def getChromInfo(self):
logger.debug("annotation_server.getChromInfo called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('chromInfo.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes objects from ChromInfo table for that genome build
models.ChromInfo.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
# http://stackoverflow.com/q/3548495
for line in handle:
t1 = line.strip().split('\t')
# Not including extraneous sequences i.e. chr6_ssto_hap7,
# chr6_random
if str(t1[0]).find('_') == -1:
item = models.ChromInfo(
genomebuild=self.GENOME_BUILD,
chrom=t1[0],
size=t1[1],
fileName=t1[2]
)
item.save()
return
def getGenes(self):
logger.debug("annotation_server.getGenes called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('ensGene.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes all objects of that genome build from table
models.Gene.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
for line in handle:
t1 = line.strip().split('\t')
item = models.Gene(genomebuild=self.GENOME_BUILD,
bin=t1[0],
name=t1[1],
chrom=t1[2],
strand=t1[3],
txStart=t1[4],
txEnd=t1[5],
cdsStart=t1[6],
cdsEnd=t1[7],
exonCount=t1[8],
exonStarts=t1[9],
exonEnds=t1[10],
score=t1[11],
name2=t1[12],
cdsStartStat=t1[13],
cdsEndStat=t1[14],
exonFrames=t1[15])
item.save()
return
def getCytoBand(self):
# chrominfo
logger.debug("annotation_server.getCytoBand called for genome: %s" % self.GENOME_BUILD_NAME )
url, file_name = self.getUrlFile('cytoBand.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes all objects from table
CytoBand.objects.filter(genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
for line in handle:
t1 = line.strip().split('\t')
item = current_table(genomebuild=self.GENOME_BUILD, chrom=t1[0], chromStart=t1[1], chromEnd=t1[2], name=t1[3], gieStain=t1[4])
item.save()
return
def getCytoBand(self):
logger.debug("annotation_server.getCytoBand called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('cytoBand.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes all objects from table
CytoBand.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
for line in handle:
t1 = line.strip().split('\t')
# FIXME: current_table is unresolved
item = current_table(
genomebuild=self.GENOME_BUILD, chrom=t1[0], chromStart=t1[1],
chromEnd=t1[2], name=t1[3], gieStain=t1[4]
)
item.save()
return
def getCytoBand(self):
logger.debug("annotation_server.getCytoBand called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('cytoBand.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes all objects from table
models.CytoBand.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
# handle = gzip.open(file_name)
# for line in handle:
# t1 = line.strip().split('\t')
# # FIXME: current_table is unresolved
# # Fritz (2016-02-22): This method does not exist in Refinery's
# # code base. Not sure what's going on here.
# item = current_table(
# genomebuild=self.GENOME_BUILD, chrom=t1[0], chromStart=t1[1],
# chromEnd=t1[2], name=t1[3], gieStain=t1[4]
# )
# item.save()
return
def getGenes(self):
logger.debug("annotation_server.getGenes called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('ensGene.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes all objects of that genome build from table
Gene.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
for line in handle:
t1 = line.strip().split('\t')
item = Gene(
genomebuild=self.GENOME_BUILD, bin=t1[0], name=t1[1],
chrom=t1[2], strand=t1[3], txStart=t1[4], txEnd=t1[5],
cdsStart=t1[6], cdsEnd=t1[7], exonCount=t1[8],
exonStarts=t1[9], exonEnds=t1[10], score=t1[11], name2=t1[12],
cdsStartStat=t1[13], cdsEndStat=t1[14], exonFrames=t1[15]
)
item.save()
return
def getCytoBand(self):
logger.debug("annotation_server.getCytoBand called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('cytoBand.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes all objects from table
models.CytoBand.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
# handle = gzip.open(file_name)
# for line in handle:
# t1 = line.strip().split('\t')
# # FIXME: current_table is unresolved
# # Fritz (2016-02-22): This method does not exist in Refinery's
# # code base. Not sure what's going on here.
# item = current_table(
# genomebuild=self.GENOME_BUILD, chrom=t1[0], chromStart=t1[1],
# chromEnd=t1[2], name=t1[3], gieStain=t1[4]
# )
# item.save()
return
def getChromInfo(self):
logger.debug("annotation_server.getChromInfo called for genome: %s",
self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile('chromInfo.txt.gz')
download_http_file(url, '', self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes objects from ChromInfo table for that genome build
models.ChromInfo.objects.filter(
genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
# http://stackoverflow.com/q/3548495
for line in handle:
t1 = line.strip().split('\t')
# Not including extraneous sequences i.e. chr6_ssto_hap7,
# chr6_random
if str(t1[0]).find('_') == -1:
item = models.ChromInfo(genomebuild=self.GENOME_BUILD,
chrom=t1[0],
size=t1[1],
fileName=t1[2])
item.save()
return
def getChromInfo(self):
# chrominfo
logger.debug("annotation_server.getChromInfo called for genome: %s" % self.GENOME_BUILD_NAME)
url, file_name = self.getUrlFile("chromInfo.txt.gz")
download_http_file(url, "", self.ANNOTATION_TEMP_DIR, as_task=False)
# deletes objects from ChromInfo table for that genome build
ChromInfo.objects.filter(genomebuild__name__exact=self.GENOME_BUILD_NAME).delete()
# reading gz file
handle = gzip.open(file_name)
# http://stackoverflow.com/questions/3548495/download-extract-and-read-a-gzip-file-in-python
for line in handle:
t1 = line.strip().split("\t")
# Not including extraneous sequences i.e. chr6_ssto_hap7, chr6_random
if str(t1[0]).find("_") == -1:
item = ChromInfo(genomebuild=self.GENOME_BUILD, chrom=t1[0], size=t1[1], fileName=t1[2])
item.save()
return
