Added SRM data to proteomics distribution data testing

Sage-Bionetworks · Nov 3, 2023 · 38697f3 · 38697f3
1 parent 72cfdb5
commit 38697f3
Show file tree

Hide file tree

Showing 6 changed files with 95 additions and 1 deletion.
diff --git a/...assets/proteomics_distribution_data/input/test_proteomics_distribution_srm_good_input.csv b/...assets/proteomics_distribution_data/input/test_proteomics_distribution_srm_good_input.csv
@@ -0,0 +1,8 @@
+uniqid,genename,uniprotid,ensg,tissue,log2_fc,ci_upr,ci_lwr,pval,cor_pval
+RPL35|P42766,RPL35,P42766,ENSG00000136942,DLPFC,-0.0763864716519552,-0.0099209909244187,-0.1428519523794917,0.0194330864811924,0.0532108844452419
+SLC6A12|P48065,SLC6A12,P48065,ENSG00000111181,DLPFC,0.0424329158355659,0.1099491140769349,-0.0250832824058029,0.303320959613638,0.5210898536952243
+PTPN11|Q06124,PTPN11,Q06124,ENSG00000179295,DLPFC,0.0064652259159073,0.0458145863390218,-0.0328841345072071,0.9213060368774064,0.9998368407824682
+PLXNB1|O43157,PLXNB1,O43157,ENSG00000164050,DLPFC,0.1315038527175516,0.2011640123915693,0.061843693043534,3.094711736695288e-05,0.0001727880719654
+STX5|Q13190,STX5,Q13190,ENSG00000162236,DLPFC,0.0042787903893951,0.1178799748681132,-0.1093223940893228,0.9957000250037246,0.999696551493841
+MTOR|P42345,MTOR,P42345,ENSG00000198793,DLPFC,-0.016913729214123,0.014911434052702,-0.0487388924809481,0.4255337386213362,0.6381170540950976
+STX1B|P61266,STX1B,P61266,ENSG00000099365,DLPFC,-0.0627896276157541,-0.018089777426611,-0.1074894778048971,0.0029030746757215,0.0092621906320641
diff --git a/...ets/proteomics_distribution_data/input/test_proteomics_distribution_srm_missing_input.csv b/...ets/proteomics_distribution_data/input/test_proteomics_distribution_srm_missing_input.csv
@@ -0,0 +1,8 @@
+uniqid,genename,uniprotid,ensg,tissue,log2_fc,ci_upr,ci_lwr,pval,cor_pval
+RPL35|P42766,RPL35,P42766,ENSG00000136942,,-0.0763864716519552,-0.0099209909244187,-0.1428519523794917,0.0194330864811924,0.0532108844452419
+SLC6A12|P48065,SLC6A12,P48065,ENSG00000111181,,0.0424329158355659,0.1099491140769349,-0.0250832824058029,0.303320959613638,0.5210898536952243
+PTPN11|Q06124,PTPN11,Q06124,ENSG00000179295,DLPFC,0.0064652259159073,0.0458145863390218,-0.0328841345072071,0.9213060368774064,0.9998368407824682
+PLXNB1|O43157,PLXNB1,O43157,ENSG00000164050,,0.1315038527175516,0.2011640123915693,0.061843693043534,3.094711736695288e-05,0.0001727880719654
+STX5|Q13190,STX5,Q13190,ENSG00000162236,DLPFC,0.0042787903893951,0.1178799748681132,-0.1093223940893228,0.9957000250037246,0.999696551493841
+MTOR|P42345,MTOR,P42345,ENSG00000198793,DLPFC,-0.016913729214123,0.014911434052702,-0.0487388924809481,0.4255337386213362,0.6381170540950976
+STX1B|P61266,STX1B,P61266,ENSG00000099365,DLPFC,-0.0627896276157541,-0.018089777426611,-0.1074894778048971,0.0029030746757215,0.0092621906320641
diff --git a/.../test_assets/proteomics_distribution_data/output/proteomics_distribution_good_output.json b/.../test_assets/proteomics_distribution_data/output/proteomics_distribution_good_output.json
@@ -43,5 +43,14 @@
     "median": 0.1132,
     "third_quartile": 0.2011,
     "type": "TMT"
+  },
+  {
+    "tissue": "DLPFC",
+    "min": -0.1363,
+    "max": 0.1209,
+    "first_quartile": -0.0399,
+    "median": 0.0043,
+    "third_quartile": 0.0244,
+    "type": "SRM"
   }
 ]
diff --git a/...ts/proteomics_distribution_data/output/proteomics_distribution_good_output_two_types.json b/...ts/proteomics_distribution_data/output/proteomics_distribution_good_output_two_types.json
@@ -0,0 +1,47 @@
+[
+  {
+    "tissue": "AntPFC",
+    "min": -0.1806,
+    "max": 0.1514,
+    "first_quartile": -0.0561,
+    "median": -0.011,
+    "third_quartile": 0.0269,
+    "type": "LFQ"
+  },
+  {
+    "tissue": "DLPFC",
+    "min": -0.1472,
