CLAMP-Cancer is a stand-alone Java application based on the Eclipse platform technologies. CLAMP-Cancer uses the Apache UIMA (Unstructured Information Management Architecture) framework. The annotation module of CLAMP-Cancer incorporates and enhances the brat rapid annotation tool . For the other individual constituents, Apache OpenNLP toolkit, Liblinear and CRF Suite are utilized in addition to in-house rule-based components. CLAMP-Cancer also use the UIMA Ruta (Rule based Text Annotation) as a rule engine to help users specify rules. CLAMP-Cancer is distributed as a ready-to-use binary package that can either be executed at the command line or carries the associated Graphic User Interface (GUI). Our distribution package includes components for jar files, CRFSuite, and a Lucene index of all levels of UMLS data.

The only prerequisite necessary to compile CLAMP-Cancer is JRE 1.8 (Java Runtime Environment). Please ensure that you have Java 8 or higher installed in your system. Run the following command in both Mac and Windows to check your version:
java –version
Here is an example of what you will see when running the command in Windows:

If your java version is not 1.8, it is available for download from the Oracle website. An UMLS account is required in order to use Level 2 and higher data in the UMLS encoding component of the system. The account can be created at https://uts.nlm.nih.gov/home.html. You will have to enter your UMLS username and password when prompted by CLAMP-Cancer in order to utilise the UMLS encoding component. CLAMP-Cancer also uses the computer’s default browsers to visualize the clinical documents. Since all browsers do not completely support all the aspects of the technologies used to implement the visualization, limitations exist in term of running the CLAMP-Cancer annotation module in the browsers. On the Windows OS, the Internet Explorer should be higher than IE9; On Macintosh computers, Safari (all versions) works well with CLAMP-Cancer.