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

Protein Networks02:26

Protein Networks

3.9K
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,...
3.9K
Protein-protein Interfaces02:04

Protein-protein Interfaces

12.5K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
12.5K
Protein-Protein Interfaces02:04

Protein-Protein Interfaces

3.7K
3.7K
Ligand Binding Sites02:40

Ligand Binding Sites

12.7K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
12.7K
Protein Organization01:24

Protein Organization

6.3K
Proteins are polymers of amino acid residues. They are versatile and responsible for different cellular functions, including DNA replication, molecular transport, catalysis, and structural support. Proteins have a hierarchical structure comprising at least three levels of organization: primary, secondary, and tertiary structure. Some large proteins have a quaternary structure where individual protein subunits are linked together.
The primary structure of a protein is its amino acid sequence....
6.3K
Conserved Binding Sites01:49

Conserved Binding Sites

4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K

You might also read

Related Articles

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

Sort by
Same author

Computationally Efficient Bayesian Estimation of Graphical Networks for Omics Data.

Journal of proteome research·2026
Same author

Comparative Analysis of Report-back of Research Results Strategies for Personal Chemical Exposure Data.

Journal of exposure science & environmental epidemiology·2026
Same author

Beta-2 Transferrin May Not Be Specific for Presence of Cerebrospinal Fluid in Middle Ear Fluid.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026
Same author

Aggregation Methods for Quantifying PTM and Structural Changes in Bottom-Up Proteomics.

Journal of proteome research·2026
Same author

OmicsMLMentor: A Web Application for Guided Machine Learning Analysis of Omics Data.

Journal of proteome research·2026
Same author

Unsupervised Semantic Segmentation Models for Region of Interest Identification.

Journal of the American Society for Mass Spectrometry·2026

Related Experiment Video

Updated: Jun 7, 2025

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay PCA in Living Cells
08:38

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay PCA in Living Cells

Published on: March 3, 2015

13.3K

Protein-Protein Interaction Networks Derived from Classical and Machine Learning-Based Natural Language Processing

David J Degnan1, Clayton W Strauch2, Moses Y Obiri3

  • 1Biological Sciences Division, Pacific Northwest National Laboratory, 902 Battelle Blvd, Richland, Washington 99354, United States.

Journal of Proteome Research
|November 11, 2024
PubMed
Summary
This summary is machine-generated.

Comparing text mining tools for protein-protein interactions (PPIs) reveals trade-offs. Classical methods yield high true positives but overconnected networks, while machine learning and large language models offer different network structures and performance based on data availability.

Keywords:
BERTGPTLLMbiological text mininglarge language modelsmachine learningnatural language processingrelationship extraction

More Related Videos

JUMPn: A Streamlined Application for Protein Co-Expression Clustering and Network Analysis in Proteomics
07:28

JUMPn: A Streamlined Application for Protein Co-Expression Clustering and Network Analysis in Proteomics

Published on: October 19, 2021

3.1K
TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks
07:02

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

Published on: May 17, 2020

24.0K

Related Experiment Videos

Last Updated: Jun 7, 2025

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay PCA in Living Cells
08:38

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay PCA in Living Cells

Published on: March 3, 2015

13.3K
JUMPn: A Streamlined Application for Protein Co-Expression Clustering and Network Analysis in Proteomics
07:28

JUMPn: A Streamlined Application for Protein Co-Expression Clustering and Network Analysis in Proteomics

Published on: October 19, 2021

3.1K
TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks
07:02

TurboID-Based Proximity Labeling for In Planta Identification of Protein-Protein Interaction Networks

Published on: May 17, 2020

24.0K

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Natural Language Processing

Background:

  • Protein-protein interactions (PPIs) are crucial for understanding biological mechanisms, from immune responses to viral infections like SARS-CoV-2.
  • Existing PPI databases are often incomplete for newly studied or understudied species.
  • Text mining offers a valuable alternative for constructing PPI networks.

Purpose of the Study:

  • To compare the performance of classical text processing, machine learning (ML)-based NLP, and large language model (LLM)-based NLP tools for extracting PPI relationships.
  • To evaluate the characteristics of PPI networks generated by different NLP approaches.

Main Methods:

  • Evaluated open-source classical text processing tools.
  • Assessed ML-based NLP methods for relationship extraction.
  • Compared LLM-based NLP tools for PPI network construction.
  • Analyzed network properties such as true positive rates and network structure.

Main Results:

  • Classical methods produced high true positive rates but resulted in overconnected networks.
  • ML-based NLP methods yielded lower true positive rates but generated networks structurally similar to the target.
  • LLM-based NLP methods showed variable performance, generally falling between classical and ML approaches.
  • Model performance was influenced by the amount of text data provided.

Conclusions:

  • The choice of NLP approach for PPI network construction depends on study-specific needs and data availability.
  • Classical methods are suitable when high sensitivity is prioritized over network specificity.
  • ML and LLM approaches offer alternatives for more structurally representative networks, with performance varying based on data volume.