AllerTOP--a server for in silico prediction of allergens.
Dimitrov I, Flower DR, Doytchinova I. · 2013
Read AllerTOP--a server for in silico prediction of allergens. by Dimitrov I, Flower DR, Doytchinova I. (2013) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc3633022.txt.
Description
Ivan Dimitrov, Darren Flower, and Irini Doytchinova built a web server that predicts allergens in BMC Bioinformatics in 2013. Older predictors worked two ways: hunting for sequence similarity to known allergens under food-safety guidelines, or matching short motifs tied to allergenicity. Both treat the property as written in a straight line of the sequence. AllerTOP instead describes each protein by the chemistry of its amino acids, compressed into forty-five numbers per protein by a covariance transform, and lets machine learning find the pattern.
Training sets held 684 food, 1,156 inhalant, and 555 toxin allergens, mirrored by non-allergens from the same species. Of five learning methods tried, the nearest-neighbor rule with three neighbors performed best. The free server also guesses the likely exposure route, food, inhaled, or toxin. Regulators screening new proteins gain a check that needs no look-alike allergen to exist.
Catalog record
| CREATOR | Dimitrov I, Flower DR, Doytchinova I. |
|---|---|
| YEAR | 2013 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |