def __init__(self, gerald, key):
self._gerald = gerald
self._key = key
-
+
def __get_attribute(self, xml_tag):
subtree = self._gerald.tree.find('LaneSpecificRunParameters')
container = subtree.find(xml_tag)
if self._keys is None:
tree = self._gerald.tree
analysis = tree.find('LaneSpecificRunParameters/ANALYSIS')
- # according to the pipeline specs I think their fields
+ # according to the pipeline specs I think their fields
# are sampleName_laneID, with sampleName defaulting to s
- # since laneIDs are constant lets just try using
+ # since laneIDs are constant lets just try using
# those consistently.
self._keys = [ x.tag.split('_')[1] for x in analysis]
return self._keys
if self.tree is None or self.summary is None:
return None
- gerald = ElementTree.Element(Gerald.GERALD,
+ gerald = ElementTree.Element(Gerald.GERALD,
{'version': unicode(Gerald.XML_VERSION)})
gerald.append(self.tree)
gerald.append(self.summary.get_elements())
self.eland_results = ELAND(xml=element)
else:
logging.warn("Unrecognized tag %s" % (element.tag,))
-
+
def gerald(pathname):
g = Gerald()
g.pathname = pathname
path, name = os.path.split(pathname)
+ logging.info("Parsing gerald config.xml")
config_pathname = os.path.join(pathname, 'config.xml')
g.tree = ElementTree.parse(config_pathname).getroot()
# parse Summary.htm file
+ logging.info("Parsing Summary.htm")
summary_pathname = os.path.join(pathname, 'Summary.htm')
g.summary = Summary(summary_pathname)
# parse eland files
"""
Grab mean/deviation out of element
"""
- return (tonumber(element.attrib['mean']),
+ return (tonumber(element.attrib['mean']),
tonumber(element.attrib['deviation']))
def parse_summary_element(element):
Mostly for the cluster number
"""
LANE_RESULT_SUMMARY = 'LaneResultSummary'
- TAGS = {
+ TAGS = {
'LaneYield': 'lane_yield',
'Cluster': 'cluster', # Raw
'ClusterPF': 'cluster_pass_filter',
'AverageAlignmentScore': 'average_alignment_score',
'PercentErrorRate': 'percent_error_rate'
}
-
+
def __init__(self, html=None, xml=None):
self.lane = None
self.lane_yield = None
def get_elements(self):
lane_result = ElementTree.Element(
- Summary.LaneResultSummary.LANE_RESULT_SUMMARY,
+ Summary.LaneResultSummary.LANE_RESULT_SUMMARY,
{'lane': self.lane})
for tag, variable_name in Summary.LaneResultSummary.TAGS.items():
value = getattr(self, variable_name)
for element in list(tree):
try:
variable_name = tags[element.tag]
- setattr(self, variable_name,
+ setattr(self, variable_name,
parse_summary_element(element))
except KeyError, e:
logging.warn('Unrecognized tag %s' % (element.tag,))
flatten the children of a <tr>...</tr>
"""
return [flatten(x) for x in row.getchildren() ]
-
+
def _parse_table(self, table):
"""
- assumes the first line is the header of a table,
+ assumes the first line is the header of a table,
and that the remaining rows are data
"""
rows = table.getchildren()
for r in rows:
data.append(self._flattened_row(r))
return data
-
+
def _extract_named_tables(self, pathname):
"""
extract all the 'named' tables from a Summary.htm file
and return as a dictionary
-
+
Named tables are <h2>...</h2><table>...</table> pairs
The contents of the h2 tag is considered to the name
of the table.
self.lane_results[lrs.lane] = lrs
def get_elements(self):
- summary = ElementTree.Element(Summary.SUMMARY,
+ summary = ElementTree.Element(Summary.SUMMARY,
{'version': unicode(Summary.XML_VERSION)})
for lane in self.lane_results.values():
summary.append(lane.get_elements())
def build_genome_fasta_map(genome_dir):
# build fasta to fasta file map
+ logging.info("Building genome map")
genome = genome_dir.split(os.path.sep)[-1]
fasta_map = {}
for vld_file in glob(os.path.join(genome_dir, '*.vld')):
else:
fasta_map[name] = os.path.join(genome, name)
return fasta_map
-
+
class ElandLane(object):
"""
Process an eland result file
if genome_map is None:
genome_map = {}
self.genome_map = genome_map
-
+
if xml is not None:
self.set_elements(xml)
if os.stat(self.pathname)[stat.ST_SIZE] == 0:
raise RuntimeError("Eland isn't done, try again later.")
+ logging.info("summarizing results for %s" % (self.pathname))
reads = 0
mapped_reads = {}
- match_codes = {'NM':0, 'QC':0, 'RM':0,
+ match_codes = {'NM':0, 'QC':0, 'RM':0,
'U0':0, 'U1':0, 'U2':0,
'R0':0, 'R1':0, 'R2':0,
}
match_codes = property(_get_match_codes)
def get_elements(self):
- lane = ElementTree.Element(ElandLane.LANE,
- {'version':
+ lane = ElementTree.Element(ElandLane.LANE,
+ {'version':
unicode(ElandLane.XML_VERSION)})
sample_tag = ElementTree.SubElement(lane, ElandLane.SAMPLE_NAME)
sample_tag.text = self.sample_name
genome_map = ElementTree.SubElement(lane, ElandLane.GENOME_MAP)
for k, v in self.genome_map.items():
item = ElementTree.SubElement(
- genome_map, ElandLane.GENOME_ITEM,
+ genome_map, ElandLane.GENOME_ITEM,
{'name':k, 'value':unicode(v)})
mapped_reads = ElementTree.SubElement(lane, ElandLane.MAPPED_READS)
for k, v in self.mapped_reads.items():
item = ElementTree.SubElement(
- mapped_reads, ElandLane.MAPPED_ITEM,
+ mapped_reads, ElandLane.MAPPED_ITEM,
{'name':k, 'value':unicode(v)})
match_codes = ElementTree.SubElement(lane, ElandLane.MATCH_CODES)
for k, v in self.match_codes.items():
item = ElementTree.SubElement(
- match_codes, ElandLane.MATCH_ITEM,
+ match_codes, ElandLane.MATCH_ITEM,
{'name':k, 'value':unicode(v)})
reads = ElementTree.SubElement(lane, ElandLane.READS)
reads.text = unicode(self.reads)
# reset dictionaries
self._mapped_reads = {}
self._match_codes = {}
-
+
for element in tree:
tag = element.tag.lower()
if tag == ElandLane.SAMPLE_NAME.lower():
def __init__(self, xml=None):
# we need information from the gerald config.xml
self.results = {}
-
+
if xml is not None:
self.set_elements(xml)
def keys(self):
return self.results.keys()
-
+
def values(self):
return self.results.values()
return self.results[key]
def get_elements(self):
- root = ElementTree.Element(ELAND.ELAND,
+ root = ElementTree.Element(ELAND.ELAND,
{'version': unicode(ELAND.XML_VERSION)})
for lane_id, lane in self.results.items():
eland_lane = lane.get_elements()
# but I needed to persist the sample_name/lane_id for
# runfolder summary_report
path, name = os.path.split(pathname)
+ logging.info("Adding eland file %s" %(name,))
split_name = name.split('_')
lane_id = split_name[1]
--- /dev/null
+"""
+Extract information about the IPAR run
+
+IPAR - class holding the properties we found
+IPAR - IPAR factory function initalized from a directory name
+fromxml - IPAR factory function initalized from an xml dump from
+ the IPAR object.
+"""
+
+import datetime
+import logging
+import os
+import re
+import stat
+import time
+
+from htsworkflow.pipelines.runfolder import \
+ ElementTree, \
+ VERSION_RE, \
+ EUROPEAN_STRPTIME
+
+class Tiles(object):
+ def __init__(self, tree):
+ self.tree = tree.find("TileSelection")
+
+ def keys(self):
+ key_list = []
+ for c in self.tree.getchildren():
+ k = c.attrib.get('Index', None)
+ if k is not None:
+ key_list.append(k)
+ return key_list
+
+ def values(self):
+ value_list = []
+ for lane in self.tree.getchildren():
+ attributes = {}
+ for child in lane.getchildren():
+ if child.tag == "Sample":
+ attributes['Sample'] = child.text
+ elif child.tag == 'TileRange':
+ attributes['TileRange'] = (int(child.attrib['Min']),int(child.attrib['Max']))
+ value_list.append(attributes)
+ return value_list
+
+ def items(self):
+ return zip(self.keys(), self.values())
+
+ def __getitem__(self, key):
+ # FIXME: this is inefficient. building the dictionary be rescanning the xml.
+ v = dict(self.items())
+ return v[key]
+
+class IPAR(object):
+ XML_VERSION=1
+
+ # xml tag names
+ IPAR = 'IPAR'
+ TIMESTAMP = 'timestamp'
+ MATRIX = 'matrix'
+ RUN = 'Run'
+
+ def __init__(self, xml=None):
+ self.tree = None
+ self.date = datetime.datetime.today()
+ self._tiles = None
+ if xml is not None:
+ self.set_elements(xml)
+
+ def _get_time(self):
+ return time.mktime(self.date.timetuple())
+ def _set_time(self, value):
+ mtime_tuple = time.localtime(value)
+ self.date = datetime.datetime(*(mtime_tuple[0:7]))
+ time = property(_get_time, _set_time,
+ doc='run time as seconds since epoch')
+
+ def _get_cycles(self):
+ if self.tree is None:
+ return None
+ cycles = self.tree.find("Cycles")
+ if cycles is None:
+ return None
+ return cycles.attrib
+
+ def _get_start(self):
+ """
+ return cycle start
+ """
+ cycles = self._get_cycles()
+ if cycles is not None:
+ return int(cycles['First'])
+ else:
+ return None
+ start = property(_get_start, doc="get cycle start")
+
+ def _get_stop(self):
+ """
+ return cycle stop
+ """
+ cycles = self._get_cycles()
+ if cycles is not None:
+ return int(cycles['Last'])
+ else:
+ return None
+ stop = property(_get_stop, doc="get cycle stop")
+
+ def _get_tiles(self):
+ if self._tiles is None:
+ self._tiles = Tiles(self.tree)
+ return self._tiles
+ tiles = property(_get_tiles)
+
+ def _get_version(self):
+ software = self.tree.find('Software')
+ if software is not None:
+ return software.attrib['Version']
+ version = property(_get_version, "IPAR software version")
+
+
+ def file_list(self):
+ """
+ Generate list of all files that should be generated by the IPAR unit
+ """
+ suffix_node = self.tree.find('RunParameters/CompressionSuffix')
+ if suffix_node is None:
+ print "find compression suffix failed"
+ return None
+ suffix = suffix_node.text
+ files = []
+ format = "%s_%s_%04d_%s.txt%s"
+ for lane, attrib in self.tiles.items():
+ for file_type in ["int","nse"]:
+ start, stop = attrib['TileRange']
+ for tile in range(start, stop+1):
+ files.append(format % (attrib['Sample'], lane, tile, file_type, suffix))
+ return files
+
+ def dump(self):
+ print "Matrix:", self.matrix
+ print "Tree:", self.tree
+
+ def get_elements(self):
+ attribs = {'version': str(IPAR.XML_VERSION) }
+ root = ElementTree.Element(IPAR.IPAR, attrib=attribs)
+ timestamp = ElementTree.SubElement(root, IPAR.TIMESTAMP)
+ timestamp.text = str(int(self.time))
+ root.append(self.tree)
+ matrix = ElementTree.SubElement(root, IPAR.MATRIX)
+ matrix.text = self.matrix
+ return root
+
+ def set_elements(self, tree):
+ if tree.tag != IPAR.IPAR:
+ raise ValueError('Expected "IPAR" SubElements')
+ xml_version = int(tree.attrib.get('version', 0))
+ if xml_version > IPAR.XML_VERSION:
+ logging.warn('IPAR XML tree is a higher version than this class')
+ for element in list(tree):
+ if element.tag == IPAR.RUN:
+ self.tree = element
+ elif element.tag == IPAR.TIMESTAMP:
+ self.time = int(element.text)
+ elif element.tag == IPAR.MATRIX:
+ self.matrix = element.text
+ else:
+ raise ValueError("Unrecognized tag: %s" % (element.tag,))
+
+def load_ipar_param_tree(paramfile):
+ """
+ look for a .param file and load it if it is an IPAR tree
+ """
+
+ tree = ElementTree.parse(paramfile).getroot()
+ run = tree.find('Run')
+ if run.attrib.has_key('Name') and run.attrib['Name'].startswith("IPAR"):
+ return run
+
+ return None
+
+def ipar(pathname):
+ """
+ Examine the directory at pathname and initalize a IPAR object
+ """
+ logging.info("Searching IPAR directory")
+ i = IPAR()
+
+ # parse firecrest directory name
+ path, name = os.path.split(pathname)
+ groups = name.split('_')
+ if groups[0] != 'IPAR':
+ raise ValueError('ipar can only process IPAR directories')
+
+ # contents of the matrix file?
+ matrix_pathname = os.path.join(pathname, 'Matrix', 's_matrix.txt')
+ i.matrix = open(matrix_pathname, 'r').read()
+
+ # look for parameter xml file
+ paramfile = os.path.join(path, '.params')
+ if os.path.exists(paramfile):
+ i.tree = load_ipar_param_tree(paramfile)
+ mtime_local = os.stat(paramfile)[stat.ST_MTIME]
+ i.time = mtime_local
+ return i
+
+def fromxml(tree):
+ """
+ Initialize a IPAR object from an element tree node
+ """
+ f = IPAR()
+ f.set_elements(tree)
+ return f
+
+if __name__ == "__main__":
+ i = ipar(os.path.expanduser('~/gec/081021_HWI-EAS229_0063_30HKUAAXX/Data/IPAR_1.01'))
+ x = i.get_elements()
+ j = fromxml(x)
+ #ElementTree.dump(x)
+ print j.date
+ print j.start
+ print j.stop
+ print i.tiles.keys()
+ print j.tiles.keys()
+ print j.tiles.items()
+ print j.file_list()
\ No newline at end of file
from htsworkflow.util.alphanum import alphanum
from htsworkflow.util.ethelp import indent, flatten
-
class PipelineRun(object):
"""
Capture "interesting" information about a pipeline run
PIPELINE_RUN = 'PipelineRun'
FLOWCELL_ID = 'FlowcellID'
- def __init__(self, pathname=None, firecrest=None, bustard=None, gerald=None, xml=None):
+ def __init__(self, pathname=None, xml=None):
if pathname is not None:
self.pathname = os.path.normpath(pathname)
else:
self.pathname = None
self._name = None
self._flowcell_id = None
- self.firecrest = firecrest
- self.bustard = bustard
- self.gerald = gerald
+ self.image_analysis = None
+ self.bustard = None
+ self.gerald = None
if xml is not None:
self.set_elements(xml)
-
+
def _get_flowcell_id(self):
# extract flowcell ID
if self._flowcell_id is None:
flowcell_id = path_fields[-1]
else:
flowcell_id = 'unknown'
-
+
logging.warning(
"Flowcell id was not found, guessing %s" % (
flowcell_id))
root = ElementTree.Element(PipelineRun.PIPELINE_RUN)
flowcell = ElementTree.SubElement(root, PipelineRun.FLOWCELL_ID)
flowcell.text = self.flowcell_id
- root.append(self.firecrest.get_elements())
+ root.append(self.image_analysis.get_elements())
root.append(self.bustard.get_elements())
root.append(self.gerald.get_elements())
return root
# this file gets imported by all the others,
# so we need to hide the imports to avoid a cyclic imports
from htsworkflow.pipelines import firecrest
+ from htsworkflow.pipelines import ipar
from htsworkflow.pipelines import bustard
from htsworkflow.pipelines import gerald
if tag == PipelineRun.FLOWCELL_ID.lower():
self._flowcell_id = element.text
#ok the xword.Xword.XWORD pattern for module.class.constant is lame
+ # you should only have Firecrest or IPAR, never both of them.
