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")
try:
tax = cPickle.load(open(sf_local.localpath_download("GO", "taxonomy.pickle"), "rb"))
except Exception:
tax = {}
## Upload taxonomy if any differences in the updated taxonomy
if any(tax.get(key, set()) != updatedTaxonomy.get(key, set())
for key in set(updatedTaxonomy)):
tax.update(updatedTaxonomy)
cPickle.dump(tax, open(os.path.join(tmp_path, "taxonomy.pickle"), "wb"))
print "Uploading", "taxonomy.pickle"
sf_server.upload(
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")
try:
tax = cPickle.load(open(sf_local.localpath_download("GO", "taxonomy.pickle"), "rb"))
except Exception:
tax = {}
## Upload taxonomy if any differences in the updated taxonomy
if any(tax.get(key, set()) != updatedTaxonomy.get(key, set())
for key in set(updatedTaxonomy)):
tax.update(updatedTaxonomy)
cPickle.dump(tax, open(os.path.join(tmp_path, "taxonomy.pickle"), "wb"))
print "Uploading", "taxonomy.pickle"
sf_server.upload(
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=[
for filename in end_files:
print "Now reading %s..." % filename
org = re.findall('/(\S{3,4})_\S{3}miRNA\.txt', filename)[0]
type_file = re.findall(org + '_(\S*)miRNA\.txt', filename)[0]
label = re.findall('/(\S{3,4}_\S{3}miRNA?)\.txt', filename)[0]
org_taxid = str(toTaxo.get(org))
org = tax.name(str(toTaxo.get(org)))
if type_file == 'mat':
serverFiles.upload("miRNA",
label,
filename,
title="miRNA: %s mature form" % org,
tags=["miRNA"] +
tax.shortname(org_taxid))
serverFiles.unprotect("miRNA", label)
print '%s mat uploaded' % org
for file_line in open(filename).readlines()[1:]:
fastprint(miRNA_path, 'a', file_line)
elif type_file == 'pre':
serverFiles.upload("miRNA",
label,
filename,
title="miRNA: %s pre-form" % org,
tags=["miRNA"] +
tax.shortname(org_taxid))
serverFiles.unprotect("miRNA", label)
print '%s pre uploaded' % org
for fx in [l.rstrip() for l in open(file_org).readlines()]:
if orgs_des[fx.split('_')[0]] in org_taxo:
end_files = miRNA_info(path, fx,orgs_des[fx.split('_')[0]])
for filename in end_files:
print "Now reading %s..." % filename
org = re.findall('/(\S{3,4})_\S{3}miRNA\.txt',filename)[0]
type_file = re.findall(org+'_(\S*)miRNA\.txt',filename)[0]
label = re.findall('/(\S{3,4}_\S{3}miRNA?)\.txt',filename)[0]
org_taxid = str(toTaxo.get(org))
org = tax.name(str(toTaxo.get(org)))
if type_file == 'mat':
serverFiles.upload("miRNA", label, filename, title="miRNA: %s mature form" % org, tags=["miRNA"] + tax.shortname(org_taxid))
serverFiles.unprotect("miRNA", label)
print '%s mat uploaded' % org
for file_line in open(filename).readlines()[1:]:
fastprint(miRNA_path,'a',file_line)
elif type_file == 'pre':
serverFiles.upload("miRNA", label, filename, title="miRNA: %s pre-form" % org, tags=["miRNA"] + tax.shortname(org_taxid))
serverFiles.unprotect("miRNA", label)
print '%s pre uploaded' % org
for file_line in open(filename).readlines()[1:]:
fastprint(premiRNA_path,'a',file_line)
else:
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)
