Merge branch 'testing' of github.com:genenetwork/genenetwork2 into testing

7 files changed, 66 insertions, 56 deletions

diff --git a/wqflask/base/GeneralObject.py b/wqflask/base/GeneralObject.py
index 249195e2..ce8e60b8 100644
--- a/wqflask/base/GeneralObject.py
+++ b/wqflask/base/GeneralObject.py
@@ -62,5 +62,5 @@ class GeneralObject:
         return s
 
     def __eq__(self, other):
-        return (len(list(self.__dict__.keys())) ==
-                len(list(other.__dict__.keys())))
+        return (len(list(self.__dict__.keys()))
+                == len(list(other.__dict__.keys())))
diff --git a/wqflask/base/data_set.py b/wqflask/base/data_set.py
index 3183363b..e20f2f98 100644
--- a/wqflask/base/data_set.py
+++ b/wqflask/base/data_set.py
@@ -150,8 +150,8 @@ class DatasetType:
                             "FROM PublishFreeze, InbredSet "
                             "WHERE InbredSet.Name = '%s' AND "
                             "PublishFreeze.InbredSetId = InbredSet.Id"),
-            'geno':  ("SELECT GenoFreeze.Id FROM GenoFreeze WHERE "
-                      "GenoFreeze.Name = \"%s\" ")
+            'geno': ("SELECT GenoFreeze.Id FROM GenoFreeze WHERE "
+                     "GenoFreeze.Name = \"%s\" ")
         }
 
         dataset_name_mapping = {
@@ -168,7 +168,8 @@ class DatasetType:
         results = g.db.execute(sql_query_mapping[t] % group_name).fetchone()
         if results:
             self.datasets[name] = dataset_name_mapping[t]
-            self.redis_instance.set("dataset_structure", json.dumps(self.datasets))
+            self.redis_instance.set(
+                "dataset_structure", json.dumps(self.datasets))
             return True
         return None
 
@@ -215,7 +216,7 @@ def create_datasets_list():
 
         if USE_REDIS:
             r.set(key, pickle.dumps(datasets, pickle.HIGHEST_PROTOCOL))
-            r.expire(key, 60*60)
+            r.expire(key, 60 * 60)
 
     return datasets
 
@@ -239,7 +240,8 @@ class Markers:
             for line in bimbam_fh:
                 marker = {}
                 marker['name'] = line.split(delimiter)[0].rstrip()
-                marker['Mb'] = float(line.split(delimiter)[1].rstrip())/1000000
+                marker['Mb'] = float(line.split(delimiter)[
+                                     1].rstrip()) / 1000000
                 marker['chr'] = line.split(delimiter)[2].rstrip()
                 markers.append(marker)
 
@@ -311,7 +313,6 @@ class HumanMarkers(Markers):
                 marker['Mb'] = float(splat[3]) / 1000000
             self.markers.append(marker)
 
-
     def add_pvalues(self, p_values):
         super(HumanMarkers, self).add_pvalues(p_values)
 
@@ -369,8 +370,8 @@ class DatasetGroup:
     def get_markers(self):
         def check_plink_gemma():
             if flat_file_exists("mapping"):
-                MAPPING_PATH = flat_files("mapping")+"/"
-                if os.path.isfile(MAPPING_PATH+self.name+".bed"):
+                MAPPING_PATH = flat_files("mapping") + "/"
+                if os.path.isfile(MAPPING_PATH + self.name + ".bed"):
                     return True
             return False
 
@@ -416,7 +417,7 @@ class DatasetGroup:
         else:
             logger.debug("Cache not hit")
 
-            genotype_fn = locate_ignore_error(self.name+".geno", 'genotype')
+            genotype_fn = locate_ignore_error(self.name + ".geno", 'genotype')
             if genotype_fn:
                 self.samplelist = get_group_samplelists.get_samplelist(
                     "geno", genotype_fn)
@@ -425,7 +426,7 @@ class DatasetGroup:
 
             if USE_REDIS:
                 r.set(key, json.dumps(self.samplelist))
-                r.expire(key, 60*5)
+                r.expire(key, 60 * 5)
 
     def all_samples_ordered(self):
         result = []
@@ -531,7 +532,7 @@ def datasets(group_name, this_group=None):
 
     if USE_REDIS:
         r.set(key, pickle.dumps(dataset_menu, pickle.HIGHEST_PROTOCOL))
-        r.expire(key, 60*5)
+        r.expire(key, 60 * 5)
 
     if this_group != None:
         this_group._datasets = dataset_menu
@@ -622,7 +623,7 @@ class DataSet:
     WHERE ProbeSetFreeze.ProbeFreezeId = ProbeFreeze.Id
     AND ProbeFreeze.TissueId = Tissue.Id
     AND (ProbeSetFreeze.Name = '%s' OR ProbeSetFreeze.FullName = '%s' OR ProbeSetFreeze.ShortName = '%s')
-                """ % (query_args), "/dataset/"+self.name+".json",
+                """ % (query_args), "/dataset/" + self.name + ".json",
                     lambda r: (r["id"], r["name"], r["full_name"],
                                r["short_name"], r["data_scale"], r["tissue"])
                 )
@@ -1031,8 +1032,8 @@ class MrnaAssayDataSet(DataSet):
             else:
                 description_display = this_trait.symbol
 
