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 Videos

Statistical evaluation of local alignment features predicting allergenicity using supervised classification

D Soeria-Atmadja1, A Zorzet, M G Gustafsson

  • 1Division of Toxicology, National Food Administration, Uppsala University, Uppsala, Sweden.

International Archives of Allergy and Immunology
|January 24, 2004
PubMed
Summary
This summary is machine-generated.

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

Combination screening in vitro identifies synergistically acting KP372-1 and cytarabine against acute myeloid leukemia.

Biochemical pharmacology·2016
Same author

In vitro discovery of promising anti-cancer drug combinations using iterative maximisation of a therapeutic index.

Scientific reports·2015
Same author

A new lymphocyte alloantigen (Ly-10) controlled by a gene linked to the Lyt-1 locus.

Immunogenetics·2012
Same author

Digital gene expression profiling of primary acute lymphoblastic leukemia cells.

Leukemia·2011
Same author

Interrogating health-related public databases from a food toxicology perspective: computational analysis of scoring data.

Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association·2011
Same author

In vitro cellular responses to cytokines and erythropoietin.

Toxicology in vitro : an international journal published in association with BIBRA·2010
Same journal

Differences in Reported Anaphylaxis Associated With Common Nonsteroidal Anti-inflammatory Drugs: A Pharmacovigilance Study.

International archives of allergy and immunology·2026
Same journal

Association of Serum Galectin-3 Binding Protein with Acute Exacerbation, Inflammation, and Airway Remodeling in Pediatric Asthma.

International archives of allergy and immunology·2026
Same journal

Effectiveness of a Provincial Law to Improve Epinephrine Use for Anaphylaxis in Schools in Alberta, Canada: A Pre-Post Study.

International archives of allergy and immunology·2026
Same journal

Rab27 a regulates dendritic cell immune tolerogenic capacity.

International archives of allergy and immunology·2026
Same journal

Burden of Hereditary Angioedema in Adults: Impact of Disease and Patient Characteristics.

International archives of allergy and immunology·2026
Same journal

Predictors of Treatment Response to Omalizumab in Children with Chronic Spontaneous Urticaria: A Real World Study.

International archives of allergy and immunology·2026
See all related articles

This study enhances food allergenicity prediction by evaluating alignment-based features and machine learning classifiers. The linear Gaussian classifier with combined alignment scores showed the most promise for assessing protein allergenicity.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Immunology

Background:

  • Previous research identified alignment score and length as promising features for predicting food allergenicity using k-nearest neighbor (kNN) classification.
  • These features are derived from the best local alignment against a database of known allergen sequences.

Purpose of the Study:

  • To comprehensively evaluate alignment-based features for general allergenicity prediction.
  • To compare the performance of different supervised machine learning algorithms for this task.

Main Methods:

  • A curated database of 318 non-redundant allergens and 1,007 non-allergens was created.
  • Three classifiers were tested: kNN, Bayesian linear Gaussian, and Bayesian quadratic Gaussian.
  • FASTA3 was used for local alignment with varied parameters, and novel performance curves were employed.

Related Experiment Videos

Main Results:

  • The linear Gaussian classifier outperformed kNN and the quadratic Gaussian classifier.
  • The best classification performance was achieved using a feature vector combining alignment scores from multiple local alignment procedures with different substitution matrices.

Conclusions:

  • The developed models are valuable for integrated assessment schemes of potential protein allergenicity.
  • These findings provide a basis for comparison with alternative bioinformatics approaches.