Skip to main content
Figure 6 | BMC Bioinformatics

Figure 6

From: Structuring and extracting knowledge for the support of hypothesis generation in molecular biology

Figure 6

Knowledge extraction workflow. The knowledge extraction workflow has three parts. The left part executes the steps of a basic text mining procedure: (i) extract protein names from the user query and add synonyms using the BioSemantics synonym service, (ii) retrieve documents from MedLine with the AIDA document search service, (iii) extract proteins with the AIDA named entity recognition service, (iv) calculate a ranking score for each discovery. The middle workflow converts the results from the text mining workflow to RDF using the biological model and the text model as template. The workflow on the right-side creates execution-level instances for the workflow components and couples these to the instances created in the middle workflow. The blue rectangles represent inputs and outputs. The pink rectangles represent sub-workflows.

Back to article page