Tutorials

Test files

Input files used to create publication data can be found at [link]

Tutorial 1: Default Use (general extension)

This tutorial assumes that the input files are a model in the standard BioRECIPES format and an LEE set from REACH.

Tutorial 2: Specifying Score and Attributes

Tutorial 3: Using VIOLIN at the terminal

This tutorial assumes that the input files are a model in the standard BioRECIPES format and an LEE set from REACH. This tutorial also assumes that the user wants to run VIOLIN for basic extension using VIOLIN’s default values, and visualization is for the total output

The use_violin_script.py script is included in the violin_tutorial folder. The input for this script allows for four classification schemes:

  1. ‘extend’ - default Kind and Match Score values for general extension

  2. ‘extend subcategories’ - general extension values with subcategories specified in Kind Score values

  3. ‘corroborate’ - Kind and Match Score values for general corroboration (preference towards strong corroborations, weak corroborations, contradictions)

  4. ‘corroborate subcategories’ - general extension values with subcategories specified in Kind Score values

as well as the same filtering options from Visualization (VIOLIN.visualize_violin)

violin_tutorial.use_violin_script.use_violin(model_file, lee_file, out_file, score='extend', filt_opt='100%')[source]

This function runs VIOLIN via a terminal command

Parameters
  • model_file (str) – Directory and filename of the the machine reading spreadsheet output Accepted files: .txt, .csv, .tsv, .xlsx

  • lee_file (str) – Directory and filename of the model file in BioRECIPE format Accepted files: .txt, .csv, .tsv, .xlsx

  • out_file (str) – Directory and filename of the output suffix

  • score (str) – Scoring scheme used for classification Options are: ‘extend’, ‘extend subcategories’, ‘corroborate’, ‘corroborate subcategories’

  • filt_opt (str) – How much VIOLIN output should be visualized. Can be filtered by top % of total score, evidence score (Se) threshold, or total score (St) threshold Accepted options are ‘X%’,’Se>Y’, or ‘St>Z’, where X, Y, and Z, are values Default is ‘100%’ (Total Output)

To run use_violin_script.py at the command line:

python use_violin_script.py test_input/ModelA.csv test_input/RA2_reading.xlsx output extend 50%

Tutorial 4: Alternative Input