Update URL and corrected test data to match current schema

- corrected "DNA" and "RNA" to "Total DNA" and "Total RNA" respectively

Author: edsu7

payload-gen-seq-experiment/main.py

@@ -33,7 +33,6 @@
 import requests
 import re
 import jsonschema
-import traceback
 
 
 TSV_FIELDS = {}
@@ -174,20 +173,20 @@ def validate_args(args):
             Usage:
                 When '-m' is provided, no other arguments can be used
                 When '-m' is not provided, please provide all of these arguments: -x, -r and -f
+                Optionally '-s' a schema URL can be provided, which the payload will be validated against
             """
         ))
 
 def validatePayload(payload,args):
     if args.schema_url:
         url=args.schema_url
     else:
-        url="https://raw.githubusercontent.com/icgc-argo/argo-metadata-schemas/master/schemas/sequencing_experiment.json"
+        url="https://submission-song.rdpc.cancercollaboratory.org/schemas/sequencing_experiment"
 
     resp=requests.get(url)
     if not resp.status_code==200:
         sys.exit("Unable to retrieve schema. Please check URL\n")
-    #print(payload)
-    #print(resp.json()['schema'])
+
     try:
         jsonschema.validate(instance=payload,schema=resp.json()['schema'])
     except jsonschema.exceptions.ValidationError as err:

payload-gen-seq-experiment/tests/input/208c5ea6-c17a-4a63-981e-4bb91d3119f2.sequencing_experiment.payload.json

@@ -58,7 +58,7 @@
     {
       "submitterSampleId": "HCC1143_BAM_INPUT",
       "matchedNormalSubmitterSampleId": null,
-      "sampleType": "RNA",
+      "sampleType": "Total RNA",
       "specimen": {
         "submitterSpecimenId": "HCC1143_BAM_INPUT",
         "tumourNormalDesignation": "Normal",

payload-gen-seq-experiment/tests/input/d9c99af9-b97d-4481-9be8-f65e57d86673.sequencing_experiment.payload.json

@@ -57,7 +57,7 @@
     {
       "submitterSampleId": "HCC1143_BAM_INPUT",
       "matchedNormalSubmitterSampleId": null,
-      "sampleType": "DNA",
+      "sampleType": "Total DNA",
       "specimen": {
         "submitterSpecimenId": "HCC1143_BAM_INPUT",
         "tumourNormalDesignation": "Normal",

payload-gen-seq-experiment/tests/input/experiment.correct.rnaseq.tsv

@@ -1,2 +1,2 @@
 type	study_id	submitter_sequencing_experiment_id	submitter_donor_id	gender	submitter_specimen_id	tumour_normal_designation	specimen_type	specimen_tissue_source	submitter_sample_id	sample_type	submitter_matched_normal_sample_id	sequencing_center	platform	platform_model	experimental_strategy	sequencing_date	read_group_count	library_strandedness
-sequencing_experiment	TEST-PRO	TEST_EXP	HCC1143	Female	HCC1143_BAM_INPUT	Normal	Cell line - derived from normal	Blood derived	HCC1143_BAM_INPUT	RNA		EXT	ILLUMINA	HiSeq 2000	RNA-Seq	2014-12-12	3	FIRST_READ_ANTISENSE_STRAND
+sequencing_experiment	TEST-PRO	TEST_EXP	HCC1143	Female	HCC1143_BAM_INPUT	Normal	Cell line - derived from normal	Blood derived	HCC1143_BAM_INPUT	Total RNA		EXT	ILLUMINA	HiSeq 2000	RNA-Seq	2014-12-12	3	FIRST_READ_ANTISENSE_STRAND

tests/data/98690064-627e-4a2b-a0c2-60fc9ca8433c.sequencing_experiment.payload.json

@@ -57,7 +57,7 @@
     {
       "submitterSampleId": "HCC1143_BAM_INPUT",
       "matchedNormalSubmitterSampleId": null,
-      "sampleType": "DNA",
+      "sampleType": "Total DNA",
       "specimen": {
         "submitterSpecimenId": "HCC1143_BAM_INPUT",
         "tumourNormalDesignation": "Normal",

tests/data/cab531fd-dc75-462f-8a73-fb7fcbf73185.sequencing_experiment.payload.json

@@ -54,7 +54,7 @@
     {
       "submitterSampleId": "HCC1143_FASTQ_INPUT",
       "matchedNormalSubmitterSampleId": "HCC1143_BAM_INPUT",
-      "sampleType": "DNA",
+      "sampleType": "Total DNA",
       "specimen": {
         "submitterSpecimenId": "HCC1143_FASTQ_INPUT",
         "tumourNormalDesignation": "Cell line - derived from tumour",

tests/data/experiment-fq.v2.tsv

@@ -1,2 +1,2 @@
 type	study_id	submitter_sequencing_experiment_id	submitter_donor_id	gender	submitter_specimen_id	tumour_normal_designation	specimen_type	specimen_tissue_source	submitter_sample_id	sample_type	submitter_matched_normal_sample_id	sequencing_center	platform	platform_model	experimental_strategy	sequencing_date	read_group_count
-sequencing_experiment	TEST-PRO	TEST_EXP	HCC1143	Female	HCC1143_FASTQ_INPUT	Tumour	Cell line - derived from tumour	Blood derived	HCC1143_FASTQ_INPUT	DNA	HCC1143_BAM_INPUT	EXT	ILLUMINA	HiSeq 2000	WGS	2014-12-12	3
+sequencing_experiment	TEST-PRO	TEST_EXP	HCC1143	Female	HCC1143_FASTQ_INPUT	Tumour	Cell line - derived from tumour	Blood derived	HCC1143_FASTQ_INPUT	Total DNA	HCC1143_BAM_INPUT	EXT	ILLUMINA	HiSeq 2000	WGS	2014-12-12	3

tests/data/experiment.v2.tsv

@@ -1,2 +1,2 @@
 type	study_id	submitter_sequencing_experiment_id	submitter_donor_id	gender	submitter_specimen_id	tumour_normal_designation	specimen_type	specimen_tissue_source	submitter_sample_id	sample_type	submitter_matched_normal_sample_id	sequencing_center	platform	platform_model	experimental_strategy	sequencing_date	read_group_count
-sequencing_experiment	TEST-PRO	TEST_EXP	HCC1143	Female	HCC1143_BAM_INPUT	Normal	Cell line - derived from normal	Blood derived	HCC1143_BAM_INPUT	DNA		EXT	ILLUMINA	HiSeq 2000	WGS	2014-12-12	3
+sequencing_experiment	TEST-PRO	TEST_EXP	HCC1143	Female	HCC1143_BAM_INPUT	Normal	Cell line - derived from normal	Blood derived	HCC1143_BAM_INPUT	Total DNA		EXT	ILLUMINA	HiSeq 2000	WGS	2014-12-12	3

tests/data/fc003ffc-f0cf-4ef6-b9bd-df5010acdbbb.sequencing_experiment.payload.json

@@ -57,7 +57,7 @@
     {
       "submitterSampleId": "HCC1143_FASTQ_INPUT",
       "matchedNormalSubmitterSampleId": "HCC1143_BAM_INPUT",
-      "sampleType": "DNA",
+      "sampleType": "Total DNA",
       "specimen": {
         "submitterSpecimenId": "HCC1143_FASTQ_INPUT",
         "tumourNormalDesignation": "Tumour",