Ab Initio Gene Identification Using Apache Spark

Computer-assisted gene identification in deoxyribonucleic acid (DNA) sequences is a challenging task, which requires intelligent pattern recognition algorithms as well as significant computing power. Gene recognition has increased importance today, when medical treatment of a patient should be adapted to the inherited features of each individual; these features may be identified through the patients’ DNA. Gene recognition is also important for identify pathological organisms and their resistance to different treatments (e.g. antibiotics). In order to allow adaptive treatment of patients, gene identification must be fast, accessible and precise. In this paper we concentrate on formulating the problem of gene identification, on determining the most popular approaches and also on finding a parallelization procedure that can reduce the execution time of an identification algorithm.