Text mining driven drug-drug interaction detection

Identifying drug-drug interactions is an important and challenging problem in computational biology and healthcare research. There are accurate, structured but limited domain knowledge and noisy, unstructured but abundant textual information available for building predictive models. The difficulty lies in mining the true patterns embedded in text data and developing efficient and effective ways to combine heterogenous types of information. We demonstrate a novel approach of leveraging augmented text-mining features to build a logistic regression model with improved prediction performance (in terms of discrimination and calibration). Our model based on synthesized features significantly outperforms the model trained with only structured features (AUC: 96% vs. 91%, Sensitivity: 90% vs. 82% and Specificity: 88% vs. 81%). Along with the quantitative results, we also show learned “latent topics”, an intermediary result of our text mining module, and discuss their implications.