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 Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
Multiple Regression01:25

Multiple Regression

Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
Protein Networks02:26

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

You might also read

Related Articles

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

Sort by
Same author

Nitrogen fixation rates increase with diazotroph richness in the global ocean.

Scientific reports·2026
Same author

Coral microbiomes as reservoirs of unknown genomic and biosynthetic diversity.

Nature·2026
Same author

Identification of a deep-branching lineage of algae using environmental plastid genomes.

Nature communications·2025
Same author

Global currents, microbial footprints.

Cell host & microbe·2025
Same author

sCIN: a contrastive learning framework for single-cell multi-omics data integration.

Briefings in bioinformatics·2025
Same author

Antagonism as a foraging strategy in microbial communities.

Science (New York, N.Y.)·2025

Related Experiment Video

Updated: Jul 14, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Reliable evaluation and learning in multi-input biological association prediction.

Sobhan Ahmadian1,2, Lucas Paoli2, Hesam Montazeri1

  • 1Department of Bioinformatics, Institute of Biochemistry and Biophysics, University of Tehran, Ghods 37, Tehran, 1417763135, Iran.

Briefings in Bioinformatics
|July 13, 2026
PubMed
Summary

This study introduces an entity-balanced framework to fairly evaluate computational biology models. It neutralizes shortcut learning, improving predictions for drug-target and virus-host interactions.

Keywords:
biological association predictiondegree ratio shortcut learningdrug synergy predictiondrug–target interaction predictionrobust model evaluationvirus–host interaction prediction

More Related Videos

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease
08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

Published on: September 20, 2024

Related Experiment Videos

Last Updated: Jul 14, 2026

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease
08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

Published on: September 20, 2024

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning in Biology

Background:

  • Multi-input association prediction is crucial for drug-target, protein-protein, and virus-host interactions.
  • Existing benchmarks overestimate model performance due to shortcut learning (degree ratio bias).
  • Current evaluation methods are often impractical or overly restrictive.

Purpose of the Study:

  • To develop a fair and robust evaluation framework for multi-input association prediction.
  • To introduce a model-agnostic training strategy to mitigate shortcut learning.
  • To enable more accurate and interpretable biological association predictions.

Main Methods:

  • Developed an entity-balanced evaluation framework to neutralize shortcut signals.
  • Balanced positive and negative associations at the entity level for fairer assessments.
  • Introduced UnbiasNet, a model-agnostic training strategy using diverse entity-balanced sub-training sets.

Main Results:

  • The framework enables fairer assessments reflecting genuine relational learning.
  • UnbiasNet effectively removes degree ratio bias, enhancing model robustness.
  • Applied to drug-target, drug synergy, and virus-host prediction, revealing shortcut reliance in existing methods.
  • Demonstrated that removing shortcuts directs models toward biologically meaningful features, improving interpretability.

Conclusions:

  • The entity-balanced framework provides a rigorous foundation for evaluating and developing computational biology models.
  • The UnbiasNet strategy enhances model robustness and interpretability by mitigating shortcut learning.
  • This approach leads to more reliable identification of meaningful biological associations.