elif tag == firecrest.Firecrest.FIRECREST.lower():
- self.firecrest = firecrest.Firecrest(xml=element)
+ self.image_analysis = firecrest.Firecrest(xml=element)
+ elif tag == ipar.IPAR.IPAR.lower():
+ self.image_analysis = ipar.IPAR(xml=element)
elif tag == bustard.Bustard.BUSTARD.lower():
self.bustard = bustard.Bustard(xml=element)
elif tag == gerald.Gerald.GERALD.lower():
Given a run tuple, find the latest date and use that as our name
"""
if self._name is None:
- tmax = max(self.firecrest.time, self.bustard.time, self.gerald.time)
+ tmax = max(self.image_analysis.time, self.bustard.time, self.gerald.time)
timestamp = time.strftime('%Y-%m-%d', time.localtime(tmax))
self._name = 'run_'+self.flowcell_id+"_"+timestamp+'.xml'
return self._name
in there gerald component.
"""
from htsworkflow.pipelines import firecrest
+ from htsworkflow.pipelines import ipar
from htsworkflow.pipelines import bustard
from htsworkflow.pipelines import gerald
- datadir = os.path.join(runfolder, 'Data')
-
- logging.info('Searching for runs in ' + datadir)
- runs = []
- for firecrest_pathname in glob(os.path.join(datadir,"*Firecrest*")):
- f = firecrest.firecrest(firecrest_pathname)
- bustard_glob = os.path.join(firecrest_pathname, "Bustard*")
+ def scan_post_image_analysis(runs, runfolder, image_analysis, pathname):
+ logging.info("Looking for bustard directories in %s" % (pathname,))
+ bustard_glob = os.path.join(pathname, "Bustard*")
for bustard_pathname in glob(bustard_glob):
+ logging.info("Found bustard directory %s" % (bustard_pathname,))
b = bustard.bustard(bustard_pathname)
gerald_glob = os.path.join(bustard_pathname, 'GERALD*')
+ logging.info("Looking for gerald directories in %s" % (pathname,))
for gerald_pathname in glob(gerald_glob):
+ logging.info("Found gerald directory %s" % (gerald_pathname,))
try:
g = gerald.gerald(gerald_pathname)
- runs.append(PipelineRun(runfolder, f, b, g))
+ p = PipelineRun(runfolder)
+ p.image_analysis = image_analysis
+ p.bustard = b
+ p.gerald = g
+ runs.append(p)
except IOError, e:
print "Ignoring", str(e)
+
+ datadir = os.path.join(runfolder, 'Data')
+
+ logging.info('Searching for runs in ' + datadir)
+ runs = []
+ # scan for firecrest directories
+ for firecrest_pathname in glob(os.path.join(datadir,"*Firecrest*")):
+ logging.info('Found firecrest in ' + datadir)
+ image_analysis = firecrest.firecrest(firecrest_pathname)
+ scan_post_image_analysis(runs, runfolder, image_analysis, firecrest_pathname)
+ # scan for IPAR directories
+ for ipar_pathname in glob(os.path.join(datadir,"IPAR_*")):
+ logging.info('Found ipar directories in ' + datadir)
+ image_analysis = ipar.ipar(ipar_pathname)
+ scan_post_image_analysis(runs, runfolder, image_analysis, ipar_pathname)
+
return runs
-
-
+
+
def extract_run_parameters(runs):
"""
Search through runfolder_path for various runs and grab their parameters
summarized_reads[genome] = genome_reads
return summarized_reads
+def summarize_lane(gerald, lane_id):
+ report = []
+ summary_results = gerald.summary.lane_results
+ eland_result = gerald.eland_results.results[lane_id]
+ report.append("Sample name %s" % (eland_result.sample_name))
+ report.append("Lane id %s" % (eland_result.lane_id,))
+ cluster = summary_results[eland_result.lane_id].cluster
+ report.append("Clusters %d +/- %d" % (cluster[0], cluster[1]))
+ report.append("Total Reads: %d" % (eland_result.reads))
+ mc = eland_result._match_codes
+ nm = mc['NM']
+ nm_percent = float(nm)/eland_result.reads * 100
+ qc = mc['QC']
+ qc_percent = float(qc)/eland_result.reads * 100
+
+ report.append("No Match: %d (%2.2g %%)" % (nm, nm_percent))
+ report.append("QC Failed: %d (%2.2g %%)" % (qc, qc_percent))
+ report.append('Unique (0,1,2 mismatches) %d %d %d' % \
+ (mc['U0'], mc['U1'], mc['U2']))
+ report.append('Repeat (0,1,2 mismatches) %d %d %d' % \
+ (mc['R0'], mc['R1'], mc['R2']))
+ report.append("Mapped Reads")
+ mapped_reads = summarize_mapped_reads(eland_result.mapped_reads)
+ for name, counts in mapped_reads.items():
+ report.append(" %s: %d" % (name, counts))
+ return report
+
def summary_report(runs):
"""
Summarize cluster numbers and mapped read counts for a runfolder
eland_keys = run.gerald.eland_results.results.keys()
eland_keys.sort(alphanum)
- lane_results = run.gerald.summary.lane_results
for lane_id in eland_keys:
- result = run.gerald.eland_results.results[lane_id]
- report.append("Sample name %s" % (result.sample_name))
- report.append("Lane id %s" % (result.lane_id,))
- cluster = lane_results[result.lane_id].cluster
- report.append("Clusters %d +/- %d" % (cluster[0], cluster[1]))
- report.append("Total Reads: %d" % (result.reads))
- mc = result._match_codes
- nm = mc['NM']
- nm_percent = float(nm)/result.reads * 100
- qc = mc['QC']
- qc_percent = float(qc)/result.reads * 100
-
- report.append("No Match: %d (%2.2g %%)" % (nm, nm_percent))
- report.append("QC Failed: %d (%2.2g %%)" % (qc, qc_percent))
- report.append('Unique (0,1,2 mismatches) %d %d %d' % \
- (mc['U0'], mc['U1'], mc['U2']))
- report.append('Repeat (0,1,2 mismatches) %d %d %d' % \
- (mc['R0'], mc['R1'], mc['R2']))
- report.append("Mapped Reads")
