Tutorials

• Using natural language to build models
  • Read INDRA Statements from a natural language string
  • Assemble the INDRA Statements into a rule-based executable model
  • Exporting the model into other common formats
• Large-Scale Machine Reading with Starcluster
  • Install REACH
  • Install Amazon S3 support
  • Install other dependencies
  • Assemble a Corpus of PMIDs
  • Process the papers with REACH
  • Extract INDRA Statements from the REACH output on S3
  • Running the whole pipeline with one script
• Large-Scale Machine Reading with Amazon Batch
  • How it Works
• Assembling everything known about a particular gene
  • Collect mechanisms from PathwayCommons and the BEL Large Corpus
  • Collect a list of publications that discuss the gene of interest
  • Get the full text or abstract corresponding to the publications
  • Read the content of the publications
  • Combine all statements and run pre-assembly
  • Assemble the statements into a network model