Machines may help predict, eliminate allergens

April 29, 2014 by Tiffany L Trent
Machines may help predict, eliminate allergens
The mold allergen Alternaria grows indoors and causes reactions that sometimes lead to asthma. The image shows the region of the allergen responsible for triggering respiratory reactions in humans.

(Phys.org) —It's well known that allergies and asthma are on the rise around the globe. Food allergies alone rose 50 percent in children from 1997 to 2011, according to a recent study at the Centers for Disease Control and Prevention.

That's part of why Chris Lawrence and Ha Dang, researchers from the Virginia Bioinformatics Institute and the Department of Biological Sciences in the College of Science at Virginia Tech, created Allerdictor, a new computational approach and software that helps predict allergens. A scientific article describing this method was recently published in the journal Bioinformatics.

"As more biotechnology derived products like new protein-based therapeutics or genetically modified plants are developed, it becomes increasingly important for potential allergens to be identified and dealt with before these come to market," said Lawrence, the project director. "Predicting allergens more accurately will also aid in basic scientific research."

The Virginia Tech scientists report that Allerdictor predicts allergens with very high accuracy at fast speeds. Instead of using standard approaches for identifying allergens, Allerdictor uses machine-learning approaches—methods borrowed from artificial intelligence research—to learn and apply that learning to analyze large-scale submissions for the presence of allergens.

This approach makes it easier and faster to scan large sequences of data, eliminating allergens and making sure businesses and consumers are protected.

Ha Dang, the first author of the paper and the developer of Allerdictor, said, "This new approach for identifying potential is also applicable when analyzing the vast amount of genomic data that is being produced from various DNA sequencing projects worldwide. Most current methods of allergen prediction tend to be slow and inaccurate, yielding false positives that skew the data. Allerdictor literally takes minutes to analyze entire genomes."

Explore further: New test traces allergens quickly

More information: Ha X. Dang and Christopher B. Lawrence. "Allerdictor: fast allergen prediction using text classification techniques." Bioinformatics (2014) 30 (8): 1120-1128 first published online January 7, 2014 DOI: 10.1093/bioinformatics/btu004

Related Stories

New test traces allergens quickly

September 15, 2010

Institute of Food Safety and the chair group Physical Chemistry and Colloid Sciences, both of which are part of Wageningen University in the Netherlands, have together developed an allergen test. This test quickly, efficiently, ...

Recommended for you

Study reveals how nanochannels select potassium ions

August 25, 2015

(Phys.org)—One of the mysteries in biology is how cells can selectively diffuse potassium across a membrane. Biological systems rely on a delicate balance between these potassium and sodium ion concentrations in the surrounding ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.