"bridgemapper.py")
c_strManualGeneIDs = sfle.d(arepa.path_repo(), sfle.c_strDirEtc,
"manual_geneid")
c_pHashBridgeDB = dict(
(strName,
sfle.d(arepa.path_arepa(), "GeneMapper", sfle.c_strDirEtc, strDB))
for strName, strDB in (
("H**o sapiens", "Hs_Derby_20120602.bridge"),
("Mus musculus", "Mm_Derby_20120602.bridge"),
("Saccharomyces cerevisiae", "Sc_Derby_20120602.bridge"),
))
pHashBridgeDBTaxIDs = {
k: arepa.org2taxid(k, True)
for k in list(c_pHashBridgeDB.keys())
}
m_hashGeneIDs = {
k: v
for k, v in
[x.split("\t") for x in sfle.readcomment(open(c_strManualGeneIDs))]
} if os.path.exists(c_strManualGeneIDs) else None
def funcCounter(iter):
return ("%02d" % next(iter))
def funcGeneIDMapping(pE,
fileDATin,
if len(sys.argv) < 2:
raise Exception("Usage: samples2pcl.py <sdrf.txt> [adf.txt]+")
strSDRF, astrADFs = sys.argv[1], sys.argv[2:]
strTaxID = None
hashSDRF = {}
aastrSDRF = arepa.entable(open(strSDRF), [issource, istable, isdesc, isorg])
for astrLine in aastrSDRF:
strSource, strTable, strDesc, strOrg = astrLine
if strSource and strTable:
hashSDRF[strTable] = (strSource, strDesc)
hashSDRF[strSource] = (strSource, strDesc)
if strOrg and (not strTaxID):
strTaxID = arepa.org2taxid(strOrg)
hashADFs = {}
for strADF in astrADFs:
aastrADF = arepa.entable(open(strADF), [isprobe, isgene, lambda x: x])
for astrLine in aastrADF:
strProbe, strGene, strX = astrLine
if strProbe and strGene:
hashADFs[strProbe] = strGene
hashCache = {}
fFirst = True
for strLine in sys.stdin:
astrLine = strLine.strip().split("\t")
strID, astrData = astrLine[0], astrLine[1:]
if fFirst:
pSOFT.open(gzip.open(strGPLGZ))
pMetadata.checksum(' '.join(checksum))
pSOFT.open(sys.stdin)
for pDS in list(pSOFT.get("DATASET").values()):
pMetadata.pmid(pDS.get_attribute("dataset_pubmed_id"))
pMetadata.title(pDS.get_attribute("dataset_title"))
pMetadata.gloss(pDS.get_attribute("dataset_description"))
pMetadata.type(
re.sub(r' by .+$', "", (pDS.get_attribute("dataset_type")
or "").lower()))
pMetadata.channels(pDS.get_attribute("dataset_channel_count"))
pMetadata.conditions(pDS.get_attribute("dataset_sample_count"))
pMetadata.platform(pDS.get_attribute("dataset_platform"))
pMetadata.taxid(
arepa.org2taxid(pDS.get_attribute("dataset_sample_organism")))
# Auxillary Metadata
if strMetadata:
astrHeaders = None
for astrLine in csv.reader(open(strMetadata), csv.excel_tab):
if astrHeaders:
for i in range(len(astrLine)):
pMetadata.setdefault(astrHeaders[i], []).append(astrLine[i])
else:
pMetadata[c_hashkeyCurated] = astrLine
astrHeaders = astrLine
# Add Mapping Status and Save
k, v = sfle.readcomment(open(strStatus))[0].split("\t")
pMetadata.update({k: v})
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE
OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
getinfo.py:
acquire intermediate information about dataset,
used to get around pathologies in scons build
"""
import arepa
import sys
import re
pHashRE = {
"gse": r'Series_platform_taxid\t"([0-9]*)"',
"gds": r'dataset_sample_organism = ([A-Za-z0-9_\- ]*)'
}
strf = sys.stdin.read()
for strKey, strVal in list(pHashRE.items()):
astrMatch = re.findall(strVal, strf)
if astrMatch:
if strKey == "gse":
print(astrMatch[0])
elif strKey == "gds":
print(arepa.org2taxid(astrMatch[0]))
astrLine = strLine.strip().split("\t")
if astrLine[0] == "PubMed ID":
metadatum(pMetadata.pmid, astrLine[1:])
elif astrLine[0] == "Investigation Title":
metadatum(pMetadata.title, astrLine[1:])
elif astrLine[0] == "Experiment Description":
metadatum(pMetadata.gloss, astrLine[1:])
elif astrLine[0] == "Experimental Design":
metadatum(pMetadata.type,
[re.sub(r' by .+$', "", s.lower()) for s in astrLine[1:]])
pMetadata.store_checksum()
if strSDRF:
aastrSDRF = arepa.entable(open(strSDRF), [
lambda s: s == "Source Name",
lambda s: re.search(r'Characteristics\s*\[Organism\]', s),
])
metadatum(pMetadata.conditions, [str(len(aastrSDRF))])
setTaxa = set()
for astrLine in aastrSDRF:
strOrg = astrLine[1]
setTaxa.add(arepa.org2taxid(strOrg) or strOrg)
metadatum(pMetadata.taxid, list(setTaxa))
for strADF in astrADFs:
for strLine in open(strADF):
astrLine = strLine.strip().split("\t")
if astrLine[0] == "Array Design Name":
metadatum(pMetadata.platform, astrLine[1:])
pMetadata.save(sys.stdout)