- mapped_reads = summarize_mapped_reads(result.mapped_reads)
- for name, counts in mapped_reads.items():
- report.append(" %s: %d" % (name, counts))
+ report.extend(summarize_lane(run.gerald, lane_id))
report.append('---')
report.append('')
return os.linesep.join(report)
logging.info("Using %s as result directory" % (result_dir,))
if not os.path.exists(result_dir):
os.mkdir(result_dir)
-
+
# create cycle_dir
- cycle = "C%d-%d" % (r.firecrest.start, r.firecrest.stop)
+ cycle = "C%d-%d" % (r.image_analysis.start, r.image_analysis.stop)
logging.info("Filling in %s" % (cycle,))
cycle_dir = os.path.join(result_dir, cycle)
if os.path.exists(cycle_dir):
logging.info("Running tar: " + " ".join(tar_cmd[:10]))
logging.info("Running bzip2: " + " ".join(bzip_cmd))
logging.info("Writing to %s" %(tar_dest_name))
-
+
tar = subprocess.Popen(tar_cmd, stdout=subprocess.PIPE, shell=False, cwd=g.pathname)
bzip = subprocess.Popen(bzip_cmd, stdin=tar.stdout, stdout=tar_dest)
tar.wait()
--- /dev/null
+"""
+Create simulated solexa/illumina runfolders for testing
+"""
+
+import os
+
+
+def make_ipar_dir(data_dir):
+ """
+ Construct an artificial ipar parameter file and directory
+ """
+ params = """<?xml version="1.0"?>
+<ImageAnalysis>
+ <Run Name="IPAR_1.01">
+ <Software Name="IPAR" Version="2.01.192.0" />
+ <Cycles First="1" Last="37" Number="37" />
+ <RunParameters>
+ <ImagingReads Index="1">
+ <FirstCycle>1</FirstCycle>
+ <LastCycle>37</LastCycle>
+ <RunFolder>081021_HWI-EAS229_0063_30HKUAAXX</RunFolder>
+ </ImagingReads>
+ <Reads Index="1">
+ <FirstCycle>1</FirstCycle>
+ <LastCycle>37</LastCycle>
+ <RunFolder>081021_HWI-EAS229_0063_30HKUAAXX</RunFolder>
+ </Reads>
+ <Compression>gzip</Compression>
+ <CompressionSuffix>.p.gz</CompressionSuffix>
+ <Instrument>HWI-EAS229</Instrument>
+ <RunFolder>081021_HWI-EAS229_0063_30HKUAAXX</RunFolder>
+ </RunParameters>
+ <ImageParameters>
+ <AutoOffsetFlag>1</AutoOffsetFlag>
+ <Fwhm>2.7</Fwhm>
+ <RemappingDistance>1.5</RemappingDistance>
+ <Threshold>4</Threshold>
+ </ImageParameters>
+ <TileSelection>
+ <Lane Index="1">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="2">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="3">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="4">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="5">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="6">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="7">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ <Lane Index="8">
+ <Sample>s</Sample>
+ <TileRange Max="100" Min="1" />
+ </Lane>
+ </TileSelection>
+ </Run>
+</ImageAnalysis>
+"""
+ f = open(os.path.join(data_dir, '.params'),'w')
+ f.write(params)
+ f.close()
+ ipar_dir = os.path.join(data_dir, 'IPAR_1.01')
+ if not os.path.exists(ipar_dir):
+ os.mkdir(ipar_dir)
+ return ipar_dir
+
+def make_flowcell_id(runfolder_dir, flowcell_id=None):
+ if flowcell_id is None:
+ flowcell_id = '207BTAAXY'
+
+ config = """<?xml version="1.0"?>
+<FlowcellId>
+ <Text>%s</Text>
+</FlowcellId>""" % (flowcell_id,)
+ config_dir = os.path.join(runfolder_dir, 'Config')
+
+ if not os.path.exists(config_dir):
+ os.mkdir(config_dir)
+ pathname = os.path.join(config_dir, 'FlowcellId.xml')
+ f = open(pathname,'w')
+ f.write(config)
+ f.close()
+
+def make_matrix(matrix_dir):
+ contents = """# Auto-generated frequency response matrix
+> A
+> C
+> G
+> T
+0.77 0.15 -0.04 -0.04
+0.76 1.02 -0.05 -0.06
+-0.10 -0.10 1.17 -0.03
+-0.13 -0.12 0.80 1.27
+"""
+ s_matrix = os.path.join(matrix_dir, 's_matrix.txt')
+ f = open(s_matrix, 'w')
+ f.write(contents)
+ f.close()
+
+def make_phasing_params(bustard_dir):
+ for lane in range(1,9):
+ pathname = os.path.join(bustard_dir, 'params%d.xml' % (lane))
+ f = open(pathname, 'w')
+ f.write("""<Parameters>
+ <Phasing>0.009900</Phasing>
+ <Prephasing>0.003500</Prephasing>
+</Parameters>
+""")
+ f.close()
+
+def make_gerald_config(gerald_dir):
+ config_xml = """<RunParameters>
+<ChipWideRunParameters>
+ <ANALYSIS>default</ANALYSIS>
+ <BAD_LANES></BAD_LANES>
+ <BAD_TILES></BAD_TILES>
+ <CONTAM_DIR></CONTAM_DIR>
+ <CONTAM_FILE></CONTAM_FILE>
+ <ELAND_GENOME>Need_to_specify_ELAND_genome_directory</ELAND_GENOME>
+ <ELAND_MULTIPLE_INSTANCES>8</ELAND_MULTIPLE_INSTANCES>
+ <ELAND_REPEAT></ELAND_REPEAT>
+ <EMAIL_DOMAIN>domain.com</EMAIL_DOMAIN>
+ <EMAIL_LIST>diane</EMAIL_LIST>
+ <EMAIL_SERVER>localhost:25</EMAIL_SERVER>
+ <EXPT_DIR>/home/diane/gec/080416_HWI-EAS229_0024_207BTAAXX/Data/C1-33_Firecrest1.8.28_19-04-2008_diane/Bustard1.8.28_19-04-2008_diane</EXPT_DIR>
+ <EXPT_DIR_ROOT>/home/diane/gec</EXPT_DIR_ROOT>
+ <FORCE>1</FORCE>
+ <GENOME_DIR>/home/diane/proj/SolexaPipeline-0.2.2.6/Goat/../Gerald/../../Genomes</GENOME_DIR>
+ <GENOME_FILE>Need_to_specify_genome_file_name</GENOME_FILE>
+ <HAMSTER_FLAG>genome</HAMSTER_FLAG>
+ <OUT_DIR>/home/diane/gec/080416_HWI-EAS229_0024_207BTAAXX/Data/C1-33_Firecrest1.8.28_19-04-2008_diane/Bustard1.8.28_19-04-2008_diane/GERALD_19-04-2008_diane</OUT_DIR>
+ <POST_RUN_COMMAND></POST_RUN_COMMAND>
+ <PRB_FILE_SUFFIX>_prb.txt</PRB_FILE_SUFFIX>
+ <PURE_BASES>12</PURE_BASES>
+ <QF_PARAMS>'((CHASTITY>=0.6))'</QF_PARAMS>
