Skip to content

Commit

Permalink
Fixes to DATS for E-GEOD-70652 and test
Browse files Browse the repository at this point in the history
  • Loading branch information
@agbeltran
agbeltran committed Mar 22, 2018
1 parent f6a582b commit ebbd22a
Show file tree
Hide file tree
Showing 2 changed files with 126 additions and 119 deletions.
239 changes: 121 additions & 118 deletions json-instances/datamed/E-GEOD-70652-dats.json
View file
Original file line number Diff line number Diff line change
@@ -1,142 +1,145 @@
{
"DataAcquisition": {
"identifiers": [
"storedIn": {
"access": [
{
"identifier": "A-GEOD-19109"
"landingPage": "https:\/\/www.ebi.ac.uk\/arrayexpress\/"
}
],
"name": "[HG-U133_Plus_2] Affymetrix Human Genome U133 Plus 2.0 Array [CDF: Brainarray HGU133Plus2_Hs_ENTREZG_v18]"
},
"Dataset": {
"storedIn": {
"access": [
{
"landingPage": "https:\/\/www.ebi.ac.uk\/arrayexpress\/"
}
],
"identifier": {
"identifier": "SCR:002964"
},
"name": "ArrayExpress",
"publishers": [
{
"abbreviation": "EBI",
"alternativeIdentifiers": [
{
"identifier": "http:\/\/www.ebi.ac.uk\/"
}
],
"identifier": {
"identifier": "SCR:004727"
},
"name": "European Bioinformatics Institute"
}
]
"identifier": {
"identifier": "SCR:002964"
},
"distributions": {
"access": [
{
"accessURL": {
"value": "https:\/\/www.ebi.ac.uk\/arrayexpress\/files\/E-GEOD-70652\/E-GEOD-70652.raw.1.zip"
},
"types": {
"value": "download"
},
"authentications": {
"value": "none"
},
"authorizations": {
"value": "none"
"name": "ArrayExpress",
"publishers": [
{
"abbreviation": "EBI",
"alternateIdentifiers": [
{
"identifier": "http:\/\/www.ebi.ac.uk\/"
}
],
"identifier": {
"identifier": "SCR:004727"
},
{
"accessURL": {
"value": "https:\/\/www.ebi.ac.uk\/arrayexpress\/files\/E-GEOD-70652\/E-GEOD-70652.processed.1.zip"
},
"types": {
"value": "download"
},
"authentications": {
"value": "none"
},
"authorizations": {
"name": "European Bioinformatics Institute"
}
]
},
"distributions": [
{
"storedIn": {
"name": "ArrayExpress"
},
"qualifiers": [ { "value": "gzip compressed" }],
"formats": [ "TXT" ],
"access": {
"landingPage": "",
"accessURL": "https:\/\/www.ebi.ac.uk\/arrayexpress\/files\/E-GEOD-70652\/E-GEOD-70652.raw.1.zip",
"types": [{
"value": "download"
}],
"authentications": [
{
"value": "none"
}
},
{
"accessURL": {
"value": "https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE70652"
},
"types": {
"value": "landing page"
},
"authentications": {
"value": "none"
},
"authorizations": {
],
"authorizations": [
{
"value": "none"
}
}
],
]
}
},

{
"storedIn": {
"name": {
"value": "Gene Expression Omnibus"
}
},
"qualifiers": {
"value": "not compressed"
"name": "ArrayExpress"
},
"formats": {
"value": "HTML"
"qualifiers": [ {"value": "gzip compressed"}],
"formats": [ "TXT" ],
"access": {
"landingPage": "",
"accessURL": "https:\/\/www.ebi.ac.uk\/arrayexpress\/files\/E-GEOD-70652\/E-GEOD-70652.processed.1.zip",
"types": [{
"value": "download"
}],
"authentications": [{
"value": "none"
}],
"authorizations": [{
"value": "none"
}]
}},
{


"storedIn": {
"name": "Gene Expression Omnibus"
},
"extraProperties": {
"value": "true"
}
},
"dates": [
{
"date": "20160303T000000+0000",
"type": {
"value": "released"
}
"qualifiers": [{
"value": "not compressed"
}],
"formats": [ "HTML" ],
"access": {
"landingPage": "",
"accessURL": "https:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE70652",
"types": [{
"value": "landing page"
}],
"authentications": [{
"value": "none"
}],
"authorizations": [{
"value": "none"
}]
},
{
"date": "20160305T000000+0000",
"type": {
"value": "modified"
"extraProperties": [{
"category": "primary",
"values": [ "true"]
}
]
}
],

