01420nas a2200265 4500008004100000020002200041022001400063245010700077210006900184260006800253300001200321490000900333520049500342100002000837700001700857700001900874700002100893700002600914700001800940700001400958700001900972700001900991700001601010856012801026 2009 eng d a978-3-642-11163-1 a0302-974300aIdentification of defensins employing recurrence quantification analysis and random forest classifiers0 aIdentification of defensins employing recurrence quantification aHEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANYbISI KolkatacDEC a152-1570 v59093 a
Defensins represent a class of antimicrobial peptides synthesized in the body acting against various microbes. In this paper we study defensins using a non-linear signal analysis method Recurrence Quantication Analysis (RQA). We used the descriptors calculated employing RQA for the classification of defensins with Random Forest Classifier. The RQA descriptors were able to capture patterns peculiar to defensins leading to an accuracy rate of 78.12% using 10-fold cross validation.
1 aKarnik, Shreyas1 aPrasad, Ajay1 aDiwevedi, Alok1 aSundararajan, V.1 aJayaraman, Valadi, K.1 aChaudhury, S.1 aMitra, S.1 aMurthy, C., A.1 aSastry, P., S.1 aPal, S., K. uhttp://library.ncl.res.in/content/identification-defensins-employing-recurrence-quantification-analysis-and-random-forest-0