+ <QHG_FILE_SUFFIX>_qhg.txt</QHG_FILE_SUFFIX>
+ <QUALITY_FORMAT>--symbolic</QUALITY_FORMAT>
+ <READ_LENGTH>32</READ_LENGTH>
+ <SEQUENCE_FORMAT>--scarf</SEQUENCE_FORMAT>
+ <SEQ_FILE_SUFFIX>_seq.txt</SEQ_FILE_SUFFIX>
+ <SIG_FILE_SUFFIX_DEPHASED>_sig2.txt</SIG_FILE_SUFFIX_DEPHASED>
+ <SIG_FILE_SUFFIX_NOT_DEPHASED>_sig.txt</SIG_FILE_SUFFIX_NOT_DEPHASED>
+ <SOFTWARE_VERSION>@(#) Id: GERALD.pl,v 1.68.2.2 2007/06/13 11:08:49 km Exp</SOFTWARE_VERSION>
+ <TILE_REGEX>s_[1-8]_[0-9][0-9][0-9][0-9]</TILE_REGEX>
+ <TILE_ROOT>s</TILE_ROOT>
+ <TIME_STAMP>Sat Apr 19 19:08:30 2008</TIME_STAMP>
+ <TOOLS_DIR>/home/diane/proj/SolexaPipeline-0.2.2.6/Goat/../Gerald</TOOLS_DIR>
+ <USE_BASES>all</USE_BASES>
+ <WEB_DIR_ROOT>http://host.domain.com/yourshare/</WEB_DIR_ROOT>
+</ChipWideRunParameters>
+<LaneSpecificRunParameters>
+ <ANALYSIS>
+ <s_1>eland</s_1>
+ <s_2>eland</s_2>
+ <s_3>eland</s_3>
+ <s_4>eland</s_4>
+ <s_5>eland</s_5>
+ <s_6>eland</s_6>
+ <s_7>eland</s_7>
+ <s_8>eland</s_8>
+ </ANALYSIS>
+ <ELAND_GENOME>
+ <s_1>/g/dm3</s_1>
+ <s_2>/g/equcab1</s_2>
+ <s_3>/g/equcab1</s_3>
+ <s_4>/g/canfam2</s_4>
+ <s_5>/g/hg18</s_5>
+ <s_6>/g/hg18</s_6>
+ <s_7>/g/hg18</s_7>
+ <s_8>/g/hg18</s_8>
+ </ELAND_GENOME>
+ <READ_LENGTH>
+ <s_1>32</s_1>
+ <s_2>32</s_2>
+ <s_3>32</s_3>
+ <s_4>32</s_4>
+ <s_5>32</s_5>
+ <s_6>32</s_6>
+ <s_7>32</s_7>
+ <s_8>32</s_8>
+ </READ_LENGTH>
+ <USE_BASES>
+ <s_1>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_1>
+ <s_2>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_2>
+ <s_3>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_3>
+ <s_4>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_4>
+ <s_5>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_5>
+ <s_6>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_6>
+ <s_7>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_7>
+ <s_8>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_8>
+ </USE_BASES>
+</LaneSpecificRunParameters>
+</RunParameters>
+"""
+ pathname = os.path.join(gerald_dir, 'config.xml')
+ f = open(pathname,'w')
+ f.write(config_xml)
+ f.close()
+
+def make_summary100_htm(gerald_dir):
+ summary_htm="""<!--RUN_TIME Wed Jul 2 06:47:44 2008 -->
+<!--SOFTWARE_VERSION @(#) $Id: jerboa.pl,v 1.94 2007/12/04 09:59:07 rshaw Exp $-->
+<html>
+<body>
+
+<a name="Top"><h2><title>080627_HWI-EAS229_0036_3055HAXX Summary</title></h2></a>
+<h1>Summary Information For Experiment 080627_HWI-EAS229_0036_3055HAXX on Machine HWI-EAS229</h1>
+<h2><br></br>Chip Summary<br></br></h2>
+<table border="1" cellpadding="5">
+<tr><td>Machine</td><td>HWI-EAS229</td></tr>
+<tr><td>Run Folder</td><td>080627_HWI-EAS229_0036_3055HAXX</td></tr>
+<tr><td>Chip ID</td><td>unknown</td></tr>
+</table>
+<h2><br></br>Chip Results Summary<br></br></h2>
+<table border="1" cellpadding="5">
+<tr>
+<td>Clusters</td>
+<td>Clusters (PF)</td>
+<td>Yield (kbases)</td>
+</tr>
+<tr><td>80933224</td>
+<td>43577803</td>
+<td>1133022</td>
+</tr>
+</table>
+<h2><br></br>Lane Parameter Summary<br></br></h2>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane</td>
+<td>Sample ID</td>
+<td>Sample Target</td>
+<td>Sample Type</td>
+<td>Length</td>
+<td>Filter</td>
+<td>Num Tiles</td>
+<td>Tiles</td>
+</tr>
+<tr>
+<td>1</td>
+<td>unknown</td>
+<td>mm9</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane1">Lane 1</a></td>
+</tr>
+<tr>
+<td>2</td>
+<td>unknown</td>
+<td>mm9</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane2">Lane 2</a></td>
+</tr>
+<tr>
+<td>3</td>
+<td>unknown</td>
+<td>mm9</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane3">Lane 3</a></td>
+</tr>
+<tr>
+<td>4</td>
+<td>unknown</td>
+<td>elegans170</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane4">Lane 4</a></td>
+</tr>
+<tr>
+<td>5</td>
+<td>unknown</td>
+<td>elegans170</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane5">Lane 5</a></td>
+</tr>
+<tr>
+<td>6</td>
+<td>unknown</td>
+<td>elegans170</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane6">Lane 6</a></td>
+</tr>
+<tr>
+<td>7</td>
+<td>unknown</td>
+<td>elegans170</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane7">Lane 7</a></td>
+</tr>
+<tr>
+<td>8</td>
+<td>unknown</td>
+<td>elegans170</td>
+<td>ELAND</td>
+<td>26</td>
+<td>'((CHASTITY>=0.6))'</td>
+<td>100</td>
+<td><a href="#Lane8">Lane 8</a></td>
+</tr>
+</table>
+<h2><br></br>Lane Results Summary<br></br></h2>
+<table border="1" cellpadding="5">
+<tr>
+<td colspan="2">Lane Info</td>
+<td colspan="8">Tile Mean +/- SD for Lane</td>
+</tr>
+<tr>
+<td>Lane </td>
+<td>Lane Yield (kbases) </td>
+<td>Clusters (raw)</td>
+<td>Clusters (PF) </td>
+<td>1st Cycle Int (PF) </td>
+<td>% intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Alignment Score (PF) </td>
+<td> % Error Rate (PF) </td>
+</tr>
+<tr>
+<td>1</td>
+<td>158046</td>
+<td>96483 +/- 9074</td>
+<td>60787 +/- 4240</td>
+<td>329 +/- 35</td>
+<td>101.88 +/- 6.03</td>
+<td>63.21 +/- 3.29</td>
+<td>70.33 +/- 0.24</td>
+<td>9054.08 +/- 59.16</td>
+<td>0.46 +/- 0.18</td>
+</tr>
+<tr>
+<td>2</td>
+<td>156564</td>
+<td>133738 +/- 7938</td>
+<td>60217 +/- 1926</td>
+<td>444 +/- 39</td>
+<td>92.62 +/- 7.58</td>
