Templating for Clinical Trials Eligibility Criteria

Scripts, data, and clusters used in the process of templating clinical trials eligibility data in order to provide more structure.

Scripts

Most scripts used for clustering and automatic templating are stored in /scripts/.

Raw Data

Raw data for both the sample set and full cancer set are stored in /Formatted Data/.

Clusters

Sample set

Clusters are stored at /clusters/final340numclusters2/.

Full cancer set

Clusters are stored at /clusters/final9knumclusters/, ordered clusters at /clusters/ordered9kclusters, clusters of cluster centers at clusters/center9kclusters/, and megaclusters at /clusters/mega9kclust/.

Other clusters

Other intermediate clusters and clustering schemes used along the way are also stored in /clusters/, but final clustering schemes are noted above.

Templates

Some templates for the full cancer set generated by the program are stored at /templates/templates/ and /templates/fillins/. Thresholds for the templates shown are noted in /templates/thresholds. All booleanized templates for the sample set are stored at /templates/booleanizedtemplates/.

Parser

Code for the parser is stored at /templates/parser/.