue 2

Abstract

Objectives

Accumulating evidence argues for a more widespread use of therapeutic drug monitoring (TDM) to support individualized medicine, especially for therapies where toxicity and efficacy are critical issues, such as in oncology. However, development of TDM assays struggles to keep pace with the rapid introduction of new drugs. Therefore, novel approaches for faster assay development are needed that also allow effortless inclusion of newly approved drugs as well as customization to smaller subsets if scientific or clinical situations require.

Methods

We applied and evaluated two machine-learning approaches i.e., a regression-based approach and an artificial neural network (ANN) to retention time (RT) prediction for efficient development of a liquid chromatography mass spectrometry (LC-MS) method quantifying 73 oral antitumor drugs (OADs) and five active metabolites. Individual steps included training, evaluation, comparison, and application of the superior approach to RT prediction, followed by stipulation of the optimal gradient.

Results

Both approaches showed excellent results for RT prediction (mean difference ± standard deviation: 2.08 % ± 9.44 % ANN; 1.78 % ± 1.93 % regression-based approach). Using the regression-based approach, the optimum gradient (4.91 % MeOH/min) was predicted with a total run time of 17.92 min. The associated method was fully validated following FDA and EMA guidelines. Exemplary modification and application of the regression-based approach to a subset of 14 uro-oncological agents resulted in a considerably shortened run time of 9.29 min.

Conclusions

Using a regression-based approach, a multi drug LC-MS assay for RT prediction was efficiently developed, which can be easily expanded to newly approved OADs and customized to smaller subsets if required.

Keywords: artificial neural networks; liquid chromatography coupled to mass spectrometry; oral antitumor drugs; plasma concentration; regression analysis; supervised machine-learning
Corresponding author: Prof. Dr. rer. nat. R. Verena Taudte, Institute of Experimental and Clinical Pharmacology and Toxicology, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany; and Core Facility for Metabolomics, Department of Medicine, Philipps-Universität Marburg, 35043 Marburg, Germany, Phone: +49 6421/58 66953, E-mail:
R. Verena Taudte: Present address: Core Facility for Metabolomics, Department of Medicine, Philipps-Universität Marburg, 35043 Marburg, Germany.

  1. Research ethics: Not applicable.

  2. Informed consent: Not applicable.

  3. Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  4. Competing interests: Martin F. Fromm has received consultancy fees from Boehringer Ingelheim and lecture fees from Janssen-Cilag. He has received third-party funds for research projects at his institution by Boehringer Ingelheim and Heidelberg Pharma Research GmbH. M.F.F. and colleagues received an earmarked financial contribution for the first award of the MSD Germany Health Award 2021. Renke Maas has received lecture fees from GWT-TUD GmbH.

  5. Research funding: None declared.

  6. Data availability: All data generated or analyzed during this study are included in this published article. The raw data can be obtained on request from the corresponding author.

References

1. Mueller-Schoell, A, Groenland, SL, Scherf-Clavel, O, van Dyk, M, Huisinga, W, Michelet, R, et al.. Therapeutic drug monitoring of oral targeted antineoplastic drugs. Eur J Clin Pharmacol 2021;77:441–64. https://doi.org/10.1007/s00228-020-03014-8.Search in Google Scholar PubMed PubMed Central

2. Papamichael, K, Afif, W, Drobne, D, Dubinsky, MC, Ferrante, M, Irving, PM, et al.. Therapeutic drug monitoring of biologics in inflammatory bowel disease: unmet needs and future perspectives. Lancet Gastroenterol Hepatol 2022;7:171–85. https://doi.org/10.1016/s2468-1253(21)00223-5.Search in Google Scholar

3. Wicha, SG, Martson, AG, Nielsen, EI, Koch, BCP, Friberg, LE, Alffenaar, JW, et al.. International Society of Anti-Infective Pharmacology (ISAP), the PK/PD study group of the European Society of Clinical Microbiology, Infectious Diseases (EPASG). From therapeutic drug monitoring to model-informed precision dosing for antibiotics. Clin Pharmacol Ther 2021;109:928–41. https://doi.org/10.1002/cpt.2202.Search in Google Scholar PubMed