+<td>45.20 +/- 3.31</td>
+<td>51.98 +/- 0.74</td>
+<td>6692.04 +/- 92.49</td>
+<td>0.46 +/- 0.09</td>
+</tr>
+<tr>
+<td>3</td>
+<td>185818</td>
+<td>152142 +/- 10002</td>
+<td>71468 +/- 2827</td>
+<td>366 +/- 36</td>
+<td>91.53 +/- 8.66</td>
+<td>47.19 +/- 3.80</td>
+<td>82.24 +/- 0.44</td>
+<td>10598.68 +/- 64.13</td>
+<td>0.41 +/- 0.04</td>
+</tr>
+<tr>
+<td>4</td>
+<td>34953</td>
+<td>15784 +/- 2162</td>
+<td>13443 +/- 1728</td>
+<td>328 +/- 40</td>
+<td>97.53 +/- 9.87</td>
+<td>85.29 +/- 1.91</td>
+<td>80.02 +/- 0.53</td>
+<td>10368.82 +/- 71.08</td>
+<td>0.15 +/- 0.05</td>
+</tr>
+<tr>
+<td>5</td>
+<td>167936</td>
+<td>119735 +/- 8465</td>
+<td>64590 +/- 2529</td>
+<td>417 +/- 37</td>
+<td>88.69 +/- 14.79</td>
+<td>54.10 +/- 2.59</td>
+<td>76.95 +/- 0.32</td>
+<td>9936.47 +/- 65.75</td>
+<td>0.28 +/- 0.02</td>
+</tr>
+<tr>
+<td>6</td>
+<td>173463</td>
+<td>152177 +/- 8146</td>
+<td>66716 +/- 2493</td>
+<td>372 +/- 39</td>
+<td>87.06 +/- 9.86</td>
+<td>43.98 +/- 3.12</td>
+<td>78.80 +/- 0.43</td>
+<td>10162.28 +/- 49.65</td>
+<td>0.38 +/- 0.03</td>
+</tr>
+<tr>
+<td>7</td>
+<td>149287</td>
+<td>84649 +/- 7325</td>
+<td>57418 +/- 3617</td>
+<td>295 +/- 28</td>
+<td>89.40 +/- 8.23</td>
+<td>67.97 +/- 1.82</td>
+<td>33.38 +/- 0.25</td>
+<td>4247.92 +/- 32.37</td>
+<td>1.00 +/- 0.03</td>
+</tr>
+<tr>
+<td>8</td>
+<td>106953</td>
+<td>54622 +/- 4812</td>
+<td>41136 +/- 3309</td>
+<td>284 +/- 37</td>
+<td>90.21 +/- 9.10</td>
+<td>75.39 +/- 2.27</td>
+<td>48.33 +/- 0.29</td>
+<td>6169.21 +/- 169.50</td>
+<td>0.86 +/- 1.22</td>
+</tr>
+<tr><td colspan="13">Tile mean across chip</td></tr>
+<tr>
+<td>Av.</td>
+<td></td>
+<td>101166</td>
+<td>54472</td>
+<td>354</td>
+<td>92.36</td>
+<td>60.29</td>
+<td>65.25</td>
+<td>8403.69</td>
+<td>0.50</td>
+</tr>
+</table>
+<h2><br></br>Expanded Lane Summary<br></br></h2>
+<table border="1" cellpadding="5">
+<tr>
+
+<tr><td colspan="2">Lane Info</td>
+<td colspan="2">Phasing Info</td>
+<td colspan="2">Raw Data (tile mean)</td>
+<td colspan="7">Filtered Data (tile mean)</td></tr>
+<td>Lane </td>
+<td>Clusters (tile mean) (raw)</td>
+<td>% Phasing </td>
+<td>% Prephasing </td>
+<td>% Error Rate (raw) </td>
+<td> Equiv Perfect Clusters (raw) </td>
+<td>% retained </td>
+<td>Cycle 2-4 Av Int (PF) </td>
+<td>Cycle 2-10 Av % Loss (PF) </td>
+<td>Cycle 10-20 Av % Loss (PF) </td>
+<td>% Align (PF) </td>
+<td>% Error Rate (PF) </td>
+<td> Equiv Perfect Clusters (PF) </td>
+</tr>
+<tr>
+<td>1</td>
+<td>96483</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>1.00</td>
+<td>49676</td>
+<td>63.21</td>
+<td>317 +/- 32</td>
+<td>0.13 +/- 0.44</td>
+<td>-1.14 +/- 0.34</td>
+<td>70.33</td>
+<td>0.46</td>
+<td>41758</td>
+</tr>
+<tr>
+<td>2</td>
+<td>133738</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>1.22</td>
+<td>40467</td>
+<td>45.20</td>
+<td>415 +/- 33</td>
+<td>0.29 +/- 0.40</td>
+<td>-0.79 +/- 0.35</td>
+<td>51.98</td>
+<td>0.46</td>
+<td>30615</td>
+</tr>
+<tr>
+<td>3</td>
+<td>152142</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>1.30</td>
+<td>78588</td>
+<td>47.19</td>
+<td>344 +/- 26</td>
+<td>0.68 +/- 0.51</td>
+<td>-0.77 +/- 0.42</td>
+<td>82.24</td>
+<td>0.41</td>
+<td>57552</td>
+</tr>
+<tr>
+<td>4</td>
+<td>15784</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>0.29</td>
+<td>11095</td>
+<td>85.29</td>
+<td>306 +/- 34</td>
+<td>0.20 +/- 0.69</td>
+<td>-1.28 +/- 0.66</td>
+<td>80.02</td>
+<td>0.15</td>
+<td>10671</td>
+</tr>
+<tr>
+<td>5</td>
+<td>119735</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>0.85</td>
+<td>60335</td>
+<td>54.10</td>
+<td>380 +/- 32</td>
+<td>0.34 +/- 0.49</td>
+<td>-1.55 +/- 4.69</td>
+<td>76.95</td>
+<td>0.28</td>
+<td>49015</td>
+</tr>
+<tr>
+<td>6</td>
+<td>152177</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>1.21</td>
+<td>70905</td>
+<td>43.98</td>
+<td>333 +/- 27</td>
+<td>0.57 +/- 0.50</td>
+<td>-0.91 +/- 0.39</td>
+<td>78.80</td>
+<td>0.38</td>
+<td>51663</td>
+</tr>
+<tr>
+<td>7</td>
+<td>84649</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>1.38</td>
+<td>21069</td>
+<td>67.97</td>
+<td>272 +/- 20</td>
+<td>1.15 +/- 0.52</td>
+<td>-0.84 +/- 0.58</td>
+<td>33.38</td>
+<td>1.00</td>
+<td>18265</td>
+</tr>
+<tr>
+<td>8</td>
+<td>54622</td>
+<td>0.7700</td>
+<td>0.3100</td>
+<td>1.17</td>
+<td>21335</td>
+<td>75.39</td>
+<td>262 +/- 31</td>
+<td>1.10 +/- 0.59</td>
+<td>-1.01 +/- 0.47</td>
+<td>48.33</td>
+<td>0.86</td>
+<td>19104</td>
+</tr>
+</table>
+<b><br></br>IVC Plots</b>
+<p> <a href='IVC.htm' target="_blank"> IVC.htm
+ </a></p>
+<b><br></br>All Intensity Plots</b>
+<p> <a href='All.htm' target="_blank"> All.htm
+ </a></p>
+<b><br></br>Error graphs: </b>
+<p> <a href='Error.htm' target="_blank"> Error.htm
+ </a></p>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane1"><h2><br></br>Lane 1<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>1</td>
+<td>0001</td>
+<td>114972</td>
+<td>326.48</td>
+<td>94.39</td>
+<td>57.44</td>
+<td>70.2</td>
+<td>9038.6</td>
+<td>0.44</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane2"><h2><br></br>Lane 2<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>2</td>
