Allerdictor is a fast and accurate sequence-based allergen prediction tool that models protein sequences as text documents and employs support vector machine in text classification for allergen prediction. Test results on multiple highly skewed datasets demonstrated that Allerdictor predicts allergens with high precision over high recall at very fast speed. For example, Allerdictor only took ∼6 minutes on a single core PC to scan a whole Swiss-Prot database of ∼540 thousand sequences and identified <1% of them as allergens.

Allerdictor is developed by the Fungal-Host Immunology Laboratory at Virginia Bioinformatics Institute. Both standalone and web server versions of Allerdictor are freely available for academic and non-profit uses. For commercial uses, please contact the authors.

Allerdictor paper is published in Bioinformatics:
  • Dang, Ha X., and Christopher B. Lawrence. "Allerdictor: fast allergen prediction using text classification techniques." Bioinformatics 30.8 (2014): 1120-1128.

Contacts: Ha Dang (hdvt.edu), Christopher Lawrence (lawrencevbi.vt.edu)