peak indexing eQTL, added ibed file format, BTO ontology, ren-lab-int…

…ernal viweing group

checkfiles/checkfiles.py

@@ -174,6 +174,7 @@ def check_format(encValData, job, path):
         ('wig', None): None,
         ('hdf5', None): None,
         ('hic', None): None,
+        ('ibed', None): None,
         ('gff', None): None,
         ('vcf', None): None,
         ('btr', None): None

src/encoded/audit/ontology_data.py

@@ -2,7 +2,7 @@
     'tissue': ['UBERON'],
     'whole organisms': ['UBERON'],
     'primary cell': ['CL'],
-    'cell line': ['CL'],
+    'cell line': ['CL', 'BTO'],
     'stem cell': ['EFO', 'CL'],
     'immortalized cell line': ['EFO'],
     'in vitro differentiated cells': ['CL', 'EFO'],

src/encoded/peak_indexer.py

@@ -43,7 +43,10 @@
     },
     'chromatin state': {
         'file_type': ['bed bed3+', 'bed bed9']
-    }
+    },
+    'eQTL': {
+        'file_type': ['bed bed3+']
+        }
 }
 
 # Species and references being indexed
@@ -121,7 +124,7 @@ def get_annotation_type(accession, request):
 
 
 def all_bed_file_uuids(request):
-    stmt = text("select distinct(resources.rid) from resources, propsheets where resources.rid = propsheets.rid and resources.item_type='file' and propsheets.properties->>'file_format' = 'bed';")
+    stmt = text("select distinct(resources.rid) from resources, propsheets where resources.rid = propsheets.rid and resources.item_type='file' and propsheets.properties->>'file_format' = 'bed' and properties->>'status' = 'released';")
     connection = request.registry[DBSESSION].connection()
     uuids = connection.execute(stmt)
     return [str(item[0]) for item in uuids]
@@ -145,8 +148,8 @@ def index_peaks(uuid, request):
     if 'File' not in context['@type'] or 'dataset' not in context:
         return
 
-    # if 'status' not in context or context['status'] != 'released':
-    #    return
+    if 'status' not in context or context['status'] != 'released':
+        return
 
     # Index human data for now
     if assembly not in _ASSEMBLIES:

src/encoded/schemas/antibody_characterization.json

@@ -181,7 +181,7 @@
                         "description": "Ontology identifier describing biosample.",
                         "comment": "NTR is a new term request identifier provided by the DCC.",
                         "type": "string",
-                        "pattern": "^(UBERON|EFO|CL|NTR|FBbt|WBbt):[0-9]{2,8}$"
+                        "pattern": "^(UBERON|EFO|CL|BTO|NTR|FBbt|WBbt):[0-9]{2,8}$"
                     },
                     "biosample_term_name": {
                         "title": "Ontology term",

src/encoded/schemas/award.json

@@ -110,6 +110,7 @@
                 "GGR",
 		"AMP",
 		"gaulton-lab-internal",
+		"ren-lab-internal",
 		"reviwer",
                 "REMC",
                 "community"

src/encoded/schemas/file.json

@@ -338,6 +338,7 @@
                         "gtf",
                         "hdf5",
                         "hic",
+			"ibed",
                         "idat",
                         "rcc",
                         "CEL",
@@ -1162,14 +1163,15 @@
         "gff": ".gff.gz",
         "gtf": ".gtf.gz",
         "hic": ".hic",
+	"ibed": ".ibed",
         "hdf5": ".h5",
         "idat": ".idat",
         "PWM":".pwm",
         "rcc": ".rcc",
         "sra": ".sra",
         "tagAlign": ".tagAlign.gz",
         "tar": ".tar.gz",
-        "tsv": ".tsv",
+        "tsv": ".tsv.gz",
         "csv": ".csv",
         "vcf": ".vcf.gz",
         "wig": ".wig.gz",

src/encoded/schemas/mixins.json

@@ -221,7 +221,7 @@
             "description": "Ontology identifier describing biosample.",
             "comment": "NTR is a new term request identifier provided by the DCC.",
             "type": "string",
-            "pattern": "^(UBERON|EFO|CL|NTR|FBbt|WBbt):[0-9]{2,8}$"
+            "pattern": "^(UBERON|BTO|EFO|CL|NTR|FBbt|WBbt):[0-9]{2,8}$"
         },
         "biosample_term_name": {
             "title": "Ontology term",

src/encoded/schemas/namespaces.json

@@ -20,6 +20,7 @@
     "PMID": "https://www.ncbi.nlm.nih.gov/pubmed/?term=",
     "PMCID": "https://www.ncbi.nlm.nih.gov/pmc/articles/",
     "doi": "http://dx.doi.org/doi:",
+    "BTO": "http://purl.obolibrary.org/obo/BTO_",
     "EFO": "http://www.ebi.ac.uk/efo/EFO_",
     "CL": "http://purl.obolibrary.org/obo/CL_",
     "UBERON": "http://purl.obolibrary.org/obo/UBERON_",

src/encoded/schemas/user.json

@@ -79,6 +79,7 @@
                     "REMC",
 		    "AMP",
 		    "gaulton-lab-internal",
+		    "ren-lab-internal",
 		    "reviwer",
                     "community"
                 ]

src/encoded/static/components/biosample.js

@@ -482,6 +482,7 @@ var BiosampleTermId = createReactClass({
     // Specific term IDs are appended to these after converting ':' to '_'.
     urlMap: {
         'EFO': 'http://www.ebi.ac.uk/efo/',
+	'BTO': 'http://www.ontobee.org/ontology/BTO?iri=http://purl.obolibrary.org/obo/',
         'UBERON': 'http://www.ontobee.org/ontology/UBERON?iri=http://purl.obolibrary.org/obo/',
         'CL': 'http://www.ontobee.org/ontology/CL?iri=http://purl.obolibrary.org/obo/'
     },

src/encoded/types/dataset.py

@@ -38,6 +38,7 @@ def calculate_assembly(request, files_list, status):
     viewable_file_formats = ['bigWig',
                              'bigBed',
                              'hic',
+                             'ibed',
                              'long range chromatin interactions',
                              'narrowPeak',
                              'broadPeak',