Prediction of the protein structural class by specific peptide frequencies

Susan Costantini, Angelo M. Facchiano

Research output: Contribution to journalArticle


We evaluated the i-peptides occurrence frequency in the protein sequences belonging to the two datasets which include proteins with a sequence similarity lower than 25% and 40%, respectively. We worked out a new structural class prediction algorithm using the most frequent i-peptides (with i = 2, 3, 4), which characterize the four structural classes. Using the tri-peptides, much more able to gain structural information from sequences compared to the di-peptides, the best results were obtained. Compared to the other methods, similarly founded on peptide occurrence frequencies, our method achieves the best prediction accuracy. We compared it also with methods founded on more sophisticated computational approaches.

Original languageEnglish
Pages (from-to)226-229
Number of pages4
Issue number2
Publication statusPublished - Feb 2009


  • Low sequence similarity
  • Peptides occurrence frequency
  • Protein structural class
  • Structural class prediction

ASJC Scopus subject areas

  • Biochemistry

Fingerprint Dive into the research topics of 'Prediction of the protein structural class by specific peptide frequencies'. Together they form a unique fingerprint.

  • Cite this