Integrating text mining with experimentation
Systems Biology approaches are used by scientists to combine multiple tools and create accurate models of complex biological systems. The challenge is to integrate complex and highly diverse molecular biology insights with high-throughput ‘omics’ data sets into a conceptual framework — one that is holistic, quantitative and predictive. I2E provides an invaluable tool giving scientists the ability to extract data across any type of literature resource.
Data can be biological, e.g. standardized gene and protein names; medical, e.g. names of diseases and disorders; chemical, e.g. compounds and specific drugs; or numerical, e.g. dosages and concentrations.The linguistic capabilities of I2E also allow the user to link these concepts together and visualize the information that is captured, thus providing new insights for interpreting experimental evidence.
“Scientific literature must be in a computationally accessible format to be used for systems biology studies and custom curation is frequently needed. However, text analytics speeds creation of custom annotation by as much as an order of magnitude, lowering the barrier to accessing the wealth of information available in scientific literature,”
Phoebe Roberts, Library & Information Services, Biogen Idec