diff options
Diffstat (limited to 'scripts')
| -rwxr-xr-x | scripts/maintenance/QTL_Reaper_v6.py | 10 | ||||
| -rw-r--r-- | scripts/maintenance/Update_Case_Attributes_MySQL_tab.py | 2 | ||||
| -rwxr-xr-x | scripts/maintenance/delete_genotypes.py | 16 | ||||
| -rwxr-xr-x | scripts/maintenance/delete_phenotypes.py | 14 | ||||
| -rwxr-xr-x | scripts/maintenance/load_genotypes.py | 20 | ||||
| -rwxr-xr-x | scripts/maintenance/load_phenotypes.py | 40 | ||||
| -rwxr-xr-x | scripts/maintenance/readProbeSetMean_v7.py | 76 | ||||
| -rwxr-xr-x | scripts/maintenance/readProbeSetSE_v7.py | 508 |
8 files changed, 342 insertions, 344 deletions
diff --git a/scripts/maintenance/QTL_Reaper_v6.py b/scripts/maintenance/QTL_Reaper_v6.py index e50dbd40..35f2d1a1 100755 --- a/scripts/maintenance/QTL_Reaper_v6.py +++ b/scripts/maintenance/QTL_Reaper_v6.py @@ -7,7 +7,7 @@ import reaper import MySQLdb import time -con = MySQLdb.Connect(db='db_webqtl',user='username',passwd='', host="localhost") +con = MySQLdb.Connect(db='db_webqtl', user='username', passwd='', host="localhost") cursor = con.cursor() genotypeDir = '/gnshare/gn/web/genotypes/' @@ -23,7 +23,7 @@ for item in results: ProbeSetFreezeIds=sys.argv[1:] if ProbeSetFreezeIds: #####convert the Ids to integer - ProbeSetFreezeIds=map(int, ProbeSetFreezeIds) + ProbeSetFreezeIds=list(map(int, ProbeSetFreezeIds)) else: #####get all of the dataset that need be updated @@ -53,7 +53,7 @@ for ProbeSetFreezeId in ProbeSetFreezeIds: #if InbredSetId==12: # InbredSetId=2 - print ProbeSetFreezeId, InbredSets[InbredSetId] + print((ProbeSetFreezeId, InbredSets[InbredSetId])) genotype_1.read(InbredSets[InbredSetId]) locuses = [] @@ -102,7 +102,7 @@ for ProbeSetFreezeId in ProbeSetFreezeIds: kj += 1 if kj%1000==0: - print ProbeSetFreezeId, InbredSets[InbredSetId],kj + print((ProbeSetFreezeId, InbredSets[InbredSetId], kj)) - print ProbeSetFreezeIds + print(ProbeSetFreezeIds) diff --git a/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py b/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py index 0f8602c9..bf796df4 100644 --- a/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py +++ b/scripts/maintenance/Update_Case_Attributes_MySQL_tab.py @@ -24,4 +24,4 @@ for row in csv_data: #close the connection to the database. mydb.commit() cursor.close() -print "Done" \ No newline at end of file +print("Done") \ No newline at end of file diff --git a/scripts/maintenance/delete_genotypes.py b/scripts/maintenance/delete_genotypes.py index fa693f0f..b7f83758 100755 --- a/scripts/maintenance/delete_genotypes.py +++ b/scripts/maintenance/delete_genotypes.py @@ -8,26 +8,26 @@ import genotypes def main(argv): # config config = utilities.get_config(argv[1]) - print "config:" + print("config:") for item in config.items('config'): - print "\t%s" % (str(item)) + print(("\t%s" % (str(item)))) # var - print "variable:" + print("variable:") inbredsetid = config.get('config', 'inbredsetid') - print "\tinbredsetid: %s" % inbredsetid + print(("\tinbredsetid: %s" % inbredsetid)) # datafile datafile = open(config.get('config', 'datafile'), 'r') datafile = csv.reader(datafile, delimiter='\t', quotechar='"') - datafile.next() + next(datafile) delrowcount = 0 for row in datafile: if len(row) == 0: continue genoname = row[0] delrowcount += genotypes.delete(genoname, inbredsetid) - print "deleted %d genotypes" % (delrowcount) + print(("deleted %d genotypes" % (delrowcount))) if __name__ == "__main__": - print "command line arguments:\n\t%s" % sys.argv + print(("command line arguments:\n\t%s" % sys.argv)) main(sys.argv) - print "exit successfully" + print("exit successfully") diff --git a/scripts/maintenance/delete_phenotypes.py b/scripts/maintenance/delete_phenotypes.py index 326c466e..60dbec61 100755 --- a/scripts/maintenance/delete_phenotypes.py +++ b/scripts/maintenance/delete_phenotypes.py @@ -8,13 +8,13 @@ import phenotypes def main(argv): # config config = utilities.get_config(argv[1]) - print "config:" + print("config:") for item in config.items('config'): - print "\t%s" % (str(item)) + print(("\t%s" % (str(item)))) # var - print "variable:" + print("variable:") inbredsetid = config.get('config', 'inbredsetid') - print "\tinbredsetid: %s" % inbredsetid + print(("\tinbredsetid: %s" % inbredsetid)) # datafile datafile = open(config.get('config', 'datafile'), 'r') datafile = csv.reader(datafile, delimiter='\t', quotechar='"') @@ -27,9 +27,9 @@ def main(argv): except: continue delrowcount += phenotypes.delete(publishxrefid=publishxrefid, inbredsetid=inbredsetid) - print "deleted %d phenotypes" % (delrowcount) + print(("deleted %d phenotypes" % (delrowcount))) if __name__ == "__main__": - print "command line arguments:\n\t%s" % sys.argv + print(("command line arguments:\n\t%s" % sys.argv)) main(sys.argv) - print "exit successfully" + print("exit successfully") diff --git a/scripts/maintenance/load_genotypes.py b/scripts/maintenance/load_genotypes.py index 338483f4..51278d48 100755 --- a/scripts/maintenance/load_genotypes.py +++ b/scripts/maintenance/load_genotypes.py @@ -8,7 +8,7 @@ def main(argv): config = utilities.get_config(argv[1]) print("config file:") for item in config.items('config'): - print("\t%s" % str(item)) + print(("\t%s" % str(item))) parse_genofile(config, fetch_parameters(config)) def fetch_parameters(config): @@ -19,8 +19,8 @@ def fetch_parameters(config): config_dic['dataid'] = datastructure.get_nextdataid_genotype() config_dic['genofile'] = config.get('config', 'genofile') print("config dictionary:") - for k, v in config_dic.items(): - print("\t%s: %s" % (k, v)) + for k, v in list(config_dic.items()): + print(("\t%s: %s" % (k, v))) return config_dic def parse_genofile(config, config_dic): @@ -42,10 +42,10 @@ def parse_genofile(config, config_dic): if line.lower().startswith("chr"): # print("geno file meta dictionary:") - for k, v in meta_dic.items(): - print("\t%s: %s" % (k, v)) + for k, v in list(meta_dic.items()): + print(("\t%s: %s" % (k, v))) # - print("geno file head:\n\t%s" % line) + print(("geno file head:\n\t%s" % line)) strainnames = line.split()[4:] config_dic['strains'] = datastructure.get_strains_bynames(inbredsetid=config_dic['inbredsetid'], strainnames=strainnames, updatestrainxref="yes") continue @@ -81,7 +81,7 @@ def check_or_insert_geno(config_dic, marker_dic): result = cursor.fetchone() if result: genoid = result[0] - print("get geno record: %d" % genoid) + print(("get geno record: %d" % genoid)) else: sql = """ INSERT INTO Geno @@ -95,7 +95,7 @@ def check_or_insert_geno(config_dic, marker_dic): cursor.execute(sql, (config_dic['speciesid'], marker_dic['locus'], marker_dic['locus'], marker_dic['chromosome'], marker_dic['mb'])) rowcount = cursor.rowcount genoid = con.insert_id() - print("INSERT INTO Geno: %d record: %d" % (rowcount, genoid)) + print(("INSERT INTO Geno: %d record: %d" % (rowcount, genoid))) return genoid def check_genoxref(config_dic, marker_dic): @@ -146,9 +146,9 @@ def insert_genoxref(config_dic, marker_dic): """ cursor.execute(sql, (config_dic['genofreezeid'], marker_dic['genoid'], config_dic['dataid'], marker_dic['cm'], 'N')) rowcount = cursor.rowcount - print("INSERT INTO GenoXRef: %d record" % (rowcount)) + print(("INSERT INTO GenoXRef: %d record" % (rowcount))) if __name__ == "__main__": - print("command line arguments:\n\t%s" % sys.argv) + print(("command line arguments:\n\t%s" % sys.argv)) main(sys.argv) print("exit successfully") diff --git a/scripts/maintenance/load_phenotypes.py b/scripts/maintenance/load_phenotypes.py index c3c6570b..759d2eec 100755 --- a/scripts/maintenance/load_phenotypes.py +++ b/scripts/maintenance/load_phenotypes.py @@ -7,37 +7,37 @@ import datastructure def