4. Verheijen, RB, Yu, H, Schellens, JHM, Beijnen, JH, Steeghs, N, Huitema, ADR. Practical recommendations for therapeutic drug monitoring of kinase inhibitors in oncology. Clin Pharmacol Ther 2017;102:765–76. https://doi.org/10.1002/cpt.787.Search in Google Scholar PubMed PubMed Central

5. Dürr, P, Schlichtig, K, Kelz, C, Deutsch, B, Maas, R, Eckart, MJ, et al.. The randomized AMBORA trial: impact of pharmacological/pharmaceutical care on medication safety and patient-reported outcomes during treatment with new oral anticancer agents. J Clin Oncol 2021;39:1983–94. https://doi.org/10.1200/jco.20.03088.Search in Google Scholar

6. Schlichtig, K, Cuba, L, Dürr, P, Bellut, L, Meidenbauer, N, Kunath, F, et al.. New oral antitumor drugs and medication safety in uro-oncology: implications for clinical practice based on a subgroup analysis of the AMBORA trial. J Clin Med 2022;11:4558. https://doi.org/10.3390/jcm11154558.Search in Google Scholar PubMed PubMed Central

7. Schlichtig, K, Dürr, P, Dörje, F, Fromm, MF. New oral anti-cancer drugs and medication safety. Dtsch Arztebl Int 2019;116:775–82. https://doi.org/10.3238/arztebl.2019.0775.Search in Google Scholar PubMed PubMed Central

8. Merienne, C, Rousset, M, Ducint, D, Castaing, N, Titier, K, Molimard, M, et al.. High throughput routine determination of 17 tyrosine kinase inhibitors by LC-MS/MS. J Pharm Biomed Anal 2018;150:112–20. https://doi.org/10.1016/j.jpba.2017.11.060.Search in Google Scholar PubMed

9. Aghai, F, Zimmermann, S, Kurlbaum, M, Jung, P, Pelzer, T, Klinker, H, et al.. Development and validation of a sensitive liquid chromatography tandem mass spectrometry assay for the simultaneous determination of ten kinase inhibitors in human serum and plasma. Anal Bioanal Chem 2021;413:599–612. https://doi.org/10.1007/s00216-020-03031-7.Search in Google Scholar PubMed PubMed Central

10. Janssen, JM, de Vries, N, Venekamp, N, Rosing, H, Huitema, ADR, Beijnen, JH. Development and validation of a liquid chromatography-tandem mass spectrometry assay for nine oral anticancer drugs in human plasma. J Pharm Biomed Anal 2019;174:561–6. https://doi.org/10.1016/j.jpba.2019.06.034.Search in Google Scholar PubMed

11. Andriamanana, I, Gana, I, Duretz, B, Hulin, A. Simultaneous analysis of anticancer agents bortezomib, imatinib, nilotinib, dasatinib, erlotinib, lapatinib, sorafenib, sunitinib and vandetanib in human plasma using LC/MS/MS. J Chromatogr B: Anal Technol Biomed Life Sci 2013;926:83–91. https://doi.org/10.1016/j.jchromb.2013.01.037.Search in Google Scholar PubMed

12. Rousset, M, Titier, K, Bouchet, S, Dutriaux, C, Pham-Ledard, A, Prey, S, et al.. An UPLC-MS/MS method for the quantification of BRAF inhibitors (vemurafenib, dabrafenib) and MEK inhibitors (cobimetinib, trametinib, binimetinib) in human plasma. Application to treated melanoma patients. Clin Chim Acta 2017;470:8–13. https://doi.org/10.1016/j.cca.2017.04.009.Search in Google Scholar PubMed

13. Guo, ZX, Wu, YE, Shi, HY, van den Anker, J, Liang, P, Zheng, Y, et al.. A liquid chromatography-tandem mass spectrometry method for simultaneous quantification of thirty-nine tyrosine kinase inhibitors in human plasma. J Pharm Biomed Anal 2023;224:115159. https://doi.org/10.1016/j.jpba.2022.115159.Search in Google Scholar PubMed

