On branch master

4 files changed, 49 insertions, 26 deletions

diff --git a/wqflask/maintenance/dataset/datastructure.py b/wqflask/maintenance/dataset/datastructure.py
index 73e1c0d8..f94009f5 100644
--- a/wqflask/maintenance/dataset/datastructure.py
+++ b/wqflask/maintenance/dataset/datastructure.py
@@ -1,11 +1,7 @@
-import sys
-sys.path.append('.')
-sys.path.append('..')
-
-from utilities import db
+import utilities
 
 def get_probesetfreeze(inbredsetid):
-    cursor = db.get_cursor()
+    cursor = utilities.get_cursor()
     sql = """
         SELECT ProbeSetFreeze.`Id`, ProbeSetFreeze.`Name`, ProbeSetFreeze.`FullName`
         FROM ProbeSetFreeze, ProbeFreeze
@@ -14,4 +10,14 @@ def get_probesetfreeze(inbredsetid):
         """
     cursor.execute(sql, (inbredsetid))
     return cursor.fetchall()
+
+def get_probesetfreeze(probesetfreezeid):
+    cursor = utilities.get_cursor()
+    sql = """
+        SELECT ProbeSetFreeze.`Id`, ProbeSetFreeze.`Name`, ProbeSetFreeze.`FullName`
+        FROM ProbeSetFreeze
+        WHERE ProbeSetFreeze.`Id`=%s
+        """
+    cursor.execute(sql, (probesetfreezeid))
+    return cursor.fetchone()
     
\ No newline at end of file
diff --git a/wqflask/maintenance/dataset/phenotypes.py b/wqflask/maintenance/dataset/phenotypes.py
index c31ad0e3..1f58d9a8 100644
--- a/wqflask/maintenance/dataset/phenotypes.py
+++ b/wqflask/maintenance/dataset/phenotypes.py
@@ -1,10 +1,6 @@
 # Author:               Lei Yan
 
 # import
-import sys
-import os
-import re
-import MySQLdb
 
 import utilities
 
@@ -48,10 +44,10 @@ def fetch():
     print "get %d phenotypes" % (len(results))
     for phenotyperow in results:
         publishxrefid = phenotyperow[0]
-        authors = clearspaces(phenotyperow[1])
-        original_description = clearspaces(phenotyperow[2])
-        pre_publication_description = clearspaces(phenotyperow[3])
-        post_publication_description = clearspaces(phenotyperow[4])
+        authors = utilities.clearspaces(phenotyperow[1])
+        original_description = utilities.clearspaces(phenotyperow[2])
+        pre_publication_description = utilities.clearspaces(phenotyperow[3])
+        post_publication_description = utilities.clearspaces(phenotyperow[4])
         phenotypesfile.write("%s\t%s\t%s\t%s\t%s\t" % (publishxrefid, authors, original_description, pre_publication_description, post_publication_description))
         sql = """
             SELECT Strain.Name, PublishData.value
@@ -80,14 +76,6 @@ def fetch():
         phenotypesfile.flush()
     # release
     phenotypesfile.close()
-
-def clearspaces(s):
-    if s:
-        s = re.sub('\s+', ' ', s)
-        s = s.strip()
-        return s
-    else:
-        return None
     
 # main
 if __name__ == "__main__":
diff --git a/wqflask/maintenance/dataset/probesets.py b/wqflask/maintenance/dataset/probesets.py
index 06b9a394..26d794a8 100644
--- a/wqflask/maintenance/dataset/probesets.py
+++ b/wqflask/maintenance/dataset/probesets.py
@@ -1,6 +1,7 @@
 import sys
 
 import utilities
+import datastructure
 import genotypes
 
 def get_probesetxref(probesetfreezeid):
@@ -48,7 +49,7 @@ def get_probesetxref_probesetfreezeid(locus, probesetfreezeid):
 def get_probesetxref_inbredsetid(locus, inbredsetid):
     cursor = utilities.get_cursor()
     sql = """
-        SELECT ProbeSetXRef.`ProbeSetId`, ProbeSetXRef.`mean`, ProbeSetXRef.`LRS`, ProbeSetXRef.`Locus`
+        SELECT ProbeSetXRef.`ProbeSetId`, ProbeSetXRef.`mean`, ProbeSetXRef.`LRS`, ProbeSetXRef.`Locus`, ProbeSetXRef.`ProbeSetFreezeId`
         FROM (ProbeSetXRef, ProbeSetFreeze, ProbeFreeze)
         WHERE ProbeSetXRef.`ProbeSetFreezeId`=ProbeSetFreeze.`Id`
         AND ProbeSetFreeze.`ProbeFreezeId`=ProbeFreeze.`Id`
@@ -63,6 +64,13 @@ def get_normalized_probeset(locus, inbredsetid):
     probesetxrefs = get_probesetxref_inbredsetid(locus, inbredsetid)
     for probesetxref in probesetxrefs:
         normalized_probeset = []
+        #
+        probesetfreezeid = probesetxref[4]
+        probesetfreeze = datastructure.get_probesetfreeze(probesetfreezeid)
+        normalized_probeset.append(probesetfreeze[0])
+        normalized_probeset.append(probesetfreeze[1])
+        normalized_probeset.append(probesetfreeze[2])
+        #
         probesetid = probesetxref[0]
         probeset = get_probeset(probesetid)
         normalized_probeset.append(probeset[1])
@@ -71,13 +79,25 @@ def get_normalized_probeset(locus, inbredsetid):
         normalized_probeset.append(probeset[4])
         normalized_probeset.append(probeset[5])
         normalized_probeset.append(probeset[6])
+        #
         normalized_probeset.append(probesetxref[1])
         normalized_probeset.append(probesetxref[2])
+        #
         locus = probesetxref[3]
         geno = genotypes.get_geno(inbredsetid=inbredsetid, name=locus)
         normalized_probeset.append(geno[2])
         normalized_probeset.append(geno[3])
+        #
         normalized_probesets.append(normalized_probeset)
-    print normalized_probesets[:2]
 
-get_normalized_probeset(locus="rs3663871", inbredsetid=1)
+locus="rs3663871"
+inbredsetid=1
+
+results = get_normalized_probeset(locus=locus, inbredsetid=inbredsetid)
+file = open('probesets_%s.txt' % (locus), 'w+')
+file.write("GN dataset ID\t\n")
+file.flush()
+for row in results:
+    file.write(row[0])
+    file.flush()
+file.close()
diff --git a/wqflask/maintenance/dataset/utilities.py b/wqflask/maintenance/dataset/utilities.py
index 453ee707..5ffa9047 100644
--- a/wqflask/maintenance/dataset/utilities.py
+++ b/wqflask/maintenance/dataset/utilities.py
@@ -1,4 +1,5 @@
 import MySQLdb
+import re
 
 def get_cursor():
     host = 'localhost'
@@ -7,4 +8,12 @@ def get_cursor():
     db = 'db_webqtl'
     con = MySQLdb.Connect(db=db, host=host, user=user, passwd=passwd)
     cursor = con.cursor()
-    return cursor
\ No newline at end of file
+    return cursor
+    
+def clearspaces(s):
+    if s:
+        s = re.sub('\s+', ' ', s)
+        s = s.strip()
+        return s
+    else:
+        return None