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

Cross-reactivity00:42

Cross-reactivity

30.9K
Overview
30.9K

You might also read

Related Articles

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

Sort by
Same author

Revised Adaptive Immune Receptor Data in the Immune Epitope Database.

bioRxiv : the preprint server for biology·2026
Same author

Cancer epitope prediction tools and analysis pipelines in CEDAR.

Nucleic acids research·2026
Same author

VO: The Vaccine Ontology.

Scientific data·2026
Same author

The Cell Ontology in the age of single-cell omics.

Scientific data·2026
Same author

NetMHCIIphosPan: A Machine Learning Tool for Predicting HLA Class II Antigen Presentation of Phosphorylated Peptides.

Journal of proteome research·2026
Same author

Empiric azithromycin alters the upper respiratory microbiome and resistome without anti-inflammatory benefit in COVID-19.

Nature microbiology·2026

Related Experiment Video

Updated: May 21, 2025

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes
07:59

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

14.9K

Standardizing free-text data exemplified by two fields from the Immune Epitope Database.

Sebastian Duesing1, Jason Bennett2, James A Overton3

  • 1Center for Vaccine Innovation, La Jolla Institute for Immunology, La Jolla, CA, 92037, USA. sduesing@lji.org.

Journal of Biomedical Semantics
|March 23, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a tool to normalize unstructured biomedical text data, improving its usability for automated analysis and data querying. The normalization process significantly reduces data variance, enhancing searchability and enabling integration with formal ontologies.

Keywords:
Data normalizationData standardizationFree-text dataImmune epitope databaseOntologyUnstructured data

More Related Videos

Synthetic Antigen Controls for Immunohistochemistry
09:30

Synthetic Antigen Controls for Immunohistochemistry

Published on: August 23, 2021

2.4K
Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing
08:51

Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing

Published on: March 15, 2019

12.3K

Related Experiment Videos

Last Updated: May 21, 2025

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes
07:59

A High Throughput MHC II Binding Assay for Quantitative Analysis of Peptide Epitopes

Published on: March 25, 2014

14.9K
Synthetic Antigen Controls for Immunohistochemistry
09:30

Synthetic Antigen Controls for Immunohistochemistry

Published on: August 23, 2021

2.4K
Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing
08:51

Identification of Mouse and Human Antibody Repertoires by Next-Generation Sequencing

Published on: March 15, 2019

12.3K

Area of Science:

  • Biomedical Informatics
  • Data Science
  • Natural Language Processing

Background:

  • Unstructured biomedical free text is underutilized due to extraction challenges.
  • Data normalization is key to using structured vocabularies and ontologies.
  • This study focuses on normalizing 'age' and 'data-location' fields from the Immune Epitope Database (IEDB).

Purpose of the Study:

  • To present an adaptable tool for normalizing free-text biomedical data.
  • To evaluate the tool's application on specific fields within the IEDB.
  • To demonstrate how normalization enhances data findability and usability.

Main Methods:

  • Developed a three-step normalization process: character, word, and phrase normalization.
  • Created generalizable rules applied using the developed tool.
  • Applied the tool to 4095 distinct 'age' values and 251,810 'data-location' values in the IEDB.

Main Results:

  • The normalization tool achieved high output validity across all stages for both datasets.
  • Character normalization yielded >99.97% validity; word normalization >98.06%; phrase normalization >83.81%.
  • Specifically, 'age' data reached 83.81% validity after phrase normalization, while 'data-location' reached 97.95%.

Conclusions:

  • A generalizable approach for normalizing free-text database fields was successfully developed.
  • The one-time effort of rule creation can be applied to ongoing data curation.
  • Standardization significantly reduces data variance, improving search functionality and ontology linkage.