main(argv): # config config = utilities.get_config(argv[1]) - print "config:" + print("config:") for item in config.items('config'): - print "\t%s" % (str(item)) + print(("\t%s" % (str(item)))) # var inbredsetid = config.get('config', 'inbredsetid') - print "inbredsetid: %s" % inbredsetid + print(("inbredsetid: %s" % inbredsetid)) species = datastructure.get_species(inbredsetid) speciesid = species[0] - print "speciesid: %s" % speciesid + print(("speciesid: %s" % speciesid)) dataid = datastructure.get_nextdataid_phenotype() - print "next data id: %s" % dataid + print(("next data id: %s" % dataid)) cursor, con = utilities.get_cursor() # datafile datafile = open(config.get('config', 'datafile'), 'r') phenotypedata = csv.reader(datafile, delimiter='\t', quotechar='"') - phenotypedata_head = phenotypedata.next() - print "phenotypedata head:\n\t%s" % phenotypedata_head + phenotypedata_head = next(phenotypedata) + print(("phenotypedata head:\n\t%s" % phenotypedata_head)) strainnames = phenotypedata_head[1:] strains = datastructure.get_strains_bynames(inbredsetid=inbredsetid, strainnames=strainnames, updatestrainxref="yes") # metafile metafile = open(config.get('config', 'metafile'), 'r') phenotypemeta = csv.reader(metafile, delimiter='\t', quotechar='"') - phenotypemeta_head = phenotypemeta.next() - print "phenotypemeta head:\n\t%s" % phenotypemeta_head - print + phenotypemeta_head = next(phenotypemeta) + print(("phenotypemeta head:\n\t%s" % phenotypemeta_head)) + print() # load for metarow in phenotypemeta: # - datarow_value = phenotypedata.next() - datarow_se = phenotypedata.next() - datarow_n = phenotypedata.next() + datarow_value = next(phenotypedata) + datarow_se = next(phenotypedata) + datarow_n = next(phenotypedata) # Phenotype sql = """ INSERT INTO Phenotype @@ -67,7 +67,7 @@ def main(argv): )) rowcount = cursor.rowcount phenotypeid = con.insert_id() - print "INSERT INTO Phenotype: %d record: %d" % (rowcount, phenotypeid) + print(("INSERT INTO Phenotype: %d record: %d" % (rowcount, phenotypeid))) # Publication publicationid = None # reset pubmed_id = utilities.to_db_string(metarow[0], None) @@ -81,7 +81,7 @@ def main(argv): re = cursor.fetchone() if re: publicationid = re[0] - print "get Publication record: %d" % publicationid + print(("get Publication record: %d" % publicationid)) if not publicationid: sql = """ INSERT INTO Publication @@ -109,7 +109,7 @@ def main(argv): )) rowcount = cursor.rowcount publicationid = con.insert_id() - print "INSERT INTO Publication: %d record: %d" % (rowcount, publicationid) + print(("INSERT INTO Publication: %d record: %d" % (rowcount, publicationid))) # data for index, strain in enumerate(strains): # @@ -158,14 +158,14 @@ def main(argv): cursor.execute(sql, (inbredsetid, phenotypeid, publicationid, dataid, "")) rowcount = cursor.rowcount publishxrefid = con.insert_id() - print "INSERT INTO PublishXRef: %d record: %d" % (rowcount, publishxrefid) + print(("INSERT INTO PublishXRef: %d record: %d" % (rowcount, publishxrefid))) # for loop next dataid += 1 - print + print() # release con.close() if __name__ == "__main__": - print "command line arguments:\n\t%s" % sys.argv + print(("command line arguments:\n\t%s" % sys.argv)) main(sys.argv) - print "exit successfully" + print("exit successfully") diff --git a/scripts/maintenance/readProbeSetMean_v7.py b/scripts/maintenance/readProbeSetMean_v7.py index e9c8f25c..59a51cf9 100755 --- a/scripts/maintenance/readProbeSetMean_v7.py +++ b/scripts/maintenance/readProbeSetMean_v7.py @@ -31,20 +31,20 @@ def translateAlias(str): dataStart = 1 -GeneChipId = int( raw_input("Enter GeneChipId:") ) -ProbeSetFreezeId = int( raw_input("Enter ProbeSetFreezeId:") ) -input_file_name = raw_input("Enter file name with suffix:") +GeneChipId = int( input("Enter GeneChipId:") ) +ProbeSetFreezeId = int( input("Enter ProbeSetFreezeId:") ) +input_file_name = input("Enter file name with suffix:") fp = open("%s" % input_file_name, 'rb') try: passwd = getpass.getpass('Please enter mysql password here : ') - con = MySQLdb.Connect(db='db_webqtl',host='localhost', user='username',passwd=passwd) + con = MySQLdb.Connect(db='db_webqtl', host='localhost', user='username', passwd=passwd) db = con.cursor() - print "You have successfully connected to mysql.