+    "max": 0.146,
+    "first_quartile": -0.0373,
+    "median": 0.018,
+    "third_quartile": 0.036,
+    "type": "LFQ"
+  },
+  {
+    "tissue": "MFG",
+    "min": -0.0979,
+    "max": 0.0192,
+    "first_quartile": -0.054,
+    "median": -0.0339,
+    "third_quartile": -0.0247,
+    "type": "LFQ"
+  },
+  {
+    "tissue": "TCX",
+    "min": -0.3847,
+    "max": 0.3455,
+    "first_quartile": -0.1109,
+    "median": -0.0953,
+    "third_quartile": 0.0717,
+    "type": "LFQ"
+  },
+  {
+    "tissue": "DLPFC",
+    "min": -0.4097,
+    "max": 0.5676,
+    "first_quartile": -0.0432,
+    "median": 0.1132,
+    "third_quartile": 0.2011,
+    "type": "TMT"
+  }
+]
diff --git a/...st_assets/proteomics_distribution_data/output/proteomics_distribution_missing_output.json b/...st_assets/proteomics_distribution_data/output/proteomics_distribution_missing_output.json
@@ -43,5 +43,14 @@
     "median": 0.1104,
     "third_quartile": 0.2545,
     "type": "TMT"
+  },
+  {
+    "tissue": "DLPFC",
+    "min": -0.0782,
+    "max": 0.0546,
+    "first_quartile": -0.0284,
+    "median": -0.0063,
+    "third_quartile": 0.0048,
+    "type": "SRM"
   }
 ]
diff --git a/tests/transform/test_proteomics_distribution_data.py b/tests/transform/test_proteomics_distribution_data.py
@@ -18,40 +18,53 @@ class TestTransformProteomicsDistributionData:
             {
                 "proteomics": "test_proteomics_distribution_lfq_good_input.csv",
                 "proteomics_tmt": "test_proteomics_distribution_tmt_good_input.csv",
+                "proteomics_srm": "test_proteomics_distribution_srm_good_input.csv"
             },
             "proteomics_distribution_good_output.json",
         ),
         (  # pass with imperfect data
             {
                 "proteomics": "test_proteomics_distribution_lfq_missing_input.csv",
                 "proteomics_tmt": "test_proteomics_distribution_tmt_missing_input.csv",
+                "proteomics_srm": "test_proteomics_distribution_srm_missing_input.csv"
             },
             "proteomics_distribution_missing_output.json",
         ),
+        ( # pass with only two of the three proteomics types
+            {
+                "proteomics": "test_proteomics_distribution_lfq_good_input.csv",
+                "proteomics_tmt": "test_proteomics_distribution_tmt_good_input.csv",
+            },
+            "proteomics_distribution_good_output_two_types.json",
+        )
     ]
     pass_test_ids = [
-        "Pass with good data (LFQ and TMT)",
+        "Pass with good data",
         "Pass with missing data",
+        "Pass with only two out of three proteomics types (LFQ, TMT)"
     ]
     fail_test_data = [
         (  # fail with bad data type
             {
                 "proteomics": "test_proteomics_distribution_lfq_wrong_data_type.csv",
                 "proteomics_tmt": "test_proteomics_distribution_tmt_good_input.csv",
+                "proteomics_srm": "test_proteomics_distribution_srm_good_input.csv",
             },
             KeyError,
         ),
         (  # fail with all NA data
             {
                 "proteomics": "test_proteomics_distribution_lfq_good_input.csv",
                 "proteomics_tmt": "test_proteomics_distribution_tmt_bad_input.csv",
+                "proteomics_srm": "test_proteomics_distribution_srm_good_input.csv",
             },
             KeyError,
         ),
         (  # fail with bad name
             {
                 "bad_name": "test_proteomics_distribution_lfq_good_input.csv",
                 "proteomics_tmt": "test_proteomics_distribution_tmt_good_input.csv",
+                "proteomics_srm": "test_proteomics_distribution_srm_good_input.csv",
             },
             ValueError,
         ),