Rice is one of the major global food crops. Although the overall yield of rice has been increasing, the growing population and adverse climatic changes pose huge challenges for their sustained production in the future. Therefore, systematic approaches are highly required to explore their effects on cereal crops’ phenotypic and cellular responses. It could be achieved by combining the available multiple high throughput data such as genomics, metabolomics, proteomics and transcriptomics, thereby analyzing the possible biochemical adaptations to several abiotic and biotic stresses, and subsequently improving the crop yield. Concurrently, the advent of constraint-based metabolic reconstruction and analysis paves way to characterize cellular physiology under various stresses via the mathematical network models. We have employed similar systems biology approach, and initially developed a core mathematical model of rice to characterize cellular behaviour and metabolic states under various abiotic stress conditions. The core model was then further expanded to reconstruct a fully compartmentalized genome scale metabolic model. Subsequently, transcriptomics and metabolomics data were systematically integrated with the model to identify the potential candidate regulatory genes as new breeding targets for improving rice production. In addition, we have also reconstructed a genome-scale metabolic model of Xanthomonas oryzae pathovar oryzae (Xoo) that causes leaf blight in rice leading to severe yield losses. In future, in silico model-guided framework can be further extended by including comprehensive genome-scale model of rice and its leaf microbiome for characterizing their interactions. This may allow us to systematically devise new strategies to control leaf blight in rice.