According to the latest cancer statistics reported from India, oral cancer is the top-most cause of cancer related deaths in men, and it contributes about 23% of deaths caused by all cancer types in men. India has become an epicenter of oral cancer-related mortalities, and according to a rough estimate more than half of the worldwide oral cancer mortalities are from India �C. Oral cancer is currently managed through surgery, radiation and chemotherapy. Cetuximab is the only approved targeted therapy available for oral cancer, which targets epidermal growth factor receptor involved in cell growth. Targeted therapies have shown their usefulness in managing various EPZ005687 cancers, mostly because of its ability to reduce toxicities by several folds when compared with chemotherapeutic drugs. The acquisition of resistance to targeted cancer therapies due to an emergence of various genetic and/or non-genetic mechanisms, have seriously undermined their clinical application. The challenge of emergence of drug resistance in cancer cells can be addressed by – targeting multiple targets by combination therapy, designing a drug against molecular target which are involved in diverse pathways critically linked with survival, growth and proliferation of cancer cells, or by the combination of and. The current study, attempts to identify potential therapeutic targets for oral cancer that are associated with multiple cancer hallmarks, which can facilitate rational discovery of effective therapies for oral cancer. We have used microarray datasets available from NCBI-GEO database, to study transcriptional profiles specifically altered in oral cancer. We have integrated dataset from two studies with similar experimental design to derive meaningful results from underlying dataset with improved statistical power. The direct integration of dataset from different studies is challenging due to existence of myriad sources of non-biological variations, often referred as ��batch-effects��. Such probe-level integration of dataset from two different studies is possible by removing FLI-06 batch-effects by cross platform normalization. Different analytical methods have been integrated to enable logical selection of the most promising therapeutic targets for oral cancer.