14. Kehl, N, Schlichtig, K, Dürr, P, Bellut, L, Dörje, F, Fietkau, R, et al.. An easily expandable multi-drug LC-MS assay for the simultaneous quantification of 57 oral antitumor drugs in human plasma. Cancers 2021;13:6329. https://doi.org/10.3390/cancers13246329.Search in Google Scholar PubMed PubMed Central

15. Taudte, RV, Roux, C, Bishop, D, Blanes, L, Doble, P, Beavis, A. Development of a UHPLC method for the detection of organic gunshot residues using artificial neural networks. Anal Methods 2015;7:7447–54. https://doi.org/10.1039/c5ay00306g.Search in Google Scholar

16. Enmark, M, Haggstrom, J, Samuelsson, J, Fornstedt, T. Building machine-learning-based models for retention time and resolution predictions in ion pair chromatography of oligonucleotides. J Chromatogr A 2022;1671:462999. https://doi.org/10.1016/j.chroma.2022.462999.Search in Google Scholar PubMed

17. Fedorova, ES, Matyushin, DD, Plyushchenko, IV, Stavrianidi, AN, Buryak, AK. Deep learning for retention time prediction in reversed-phase liquid chromatography. J Chromatogr A 2022;1664:462792. https://doi.org/10.1016/j.chroma.2021.462792.Search in Google Scholar PubMed

18. de Cripan, SM, Cereto-Massague, A, Herrero, P, Barcaru, A, Canela, N, Domingo-Almenara, X. Machine learning-based retention time prediction of trimethylsilyl derivatives of metabolites. Biomedicines 2022;10:879. https://doi.org/10.3390/biomedicines10040879.Search in Google Scholar PubMed PubMed Central

19. Domingo-Almenara, X, Guijas, C, Billings, E, Montenegro-Burke, JR, Uritboonthai, W, Aisporna, AE, et al.. The METLIN small molecule dataset for machine learning-based retention time prediction. Nat Commun 2019;10:5811. https://doi.org/10.1038/s41467-019-13680-7.Search in Google Scholar PubMed PubMed Central

20. Dolan, JW. Temperature selectivity in reversed-phase high performance liquid chromatography. J Chromatogr A 2002;965:195–205. https://doi.org/10.1016/s0021-9673(01)01321-8.Search in Google Scholar PubMed

21. Zhu, PL, Dolan, JW, Snyder, LR. Combined use of temperature and solvent strength in reversed-phase gradient elution II. Comparing selectivity for different samples and systems. J Chromatogr A 1996;756:41–50. https://doi.org/10.1016/s0021-9673(96)00722-4.Search in Google Scholar

22. Sildir, H, Sarrafi, S, Aydin, E. Optimal artificial neural network architecture design for modeling an industrial ethylene oxide plant. Comput Chem Eng 2022;163:107850. https://doi.org/10.1016/j.compchemeng.2022.107850.Search in Google Scholar

23. European Medicine Ageny. ICH guideline M10 on bioanalytical method validation and study sample analysis; 2022. Available from: https://www.ema.europa.eu/en/documents/scientific-guideline/ich-guideline-m10-bioanalytical-method-validation-step-5_en.pdf [Accessed Jan 10, 2023].Search in Google Scholar

24. U.S. Food and Drug Administration (FDA). Bioanalytical method validation guidance for industry; 2018. Available from: https://www.fda.gov/files/drugs/published/Bioanalytical-Method-Validation-Guidance-for-Industry.pdf [Accessed Jan 10, 2023].Search in Google Scholar

25. Ross, DH, Cho, JH, Zhang, R, Hines, KM, Xu, L. LiPydomics: a python package for comprehensive prediction of lipid collision cross sections and retention times and analysis of ion mobility-mass spectrometry-based lipidomics data. Anal Chem 2020;92:14967–75. https://doi.org/10.1021/acs.analchem.0c02560.Search in Google Scholar PubMed PubMed Central

26. Kosters, M, Leufken, J, Leidel, SA. SMITER-a python library for the simulation of LC-MS/MS experiments. Genes 2021;12:396. https://doi.org/10.3390/genes12030396.Search in Google Scholar PubMed PubMed Central