-            if (len(description_display) > 1 and description_display != 'N/A' and
-                    len(target_string) > 1 and target_string != 'None'):
+            if (len(description_display) > 1 and description_display != 'N/A'
+                    and len(target_string) > 1 and target_string != 'None'):
                 description_display = description_display + '; ' + target_string.strip()
 
             # Save it for the jinja2 template
diff --git a/wqflask/base/mrna_assay_tissue_data.py b/wqflask/base/mrna_assay_tissue_data.py
index 1f8224af..882ae911 100644
--- a/wqflask/base/mrna_assay_tissue_data.py
+++ b/wqflask/base/mrna_assay_tissue_data.py
@@ -9,7 +9,8 @@ from utility.db_tools import escape
 
 
 from utility.logger import getLogger
-logger = getLogger(__name__ )
+logger = getLogger(__name__)
+
 
 class MrnaAssayTissueData:
 
@@ -20,7 +21,7 @@ class MrnaAssayTissueData:
 
         self.data = collections.defaultdict(Bunch)
 
-        query =  '''select t.Symbol, t.GeneId, t.DataId, t.Chr, t.Mb, t.description, t.Probe_Target_Description
+        query = '''select t.Symbol, t.GeneId, t.DataId, t.Chr, t.Mb, t.description, t.Probe_Target_Description
                         from (
                         select Symbol, max(Mean) as maxmean
                         from TissueProbeSetXRef
@@ -31,14 +32,14 @@ class MrnaAssayTissueData:
         # Due to the limit size of TissueProbeSetFreezeId table in DB,
         # performance of inner join is acceptable.MrnaAssayTissueData(gene_symbols=symbol_list)
         if len(gene_symbols) == 0:
-            query +=  '''Symbol!='' and Symbol Is Not Null group by Symbol)
+            query += '''Symbol!='' and Symbol Is Not Null group by Symbol)
                 as x inner join TissueProbeSetXRef as t on t.Symbol = x.Symbol
                 and t.Mean = x.maxmean;
                     '''
         else:
             in_clause = db_tools.create_in_clause(gene_symbols)
 
-            #ZS: This was in the query, not sure why: http://docs.python.org/2/library/string.html?highlight=lower#string.lower
+            # ZS: This was in the query, not sure why: http://docs.python.org/2/library/string.html?highlight=lower#string.lower
             query += ''' Symbol in {} group by Symbol)
                 as x inner join TissueProbeSetXRef as t on t.Symbol = x.Symbol
                 and t.Mean = x.maxmean;
@@ -64,16 +65,16 @@ class MrnaAssayTissueData:
                 self.data[symbol].probe_target_description = result.Probe_Target_Description
 
     ###########################################################################
-    #Input: cursor, symbolList (list), dataIdDict(Dict)
-    #output: symbolValuepairDict (dictionary):one dictionary of Symbol and Value Pair,
+    # Input: cursor, symbolList (list), dataIdDict(Dict)
+    # output: symbolValuepairDict (dictionary):one dictionary of Symbol and Value Pair,
     #        key is symbol, value is one list of expression values of one probeSet;
-    #function: get one dictionary whose key is gene symbol and value is tissue expression data (list type).
-    #Attention! All keys are lower case!
+    # function: get one dictionary whose key is gene symbol and value is tissue expression data (list type).
+    # Attention! All keys are lower case!
     ###########################################################################
 
     def get_symbol_values_pairs(self):
         id_list = [self.data[symbol].data_id for symbol in self.data]
-        
+
         symbol_values_dict = {}
 
         if len(id_list) > 0:
@@ -87,6 +88,7 @@ class MrnaAssayTissueData:
                 if result.Symbol.lower() not in symbol_values_dict:
                     symbol_values_dict[result.Symbol.lower()] = [result.value]
                 else:
-                    symbol_values_dict[result.Symbol.lower()].append(result.value)
+                    symbol_values_dict[result.Symbol.lower()].append(
+                        result.value)
 
         return symbol_values_dict
diff --git a/wqflask/base/species.py b/wqflask/base/species.py
index eae3325a..e3c29916 100644
--- a/wqflask/base/species.py
+++ b/wqflask/base/species.py
@@ -4,7 +4,8 @@ from flask import Flask, g
 
 
 from utility.logger import getLogger
-logger = getLogger(__name__ )
+logger = getLogger(__name__)
+
 
 class TheSpecies:
     def __init__(self, dataset=None, species_name=None):
@@ -15,6 +16,7 @@ class TheSpecies:
             self.dataset = dataset
             self.chromosomes = Chromosomes(dataset=self.dataset)
 
