molecular subtyping EPN update

.circleci/config.yml

@@ -54,10 +54,9 @@ jobs:
           name: Molecular subtyping Chordoma
           command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-chordoma/run-molecular-subtyping-chordoma.sh
 
-      # This is failing - a fix is tracked in https://github.com/AlexsLemonade/OpenPBTA-analysis/issues/755#issuecomment-692681410
-      # - run:
-      #     name: Molecular subtyping - Ependymoma
-      #     command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-EPN/run-molecular-subtyping-EPN.sh
+      - run:
+          name: Molecular subtyping - Ependymoma
+          command: OPENPBTA_SUBSET=0 ./scripts/run_in_ci.sh bash analyses/molecular-subtyping-EPN/run-molecular-subtyping-EPN.sh
 
       - run:
           name: Molecular Subtyping - LGAT

analyses/molecular-subtyping-EPN/00-subset-for-EPN.R

@@ -52,7 +52,9 @@ expression <- readr::read_rds(opts$expression)
 
 epn_samples <- histologies %>%
   filter(experimental_strategy == "RNA-Seq",
-         integrated_diagnosis == "Ependymoma") %>%
+         # All Ependymoma samples are captured in pathology_diagnosis
+         # pathology_free_text_diagnosis adds no additional samples
+         pathology_diagnosis == "Ependymoma") %>%
   pull(Kids_First_Biospecimen_ID)
 
 # Subsetting expression columns with column names/BSIDs that are in the list of ependymoma samples

analyses/molecular-subtyping-EPN/01-make_notebook_RNAandDNA.py

@@ -40,7 +40,7 @@ def group_disease(primary_site):
 
 
 # Filtering for ependymoma samples 
-EP = pbta_histologies[pbta_histologies["integrated_diagnosis"]=="Ependymoma"]
+EP = pbta_histologies[pbta_histologies["pathology_diagnosis"]=="Ependymoma"]
 EP_rnaseq_samples = EP[EP["experimental_strategy"] == "RNA-Seq"][["Kids_First_Biospecimen_ID", "primary_site", 
 	"Kids_First_Participant_ID", "sample_id", "experimental_strategy"]]
 EP_rnaseq_samples["disease_group"] = [group_disease(primary) for primary in EP_rnaseq_samples["primary_site"]]