Ignore src_cd column (10th) in subj. sample file.

thehyve · Mar 24, 2016 · 6549693 · 6549693
1 parent 195fa94
commit 6549693
Show file tree

Hide file tree

Showing 4 changed files with 11 additions and 12 deletions.
diff --git a/docs/proteomics.md b/docs/proteomics.md
@@ -39,12 +39,12 @@ Subject-Sample Mapping
 
 Here is a subject-sample mapping example file:
 
-| trial_name | site_id | subject_id | sample_cd               | platform   | sample_type | tissue_type | time_point | cat_cd                                                                                                                   | src_cd |
-|------------|---------|------------|-------------------------|------------|-------------|-------------|------------|--------------------------------------------------------------------------------------------------------------------------|--------|
-| CLUC       |         | CACO2      | LFQ.intensity.CACO2_1   | PROT_ANNOT | LFQ-1       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios | STD    |
-| CLUC       |         | CACO2      | LFQ.intensity.CACO2_2   | PROT_ANNOT | LFQ-2       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios | STD    |
-| CLUC       |         | COLO205    | LFQ.intensity.COLO205_1 | PROT_ANNOT | LFQ-1       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios | STD    |
-| CLUC       |         | COLO205    | LFQ.intensity.COLO205_2 | PROT_ANNOT | LFQ-2       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios | STD    |
+| trial_name | site_id | subject_id | sample_cd               | platform   | sample_type | tissue_type | time_point | cat_cd                                                                                                                   |
+|------------|---------|------------|-------------------------|------------|-------------|-------------|------------|--------------------------------------------------------------------------------------------------------------------------|
+| CLUC       |         | CACO2      | LFQ.intensity.CACO2_1   | PROT_ANNOT | LFQ-1       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios |
+| CLUC       |         | CACO2      | LFQ.intensity.CACO2_2   | PROT_ANNOT | LFQ-2       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios |
+| CLUC       |         | COLO205    | LFQ.intensity.COLO205_1 | PROT_ANNOT | LFQ-1       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios |
+| CLUC       |         | COLO205    | LFQ.intensity.COLO205_2 | PROT_ANNOT | LFQ-2       | Colon       | Week1      | Molecular profiling+High-throughput molecular profiling+Expression (protein)+LC-MS-MS+Protein level+SAMPLETYPE+MZ ratios |
 
 
 Data

diff --git a/docs/subject-sample-mapping.md b/docs/subject-sample-mapping.md
@@ -2,9 +2,9 @@
 
 This is the mapping file format:
 
-| `STUDY_ID` | `SITE_ID` | `SUBJECT_ID`     | `SAMPLE_CD` | `PLATFORM`   | `SAMPLE_TYPE`| `TISSUE_TYPE`  | `TIME_POINT`   | `CATEGORY_CD`                      | `SOURCE_CD` |
-|------------|-----------|------------------|-------------|--------------|--------------|----------------|----------------|------------------------------------|-------------|
-| GSE8581    |           | GSE8581GSM210005 | GSM210005   | GPL570_BOGUS | Human        | Lung           | Week1          | Biomarker_Data+PLATFORM+TISSUETYPE | STD         |
+| `STUDY_ID` | `SITE_ID` | `SUBJECT_ID`     | `SAMPLE_CD` | `PLATFORM`   | `SAMPLE_TYPE`| `TISSUE_TYPE`  | `TIME_POINT`   | `CATEGORY_CD`                      |
+|------------|-----------|------------------|-------------|--------------|--------------|----------------|----------------|------------------------------------|
+| GSE8581    |           | GSE8581GSM210005 | GSM210005   | GPL570_BOGUS | Human        | Lung           | Week1          | Biomarker_Data+PLATFORM+TISSUETYPE |
 
 The first row is skipped. It must be present, otherwise the first assay will be
 ignored.
@@ -30,4 +30,3 @@ ignored.
   created. Components of the path are separated with `+`. It can include several
   placeholders (see the descriptions of the other columns). In principle it can
   differ among the several assays, but that code path has never been tested.
-- `SOURCE_CD` is ignored (must be present as a last column).
diff --git a/src/main/groovy/org/transmartproject/batch/highdim/assays/AssayStepsConfig.groovy b/src/main/groovy/org/transmartproject/batch/highdim/assays/AssayStepsConfig.groovy
@@ -53,7 +53,8 @@ class AssayStepsConfig implements StepBuildingConfigurationTrait {
                 delimiter: DELIMITER_TAB,
                 names: ['studyId', 'siteId', 'subjectId', 'sampleCd',
                         'platform', 'sampleType', 'tissueType', 'timePoint',
-                        'categoryCd', 'source_cd'],
+                        'categoryCd'],
+                strict: false
         )
         new FlatFileItemReader(
                 lineMapper: new DefaultLineMapper(

diff --git a/src/main/groovy/org/transmartproject/batch/highdim/assays/MappingFileRow.groovy b/src/main/groovy/org/transmartproject/batch/highdim/assays/MappingFileRow.groovy
@@ -20,7 +20,6 @@ class MappingFileRow {
     String sampleType
     String timePoint
     String categoryCd /* the path under TOP_NODE */
-    String sourceCd /* IGNORED */
 
     void setStudyId(String studyId) {
         /* normalize study id */