def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
stagebox = dropbox.make_stagebox(log, info)
dropbox.keys_to_dropbox(log, info, ['ROSETTA_COMPRESSEDOUT'], stagebox)
dsattr = {}
dsattr['SPACE'] = info['SPACE']
dsattr['PROJECT'] = info['PROJECT']
dsattr['EXPERIMENT'] = info['OUTEXPERIMENT']
dsattr['DATASET_TYPE'] = 'ROSETTA_OUTFILE'
path = os.path.join(stagebox, 'dataset.attributes')
IniInfoHandler().write(dsattr, path)
dsprop = {}
for key in [
'SEQ', 'COMMENT', 'ROSETTA_VERSION', 'RUN__PROTOCOL',
'RUN__SHUFFLE', 'INFRASTRUCTURE', 'N_MODELS', 'DATABASE',
'IN__FILE__ALIGNMENT', 'CM__ALN_FORMAT', 'FRAG3', 'FRAG9',
'IN__FILE__FASTA', 'IN__FILE__FULLATOM',
'IN__FILE__PSIPRED_SS2', 'IN__DETECT_DISULF',
'IN__FILE__TEMPLATE_PDB', 'LOOPS__FRAG_SIZES',
'LOOPS__FRAG_FILES', 'IDEALIZE_AFTER_LOOP_CLOSE',
'LOOPS__EXTENDED', 'LOOPS__BUILD_INITIAL', 'LOOPS__REMODEL',
'LOOPS__RELAX', 'RANDOM_GROW_LOOPS_BY',
'SELECT_BEST_LOOP_FROM', 'RELAX__FAST',
'RELAX__DEFAULT_REPEATS', 'SILENT_DECOYTIME',
'FAIL_ON_BAD_HBOND', 'BGDT', 'EVALUATION__GDTMM',
'OUT__FILE__SILENT_STRUCT_TYPE'
]:
dsprop[key] = info[key]
path = os.path.join(stagebox, 'dataset.properties')
IniInfoHandler().write(dsprop, path)
dropbox.move_stage_to_dropbox(log,
stagebox,
info['DROPBOX'],
keepCopy=False)
return info
def _generateINIs(self, info, log, pepxmls, codes):
total = len(codes)
for i, code, pepxml in zip(range(total), codes, pepxmls):
dict = info.copy()
dict['MZXML'] = code + '.mzMXL'
dict['DATASET_CODE'] = code.split('~')[1]
dict[Keys.PEPXML] = pepxml
dict[Keys.SUBJOBLIST] = "%s%s%d%s%d" % (
'DATASET_CODE', Keys.SUBJOBSEP, i, Keys.SUBJOBSEP, total)
out = info[Keys.SPLIT] + "_" + str(i)
IniInfoHandler().write(dict, out)
log.debug("Wrote " + out)
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
info['DROPBOXSTAGE'] = dropbox.make_stagebox(log, info)
#copy files
keys = ['PEPCSV', 'PROTCSV', 'CONSENSUSXML']
dropbox.keys_to_dropbox(log, info, keys, info['DROPBOXSTAGE'])
#compress TOPPAS files
archive = os.path.join(info['DROPBOXSTAGE'], 'toppasfiles.zip')
subprocess.check_call('zip -v ' + archive + ' ' +
" ".join(info['TOPPASFILES']),
shell=True)
#compress XML files
archive = os.path.join(info['DROPBOXSTAGE'], 'featurexmls.zip')
subprocess.check_call('zip -jv ' + archive + ' ' +
" ".join(info['FEATUREXML']),
shell=True)
#protxml special naming
filename = os.path.basename(info['DROPBOXSTAGE']) + '.prot.xml'
filepath = os.path.join(info['DROPBOXSTAGE'], filename)
shutil.copy(info['PROTXML'], filepath)
#properties file
expinfo = info.copy()
expinfo['PARENT-DATA-SET-CODES'] = info[Keys.DATASET_CODE]
expinfo['BASE_EXPERIMENT'] = info['EXPERIMENT']
expinfo['QUANTIFICATION_TYPE'] = 'LABEL-FREE'
expinfo['PEAKPICKER'] = 'YES'
expinfo['MAPALIGNER'] = 'YES'
proppath = os.path.join(info['DROPBOXSTAGE'],
'quantification.properties')
IniInfoHandler().write(expinfo, proppath)
#create witolds LFQ report mail
reportcmd = 'mailLFQ.sh %s %s %s %s 2>&1' % (
proppath, expinfo['PEPCSV'], expinfo['PROTCSV'], getpass.getuser())