\n" + print("You have successfully connected to mysql.\n") except: - print "You entered incorrect password.\n" + print("You entered incorrect password.\n") sys.exit(0) time0 = time.time() @@ -55,22 +55,22 @@ time0 = time.time() # generate the gene list of expression data here # ######################################################################### -print 'Checking if each line have same number of members' +print('Checking if each line have same number of members') GeneList = [] isCont = 1 header = fp.readline() -header = string.split(string.strip(header),'\t') -header = map(string.strip, header) +header = string.split(string.strip(header), '\t') +header = list(map(string.strip, header)) nfield = len(header) line = fp.readline() kj=0 while line: - line2 = string.split(string.strip(line),'\t') - line2 = map(string.strip, line2) + line2 = string.split(string.strip(line), '\t') + line2 = list(map(string.strip, line2)) if len(line2) != nfield: - print "Error : " + line + print(("Error : " + line)) isCont = 0 GeneList.append(line2[0]) @@ -78,30 +78,29 @@ while line: kj+=1 if kj%100000 == 0: - print 'checked ',kj,' lines' + print(('checked ', kj, ' lines')) -GeneList = map(string.lower, GeneList) -GeneList.sort() +GeneList = sorted(map(string.lower, GeneList)) if isCont==0: sys.exit(0) -print 'used ',time.time()-time0,' seconds' +print(('used ', time.time()-time0, ' seconds')) ######################################################################### # # Check if each strain exist in database # generate the string id list of expression data here # ######################################################################### -print 'Checking if each strain exist in database' +print('Checking if each strain exist in database') isCont = 1 fp.seek(0) header = fp.readline() -header = string.split(string.strip(header),'\t') -header = map(string.strip, header) -header = map(translateAlias, header) +header = string.split(string.strip(header), '\t') +header = list(map(string.strip, header)) +header = list(map(translateAlias, header)) header = header[dataStart:] Ids = [] for item in header: @@ -109,26 +108,26 @@ for item in header: db.execute('select Id from Strain where Name = "%s"' % item) Ids.append(db.fetchall()[0][0]) except: - print item,'does not exist, check the if the strain name is correct' + print((item, 'does not exist, check the if the strain name is correct')) isCont=0 if isCont==0: sys.exit(0) -print 'used ',time.time()-time0,' seconds' +print(('used ', time.time()-time0, ' seconds')) ######################################################################## # # Check if each ProbeSet exist in database # ######################################################################## -print 'Check if each ProbeSet exist in database' +print('Check if each ProbeSet exist in database') ##---- find PID is name or target ----## line = fp.readline() line = fp.readline() -line2 = string.split(string.strip(line),'\t') -line2 = map(string.strip, line2) +line2 = string.split(string.strip(line), '\t') +line2 = list(map(string.strip, line2)) PId = line2[0] db.execute('select Id from ProbeSet where Name="%s" and ChipId=%d' % (PId, GeneChipId) ) @@ -146,11 +145,10 @@ Names = [] for item in results: Names.append(item[0]) -print Names +print(Names) -Names = map(string.lower, Names) +Names = sorted(map(string.lower, Names)) -Names.sort() # -- Fixed the lower case problem of ProbeSets affx-mur_b2_at