+
 class IndChromosome:
     def __init__(self, name, length):
         self.name = name
@@ -25,6 +27,7 @@ class IndChromosome:
         """Chromosome length in megabases"""
         return self.length / 1000000
 
+
 class Chromosomes:
     def __init__(self, dataset=None, species=None):
         self.chromosomes = collections.OrderedDict()
@@ -52,4 +55,5 @@ class Chromosomes:
         results = g.db.execute(query).fetchall()
 
         for item in results:
-            self.chromosomes[item.OrderId] = IndChromosome(item.Name, item.Length)
+            self.chromosomes[item.OrderId] = IndChromosome(
+                item.Name, item.Length)
diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py
index 5574128d..d09cfd40 100644
--- a/wqflask/base/trait.py
+++ b/wqflask/base/trait.py
@@ -479,9 +479,9 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False):
             else:
                 description_display = trait.symbol
 
-            if (str(description_display or "") != "" and
-                description_display != 'N/A' and
-                    str(target_string or "") != "" and target_string != 'None'):
+            if (str(description_display or "") != ""
+                and description_display != 'N/A'
+                    and str(target_string or "") != "" and target_string != 'None'):
                 description_display = description_display + '; ' + target_string.strip()
 
             # Save it for the jinja2 template
@@ -575,6 +575,6 @@ def retrieve_trait_info(trait, dataset, get_qtl_info=False):
                 if str(trait.lrs or "") != "":
                     trait.LRS_score_repr = LRS_score_repr = '%3.1f' % trait.lrs
     else:
-        raise KeyError(repr(trait.name) +
-                       ' information is not found in the database.')
+        raise KeyError(repr(trait.name)
+                       + ' information is not found in the database.')
     return trait
diff --git a/wqflask/base/webqtlCaseData.py b/wqflask/base/webqtlCaseData.py
index aa55470f..25b6cb8a 100644
--- a/wqflask/base/webqtlCaseData.py
+++ b/wqflask/base/webqtlCaseData.py
@@ -28,17 +28,20 @@ import utility.tools
 
 utility.tools.show_settings()
 
+
 class webqtlCaseData:
     """one case data in one trait"""
 
     def __init__(self, name, value=None, variance=None, num_cases=None, name2=None):
         self.name = name
-        self.name2 = name2                  # Other name (for traits like BXD65a)
+        # Other name (for traits like BXD65a)
+        self.name2 = name2
         self.value = value                  # Trait Value
         self.variance = variance            # Trait Variance
         self.num_cases = num_cases          # Number of individuals/cases
         self.extra_attributes = None
-        self.this_id = None   # Set a sane default (can't be just "id" cause that's a reserved word)
+        # Set a sane default (can't be just "id" cause that's a reserved word)
+        self.this_id = None
         self.outlier = None   # Not set to True/False until later
 
     def __repr__(self):
@@ -78,4 +81,4 @@ class webqtlCaseData:
     def display_num_cases(self):
         if self.num_cases is not None:
             return "%s" % self.num_cases
-        return "x"
\ No newline at end of file
+        return "x"
diff --git a/wqflask/base/webqtlConfig.py b/wqflask/base/webqtlConfig.py
index bb8704a5..39947158 100644
--- a/wqflask/base/webqtlConfig.py
+++ b/wqflask/base/webqtlConfig.py
@@ -1,4 +1,4 @@
-#########################################'
+# '
 #      Environment Variables - public
 #
 # Note: much of this needs to handled by the settings/environment
@@ -10,35 +10,35 @@
 
 from utility.tools import valid_path, mk_dir, assert_dir, assert_writable_dir, flat_files, TEMPDIR
 
-#Debug Level
-#1 for debug, mod python will reload import each time
+# Debug Level
+# 1 for debug, mod python will reload import each time
 DEBUG = 1
 
-#USER privilege
-USERDICT = {'guest':1,'user':2, 'admin':3, 'root':4}
+# USER privilege
+USERDICT = {'guest': 1, 'user': 2, 'admin': 3, 'root': 4}
 
