Jove
Visualize
Contact Us

Related Experiment Videos

Predicting biotransformation potential from molecular structure.

Yu Borodina1, A Sadym, D Filimonov

  • 1Laboratory of Structure-Function Based Drug Design, Institute of Biomedical Chemistry of Russian Academy of Medical Sciences, 10 Pogodinskaya Str, Moscow 119121, Russia. borodina@ibmh.msk.su

Journal of Chemical Information and Computer Sciences
|September 23, 2003
PubMed
Summary

The PASS-BioTransfo program accurately predicts chemical biotransformations, identifying enzyme involvement. This computational tool achieves high accuracy in predicting diverse biotransformation classes for drug metabolism and chemical compound analysis.

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

Black Hole Spectroscopy and Tests of General Relativity with GW250114.

Physical review letters·2026
Same author

GW250114: Testing Hawking's Area Law and the Kerr Nature of Black Holes.

Physical review letters·2025
Same author

Evaluation of the effectiveness of personalised therapy for the patients with irritable bowel syndrome.

Beneficial microbes·2023
Same author

Search for Subsolar-Mass Binaries in the First Half of Advanced LIGO's and Advanced Virgo's Third Observing Run.

Physical review letters·2022
Same author

Constraints on Cosmic Strings Using Data from the Third Advanced LIGO-Virgo Observing Run.

Physical review letters·2021
Same author

mTORC1 - a potential player in the pathogenesis of hidradenitis suppurativa?

Journal of the European Academy of Dermatology and Venereology : JEADV·2021
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

Area of Science:

  • Computational chemistry
  • Pharmacology
  • Biochemistry

Background:

  • Biotransformation prediction is crucial for drug discovery and toxicology.
  • Existing methods may lack comprehensive coverage of diverse transformation types and enzyme specificities.

Purpose of the Study:

  • To introduce PASS-BioTransfo, a novel program for predicting chemical biotransformation classes.
  • To evaluate the accuracy and scope of PASS-BioTransfo using established databases.

Main Methods:

  • PASS-BioTransfo was trained and evaluated using biotransformation data from the Metabolite (MDL) and Metabolism (Accelrys) databases.
  • Leave-one-out (LOO) cross-validation was employed to estimate prediction accuracy.
  • Cross-prediction analyses were performed using different training and evaluation sets.

Related Experiment Videos

Main Results:

  • When trained on the Metabolite database, PASS-BioTransfo predicted 1927 biotransformation classes with an average accuracy of 88% (LOO CV).
  • Training on the Metabolism database yielded 178 predicted biotransformation classes with an average accuracy of 85% (LOO CV).
  • Cross-prediction results demonstrated the model's robustness and generalizability across different datasets.

Conclusions:

  • PASS-BioTransfo is an effective tool for predicting a wide range of chemical biotransformations.
  • The program demonstrates high accuracy and potential for application in drug metabolism studies and chemical safety assessments.