doesn't exist --# ##---- compare genelist with names ----## @@ -170,7 +168,7 @@ while x<len(GeneList) and y<len(Names): y += 1 if x%100000==0: - print 'check Name, checked %d lines'%x + print(('check Name, checked %d lines'%x)) while x<len(GeneList): GeneList2.append(GeneList[x]) @@ -180,20 +178,20 @@ isCont=1 ferror = open("ProbeSetError.txt", "wb") for item in GeneList2: ferror.write(item + " doesn't exist \n") - print item, " doesn't exist, check if the ProbeSet name is correct" + print((item, " doesn't exist, check if the ProbeSet name is correct")) isCont = 0 if isCont==0: sys.exit(0) -print 'used ',time.time()-time0,' seconds' +print(('used ', time.time()-time0, ' seconds')) ######################################################################### # # Insert data into database # ######################################################################### -print 'getting ProbeSet/Id' +print('getting ProbeSet/Id') #---- get Name/Id map ----# @@ -202,16 +200,16 @@ results = db.fetchall() NameIds = {} for item in results: NameIds[item[0]] = item[1] -print 'used ',time.time()-time0,' seconds' +print(('used ', time.time()-time0, ' seconds')) -print 'inserting data' +print('inserting data') ##---- get old max dataId ----## db.execute('select max(Id) from ProbeSetData') maxDataId = int(db.fetchall()[0][0]) bmax = maxDataId -print "old_max = %d\n" % bmax +print(("old_max = %d\n" % bmax)) ##---- insert data ----## fp.seek(0) @@ -222,8 +220,8 @@ kj = 0 values1 = [] values2 = [] while line: - line2 = string.split(string.strip(line),'\t') - line2 = map(string.strip, line2) + line2 = string.split(string.strip(line), '\t') + line2 = list(map(string.strip, line2)) PId = line2[0] recordId = NameIds[PId] @@ -255,8 +253,8 @@ while line: values1=[] values2=[] - print 'Inserted ', kj,' lines' - print 'used ',time.time()-time0,' seconds' + print(('Inserted ', kj, ' lines')) + print(('used ', time.time()-time0, ' seconds')) line = fp.readline() diff --git a/scripts/maintenance/readProbeSetSE_v7.py b/scripts/maintenance/readProbeSetSE_v7.py index fd6f0bb8..20a846a4 100755 --- a/scripts/maintenance/readProbeSetSE_v7.py +++ b/scripts/maintenance/readProbeSetSE_v7.py @@ -1,254 +1,254 @@ -#!/usr/bin/python2 -"""This script use the nearest marker to the transcript as control, increasing permutation rounds according to the p-value""" -######################################################################## -# Last Updated Sep 27, 2011 by Xiaodong -# This version fix the bug that incorrectly exclude the first 2 probesetIDs -######################################################################## - -import string -import sys -import MySQLdb -import getpass -import time - - -def translateAlias(str): - if str == "B6": - return "C57BL/6J" - elif str == "D2": - return "DBA/2J" - else: - return str - -######################################################################## -# -# Indicate Data Start Position, ProbeFreezeId, GeneChipId, DataFile -# -######################################################################## - -dataStart = 1 - -GeneChipId = int( raw_input("Enter GeneChipId:") ) -ProbeSetFreezeId = int( raw_input("Enter ProbeSetFreezeId:") ) -input_file_name = raw_input("Enter file name with suffix:") - -fp = open("%s" % input_file_name, 'rb') - - -try: - passwd = getpass.getpass('Please enter mysql password here : ') - con = MySQLdb.Connect(db='db_webqtl',host='localhost', user='username',passwd=passwd) - - db = con.cursor() - print "You have successfully connected to mysql.\n" -except: - print "You entered incorrect password.