filename = os.path.join(tmp_path, "gene_association." + org + ".tar.gz")
obiGO.Annotations.DownloadAnnotations(org, filename)
## Load the annotations to test them and collect all taxon ids from them
print filename
a = obiGO.Annotations(filename, genematcher=obiGene.GMDirect())
taxons = set([ann.Taxon for ann in a.annotations])
## exclude taxons with cardinality 2
taxons = [tax for tax in taxons if "|" not in tax]
for tax in taxons:
taxid = tax.split(":", 1)[-1]
updatedTaxonomy[taxid].add(org)
del a
orgName = obiTaxonomy.name(commonOrgs[org])
taxid = obiTaxonomy.taxname_to_taxid(orgName)
print "Uploading", "gene_association." + org + ".tar.gz"
sf_server.upload(
"GO", "gene_association." + org + ".tar.gz", filename,
title="GO Annotations for " + orgName,
tags=["gene", "annotation", "ontology", "GO", orgName,
"#uncompressed:%i" % uncompressedSize(filename),
"#organism:" + orgName,
"#version:%i" % obiGO.Annotations.version] +
(["essential"] if org in essentialOrgs else []) +
obiTaxonomy.shortname(taxid)
)
sf_server.unprotect("GO", "gene_association." + org + ".tar.gz")
filename = os.path.join(tmp_path, "gene_association." + org + ".tar.gz")
obiGO.Annotations.DownloadAnnotations(org, filename)
## Load the annotations to test them and collect all taxon ids from them
print filename
a = obiGO.Annotations(filename, genematcher=obiGene.GMDirect())
taxons = set([ann.Taxon for ann in a.annotations])
## exclude taxons with cardinality 2
taxons = [tax for tax in taxons if "|" not in tax]
for tax in taxons:
taxid = tax.split(":", 1)[-1]
updatedTaxonomy[taxid].add(org)
del a
orgName = obiTaxonomy.name(commonOrgs[org])
taxid = obiTaxonomy.taxname_to_taxid(orgName)
print "Uploading", "gene_association." + org + ".tar.gz"
sf_server.upload(
"GO", "gene_association." + org + ".tar.gz", filename,
title="GO Annotations for " + orgName,
tags=["gene", "annotation", "ontology", "GO", orgName,
"#uncompressed:%i" % uncompressedSize(filename),
"#organism:" + orgName,
"#version:%i" % obiGO.Annotations.version] +
(["essential"] if org in essentialOrgs else []) +
obiTaxonomy.shortname(taxid)
)
sf_server.unprotect("GO", "gene_association." + org + ".tar.gz")
for hi in hist:
if any(hi.startswith(id + "\t") for id in taxids):
history[hi.split("\t", 1)[0]].append(hi.strip())
for taxid, genes in genes.items():
filename = os.path.join(tmpdir, "gene_info.%s.db" % taxid)
f = open(filename, "wb")
f.write("\n".join(genes))
f.flush()
f.close()
print "Uploading", filename
sf_server.upload(
"NCBI_geneinfo",
"gene_info.%s.db" % taxid,
filename,
title="NCBI gene info for %s" % obiTaxonomy.name(taxid),
tags=["NCBI", "gene info", "gene_names",
obiTaxonomy.name(taxid)] + obiTaxonomy.shortname(taxid) +
(["essential"] if taxid in essential else []))
sf_server.unprotect("NCBI_geneinfo", "gene_info.%s.db" % taxid)
filename = os.path.join(tmpdir, "gene_history.%s.db" % taxid)
f = open(filename, "wb")
f.write("\n".join(history.get(taxid, "")))
f.flush()
f.close()
print "Uploading", filename
sf_server.upload("NCBI_geneinfo",
"gene_history.%s.db" % taxid,
filename,
title="NCBI gene history for %s" %
##############################################################################################################################################################
##############################################################################################################################################################
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):
##############################################################################################################################################################
##############################################################################################################################################################
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):
if any(gi.startswith(id + "\t") for id in taxids):
genes[gi.split("\t", 1)[0]].append(gi.strip())
history = dict([(taxid, []) for taxid in taxids])
for hi in hist:
if any(hi.startswith(id + "\t") for id in taxids):
history[hi.split("\t", 1)[0]].append(hi.strip())
for taxid, genes in genes.items():
filename = os.path.join(tmpdir, "gene_info.%s.db" % taxid)
f = open(filename, "wb")
f.write("\n".join(genes))
f.flush()
f.close()
print "Uploading", filename
sf_server.upload("NCBI_geneinfo", "gene_info.%s.db" % taxid, filename,
title = "NCBI gene info for %s" % obiTaxonomy.name(taxid),
tags = ["NCBI", "gene info", "gene_names", obiTaxonomy.name(taxid)] + obiTaxonomy.shortname(taxid) + (["essential"] if taxid in essential else []))
sf_server.unprotect("NCBI_geneinfo", "gene_info.%s.db" % taxid)
filename = os.path.join(tmpdir, "gene_history.%s.db" % taxid)
f = open(filename, "wb")
f.write("\n".join(history.get(taxid, "")))
f.flush()
f.close()
print "Uploading", filename
sf_server.upload("NCBI_geneinfo", "gene_history.%s.db" % taxid, filename,
title = "NCBI gene history for %s" % obiTaxonomy.name(taxid),
tags = ["NCBI", "gene info", "history", "gene_names", obiTaxonomy.name(taxid)] + obiTaxonomy.shortname(taxid) + (["essential"] if taxid in essential else []))
sf_server.unprotect("NCBI_geneinfo", "gene_history.%s.db" % taxid)