Merge pull request #14 from broadinstitute/add-columns-to-released-pr…

…-meta Add columns to OmicsProfiles.csv, update files released to public
broadinstitute · Mar 29, 2024 · 7b6e513 · 7b6e513
2 parents 0e9e5a2 + c521c46
commit 7b6e513
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 3 deletions.
diff --git a/depmap_omics_upload/config.json b/depmap_omics_upload/config.json
@@ -123,7 +123,10 @@
         "ModelCondition",
         "ModelID",
         "Datatype",
-        "Baits"
+        "Baits",
+        "actual_seq_technology",
+        "Stranded",
+        "Source"
     ],
     "virtual_filenames_nummat_exp_model": {
         "proteinCoding_genes_tpm_logp1_profile": "OmicsExpressionProteinCodingGenesTPMLogp1",
@@ -194,7 +197,8 @@
         "internal": [],
         "dmc": [],
         "public": [
-            "structuralVariants_profile"
+            "structuralVariants_profile",
+            "armLevelCNA_profile"
         ]
     },
     "taiga_expression": "expression-d035",

diff --git a/depmap_omics_upload/upload.py b/depmap_omics_upload/upload.py
@@ -373,7 +373,11 @@ def makeProfileTable(prs, columns=config["profile_table_cols"]):
     """
     mytracker = track.SampleTracker()
     pr_table = mytracker.add_model_cols_to_prtable(["ModelID"])
-    pr_table = pr_table.loc[prs, columns].rename(columns={"Baits": "WESKit"})
+    seq_table = mytracker.read_seq_table()
+    mc_table = mytracker.read_mc_table()
+    pr_table["Stranded"] = pr_table["MainSequencingID"].map(dict(zip(seq_table.index, seq_table.stranded)))
+    pr_table["Source"] = pr_table["ModelCondition"].map(dict(zip(mc_table.index, mc_table.Source)))
+    pr_table = pr_table.loc[prs, columns].rename(columns={"Baits": "WESKit", "actual_seq_technology": "Product"})
     pr_table = pr_table[pr_table["Datatype"].isin(["rna", "wgs", "wes", "SNParray"])]
     pr_table.loc[
         pr_table[pr_table["Datatype"].isin(["rna", "wgs", "SNParray"])].index.tolist(),