\n" - sys.exit(0) - -time0 = time.time() -######################################################################## -# -# Indicate Data Start Position, ProbeFreezeId, GeneChipId, DataFile -# -######################################################################## - -#GeneChipId = 4 -#dataStart = 1 -#ProbeSetFreezeId = 359 #JAX Liver 6C Affy M430 2.0 (Jul11) MDP -#fp = open("GSE10493_AllSamples_6C_Z_AvgSE.txt", 'rb') - - -######################################################################### -# -# Check if each line have same number of members -# generate the gene list of expression data here -# -######################################################################### -print 'Checking if each line have same number of members' - -GeneList = [] -isCont = 1 -header = fp.readline() -header = string.split(string.strip(header),'\t') -header = map(string.strip, header) -nfield = len(header) -line = fp.readline() - -kj=0 -while line: - line2 = string.split(string.strip(line),'\t') - line2 = map(string.strip, line2) - if len(line2) != nfield: - print "Error : " + line - isCont = 0 - - GeneList.append(line2[0]) - line = fp.readline() - - kj+=1 - if kj%100000 == 0: - print 'checked ',kj,' lines' - -GeneList = map(string.lower, GeneList) -GeneList.sort() - -if isCont==0: - sys.exit(0) - - -print 'used ',time.time()-time0,' seconds' -######################################################################### -# -# Check if each strain exist in database -# generate the string id list of expression data here -# -######################################################################### -print 'Checking if each strain exist in database' - -isCont = 1 -fp.seek(0) -header = fp.readline() -header = string.split(string.strip(header),'\t') -header = map(string.strip, header) -header = map(translateAlias, header) -header = header[dataStart:] -Ids = [] -for item in header: - try: - db.execute('select Id from Strain where Name = "%s"' % item) - Ids.append(db.fetchall()[0][0]) - except: - print item,'does not exist, check the if the strain name is correct' - isCont=0 - -if isCont==0: - sys.exit(0) - - -print 'used ',time.time()-time0,' seconds' -######################################################################## -# -# Check if each ProbeSet exist in database -# -######################################################################## -print 'Check if each ProbeSet exist in database' - -##---- find PID is name or target ----## -line = fp.readline() -line = fp.readline() -line2 = string.split(string.strip(line),'\t') -line2 = map(string.strip, line2) -PId = line2[0] - -db.execute('select Id from ProbeSet where Name="%s" and ChipId=%d' % (PId, GeneChipId)) -results = db.fetchall() -IdStr = 'TargetId' -if len(results)>0: - IdStr = 'Name' - - -##---- get Name/TargetId list from database ----## -db.execute('select distinct(%s) from ProbeSet where ChipId=%d order by %s' % (IdStr, GeneChipId, IdStr)) -results = db.fetchall() - -Names = [] -for item in results: - Names.append(item[0]) -Names = map(string.lower, Names) -Names.sort() # -- Fixed the lower case problem of ProbeSets affx-mur_b2_at doesn't exist --# - -##---- compare genelist with names ----## -x=y=0 -x1=-1 -GeneList2=[] -while x<len(GeneList) and y<len(Names): - if GeneList[x]==Names[y]: - x += 1 - y += 1 - elif GeneList[x]<Names[y]: - if x!=x1: - GeneList2.append(GeneList[x]) - x1 = x - x += 1 - elif GeneList[x]>Names[y]: - y += 1 - - if x%100000==0: - print 'check Name, checked %d lines'%x - -while x<len(GeneList): - GeneList2.append(GeneList[x]) - x += 1 - -isCont=1 -ferror = open("ProbeSetError.txt", "wb") -for item in GeneList2: - ferror.write(item + " doesn't exist \n") - print item, " doesn't exist" - isCont = 0 - -if isCont==0: - sys.exit(0) - - -print 'used ',time.time()-time0,' seconds' -############################# -#Insert new Data into SE -############################ -db.execute(""" - select ProbeSet.