Title :
Prediction of antimicrobial activity of peptides using relational machine learning
Author :
Szaboova, A. ; Kuzelka, O. ; Zelezny, F.
Author_Institution :
Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
Abstract :
We apply relational machine learning techniques to predict antimicrobial activity of peptides. We follow our successful strategy (Szabóová et al., MLSB 2010) to prediction of DNA-binding propensity of proteins from structural features. We exploit structure prediction methods to obtain peptides´ spatial structures, then we construct the structural relational features. We use these relational features as attributes in a regression model. We apply this methodology to antimicrobial activity prediction of peptides achieving better predictive accuracies than a state-of-the-art approach.
Keywords :
DNA; biology computing; learning (artificial intelligence); proteins; regression analysis; DNA-binding propensity; peptide antimicrobial activity prediction; peptide spatial structure; protein; regression model; relational machine learning techniques; structural relational features; structure prediction methods; Amino acids; Learning systems; Machine learning; Microorganisms; Microwave integrated circuits; Peptides; Proteins; Antimicrobial activity prediction; data mining; peptides; relational machine learning;
Conference_Titel :
Bioinformatics and Biomedicine Workshops (BIBMW), 2012 IEEE International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
978-1-4673-2746-6
Electronic_ISBN :
978-1-4673-2744-2
DOI :
10.1109/BIBMW.2012.6470203