27. Pasin, D, Mollerup, CB, Rasmussen, BS, Linnet, K, Dalsgaard, PW. Development of a single retention time prediction model integrating multiple liquid chromatography systems: application to new psychoactive substances. Anal Chim Acta 2021;1184:339035. https://doi.org/10.1016/j.aca.2021.339035.Search in Google Scholar PubMed

28. Bonini, P, Kind, T, Tsugawa, H, Barupal, DK, Fiehn, O. Retip: retention time prediction for compound annotation in untargeted metabolomics. Anal Chem 2020;92:7515–22. https://doi.org/10.1021/acs.analchem.9b05765.Search in Google Scholar PubMed PubMed Central

Supplementary Material

This article contains supplementary material (https://doi.org/10.1515/cclm-2023-0468).

Received: 2023-05-09
Accepted: 2023-07-31
Published Online: 2023-08-23
Published in Print: 2024-01-26

© 2023 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Editorial
  3. Rapid rule-in and rule-out protocols of acute myocardial infarction using hs-cTnI and hs-cTnT methods
  4. Reviews
  5. A guide to conducting systematic reviews of clinical laboratory tests
  6. Improving diagnosis and treatment of hypomagnesemia
  7. Opininon Paper
  8. Documenting and validating metrological traceability of serum alanine aminotransferase measurements: a priority for medical laboratory community for providing high quality service in hepatology
  9. EFLM Paper
  10. Assessing the status of European laboratories in evaluating biomarkers for chronic kidney diseases (CKD) and recommendations for improvement: insights from the 2022 EFLM Task Group on CKD survey
  11. General Clinical Chemistry and Laboratory Medicine
  12. Bland and Altman agreement method: to plot differences against means or differences against standard? An endless tale?
  13. Assessment of three equations to calculate plasma LDL cholesterol concentration in fasting and non-fasting hypertriglyceridemic patients
  14. Validation of metrological traceability of the new generation of Abbott Alinity alkaline phosphatase assay
  15. Quality assurance programs for vitamin A and E in serum: are we doing enough to assess laboratory performance?
  16. A supervised machine-learning approach for the efficient development of a multi method (LC-MS) for a large number of drugs and subsets thereof: focus on oral antitumor agents
  17. Performance evaluation of alternate ESR measurement method using BC-780 automated hematology analyzer: a comparison study with the Westergren reference method
  18. Total error in lymphocyte subpopulations by flow cytometry-based in state of the art using Spanish EQAS data
  19. Development and multi-center validation of a fully automated digital immunoassay for neurofilament light chain: toward a clinical blood test for neuronal injury
  20. CSF and plasma Aβ42/40 across Alzheimer’s disease continuum: comparison of two ultrasensitive Simoa® assays targeting distinct amyloid regions
  21. Improving regional medical laboratory center report quality through a report recall management system
  22. Cardiovascular Diseases
  23. Evaluation of the analytical and clinical performance of a new high-sensitivity cardiac troponin I assay: hs-cTnI (CLIA) assay
  24. Hemodialysis and biomarkers of myocardial infarction – a cohort study
  25. Letters to the Editor
  26. Chatbot GPT can be grossly inaccurate
  27. Blood collection in heparin vs. EDTA results in an inflammasome-independent increase in monocyte distribution width at 4 h
  28. Week-to-week within-subject and between-subject biological variation of copeptin
  29. The effect of unintended shortage in technical resources on the quality of endpoint clinical laboratory diagnosis
  30. Epigenetic signatures of cfDNA enable a topological assignment of tissue damage
  31. Six Sigma driven QC in antibody testing for infectious diseases
  32. Extensive analytical evaluation of the performances of the new DiaSys PCT assay and comparison with Elecsys B·R·A·H·M·S PCT test on Roche Cobas and B·R·A·H·M·S PCT-sensitive Kryptor
  33. Comment to: Extensive analytical evaluation of the performances of the new DiaSys PCT assay and comparison with Elecsys B·R·A·H·M·S PCT test on Roche Cobas and B·R·A·H·M·S PCT-sensitive Kryptor
  34. Evaluation of serum cortisol measurement by Ortho Vitro after stimulation by ACTH or insulin hypoglycaemia
  35. Diagnostic and prognostic value of quantitative detection of antimitochondrial antibodies subtype M2 using chemiluminescence immunoassay in primary biliary cholangitis
  36. Blood plasma biomarkers for Alzheimer’s disease: Aβ1–42/1–40 vs. AβX–42/X–40
https://doi.org/10.1515/cclm-2023-0468
Keywords for this article
artificial neural networks; liquid chromatography coupled to mass spectrometry; oral antitumor drugs; plasma concentration; regression analysis; supervised machine-learning