%s, ProbeSetXRef.DataId from ProbeSet, ProbeSetXRef - where ProbeSet.Id=ProbeSetXRef.ProbeSetId and ProbeSetXRef.ProbeSetFreezeId=%d""" - % (IdStr, ProbeSetFreezeId)) -results = db.fetchall() - -ProbeNameId = {} -for Name, Id in results: - ProbeNameId[Name] = Id - -ferror = open("ProbeError.txt", "wb") - -DataValues = [] - -fp.seek(0) #XZ add this line -line = fp.readline() #XZ add this line -line = fp.readline() - -kj = 0 -while line: - line2 = string.split(string.strip(line),'\t') - line2 = map(string.strip, line2) - - CellId = line2[0] - if not ProbeNameId.has_key(CellId): - ferror.write(CellId + " doesn't exist\n") - print CellId, " doesn't exist" - else: - DataId = ProbeNameId[CellId] - datasorig = line2[dataStart:] - - i = 0 - for item in datasorig: - if item != '': - value = '('+str(DataId)+','+str(Ids[i])+','+str(item)+')' - DataValues.append(value) - i += 1 - - kj += 1 - if kj % 100 == 0: - Dataitems = ','.join(DataValues) - cmd = 'insert ProbeSetSE values %s' % Dataitems - db.execute(cmd) - - DataValues = [] - print 'inserted ',kj,' lines' - print 'used ',time.time()-time0,' seconds' - line = fp.readline() - -if len(DataValues)>0: - DataValues = ','.join(DataValues) - cmd = 'insert ProbeSetSE values %s' % DataValues - db.execute(cmd) - -con.close() - - +#!/usr/bin/python2 +"""This script use the nearest marker to the transcript as control, increasing permutation rounds according to the p-value""" +######################################################################## +# Last Updated Sep 27, 2011 by Xiaodong +# This version fix the bug that incorrectly exclude the first 2 probesetIDs +######################################################################## + +import string +import sys +import MySQLdb +import getpass +import time + + +def translateAlias(str): + if str == "B6": + return "C57BL/6J" + elif str == "D2": + return "DBA/2J" + else: + return str + +######################################################################## +# +# Indicate Data Start Position, ProbeFreezeId, GeneChipId, DataFile +# +######################################################################## + + +dataStart = 1 + +GeneChipId = int(input("Enter GeneChipId:")) +ProbeSetFreezeId = int(input("Enter ProbeSetFreezeId:")) +input_file_name = input("Enter file name with suffix:") + +fp = open("%s" % input_file_name, 'rb') + + +try: + passwd = getpass.getpass('Please enter mysql password here : ') + con = MySQLdb.Connect(db='db_webqtl', host='localhost', + user='username', passwd=passwd) + + db = con.cursor() + print("You have successfully connected to mysql.\n") +except: + print("You entered incorrect password.\n") + sys.exit(0) + +time0 = time.time() +######################################################################## +# +# Indicate Data Start Position, ProbeFreezeId, GeneChipId, DataFile +# +######################################################################## + +#GeneChipId = 4 +#dataStart = 1 +# ProbeSetFreezeId = 359 #JAX Liver 6C Affy M430 2.0 (Jul11) MDP +#fp = open("GSE10493_AllSamples_6C_Z_AvgSE.txt", 'rb') + + +######################################################################### +# +# Check if each line have same number of members +# generate the gene list of expression data here +# +######################################################################### +print('Checking if each line have same number of members') + +GeneList = [] +isCont = 1 +header = fp.readline() +header = string.split(string.strip(header), '\t') +header = list(map(string.strip, header)) +nfield = len(header) +line = fp.readline() + +kj = 0 +while line: + line2 = string.split(string.strip(line), '\t') + line2 = list(map(string.strip, line2)) + if len(line2) != nfield: + isCont = 0 + print(("Error : " + line)) + + GeneList.append(line2[0]) + line = fp.readline() + + kj += 1 + if kj % 100000 == 0: + print(('checked ', kj, ' lines')) + +GeneList = sorted(map(string.lower, GeneList)) + +if isCont == 0: + sys.exit(0) + + +print(('used ', time.time()-time0, ' seconds')) +######################################################################### +# +# Check