Classification of multi-genomic data using MapReduce paradigm

Counting the number of occurences of a substring in a string is a problem in many applications. This paper suggests a fast and efficient solution for the field of bioinformatics. A k-mer is a k-length substring of a biological sequence. k-mer counting is defined as counting the number of occurences of all the possible k-mers in a biological sequence. k-mer counting has uses in applications ranging from error correction of sequencing reads, genome assembly, disease prediction and feature extraction. We provide a Hadoop based solution to solve the k-mer counting problem and then use this for classification of multi-genomic data. The classification is done using classifiers like Naive Bayes, Decision Tree and Support Vector Machine(SVM). Accuracy of more than 99% is observed.