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 Video

Updated: May 17, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Deep learning for assay nuisance compound detection using a gated co-attention graph embedding model (CAGE-Fusion).

Siddhant Rath1, Saswati Panda1, Steven J Berthel1,2

  • 1Texas A&M University, College Station, TX, USA.

Journal of Cheminformatics
|May 15, 2026
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

In vitro cleavage requirements and specificities of mycobacterial RNase E.

Biochemical and biophysical research communications·2026
Same author

Building and managing a complex drug discovery consortium: insights from the tuberculosis drug accelerator.

Drug discovery today·2026
Same author

Integrating chemical, genetic, and feasibility assessments for anti-tubercular target validation.

EMBO molecular medicine·2026
Same author

Multiscale Molecular Modeling to Reveal Interactions between the Atomic Force Microscopy Tip and Lipid Bilayer Stacks.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Intranasal PIV5-vectored SARS-COV-2 KP.2 vaccine protects against homologous and heterologous challenge in mice and hamsters.

Vaccine·2026
Same author

Mycobacterium tuberculosis MutT4/RppH is an RNA pyrophosphohydrolase that forms condensate-like bodies and impacts mRNA degradation.

Nucleic acids research·2026

We developed CAGE-Fusion, a novel deep learning model that integrates molecular graph and sequence data to accurately identify nuisance compounds in drug discovery. This approach improves prediction accuracy and reduces costly false positives.

Area of Science:

  • Computational chemistry
  • Drug discovery informatics
  • Machine learning in cheminformatics

Background:

  • Nuisance compounds in drug discovery cause false positives by interfering with assays through mechanisms like aggregation or reactivity.
  • Existing methods struggle to filter these compounds, leading to wasted resources.
  • Current deep learning models often process molecular graphs or SMILES sequences independently.

Purpose of the Study:

  • To introduce CAGE-Fusion, a multimodal deep learning framework for improved nuisance compound detection.
  • To leverage co-attention mechanisms for enhanced molecular representation learning.
  • To provide a chemically coherent embedding by integrating graph and sequence data.

Main Methods:

  • Developed CAGE-Fusion, a multimodal framework using a gated co-attention mechanism.
Keywords:
Assay nuisanceCheminformaticsCo-attention mechanismDeep learningGraph Neural Networks (GNN)PAINS (Pan-Assay Interference Compounds)

Related Experiment Videos

Last Updated: May 17, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Enabled bidirectional information exchange between graph-based and sequence-based encoders.
  • Iteratively refined atom and token embeddings for cross-modal dependency capture.

    • Main Results:

    • CAGE-Fusion achieved competitive performance on MoleculeNet benchmarks.
    • Demonstrated high accuracy in nuisance compound classification with macro-averaged PR-AUC of 0.73 and ROC-AUC of 0.94.
    • The model effectively visualizes attention-weighted regions for classification decisions.

    Conclusions:

    • CAGE-Fusion offers a powerful approach for identifying assay nuisance compounds by integrating diverse molecular representations.
    • The framework enhances predictive performance and provides interpretable insights.
    • This method aids in reducing false positives and optimizing resource allocation in drug discovery.