Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Multivariate adaptive regression splines (MARS) in chromatographic quantitative structure-retention relationship

R Put1, Q S Xu, D L Massart

  • 1ChemoAC, Department of Pharmaceutical and Biomedical Analysis, Pharmaceutical Institute, Vrije Universiteit Brussel, Laarbeeklaan 103, B-1090 Brussels, Belgium.

Journal of Chromatography. A
|November 25, 2004
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Evaluation of data preprocessings for the comparison of GC-MS chemical profiles of seized cannabis samples.

Forensic science international·2020
Same author

Flavonoids from Boldoa purpurascens inhibit proinflammatory cytokines (TNF-α and IL-6) and the expression of COX-2.

Phytotherapy research : PTR·2018
Same author

Breakage and drying behaviour of granules in a continuous fluid bed dryer: Influence of process parameters and wet granule transfer.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2018
Same author

[The national anti-opium-smoking campaigns across the country in the Republican Period].

Zhonghua yi shi za zhi (Beijing, China : 1980)·2018
Same author

Integrated network analysis to identify the key genes, transcription factors, and microRNAs involved in hepatocellular carcinoma.

Neoplasma·2018
Same author

Response to "Prognostic value of pathologic grade for patients with oral squamous cell carcinoma: Methodological issues".

Oral diseases·2017

Multivariate adaptive regression splines (MARS) effectively predict drug retention factors using molecular descriptors. The optimal model captures hydrophobicity, size, complexity, shape, and polarizability for accurate quantitative structure-retention relationships.

Area of Science:

  • * Computational Chemistry
  • * Cheminformatics
  • * Analytical Chemistry

Background:

  • * Quantitative structure-retention relationships (QSRRs) are crucial for predicting chromatographic behavior.
  • * Multivariate adaptive regression splines (MARS) offer a flexible modeling approach for complex datasets.
  • * Understanding drug retention mechanisms aids in drug discovery and development.

Purpose of the Study:

  • * To develop and validate MARS models for predicting drug retention factors (log k(w)).
  • * To identify key molecular descriptors influencing drug retention on a PBD column.
  • * To explore alternative modeling strategies and feature selection techniques.

Main Methods:

  • * Application of Multivariate Adaptive Regression Splines (MARS) to build QSRR models.

Related Experiment Videos

  • * Use of 83 structurally diverse drugs and 266 molecular descriptors.
  • * Investigation of Classification and Regression Trees (CART) for feature selection.

    • Main Results:

    • * An optimal MARS model with 34 basis functions was developed, demonstrating acceptable predictive performance.
    • * Key descriptors related to hydrophobicity, molecular size, complexity, shape, and polarizability were identified.
    • * Alternative models, including those using log P or the top three descriptors, were explored.

    Conclusions:

    • * MARS is a suitable methodology for building predictive QSRR models.
    • * Molecular descriptors encompassing various properties are important for describing drug retention.
    • * Feature selection and model complexity influence predictive accuracy.