Merge branch 'testing' into 360_update_htmlgen

3 files changed, 70 insertions, 26 deletions

diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py
index b324ac74..41de8492 100644
--- a/wqflask/base/data_set.py
+++ b/wqflask/base/data_set.py
@@ -46,6 +46,8 @@ from utility import chunks
 from utility import gen_geno_ob
 from utility.tools import locate, locate_ignore_error, flat_files
 
+from wqflask.api import gen_menu
+
 from maintenance import get_group_samplelists
 
 from MySQLdb import escape_string as escape
@@ -92,7 +94,7 @@ Publish or ProbeSet. E.g.
         """
         self.datasets = {}
         if USE_GN_SERVER:
-            data = menu_main()
+            data = gen_menu.gen_dropdown_json()
         else:
             file_name = "wqflask/static/new/javascript/dataset_menu_structure.json"
             with open(file_name, 'r') as fh:
@@ -289,7 +291,6 @@ class DatasetGroup(object):
         self.parlist = None
         self.get_f1_parent_strains()
 
-        self.accession_id = self.get_accession_id()
         self.mapping_id, self.mapping_names = self.get_mapping_methods()
 
         self.species = webqtlDatabaseFunction.retrieve_species(self.name)
@@ -299,20 +300,6 @@ class DatasetGroup(object):
         self._datasets = None
         self.genofile = None
 
-    def get_accession_id(self):
-        results = g.db.execute("""select InfoFiles.GN_AccesionId from InfoFiles, PublishFreeze, InbredSet where
-                    InbredSet.Name = %s and
-                    PublishFreeze.InbredSetId = InbredSet.Id and
-                    InfoFiles.InfoPageName = PublishFreeze.Name and
-                    PublishFreeze.public > 0 and
-                    PublishFreeze.confidentiality < 1 order by
-                    PublishFreeze.CreateTime desc""", (self.name)).fetchone()
-
-        if results != None:
-            return str(results[0])
-        else:
-            return "None"
-
     def get_mapping_methods(self):
 
         mapping_id = g.db.execute("select MappingMethodId from InbredSet where Name= '%s'" % self.name).fetchone()[0]
@@ -384,7 +371,7 @@ class DatasetGroup(object):
         [result.extend(l) for l in lists if l]
         return result
 
-    def read_genotype_file(self):
+    def read_genotype_file(self, use_reaper=False):
         '''Read genotype from .geno file instead of database'''
         #genotype_1 is Dataset Object without parents and f1
         #genotype_2 is Dataset Object with parents and f1 (not for intercross)
@@ -396,9 +383,12 @@ class DatasetGroup(object):
             full_filename = str(locate(self.genofile, 'genotype'))
         else:
             full_filename = str(locate(self.name + '.geno', 'genotype'))
-        #genotype_1.read(full_filename)
 
-        genotype_1 = gen_geno_ob.genotype(full_filename)
+        if use_reaper:
+            genotype_1 = reaper.Dataset()
+            genotype_1.read(full_filename)
+        else:
+            genotype_1 = gen_geno_ob.genotype(full_filename)
 
         if genotype_1.type == "group" and self.parlist:
             genotype_2 = genotype_1.add(Mat=self.parlist[0], Pat=self.parlist[1])       #, F1=_f1)
@@ -445,7 +435,7 @@ def datasets(group_name, this_group = None):
             and InbredSet.Name like %s
             and ProbeSetFreeze.public > %s
             and ProbeSetFreeze.confidentiality < 1
-          ORDER BY Tissue.Name)
+          ORDER BY Tissue.Name, ProbeSetFreeze.OrderList DESC)
         ''' % (group_name, webqtlConfig.PUBLICTHRESH,
               group_name, webqtlConfig.PUBLICTHRESH,
               "'" + group_name + "'", webqtlConfig.PUBLICTHRESH))
@@ -507,6 +497,7 @@ class DataSet(object):
             self.check_confidentiality()
             self.retrieve_other_names()
             self.group = DatasetGroup(self)   # sets self.group and self.group_id and gets genotype
+            self.accession_id = self.get_accession_id()
         if get_samplelist == True:
              self.group.get_samplelist()
         self.species = species.TheSpecies(self)
@@ -521,6 +512,31 @@ class DataSet(object):
     def riset():
         Weve_Renamed_This_As_Group
 
+    def get_accession_id(self):
+        if self.type == "Publish":
+            results = g.db.execute("""select InfoFiles.GN_AccesionId from InfoFiles, PublishFreeze, InbredSet where
+                        InbredSet.Name = %s and
+                        PublishFreeze.InbredSetId = InbredSet.Id and
+                        InfoFiles.InfoPageName = PublishFreeze.Name and
+                        PublishFreeze.public > 0 and
+                        PublishFreeze.confidentiality < 1 order by
+                        PublishFreeze.CreateTime desc""", (self.group.name)).fetchone()
+        elif self.type == "Geno":
+            results = g.db.execute("""select InfoFiles.GN_AccesionId from InfoFiles, GenoFreeze, InbredSet where
+                        InbredSet.Name = %s and
+                        GenoFreeze.InbredSetId = InbredSet.Id and
+                        InfoFiles.InfoPageName = GenoFreeze.ShortName and
+                        GenoFreeze.public > 0 and
+                        GenoFreeze.confidentiality < 1 order by
+                        GenoFreeze.CreateTime desc""", (self.group.name)).fetchone()
+        else:
+            results = None
+
+        if results != None:
+            return str(results[0])
+        else:
+            return "None"
+
     def retrieve_other_names(self):
         """This method fetches the the dataset names in search_result.
 
diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py
index 6fecf725..58169b5c 100644
--- a/wqflask/base/trait.py
+++ b/wqflask/base/trait.py
@@ -3,6 +3,7 @@ from __future__ import absolute_import, division, print_function
 import string
 import resource
 import codecs
+import requests
 
 import redis
 Redis = redis.StrictRedis()
@@ -120,11 +121,34 @@ class GeneralTrait(object):
     @property
     def alias_fmt(self):
         '''Return a text formatted alias'''
+
+        alias = 'Not available'
         if self.alias:
             alias = string.replace(self.alias, ";", " ")
             alias = string.join(string.split(alias), ", ")
-        else:
-            alias = 'Not available'
+
+        return alias
+
+    @property
+    def wikidata_alias_fmt(self):
+        '''Return a text formatted alias'''
+
+        alias = 'Not available'
+        if self.symbol:
+            human_response = requests.get("http://gn2.genenetwork.org/gn3/gene/aliases/" + self.symbol.upper())
+            mouse_response = requests.get("http://gn2.genenetwork.org/gn3/gene/aliases/" + self.symbol.capitalize())
+            other_response = requests.get("http://gn2.genenetwork.org/gn3/gene/aliases/" + self.symbol.lower())
+            alias_list = json.loads(human_response.content) + json.loads(mouse_response.content) + json.loads(other_response.content)
+
+            filtered_aliases = []
+            seen = set()
+            for item in alias_list:
+                if item in seen:
+                    continue
+                else:
+                    filtered_aliases.append(item)
+                    seen.add(item)
+            alias = "; ".join(filtered_aliases)
 
         return alias
 
@@ -396,8 +420,10 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False):
         #XZ: assign SQL query result to trait attributes.
         for i, field in enumerate(dataset.display_fields):
             holder = trait_info[i]
-            if isinstance(trait_info[i], basestring):
-                holder = unicode(trait_info[i], "utf-8", "ignore")
+            # if isinstance(trait_info[i], basestring):
+            #     logger.debug("HOLDER:", holder)
+            #     logger.debug("HOLDER2:", holder.decode(encoding='latin1'))
+            #     holder = unicode(trait_info[i], "utf-8", "ignore")
             setattr(trait, field, holder)
 
         if dataset.type == 'Publish':
diff --git a/wqflask/base/webqtlConfig.py b/wqflask/base/webqtlConfig.py
index b14cc4b0..0b884815 100644
--- a/wqflask/base/webqtlConfig.py
+++ b/wqflask/base/webqtlConfig.py
@@ -43,6 +43,7 @@ HOMOLOGENE_ID = "http://www.ncbi.nlm.nih.gov/homologene/?term=%s"
 GENOTATION_URL = "http://www.genotation.org/Getd2g.pl?gene_list=%s"
 GTEX_URL = "https://www.gtexportal.org/home/gene/%s"
 GENEBRIDGE_URL = "https://www.systems-genetics.org/modules_by_gene/%s?organism=%s"
+GENEMANIA_URL = "https://genemania.org/search/%s/%s"
 UCSC_REFSEQ = "http://genome.cse.ucsc.edu/cgi-bin/hgTracks?db=%s&hgg_gene=%s&hgg_chrom=chr%s&hgg_start=%s&hgg_end=%s"
 BIOGPS_URL = "http://biogps.org/?org=%s#goto=genereport&id=%s"
 STRING_URL = "http://string-db.org/newstring_cgi/show_network_section.pl?identifier=%s"
@@ -52,7 +53,9 @@ ABA_URL = "http://mouse.brain-map.org/search/show?search_type=gene&search_term=%
 EBIGWAS_URL = "https://www.ebi.ac.uk/gwas/search?query=%s"
 WIKI_PI_URL = "http://severus.dbmi.pitt.edu/wiki-pi/index.php/search?q=%s"
 ENSEMBLETRANSCRIPT_URL="http://useast.ensembl.org/Mus_musculus/Transcript/Idhistory?t=%s"
-DBSNP = 'http://www.ncbi.nlm.nih.gov/SNP/snp_ref.cgi?type=rs&rs=%s'
+DBSNP = 'http://ensembl.org/Mus_musculus/Variation/Population?v=%s'
+PROTEIN_ATLAS_URL = "http://www.proteinatlas.org/search/%s"
+OPEN_TARGETS_URL = "https://genetics.opentargets.org/gene/%s"
 
 # Temporary storage (note that this TMPDIR can be set as an
 # environment variable - use utility.tools.TEMPDIR when you
@@ -87,4 +90,3 @@ if not valid_path(JSON_GENODIR):
 PORTADDR = "http://50.16.251.170"
 INFOPAGEHREF = '/dbdoc/%s.html'
 CGIDIR = '/webqtl/' #XZ: The variable name 'CGIDIR' should be changed to 'PYTHONDIR'
-SCRIPTFILE = 'main.py'