+<td>0001</td>
+<td>147793</td>
+<td>448.12</td>
+<td>83.68</td>
+<td>38.57</td>
+<td>53.7</td>
+<td>6905.4</td>
+<td>0.54</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane3"><h2><br></br>Lane 3<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>3</td>
+<td>0001</td>
+<td>167904</td>
+<td>374.05</td>
+<td>86.91</td>
+<td>40.36</td>
+<td>81.3</td>
+<td>10465.0</td>
+<td>0.47</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane4"><h2><br></br>Lane 4<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>4</td>
+<td>0001</td>
+<td>20308</td>
+<td>276.85</td>
+<td>92.87</td>
+<td>84.26</td>
+<td>80.4</td>
+<td>10413.8</td>
+<td>0.16</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane5"><h2><br></br>Lane 5<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane6"><h2><br></br>Lane 6<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>6</td>
+<td>0001</td>
+<td>166844</td>
+<td>348.12</td>
+<td>77.59</td>
+<td>38.13</td>
+<td>79.7</td>
+<td>10264.4</td>
+<td>0.44</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane7"><h2><br></br>Lane 7<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>7</td>
+<td>0001</td>
+<td>98913</td>
+<td>269.90</td>
+<td>86.66</td>
+<td>64.55</td>
+<td>33.2</td>
+<td>4217.5</td>
+<td>1.02</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+<a name="Lane8"><h2><br></br>Lane 8<br></br></h2></a>
+<table border="1" cellpadding="5">
+<tr>
+<td>Lane </td>
+<td>Tile </td>
+<td>Clusters (raw)</td>
+<td>Av 1st Cycle Int (PF) </td>
+<td>Av % intensity after 20 cycles (PF) </td>
+<td>% PF Clusters </td>
+<td>% Align (PF) </td>
+<td>Av Alignment Score (PF) </td>
+<td>% Error Rate (PF) </td>
+</tr>
+<tr>
+<td>8</td>
+<td>0001</td>
+<td>64972</td>
+<td>243.60</td>
+<td>89.40</td>
+<td>73.17</td>
+<td>48.3</td>
+<td>6182.8</td>
+<td>0.71</td>
+</tr>
+</table>
+<td><a href="#Top">Back to top</a></td>
+</body>
+</html>
+"""
+ pathname = os.path.join(gerald_dir, 'Summary.htm')
+ f = open(pathname, 'w')
+ f.write(summary_htm)
+ f.close()
+
+def make_eland_results(gerald_dir):
+ eland_result = """>HWI-EAS229_24_207BTAAXX:1:7:599:759 ACATAGNCACAGACATAAACATAGACATAGAC U0 1 1 3 chrUextra.fa 28189829 R D.
+>HWI-EAS229_24_207BTAAXX:1:7:205:842 AAACAANNCTCCCAAACACGTAAACTGGAAAA U1 0 1 0 chr2L.fa 8796855 R DD 24T
+>HWI-EAS229_24_207BTAAXX:1:7:776:582 AGCTCANCCGATCGAAAACCTCNCCAAGCAAT NM 0 0 0
+>HWI-EAS229_24_207BTAAXX:1:7:205:842 AAACAANNCTCCCAAACACGTAAACTGGAAAA U1 0 1 0 Lambda.fa 8796855 R DD 24T
+"""
+ for i in range(1,9):
+ pathname = os.path.join(gerald_dir,
+ 's_%d_eland_result.txt' % (i,))
+ f = open(pathname, 'w')
+ f.write(eland_result)
+ f.close()
from htsworkflow.pipelines import runfolder
from htsworkflow.pipelines.runfolder import ElementTree
+from htsworkflow.pipelines.test.simulate_runfolder import *
-def make_flowcell_id(runfolder_dir, flowcell_id=None):
- if flowcell_id is None:
- flowcell_id = '207BTAAXY'
-
- config = """<?xml version="1.0"?>
-<FlowcellId>
- <Text>%s</Text>
-</FlowcellId>""" % (flowcell_id,)
- config_dir = os.path.join(runfolder_dir, 'Config')
-
- if not os.path.exists(config_dir):
- os.mkdir(config_dir)
- pathname = os.path.join(config_dir, 'FlowcellId.xml')
- f = open(pathname,'w')
- f.write(config)
- f.close()
-
-def make_matrix(matrix_dir):
- contents = """# Auto-generated frequency response matrix
-> A
-> C
-> G
-> T
-0.77 0.15 -0.04 -0.04
-0.76 1.02 -0.05 -0.06
--0.10 -0.10 1.17 -0.03
--0.13 -0.12 0.80 1.27
-"""
- s_matrix = os.path.join(matrix_dir, 's_matrix.txt')
- f = open(s_matrix, 'w')
- f.write(contents)
- f.close()
-
-def make_phasing_params(bustard_dir):
- for lane in range(1,9):
- pathname = os.path.join(bustard_dir, 'params%d.xml' % (lane))
- f = open(pathname, 'w')
- f.write("""<Parameters>
- <Phasing>0.009900</Phasing>
- <Prephasing>0.003500</Prephasing>
-</Parameters>
-""")
- f.close()
-
-def make_gerald_config(gerald_dir):
- config_xml = """<RunParameters>
-<ChipWideRunParameters>
- <ANALYSIS>default</ANALYSIS>
- <BAD_LANES></BAD_LANES>
- <BAD_TILES></BAD_TILES>
- <CONTAM_DIR></CONTAM_DIR>
- <CONTAM_FILE></CONTAM_FILE>
- <ELAND_GENOME>Need_to_specify_ELAND_genome_directory</ELAND_GENOME>
- <ELAND_MULTIPLE_INSTANCES>8</ELAND_MULTIPLE_INSTANCES>
- <ELAND_REPEAT></ELAND_REPEAT>
- <EMAIL_DOMAIN>domain.com</EMAIL_DOMAIN>
- <EMAIL_LIST>diane</EMAIL_LIST>
- <EMAIL_SERVER>localhost:25</EMAIL_SERVER>
- <EXPT_DIR>/home/diane/gec/080416_HWI-EAS229_0024_207BTAAXX/Data/C1-33_Firecrest1.8.28_19-04-2008_diane/Bustard1.8.28_19-04-2008_diane</EXPT_DIR>
- <EXPT_DIR_ROOT>/home/diane/gec</EXPT_DIR_ROOT>
- <FORCE>1</FORCE>
- <GENOME_DIR>/home/diane/proj/SolexaPipeline-0.2.2.6/Goat/../Gerald/../../Genomes</GENOME_DIR>
- <GENOME_FILE>Need_to_specify_genome_file_name</GENOME_FILE>
- <HAMSTER_FLAG>genome</HAMSTER_FLAG>
- <OUT_DIR>/home/diane/gec/080416_HWI-EAS229_0024_207BTAAXX/Data/C1-33_Firecrest1.8.28_19-04-2008_diane/Bustard1.8.28_19-04-2008_diane/GERALD_19-04-2008_diane</OUT_DIR>
- <POST_RUN_COMMAND></POST_RUN_COMMAND>
- <PRB_FILE_SUFFIX>_prb.txt</PRB_FILE_SUFFIX>
- <PURE_BASES>12</PURE_BASES>
- <QF_PARAMS>'((CHASTITY>=0.6))'</QF_PARAMS>
