sf_server.upload(
"GO", "gene_ontology_edit.obo.tar.gz", filename,
title="Gene Ontology (GO)",
tags=["gene", "ontology", "GO", "essential",
"#uncompressed:%i" % uncompressedSize(filename),
"#version:%i" % obiGO.Ontology.version]
)
sf_server.unprotect("GO", "gene_ontology_edit.obo.tar.gz")
orgMap = {"352472": "44689", "562": "83333", "3055": None,
"7955": None, "11103": None, "2104": None, "4754":
None, "31033": None, "8355": None, "4577": None}
commonOrgs = dict([(obiGO.from_taxid(id), id)
for id in obiTaxonomy.common_taxids()
if obiGO.from_taxid(id) != None])
essentialOrgs = [obiGO.from_taxid(id)
for id in obiTaxonomy.essential_taxids()]
exclude = ["goa_uniprot", "goa_pdb", "GeneDB_tsetse", "reactome",
"goa_zebrafish", "goa_rat", "goa_mouse"]
updatedTaxonomy = defaultdict(set)
for org in list_available_organisms():
if org in exclude or org not in commonOrgs:
continue
sf_server.upload(
"GO", "gene_ontology_edit.obo.tar.gz", filename,
title="Gene Ontology (GO)",
tags=["gene", "ontology", "GO", "essential",
"#uncompressed:%i" % uncompressedSize(filename),
"#version:%i" % obiGO.Ontology.version]
)
sf_server.unprotect("GO", "gene_ontology_edit.obo.tar.gz")
orgMap = {"352472": "44689", "562": "83333", "3055": None,
"7955": None, "11103": None, "2104": None, "4754":
None, "31033": None, "8355": None, "4577": None}
commonOrgs = dict([(obiGO.from_taxid(id), id)
for id in obiTaxonomy.common_taxids()
if obiGO.from_taxid(id) != None])
essentialOrgs = [obiGO.from_taxid(id)
for id in obiTaxonomy.essential_taxids()]
exclude = ["goa_uniprot", "goa_pdb", "GeneDB_tsetse", "reactome",
"goa_zebrafish", "goa_rat", "goa_mouse"]
updatedTaxonomy = defaultdict(set)
for org in list_available_organisms():
if org in exclude or org not in commonOrgs:
continue
##############################################################################################################################################################
##############################################################################################################################################################
path = os.path.join(environ.buffer_dir, "tmp_miRNA")
print 'path: ', path
serverFiles = sf_server
try:
os.mkdir(path)
except OSError:
pass
org_taxo = [tax.name(id) for id in tax.common_taxids()]
### targets library from TargetScan
try:
tarscan_url = 'http://www.targetscan.org//vert_50//vert_50_data_download/Conserved_Site_Context_Scores.txt.zip'
zf = zipfile.ZipFile(StringIO.StringIO(urllib.urlopen(tarscan_url).read()))
arch = zf.read(zf.namelist()[0]).splitlines()[1:]
arch.pop()
mirnas = [a.split('\t')[3] for a in arch]
gene_ids = [a.split('\t')[1] for a in arch]
TargetScanLib = {}
for m, t in zip(mirnas, gene_ids):
if not (m in TargetScanLib):
sf_server.protect(DOMAIN, GDS_INFO, "0")
gds_info_datetime = datetime.fromtimestamp(0)
# read the information from the local file
gds_info, excluded = cPickle.load(file(localfile, "rb"))
# excluded should be a dictionary (GEO_ID, TAX_ID)
# if need to refresh the data base
if force_update:
gds_info, excluded = ({}, {})
# list of common organisms may have changed, rescan excluded list
excluded = dict([(id, taxid) for id, taxid in excluded.items()
if taxid not in obiTaxonomy.common_taxids()])
excluded.update([(id, info["taxid"]) for id, info in gds_info.items()
if info["taxid"] not in obiTaxonomy.common_taxids()])
gds_info = dict([(id, info) for id, info in gds_info.items()
if info["taxid"] in obiTaxonomy.common_taxids()])
# get the list of GDS files from NCBI directory
print "Retrieving ftp directory ..."
ftp = ftplib.FTP(FTP_NCBI)
ftp.login()
ftp.cwd(NCBI_DIR)
dirlist = []
ftp.dir(dirlist.append)
from datetime import timedelta
f.close()
sf_server.upload(DOMAIN, GDS_INFO, localfile, TITLE, TAGS)
sf_server.protect(DOMAIN, GDS_INFO, "0")
gds_info_datetime = datetime.fromtimestamp(0)
# read the information from the local file
gds_info, excluded = cPickle.load(file(localfile, "rb"))
# excluded should be a dictionary (GEO_ID, TAX_ID)
# if need to refresh the data base
if force_update:
gds_info, excluded = ({}, {})
# list of common organisms may have changed, rescan excluded list
excluded = dict([(id, taxid) for id, taxid in excluded.items()
if taxid not in obiTaxonomy.common_taxids()])
excluded.update([(id, info["taxid"]) for id, info in gds_info.items()
if info["taxid"] not in obiTaxonomy.common_taxids()])
gds_info = dict([(id, info) for id, info in gds_info.items()
if info["taxid"] in obiTaxonomy.common_taxids()])
# get the list of GDS files from NCBI directory
print "Retrieving ftp directory ..."
ftp = ftplib.FTP(FTP_NCBI)
ftp.login()
ftp.cwd(NCBI_DIR)
dirlist = []
ftp.dir(dirlist.append)
from datetime import timedelta
##############################################################################################################################################################
##############################################################################################################################################################
path = os.path.join(environ.buffer_dir, "tmp_miRNA")
print 'path: ', path
serverFiles = sf_server
try:
os.mkdir(path)
except OSError:
pass
org_taxo = [tax.name(id) for id in tax.common_taxids()]
### targets library from TargetScan
try:
tarscan_url = 'http://www.targetscan.org//vert_50//vert_50_data_download/Conserved_Site_Context_Scores.txt.zip'
zf = zipfile.ZipFile(StringIO(urllib.urlopen(tarscan_url).read()))
arch = zf.read(zf.namelist()[0]).splitlines()[1:]
arch.pop()
mirnas = [a.split('\t')[3] for a in arch]
gene_ids = [a.split('\t')[1] for a in arch]
TargetScanLib = {}
for m,t in zip(mirnas,gene_ids):
if not(m in TargetScanLib):