-#Set privileges
+# Set privileges
 SUPER_PRIVILEGES = {'data': 'edit', 'metadata': 'edit', 'admin': 'edit-admins'}
 DEFAULT_PRIVILEGES = {'data': 'view', 'metadata': 'view', 'admin': 'not-admin'}
 
-#minimum number of informative strains
+# minimum number of informative strains
 KMININFORMATIVE = 5
 
-#Daily download limit from one IP
+# Daily download limit from one IP
 DAILYMAXIMUM = 1000
 
-#maximum LRS value
+# maximum LRS value
 MAXLRS = 460.0
 
-#MINIMUM Database public value
+# MINIMUM Database public value
 PUBLICTHRESH = 0
 
-#EXTERNAL LINK ADDRESSES
+# EXTERNAL LINK ADDRESSES
 PUBMEDLINK_URL = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=%s&dopt=Abstract"
 UCSC_BLAT = 'http://genome.ucsc.edu/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s'
 UTHSC_BLAT = 'http://ucscbrowser.genenetwork.org/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s'
 UTHSC_BLAT2 = 'http://ucscbrowserbeta.genenetwork.org/cgi-bin/hgBlat?org=%s&db=%s&type=0&sort=0&output=0&userSeq=%s'
-GENOMEBROWSER_URL="https://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&position=%s"
+GENOMEBROWSER_URL = "https://genome.ucsc.edu/cgi-bin/hgTracks?db=%s&position=%s"
 NCBI_LOCUSID = "http://www.ncbi.nlm.nih.gov/gene?cmd=Retrieve&dopt=Graphics&list_uids=%s"
 GENBANK_ID = "http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=Nucleotide&cmd=search&doptcmdl=DocSum&term=%s"
 OMIM_ID = "http://www.ncbi.nlm.nih.gov/omim/%s"
@@ -56,7 +56,7 @@ GEMMA_URL = "http://www.chibi.ubc.ca/Gemma/gene/showGene.html?ncbiid=%s"
 ABA_URL = "http://mouse.brain-map.org/search/show?search_type=gene&search_term=%s"
 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"
+ENSEMBLETRANSCRIPT_URL = "http://useast.ensembl.org/Mus_musculus/Transcript/Idhistory?t=%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"
@@ -71,13 +71,13 @@ RRID_RAT_URL = "https://rgd.mcw.edu/rgdweb/report/strain/main.html?id=%s"
 # want to reach this base dir
 assert_writable_dir(TEMPDIR)
 
-TMPDIR               = mk_dir(TEMPDIR+'/gn2/')
+TMPDIR = mk_dir(TEMPDIR + '/gn2/')
 assert_writable_dir(TMPDIR)
 
-CACHEDIR             = mk_dir(TMPDIR+'/cache/')
+CACHEDIR = mk_dir(TMPDIR + '/cache/')
 # We can no longer write into the git tree:
-GENERATED_IMAGE_DIR  = mk_dir(TMPDIR+'generated/')
-GENERATED_TEXT_DIR   = mk_dir(TMPDIR+'generated_text/')
+GENERATED_IMAGE_DIR = mk_dir(TMPDIR + 'generated/')
+GENERATED_TEXT_DIR = mk_dir(TMPDIR + 'generated_text/')
 
 # Make sure we have permissions to access these
 assert_writable_dir(CACHEDIR)
@@ -85,12 +85,12 @@ assert_writable_dir(GENERATED_IMAGE_DIR)
 assert_writable_dir(GENERATED_TEXT_DIR)
 
 # Flat file directories
-GENODIR              = flat_files('genotype')+'/'
+GENODIR = flat_files('genotype') + '/'
 assert_dir(GENODIR)
 # assert_dir(GENODIR+'bimbam') # for gemma
 
 # JSON genotypes are OBSOLETE
-JSON_GENODIR         = flat_files('genotype/json')+'/'
+JSON_GENODIR = flat_files('genotype/json') + '/'
 if not valid_path(JSON_GENODIR):
     # fall back on old location (move the dir, FIXME)
     JSON_GENODIR = flat_files('json')
@@ -98,4 +98,4 @@ if not valid_path(JSON_GENODIR):
 # Are we using the following...?
 PORTADDR = "http://50.16.251.170"
 INFOPAGEHREF = '/dbdoc/%s.html'
-CGIDIR = '/webqtl/' #XZ: The variable name 'CGIDIR' should be changed to 'PYTHONDIR'
+CGIDIR = '/webqtl/'  # XZ: The variable name 'CGIDIR' should be changed to 'PYTHONDIR'