"dates": [
{
"date": "20160303T000000+0000",
"type": {
"value": "released"
}
],
"description": "Type II Enteropathy-associated T-cell lymphoma (Type II EATL) is an aggressive intestinal T-cell lymphoma with poor prognosis and has not been molecularly profiled. Through targeted amplicon sequencing, we identified a large portion of Type II EATL samples that harbor mutations in the STAT5B, JAK3 and GNAI2 genes. Here we performed gene expression profiling on four Type II EATL samples in order to better characterize this disease. As Type II EATL is suggested to arise from CD8+ IELs, we integrated our data with publicly available profile of CD8\u03b1\u03b1 and CD8\u03b1\u03b2 T-cells from healthy donors (GSE33374). Gene expression profiling independently demonstrated strong enrichment of several aspects of GPCR and JAK-STAT signaling pathways. Moreover, an significant association was identified with genes containing STAT5B binding sites in their promoters. Microarray gene expression profiling was performed on 4 Type II Enteropathy-associated T-cell lymphoma and a combination of unsupervised and supervised clustering was performed to determine any differentially activated pathways between samples with tumor and healthy human CD161++CD8aa and CD161++CD8ab T cells (found under accession number GSE33374)",
"licenses": "not applicable",
"title": "Gene expression profiling of Type II Enteropathy-associated T-cell lymphoma",
"aggregation": "instance of dataset",
"identifier": {
"identifier": "E-GEOD-70652"
},
"refinement": "raw",
"keywords": [
{
"value": "functional genomics"
}
],
"availability": "available",
"types": [
{
"value": "gene expression"
}
],
"creators": [
{
"value": ""
{
"date": "20160305T000000+0000",
"type": {
"value": "modified"
}
]
}
],
"description": "Type II Enteropathy-associated T-cell lymphoma (Type II EATL) is an aggressive intestinal T-cell lymphoma with poor prognosis and has not been molecularly profiled. Through targeted amplicon sequencing, we identified a large portion of Type II EATL samples that harbor mutations in the STAT5B, JAK3 and GNAI2 genes. Here we performed gene expression profiling on four Type II EATL samples in order to better characterize this disease. As Type II EATL is suggested to arise from CD8+ IELs, we integrated our data with publicly available profile of CD8\u03b1\u03b1 and CD8\u03b1\u03b2 T-cells from healthy donors (GSE33374). Gene expression profiling independently demonstrated strong enrichment of several aspects of GPCR and JAK-STAT signaling pathways. Moreover, an significant association was identified with genes containing STAT5B binding sites in their promoters. Microarray gene expression profiling was performed on 4 Type II Enteropathy-associated T-cell lymphoma and a combination of unsupervised and supervised clustering was performed to determine any differentially activated pathways between samples with tumor and healthy human CD161++CD8aa and CD161++CD8ab T cells (found under accession number GSE33374)",
"privacy": "not applicable",
"title": "Gene expression profiling of Type II Enteropathy-associated T-cell lymphoma",
"aggregation": "instance of dataset",
"identifier": {
"identifier": "E-GEOD-70652"
},
"refinement": "raw",
"keywords": [
{
"value": "functional genomics"
}
],
"availability": "available",
"types": [
{
"value": "gene expression"
}
],
"creators": [
{
}
],
"isAbout": [
{
"name": {
"value": "Homo sapiens"
}
"name": "Homo sapiens"
}
]
}}
}
6 changes: 5 additions & 1 deletion tests/test_dats_model.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,11 @@ def test_validate_dataset_9(self):

def test_validate_instance(self):
folder_path = os.path.join(self.path, "ICPSR-Dimensions")
self.assertTrue(dats_model.validate_instance(folder_path, "Dimension-33581-0001-AQ5.json", "dimension_schema.json", 0) )
self.assertTrue(dats_model.validate_instance(folder_path, "Dimension-33581-0001-AQ5.json", "dimension_schema.json", 1) )

def test_validate_instance(self):
folder_path = os.path.join(self.path, "datamed")
self.assertTrue(dats_model.validate_dataset(folder_path, "E-GEOD-70652-dats.json", 1))



Expand Down

0 comments on commit ebbd22a

Please sign in to comment.