subprocess.check_call(reportcmd, shell=True)
if os.path.exists("analyseLFQ.pdf"):
shutil.copy('analyseLFQ.pdf', info['DROPBOXSTAGE'])
dropbox.move_stage_to_dropbox(log, info['DROPBOXSTAGE'],
info['DROPBOX'])
return info
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
info['DROPBOXSTAGE'] = stagebox = dropbox.make_stagebox(log, info)
info['PEPIDX'] = info['SPLIB'].replace(".splib", ".pepidx")
dropbox.keys_to_dropbox(log, info, ['SPLIB', 'PEPIDX', 'TSV', 'TRAML'],
stagebox)
dsattr = {}
dsattr['SPACE'] = 'PERSONAL_DB'
dsattr['PROJECT'] = 'TRAML'
dsattr['EXPERIMENT'] = getpass.getuser().upper()
dsattr['EXPERIMENT_TYPE'] = "PLAIN"
dsattr['DATASET_TYPE'] = 'TRAML_DB'
dsattr['PARENT_DATASETS'] = os.path.basename(
os.path.dirname(info[Keys.PEPXML]))
path = os.path.join(stagebox, 'dataset.attributes')
IniInfoHandler().write(dsattr, path)
dsprop = {}
dsprop['VERSION'] = time.strftime("%Y%m%d%H%M%S")
dsprop['NAME'] = info.get('COMMENT', "unnamed")
dsprop['DESCRIPTION'] = info.get('DESCRIPTION', "undescribed")
dsprop['WORKFLOW'] = info['WORKFLOW']
dsprop['HASSPLIB'] = "true"
for key in [
"FDR", "MS_TYPE", "RUNRT", "RTKIT", "TSV_MASS_LIMITS",
"TSV_ION_LIMITS", "TSV_PRECISION", "TSV_CHARGE",
"TSV_REMOVE_DUPLICATES", "TSV_EXACT", "TSV_GAIN", "TSV_SERIES",
"CONSENSUS_TYPE"
]:
dsprop[key] = info[key]
#cannot use IniInfoHandlerHere because it writes NAME
config = ConfigObj(dsprop)
config.filename = os.path.join(stagebox, 'dataset.properties')
config.write()
dropbox.move_stage_to_dropbox(log,
stagebox,
info['DROPBOX'],
keepCopy=False)
return info
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info.get(
'WORKFLOW', "wff"))
stagebox = dropbox.make_stagebox(log, info)
dropbox.keys_to_dropbox(log, info, ['DUMP_MZXML'], stagebox)
dsattr = {}
dsattr['DATASET_TYPE'] = 'PLAIN'
path = os.path.join(stagebox, 'dataset.attributes')
IniInfoHandler().write(dsattr, path)
dropbox.move_stage_to_dropbox(log,
stagebox,
info['DROPBOX'],
keepCopy=False)
return info
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
info['DROPBOXSTAGE'] = dropbox.make_stagebox(log, info)
info['EXPERIMENT_CODE'] = dropbox.get_experiment_code(info)
keys = [Keys.PEPXML, 'PEPCSV', 'MAYUOUT']
dropbox.keys_to_dropbox(log, info, keys, info['DROPBOXSTAGE'])
# protxml special naming
filename = os.path.basename(info['DROPBOXSTAGE']) + '.prot.xml'
filepath = os.path.join(info['DROPBOXSTAGE'], filename)
shutil.copy(info['PROTXML'], filepath)
#search.properties requires some specific fields
sinfo = info.copy()
sinfo['FDR'] = info['FDR']
sinfo['DBASENAME'] = os.path.splitext(os.path.split(
info['DBASE'])[1])[0]
sinfo['PARENT-DATA-SET-CODES'] = info[Keys.DATASET_CODE]
# set values to NONE if they were e.g. "" before
for key in ['STATIC_MODS', 'VARIABLE_MODS']:
if info.get(key, "") == "":
sinfo[key] = 'NONE'
#lowercase required
sinfo['experiment-code'] = info['EXPERIMENT_CODE']
path = os.path.join(info['DROPBOXSTAGE'], 'search.properties')
IniInfoHandler().write(sinfo, path)
#write mail to dropbox but do not send yet (after viewer only)
