Merge pull request #350 from PediatricOpenTargets/v12-efo-final

Updated final codes per discussion on OPC Issue 526
d3b-center · Apr 27, 2023 · 5020ea4 · 5020ea4
2 parents 52d0c26 + f4a487a
commit 5020ea4
Show file tree

Hide file tree

Showing 6 changed files with 219 additions and 61 deletions.
diff --git a/analyses/efo-mondo-mapping/01-merge-auto-search-ols-terms.R b/analyses/efo-mondo-mapping/01-merge-auto-search-ols-terms.R
@@ -1,3 +1,8 @@
+# Author: Sangeeta Shukla (shuklas1@chop.edu)
+# Purpose: This scripts automates the seach to retrieve EFO, MONDO, and NCIT ontology codes for all cancer_groups found in the histologies.tsv file.
+# This reduces the manual work to only have to review the potential edge cases where the codes may not be perfect match for the cancer_groups.
+
+
 # Load required libraries
 
 suppressPackageStartupMessages({

diff --git a/analyses/efo-mondo-mapping/02-qc_efo_mondo_map.nb.html b/analyses/efo-mondo-mapping/02-qc_efo_mondo_map.nb.html
@@ -1796,20 +1796,26 @@ <h2>Read efo-mondo-map.tsv and histologies file</h2>
 
 histology_df &lt;- readr::read_tsv(file.path(integrate_dir, &quot;histologies.tsv&quot;), guess_max=100000)</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-message-begin 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 -->
+<!-- rnb-message-begin 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 -->
 <pre><code>Parsed with column specification:
 cols(
   .default = col_character(),
+  age_at_diagnosis_days = col_double(),
   OS_days = col_double(),
+  EFS_days = col_double(),
   age_last_update_days = col_double(),
-  cns_methylation_class_score = col_double(),
-  cns_methylation_subclass_score = col_double(),
-  RF_purity_ABSOLUTE = col_double(),
-  RF_purity_ESTIMATE = col_double(),
-  RF_purity_LUMP = col_double(),
   normal_fraction = col_double(),
   tumor_fraction = col_double(),
-  tumor_ploidy = col_double()
+  tumor_ploidy = col_double(),
+  age_at_event_days = col_double(),
+  age_at_chemo_start = col_double(),
+  age_at_radiation_start = col_double(),
+  tumor_fraction_RFpurify_ABSOLUTE = col_double(),
+  tumor_fraction_RFpurify_ESTIMATE = col_double(),
+  tumor_fraction_LUMP = col_double(),
+  dkfz_v11_methylation_subclass_score = col_double(),
+  dkfz_v12_methylation_subclass_score = col_double(),
+  dkfz_v12_methylation_mgmt_estimated = col_double()
 )</code></pre>
 <!-- rnb-message-end -->
 <!-- rnb-message-begin eyJkYXRhIjoiU2VlIHNwZWMoLi4uKSBmb3IgZnVsbCBjb2x1bW4gc3BlY2lmaWNhdGlvbnMuXG4ifQ== -->
@@ -1854,21 +1860,13 @@ <h2>Check to make sure all cancer groups in histologies are in efo mondo map fil
 <!-- rnb-source-begin eyJkYXRhIjoiY2FuY2VyX2dyb3VwX2VmZmVjdGl2ZVshY2FuY2VyX2dyb3VwX2VmZmVjdGl2ZSAlaW4lIGVmb19tb25kb19tYXAkY2FuY2VyX2dyb3VwXSAifQ== -->
 <pre class="r"><code>cancer_group_effective[!cancer_group_effective %in% efo_mondo_map$cancer_group] </code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-output-begin eyJkYXRhIjoiWzFdIFwiUGlsb2N5dGljIGFzdHJvY3l0b21hXCIgICAgICAgICAgXCJDTlMgQnVya2l0dCdzIGx5bXBob21hXCIgICAgICAgIFxuWzNdIFwiRGlmZnVzZSBmaWJyaWxsYXJ5IGFzdHJvY3l0b21hXCIgXCJHbGlvc2FyY29tYVwiICAgICAgICAgICAgICAgICAgIFxuWzVdIFwiTmV1cm9lcGl0aGVsaWFsIG5lb3BsYXNtXCIgICAgICBcbiJ9 -->
-<pre><code>[1] &quot;Pilocytic astrocytoma&quot;          &quot;CNS Burkitt's lymphoma&quot;        
-[3] &quot;Diffuse fibrillary astrocytoma&quot; &quot;Gliosarcoma&quot;                   
-[5] &quot;Neuroepithelial neoplasm&quot;      </code></pre>
+<!-- rnb-output-begin eyJkYXRhIjoiWzFdIFwiU3VwcmF0ZW50b3JpYWwgZXBlbmR5bW9tYVwiIFwiU3BpbmFsIGVwZW5keW1vbWFcIiAgICAgICAgXG4ifQ== -->
+<pre><code>[1] &quot;Supratentorial ependymoma&quot; &quot;Spinal ependymoma&quot;        </code></pre>
 <!-- rnb-output-end -->
-<!-- rnb-output-begin eyJkYXRhIjpbIlBpbG9jeXRpYyBhc3Ryb2N5dG9tYVxuIiwiQ05TIEJ1cmtpdHQncyBseW1waG9tYVxuIiwiRGlmZnVzZSBmaWJyaWxsYXJ5IGFzdHJvY3l0b21hXG4iLCJHbGlvc2FyY29tYVxuIiwiTmV1cm9lcGl0aGVsaWFsIG5lb3BsYXNtXG4iXX0= -->
-<pre><code>Pilocytic astrocytoma
+<!-- rnb-output-begin eyJkYXRhIjpbIlN1cHJhdGVudG9yaWFsIGVwZW5keW1vbWFcbiIsIlNwaW5hbCBlcGVuZHltb21hXG4iXX0= -->
+<pre><code>Supratentorial ependymoma
 
-CNS Burkitt's lymphoma
-
-Diffuse fibrillary astrocytoma
-
-Gliosarcoma
-
-Neuroepithelial neoplasm</code></pre>
+Spinal ependymoma</code></pre>
 <!-- rnb-output-end -->
 <!-- rnb-chunk-end -->
 <!-- rnb-text-begin -->