Package Description

Since CLAMP-Cancer is a stand-alone eclipse plugin, its folder structure is similar to other eclipse plugins.
Configuration Folder: This folder contains CLAMP-Cancer configuration files.
StartCLAMP: This is the launching point for the CLAMP-Cancer GUI. In Windows, this is an executable file while in Mac, this is an application.

CLAMP-Cancer Package Description
CLAMP-Cancer GUI

Workspace Folder:

This folder contains seven sub-folders:

  1. ComponentLibrary: contains the components used in machine learning feature extraction and NLP functions.
  2. MyCorpus: contains the customized corpus built by the users.
  3. MyPipeline: contains the customized pipeline created by users for clinical notes processing.
  4. PipelineLibrary: contains the built-in pipelines ready to use for a series of common clinical applications.
  5. Log: Includes CLAMP-Cancer run-time log files
  6. Metadata: The metadata used by CLAMP-Cancer are included in this folder.
  7. Resources: This folder includes third-party libraries. Currently it has two items:
    1. CRFSuite: the CRF implementation for Name Entity Recognition tasks
    2. Umls_index: the Lucene index built for CLAMP-Cancer based on the UMLS thesaurus.

If you want to use UMLS terminologies, then you will need to create an UMLS account. Please follow the following link to create an UMLS account if you do not have any. https://uts.nlm.nih.gov//license.html
The following table lists libraries included in CLAMP-Cancer.

Libraries included in CLAMP-Cancer
groupId artifactId version
org.cleartk cleartk-ml-liblinear 2.0.0
org.ini4j ini4j 0.5.2
org.apache.uima uimafit-core 2.1.0
com.google.code.gson gson 2.3
org.apache.uima uimaj-core 2.6.0
org.apache.uima uimaj-document-annotation 2.6.0
de.bwaldvogel liblinear 1.94
org.apache.lucene lucene-core 5.2.1
org.apache.lucene lucene-analyzers-common 5.2.1
org.apache.lucene lucene-queryparser 5.2.1
org.apache.opennlp opennlp-tools 1.5.1-incubating
org.apache.ctakes ctakes-type-system 3.2.0
org.cleartk cleartk-named-entity 0.6.6
com.googlecode.clearnlp clearnlp 1.3.1
commons-codec commons-codec 20041127.091804
dom4j dom4j 1.6.1
org.apache.uima ruta-ep-engine 2.3.0
javax.servlet servlet-api 3.0-alpha-1
com.sun.jersey jersey-client 1.19
junit junit 4.12
commons-cli commons-cli 1.3
net.jodah concurrentunit 0.4.2
org.javatuples javatuples 1.2