info['MAILFILE'] = os.path.join(info['DROPBOXSTAGE'], 'mailtext.txt')
self._writemail(info.copy())
info['DROPBOXSTAGE'] = dropbox.move_stage_to_dropbox(
log, info['DROPBOXSTAGE'], info['DROPBOX'], keepCopy=True)
return info
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
info['DROPBOXSTAGE'] = dropbox.make_stagebox(log, info)
keys = [Keys.PEPXML, 'PEPCSV']
dropbox.keys_to_dropbox(log, info, keys, info['DROPBOXSTAGE'])
#protxml special naming
filename = os.path.basename(info['DROPBOXSTAGE']) + '.prot.xml'
filepath = os.path.join(info['DROPBOXSTAGE'], filename)
shutil.copy(info['PROTXML'], filepath)
#search.properties requires some specific fields
info['DBASENAME'] = os.path.splitext(os.path.split(
info['DBASE'])[1])[0]
info['PARENT-DATA-SET-CODES'] = info[Keys.DATASET_CODE]
path = os.path.join(info['DROPBOXSTAGE'], 'search.properties')
IniInfoHandler().write(info, path)
info['DROPBOXSTAGE'] = dropbox.move_stage_to_dropbox(
log, info['DROPBOXSTAGE'], info['DROPBOX'], keepCopy=True)
return info
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
stagebox = dropbox.make_stagebox(log, info)
dropbox.keys_to_dropbox(log, info, ['APMS_OUT'], stagebox)
dsattr = {}
dsattr['DATASET_TYPE'] = 'APMS_RESULT'
dsattr['SPACE'] = info['SPACE']
dsattr['PROJECT'] = info['PROJECT']
dsattr['EXPERIMENT'] = info['OUTEXPERIMENT']
for key in ["COMMENT"]:
dsattr[key] = info[key]
path = os.path.join(stagebox, 'dataset.attributes')
IniInfoHandler().write(dsattr, path)
dropbox.move_stage_to_dropbox(log,
stagebox,
info['DROPBOX'],
keepCopy=False)
return info
def run(self, log, info):
info['WORKFLOW'] = dropbox.extendWorkflowID(info['WORKFLOW'])
info['WORKFLOW'] += " msproteomicstools@" + subprocess.check_output(
"git --git-dir=/cluster/apps/imsbtools/stable/msproteomicstools/master/.git rev-parse --short HEAD",
shell=True).strip()
info['WORKFLOW'] += " openms@" + subprocess.check_output(
"git --git-dir=/cluster/apps/openms/2.0.0-memory/OpenMS/.git rev-parse --short HEAD",
shell=True).strip()
info['DROPBOXSTAGE'] = stagebox = dropbox.make_stagebox(log, info)
expcode = dropbox.get_experiment_code(info)
#copy and compress align.csv, but not the matrix REQUEST: expcode in name
tgt = os.path.join(
stagebox, expcode + '_' + os.path.basename(info['ALIGNMENT_TSV']))
shutil.copy(info['ALIGNMENT_TSV'], tgt)
subprocess.check_call('gzip ' + stagebox + '/* 2>&1', shell=True)
tgt = os.path.join(
stagebox,
expcode + '_' + os.path.basename(info['ALIGNMENT_MATRIX']))
shutil.copy(info['ALIGNMENT_MATRIX'], tgt)
dropbox.keys_to_dropbox(log, info, ['ALIGNER_STDOUT'], stagebox)
#compress all mprophet files into one zip
archive = os.path.join(stagebox, 'pyprophet_stats.zip')
if not 'MPROPHET_STATS' in info:
info['MPROPHET_STATS'] = []
if not isinstance(info['MPROPHET_STATS'], list):
info['MPROPHET_STATS'] = [info['MPROPHET_STATS']]
for entry in info['MPROPHET_STATS']:
subprocess.check_call('zip -j ' + archive + ' ' + entry + " 2>&1",
shell=True)
#PATCH: reimport old classifier if existing was used
