Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Large-scale extraction of accurate drug-disease treatment pairs from biomedical literature for drug repurposing

Figure 1

Flow chart of the overall pattern learning, pair extraction and semantic analysis process. The entire process consisted of the following steps: (1) obtain entire MEDLINE corpus, (2) create a clean and MEDLINE-specific disease lexicon, (3) tag MEDLINE sentences with drug and disease entities, (4) extract treatment-specific patterns from tagged MEDLINE sentences using known drug-disease pairs, (5) extract new drug-disease pairs from tagged MEDLINE using selected patterns, (6) semantic analysis of extracted drug-disease pairs.

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us