Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Protein Networks

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,...

You might also read

Related Articles

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

Sort by

Same author

SPRM: spatial process and relationship modeling for multiplexed images.

Bioinformatics advances·2026

Same author

CytoSpatio: Learning cell type spatial relationships using multirange, multitype point process models.

PLoS computational biology·2025

Same author

Big1 is a cell cycle regulator linking cell size to basal body number.

bioRxiv : the preprint server for biology·2025

Same author

CytoSpatio: Learning cell type spatial relationships using multirange, multitype point process models.

bioRxiv : the preprint server for biology·2024

Same author

Improved protein interaction models predict differences in complexes between human cell lines.

bioRxiv : the preprint server for biology·2024

Same author

Flexible and robust cell type annotation for highly multiplexed tissue images.

bioRxiv : the preprint server for biology·2024

Same journal

Non-canonical amino acid incorporation enables minimally disruptive labeling of stress granule and TDP-43 proteinopathy.

eLife·2026

Same journal

Analysis of dendritic input currents during place field dynamics.

eLife·2026

Same journal

TopoMetry systematically learns and evaluates the latent geometry of single-cell data.

eLife·2026

Same journal

Navigating the path: Advice to physician-scientists on choosing a clinical specialty.

eLife·2026

Same journal

Neural activity profiles reveal overlapping, intermingled subpopulations spanning area borders in mouse sensorimotor cortex.

eLife·2026

Same journal

The exquisite mechanics of a tsetse bite.

eLife·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 23, 2026

Characterization of Complex Systems Using the Design of Experiments Approach: Transient Protein Expression in Tobacco as a Case Study

Characterization of Complex Systems Using the Design of Experiments Approach: Transient Protein Expression in Tobacco as a Case Study

Published on: January 31, 2014

Active machine learning-driven experimentation to determine compound effects on protein patterns.

Armaghan W Naik^1,2, Joshua D Kangas^1,2, Devin P Sullivan^1,2

¹Computational Biology Department, Carnegie Mellon University, Pittsburgh, United States.

|February 4, 2016

Summary

This summary is machine-generated.

This study demonstrates an active machine learning algorithm that efficiently learns the effects of chemical compounds on protein localization. The approach significantly reduces the number of experiments needed, achieving accurate results with only 29% of possible tests.

Keywords:

active learning automation of research cell biology computational biology high content screening laboratory automation machine learning mouse protein subcellular location systems biology

More Related Videos

Pulldown Assay Coupled with Co-Expression in Bacteria Cells as a Time-Efficient Tool for Testing Challenging Protein-Protein Interactions

Pulldown Assay Coupled with Co-Expression in Bacteria Cells as a Time-Efficient Tool for Testing Challenging Protein-Protein Interactions

Published on: December 23, 2022

Rapid Optimization of a Light-Inducible System to Control Mammalian Gene Expression

Rapid Optimization of a Light-Inducible System to Control Mammalian Gene Expression

Published on: November 4, 2025

Related Experiment Videos

Last Updated: Jun 23, 2026

Characterization of Complex Systems Using the Design of Experiments Approach: Transient Protein Expression in Tobacco as a Case Study

Characterization of Complex Systems Using the Design of Experiments Approach: Transient Protein Expression in Tobacco as a Case Study

Published on: January 31, 2014

Pulldown Assay Coupled with Co-Expression in Bacteria Cells as a Time-Efficient Tool for Testing Challenging Protein-Protein Interactions

Pulldown Assay Coupled with Co-Expression in Bacteria Cells as a Time-Efficient Tool for Testing Challenging Protein-Protein Interactions

Published on: December 23, 2022

Rapid Optimization of a Light-Inducible System to Control Mammalian Gene Expression

Rapid Optimization of a Light-Inducible System to Control Mammalian Gene Expression

Published on: November 4, 2025

Area of Science:

Biotechnology
Computational Biology
Cell Biology

Background:

High throughput screening (HTS) is crucial for assessing biological target responses but is often inefficient for multiple targets or conditions.
Estimating compound effects on new targets typically requires extensive separate screens or relies on potentially inaccurate modeling assumptions.
A need exists for data-driven experimental strategies to build accurate models efficiently without performing all possible experiments.

Purpose of the Study:

To demonstrate the practical application of an active machine learning algorithm for biological experimentation.
To show that this algorithm can accurately model the effects of multiple conditions on multiple biological targets without prior knowledge.
To validate the use of robotics and automated microscopy in an active learning-driven experimental workflow.

Main Methods:

An active machine learning algorithm was employed to iteratively select experiments.
The algorithm controlled liquid handling robotics and automated microscopy for executing experiments.
The system learned models of compound effects on protein subcellular localization without prior assumptions about target similarities or phenotypes.

Main Results:

The active learning system accurately predicted the effects of 48 chemical compounds on the subcellular localization of 48 proteins.
The system achieved these accurate predictions by performing only 29% of all possible experiments.
This represents the first practical demonstration of active learning guiding biological experiments for unknown phenotypes.

Conclusions:

Active machine learning offers a powerful, data-driven approach to optimize biological screening and model building.
This methodology significantly reduces experimental effort while maintaining high accuracy in predicting compound effects.
The integration of active learning with automation provides a scalable and efficient platform for biological discovery.