for key in ("MPR_LDA_PATH", "MPR_WT_PATH"):
path = info.get(key, "")
if path:
if not os.path.exists(path):
raise Exception(
"can not add %s to archive, file does not exist" %
path)
subprocess.check_call('zip -j ' + archive + ' ' + path +
" 2>&1",
shell=True)
#if 'MPR_LDA_PATH' in info and info['MPR_LDA_PATH'] != "":
#subprocess.check_call('zip -j ' + archive + ' ' + info['MPR_LDA_PATH'] + " 2>&1", shell=True)
#if 'MPR_WT_PATH' in info and info['MPR_WT_PATH'] != "":
#if not os.path.exists(info['MPR_WT_PATH']):
#raise Exception("%s does not exist" % info['MPR_WT_PATH'])
#subprocess.check_call('zip -j ' + archive + ' ' + info['MPR_WT_PATH'] + " 2>&1", shell=True)
#SPACE PROJECT given
dsinfo = {}
dsinfo['SPACE'] = info['SPACE']
dsinfo['PROJECT'] = info['PROJECT']
dsinfo['PARENT_DATASETS'] = info[Keys.DATASET_CODE]
if info.get("DB_SOURCE", "") == "PersonalDB":
if isinstance(dsinfo['PARENT_DATASETS'], list):
dsinfo['PARENT_DATASETS'].append(info["DBASE"])
else:
dsinfo['PARENT_DATASETS'] = [
dsinfo['PARENT_DATASETS'], info['DBASE']
]
dsinfo['DATASET_TYPE'] = 'SWATH_RESULT'
dsinfo['EXPERIMENT_TYPE'] = 'SWATH_SEARCH'
dsinfo['EXPERIMENT'] = expcode
path = os.path.join(stagebox, 'dataset.attributes')
IniInfoHandler().write(dsinfo, path)
expinfo = {}
expinfo['PARENT-DATA-SET-CODES'] = dsinfo['PARENT_DATASETS']
expinfo['ALIGNER_DSCORE_CUTOFF'] = info['MPR_DSCORE_CUTOFF']
for key in [
'WORKFLOW',
'COMMENT',
'TRAML',
'EXTRACTION_WINDOW',
'WINDOW_UNIT',
'RT_EXTRACTION_WINDOW',
'MIN_UPPER_EDGE_DIST',
'IRTTRAML',
'MIN_RSQ',
'MIN_COVERAGE',
'MPR_NUM_XVAL',
'MPR_LDA_PATH',
'MPR_WT_PATH',
'MPR_FRACT',
'MPR_SSL_IF',
'MPR_SSL_IL',
'MPR_SSL_TF',
'MPR_SSL_TL',
'MPR_SSL_NI',
'MPR_MAINVAR',
'MPR_VARS',
'ALIGNER_FRACSELECTED',
'ALIGNER_MAX_RT_DIFF',
'ALIGNER_METHOD',
'ALIGNER_FDR',
'ALIGNER_MAX_FDRQUAL',
'ALIGNER_TARGETFDR',
'ALIGNER_REALIGN_METHOD',
'DO_CHROMML_REQUANT',
'ALGNER_MST_USERTCORR',
'ALIGNER_MST_STDEVMULT',
'ISOTOPIC_GROUPING',
'REQUANT_METHOD',
]:
if info.get(key, "") != "":
expinfo[key] = info[key]
path = os.path.join(stagebox, 'experiment.properties')
IniInfoHandler().write(expinfo, path)
#put a copy of the whole ini into the dropbox. copy() to prevent OUTPUT being removed from main ini
IniInfoHandler().write(info.copy(),
os.path.join(stagebox, 'input.ini'))
mailtext = ""
if info.get("RUNSWATH2VIEWER", "") == "true":
try:
#destdir = "/IMSB/ra/%s/html/tapir/%s" % (getpass.getuser(), dsinfo['EXPERIMENT'])
destdir = "/nfs/195.176.109.15/nas/fs2102/biol_ibt_usr_s1/%s/tapir/%s" % (
getpass.getuser(), dsinfo['EXPERIMENT'])
makedirs_clean(destdir)
shutil.copy(info['ALIGNMENT_TSV'], destdir)
for chrom in info['CHROM_MZML']:
shutil.copy(chrom, destdir)
subprocess.call("gunzip -v %s/*.gz 2>&1" % destdir, shell=True)
mailtext = "\n\nswath2viewer was enabled. To visualize results use e.g.\n" \
"user@crick# /opt/imsb/georger/py26/bin/python " \
"/opt/imsb/georger/msproteomicstools/gui/TAPIR.py --in %s/*" % destdir
except Exception, e:
log.warn("swath2viewer failed! " + e.message)