Jove
Visualize
Contact Us

Related Experiment Videos

Modified linear regression predicts drug-target interactions accurately.

Krisztian Buza1,2, Ladislav Peška3, Júlia Koller4

  • 1Faculty of Informatics, ELTE - Eötvös Loránd University, Budapest, Hungary.

Plos One
|April 7, 2020
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

Sex-Specific Role of NPVF Signalling in Homeostatic Control.

Biomolecules·2026
Same author

Electrophysiological indices of reward anticipation as ADHD risk and prognostic biomarkers.

European child & adolescent psychiatry·2024
Same author

Probing the biological consequences of a previously undescribed de novo mutation of ZMYND11 in a schizophrenia patient by CRISPR genome editing and induced pluripotent stem cell based in vitro disease-modeling.

Schizophrenia research·2024
Same author

Critical role of lateral habenula circuits in the control of stress-induced palatable food consumption.

Neuron·2023
Same author

NPFF signalling is critical for thermosensory and dietary regulation of thermogenesis.

Neuropeptides·2022
Same author

Central NPFF signalling is critical in the regulation of glucose homeostasis.

Molecular metabolism·2022
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

This study introduces Asymmetric Loss Models (ALM) for predicting drug-target interactions (DTI), outperforming existing methods. ALM offers a more chemically realistic approach to DTI prediction.

Area of Science:

  • Computational chemistry
  • Bioinformatics
  • Machine learning

Background:

  • Accurate drug-target interaction (DTI) prediction is crucial for drug discovery.
  • Current DTI prediction methods, including bipartite local models (BLM), have limitations.

Purpose of the Study:

  • To introduce a novel framework, Asymmetric Loss Models (ALM), for enhanced DTI prediction.
  • To improve the accuracy and chemical realism of DTI prediction models.

Main Methods:

  • Developed and applied Asymmetric Loss Models (ALM).
  • Integrated ALM with Bipartite Local Models (BLM) for DTI prediction.
  • Evaluated the approach on real-world DTI datasets.

Main Results:

  • The proposed ALM framework demonstrates superior performance compared to existing DTI prediction techniques.

Related Experiment Videos

  • ALM shows improved accuracy over state-of-the-art methods, including recent BLM versions.
  • The approach aligns better with underlying chemical principles than conventional regression.

    • Conclusions:

    • Asymmetric Loss Models (ALM) represent a significant advancement in drug-target interaction prediction.
    • The ALM-enhanced BLM approach offers a more accurate and chemically relevant method for DTI analysis.
    • This framework has the potential to accelerate drug discovery and development.