A machine learning approach for detecting MAP kinase in the genome of Oryza sativa L. ssp. indica

Plant development and crop yield are highly influenced by temperature. High temperature negatively affects different stages of plant development in rice, mainly booting and flowering. Identifying candidate genes associated with high-temperature stress response may provide knowledge for the improvement of heat tolerance in rice. As the rice genome sequencing has already been undertaken, a major work challenge is annotating proteins and decoding their functionalities. MAP kinase (MAPK) proteins are involved in signaling various abiotic and biotic stresses, like temperature stress or drought, wounding and pathogen infection. Moreover, MAPKs have also been implicated in cell cycle and developmental processes. In this study, an attempt has been made in developing a MAP kinase prediction tool for rice, MapPred. The computational approach has been developed using Sequential Minimum Optimization (SMO) algorithm in Weka workbench, and a sensitivity of 100% was obtained using dipeptide method. MapPred was also tested with three plants, namely Arabidopsis, maize and tomato to prove that developed tool has higher accuracy with rice than other plants which further proves the higher prediction accuracy of species-specific tools. Prediction performance of MapPred was evaluated using cross validation, independent data test and leave one out validation. Our experimental results demonstrated that proposed algorithm based on dipeptide method could be very effective in the computational approach for predicting MAPK proteins in Oryza sativasubsp.indica.