Journal: PLoS Computational Biology
Article Title: Building Disease-Specific Drug-Protein Connectivity Maps from Molecular Interaction Networks and PubMed Abstracts
doi: 10.1371/journal.pcbi.1000450
Figure Lengend Snippet: Two curated data sources (DrugBank and CTD) and two computational methods (Chi2 and BITOLA) were selected to compare against the performance of our approach on AD drug identifications. DrugBank and CTD manually curated database content about disease-modifying gene/proteins and drugs. Chi2 is a baseline system using commonly Chi-square statistical method to identify significant co-occurring drug-disease relationships cited in PubMed abstracts. BITOLA (Biomedical Discovery Support System) is a computational system based on natural language processing that can extract drug-protein relation in a disease context. The histogram shows sensitivity, specificity, PPV (positive predictive value), F-score, and ACC (accuracy) of each group. These performance measurements are defined in the section.
Article Snippet: The four systems that we compared includes: DrugBank , CTD (the Comparative Toxicogenomics Database) , a baseline system using the common Chi-square (χ 2 ) method , and BITOLA (Biomedical Discovery Support System) .
Techniques: