Hi JMP Community,
I need to classify unstructured text annotations (see attached table) based on a list of predefined keywords.
For example:
- GROUP1
- AIZARANI_LIVER_C2_KUPFFER_CELLS_1 ==> MACROPHAGE
- CUI_DEVELOPING_HEART_C8_MACROPHAGE ==> MACROPHAGE
- ...
- GROUP2
- AIZARANI_LIVER_C8_RESIDENT_B_CELLS_1 ==> B - PLASMA CELLS
- AIZARANI_LIVER_C22_RESIDENT_B_CELLS_2 ==> B - PLASMA CELLS
- HAY_BONE_MARROW_PLASMA_CELL ==> B - PLASMA CELLS
- ...
Since there are > 400 rows/annotations, I am looking for a semi-automated method that would be faster than a manual RECODE.
Note: I wonder if TEXT EXPLORER could help here.
Thank you.
Best,
TS