Articles in the same Issue

  1. Frontmatter
  2. Editorial
  3. Rapid rule-in and rule-out protocols of acute myocardial infarction using hs-cTnI and hs-cTnT methods
  4. Reviews
  5. A guide to conducting systematic reviews of clinical laboratory tests
  6. Improving diagnosis and treatment of hypomagnesemia
  7. Opininon Paper
  8. Documenting and validating metrological traceability of serum alanine aminotransferase measurements: a priority for medical laboratory community for providing high quality service in hepatology
  9. EFLM Paper
  10. Assessing the status of European laboratories in evaluating biomarkers for chronic kidney diseases (CKD) and recommendations for improvement: insights from the 2022 EFLM Task Group on CKD survey
  11. General Clinical Chemistry and Laboratory Medicine
  12. Bland and Altman agreement method: to plot differences against means or differences against standard? An endless tale?
  13. Assessment of three equations to calculate plasma LDL cholesterol concentration in fasting and non-fasting hypertriglyceridemic patients
  14. Validation of metrological traceability of the new generation of Abbott Alinity alkaline phosphatase assay
  15. Quality assurance programs for vitamin A and E in serum: are we doing enough to assess laboratory performance?
  16. A supervised machine-learning approach for the efficient development of a multi method (LC-MS) for a large number of drugs and subsets thereof: focus on oral antitumor agents
  17. Performance evaluation of alternate ESR measurement method using BC-780 automated hematology analyzer: a comparison study with the Westergren reference method
  18. Total error in lymphocyte subpopulations by flow cytometry-based in state of the art using Spanish EQAS data
  19. Development and multi-center validation of a fully automated digital immunoassay for neurofilament light chain: toward a clinical blood test for neuronal injury
  20. CSF and plasma Aβ42/40 across Alzheimer’s disease continuum: comparison of two ultrasensitive Simoa® assays targeting distinct amyloid regions
  21. Improving regional medical laboratory center report quality through a report recall management system
  22. Cardiovascular Diseases
  23. Evaluation of the analytical and clinical performance of a new high-sensitivity cardiac troponin I assay: hs-cTnI (CLIA) assay
  24. Hemodialysis and biomarkers of myocardial infarction – a cohort study
  25. Letters to the Editor
  26. Chatbot GPT can be grossly inaccurate
  27. Blood collection in heparin vs. EDTA results in an inflammasome-independent increase in monocyte distribution width at 4 h
  28. Week-to-week within-subject and between-subject biological variation of copeptin
  29. The effect of unintended shortage in technical resources on the quality of endpoint clinical laboratory diagnosis
  30. Epigenetic signatures of cfDNA enable a topological assignment of tissue damage
  31. Six Sigma driven QC in antibody testing for infectious diseases
  32. Extensive analytical evaluation of the performances of the new DiaSys PCT assay and comparison with Elecsys B·R·A·H·M·S PCT test on Roche Cobas and B·R·A·H·M·S PCT-sensitive Kryptor
  33. Comment to: Extensive analytical evaluation of the performances of the new DiaSys PCT assay and comparison with Elecsys B·R·A·H·M·S PCT test on Roche Cobas and B·R·A·H·M·S PCT-sensitive Kryptor
  34. Evaluation of serum cortisol measurement by Ortho Vitro after stimulation by ACTH or insulin hypoglycaemia
  35. Diagnostic and prognostic value of quantitative detection of antimitochondrial antibodies subtype M2 using chemiluminescence immunoassay in primary biliary cholangitis
  36. Blood plasma biomarkers for Alzheimer’s disease: Aβ1–42/1–40 vs. AβX–42/X–40
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 31.10.2025 from https://www.degruyterbrill.com/document/doi/10.1515/cclm-2023-0468/html
Scroll to top button