if each strain exist in database +# generate the string id list of expression data here +# +######################################################################### +print('Checking if each strain exist in database') + +isCont = 1 +fp.seek(0) +header = fp.readline() +header = string.split(string.strip(header), '\t') +header = list(map(string.strip, header)) +header = list(map(translateAlias, header)) +header = header[dataStart:] +Ids = [] +for item in header: + try: + db.execute('select Id from Strain where Name = "%s"' % item) + Ids.append(db.fetchall()[0][0]) + except: + isCont = 0 + print((item, 'does not exist, check the if the strain name is correct')) + +if isCont == 0: + sys.exit(0) + + +print(('used ', time.time()-time0, ' seconds')) +######################################################################## +# +# Check if each ProbeSet exist in database +# +######################################################################## +print('Check if each ProbeSet exist in database') + +##---- find PID is name or target ----## +line = fp.readline() +line = fp.readline() +line2 = string.split(string.strip(line), '\t') +line2 = list(map(string.strip, line2)) +PId = line2[0] + +db.execute('select Id from ProbeSet where Name="%s" and ChipId=%d' % + (PId, GeneChipId)) +results = db.fetchall() +IdStr = 'TargetId' +if len(results) > 0: + IdStr = 'Name' + + +##---- get Name/TargetId list from database ----## +db.execute('select distinct(%s) from ProbeSet where ChipId=%d order by %s' % ( + IdStr, GeneChipId, IdStr)) +results = db.fetchall() + +Names = [] +for item in results: + Names.append(item[0]) + Names = sorted(map(string.lower, Names)) + +##---- compare genelist with names ----## +x = y = 0 +x1 = -1 +GeneList2 = [] +while x < len(GeneList) and y < len(Names): + if GeneList[x] == Names[y]: + x += 1 + y += 1 + elif GeneList[x] < Names[y]: + if x != x1: + GeneList2.append(GeneList[x]) + x1 = x + x += 1 + elif GeneList[x] > Names[y]: + y += 1 + + if x % 100000 == 0: + print(('check Name, checked %d lines' % x)) + +while x < len(GeneList): + GeneList2.append(GeneList[x]) + x += 1 + +isCont = 1 +ferror = open("ProbeSetError.txt", "wb") +for item in GeneList2: + ferror.write(item + " doesn't exist \n") + isCont = 0 + + print((item, " doesn't exist")) +if isCont == 0: + sys.exit(0) + + +print(('used ', time.time()-time0, ' seconds')) +############################# +# Insert new Data into SE +############################ +db.execute(""" + select ProbeSet.%s, ProbeSetXRef.DataId from ProbeSet, ProbeSetXRef + where ProbeSet.Id=ProbeSetXRef.ProbeSetId and ProbeSetXRef.ProbeSetFreezeId=%d""" + % (IdStr, ProbeSetFreezeId)) +results = db.fetchall() + +ProbeNameId = {} +for Name, Id in results: + ProbeNameId[Name] = Id + +ferror = open("ProbeError.txt", "wb") + +DataValues = [] + +fp.seek(0) # XZ add this line +line = fp.readline() # XZ add this line +line = fp.readline() + +kj = 0 +while line: + line2 = string.split(string.strip(line), '\t') + line2 = list(map(string.strip, line2)) + + CellId = line2[0] + if CellId not in ProbeNameId: + ferror.write(CellId + " doesn't exist\n") + else: + DataId = ProbeNameId[CellId] + datasorig = line2[dataStart:] + + i = 0 + for item in datasorig: + if item != '': + value = '('+str(DataId)+','+str(Ids[i])+','+str(item)+')' + DataValues.append(value) + i += 1 + + kj += 1 + if kj % 100 == 0: + Dataitems = ','.join(DataValues) + cmd = 'insert ProbeSetSE values %s' % Dataitems + db.execute(cmd) + + DataValues = [] + line = fp.readline() + print((CellId, " doesn't exist")) + print(('inserted ', kj, ' lines')) + print(('used ', time.time()-time0, ' seconds')) + +if len(DataValues) > 0: + DataValues = ','.join(DataValues) + cmd = 'insert ProbeSetSE values %s' % DataValues + db.execute(cmd) + +con.close() |