- <QHG_FILE_SUFFIX>_qhg.txt</QHG_FILE_SUFFIX>
- <QUALITY_FORMAT>--symbolic</QUALITY_FORMAT>
- <READ_LENGTH>32</READ_LENGTH>
- <SEQUENCE_FORMAT>--scarf</SEQUENCE_FORMAT>
- <SEQ_FILE_SUFFIX>_seq.txt</SEQ_FILE_SUFFIX>
- <SIG_FILE_SUFFIX_DEPHASED>_sig2.txt</SIG_FILE_SUFFIX_DEPHASED>
- <SIG_FILE_SUFFIX_NOT_DEPHASED>_sig.txt</SIG_FILE_SUFFIX_NOT_DEPHASED>
- <SOFTWARE_VERSION>@(#) Id: GERALD.pl,v 1.68.2.2 2007/06/13 11:08:49 km Exp</SOFTWARE_VERSION>
- <TILE_REGEX>s_[1-8]_[0-9][0-9][0-9][0-9]</TILE_REGEX>
- <TILE_ROOT>s</TILE_ROOT>
- <TIME_STAMP>Sat Apr 19 19:08:30 2008</TIME_STAMP>
- <TOOLS_DIR>/home/diane/proj/SolexaPipeline-0.2.2.6/Goat/../Gerald</TOOLS_DIR>
- <USE_BASES>all</USE_BASES>
- <WEB_DIR_ROOT>http://host.domain.com/yourshare/</WEB_DIR_ROOT>
-</ChipWideRunParameters>
-<LaneSpecificRunParameters>
- <ANALYSIS>
- <s_1>eland</s_1>
- <s_2>eland</s_2>
- <s_3>eland</s_3>
- <s_4>eland</s_4>
- <s_5>eland</s_5>
- <s_6>eland</s_6>
- <s_7>eland</s_7>
- <s_8>eland</s_8>
- </ANALYSIS>
- <ELAND_GENOME>
- <s_1>/g/dm3</s_1>
- <s_2>/g/equcab1</s_2>
- <s_3>/g/equcab1</s_3>
- <s_4>/g/canfam2</s_4>
- <s_5>/g/hg18</s_5>
- <s_6>/g/hg18</s_6>
- <s_7>/g/hg18</s_7>
- <s_8>/g/hg18</s_8>
- </ELAND_GENOME>
- <READ_LENGTH>
- <s_1>32</s_1>
- <s_2>32</s_2>
- <s_3>32</s_3>
- <s_4>32</s_4>
- <s_5>32</s_5>
- <s_6>32</s_6>
- <s_7>32</s_7>
- <s_8>32</s_8>
- </READ_LENGTH>
- <USE_BASES>
- <s_1>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_1>
- <s_2>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_2>
- <s_3>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_3>
- <s_4>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_4>
- <s_5>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_5>
- <s_6>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_6>
- <s_7>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_7>
- <s_8>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_8>
- </USE_BASES>
-</LaneSpecificRunParameters>
-</RunParameters>
-"""
- pathname = os.path.join(gerald_dir, 'config.xml')
- f = open(pathname,'w')
- f.write(config_xml)
- f.close()
-
def make_summary_htm(gerald_dir):
summary_htm = """<!--RUN_TIME Mon Apr 21 11:52:25 2008 -->
r2 = runfolder.PipelineRun(xml=xml)
self.failUnlessEqual(r1.name, r2.name)
- self.failIfEqual(r2.firecrest, None)
+ self.failIfEqual(r2.image_analysis, None)
self.failIfEqual(r2.bustard, None)
self.failIfEqual(r2.gerald, None)
from htsworkflow.pipelines import runfolder
from htsworkflow.pipelines.runfolder import ElementTree
+from htsworkflow.pipelines.test.simulate_runfolder import *
-def make_flowcell_id(runfolder_dir, flowcell_id=None):
- if flowcell_id is None:
- flowcell_id = '207BTAAXY'
-
- config = """<?xml version="1.0"?>
-<FlowcellId>
- <Text>%s</Text>
-</FlowcellId>""" % (flowcell_id,)
- config_dir = os.path.join(runfolder_dir, 'Config')
-
- if not os.path.exists(config_dir):
- os.mkdir(config_dir)
- pathname = os.path.join(config_dir, 'FlowcellId.xml')
- f = open(pathname,'w')
- f.write(config)
- f.close()
-
-def make_matrix(matrix_dir):
- contents = """# Auto-generated frequency response matrix
-> A
-> C
-> G
-> T
-0.77 0.15 -0.04 -0.04
-0.76 1.02 -0.05 -0.06
--0.10 -0.10 1.17 -0.03
--0.13 -0.12 0.80 1.27
-"""
- s_matrix = os.path.join(matrix_dir, 's_matrix.txt')
- f = open(s_matrix, 'w')
- f.write(contents)
- f.close()
-
-def make_phasing_params(bustard_dir):
- for lane in range(1,9):
- pathname = os.path.join(bustard_dir, 'params%d.xml' % (lane))
- f = open(pathname, 'w')
- f.write("""<Parameters>
- <Phasing>0.009900</Phasing>
- <Prephasing>0.003500</Prephasing>
-</Parameters>
-""")
- f.close()
-
-def make_gerald_config(gerald_dir):
- config_xml = """<RunParameters>
-<ChipWideRunParameters>
- <ANALYSIS>default</ANALYSIS>
- <BAD_LANES></BAD_LANES>
- <BAD_TILES></BAD_TILES>
- <CONTAM_DIR></CONTAM_DIR>
- <CONTAM_FILE></CONTAM_FILE>
- <ELAND_GENOME>Need_to_specify_ELAND_genome_directory</ELAND_GENOME>
- <ELAND_MULTIPLE_INSTANCES>8</ELAND_MULTIPLE_INSTANCES>
- <ELAND_REPEAT></ELAND_REPEAT>
- <EMAIL_DOMAIN>domain.com</EMAIL_DOMAIN>
- <EMAIL_LIST>diane</EMAIL_LIST>
- <EMAIL_SERVER>localhost:25</EMAIL_SERVER>
- <EXPT_DIR>/home/diane/gec/080416_HWI-EAS229_0024_207BTAAXX/Data/C1-33_Firecrest1.8.28_19-04-2008_diane/Bustard1.8.28_19-04-2008_diane</EXPT_DIR>
- <EXPT_DIR_ROOT>/home/diane/gec</EXPT_DIR_ROOT>
- <FORCE>1</FORCE>
- <GENOME_DIR>/home/diane/proj/SolexaPipeline-0.2.2.6/Goat/../Gerald/../../Genomes</GENOME_DIR>
- <GENOME_FILE>Need_to_specify_genome_file_name</GENOME_FILE>
- <HAMSTER_FLAG>genome</HAMSTER_FLAG>
- <OUT_DIR>/home/diane/gec/080416_HWI-EAS229_0024_207BTAAXX/Data/C1-33_Firecrest1.8.28_19-04-2008_diane/Bustard1.8.28_19-04-2008_diane/GERALD_19-04-2008_diane</OUT_DIR>
- <POST_RUN_COMMAND></POST_RUN_COMMAND>
- <PRB_FILE_SUFFIX>_prb.txt</PRB_FILE_SUFFIX>
- <PURE_BASES>12</PURE_BASES>
- <QF_PARAMS>'((CHASTITY>=0.6))'</QF_PARAMS>
- <QHG_FILE_SUFFIX>_qhg.txt</QHG_FILE_SUFFIX>
- <QUALITY_FORMAT>--symbolic</QUALITY_FORMAT>
- <READ_LENGTH>32</READ_LENGTH>
- <SEQUENCE_FORMAT>--scarf</SEQUENCE_FORMAT>
- <SEQ_FILE_SUFFIX>_seq.txt</SEQ_FILE_SUFFIX>
- <SIG_FILE_SUFFIX_DEPHASED>_sig2.txt</SIG_FILE_SUFFIX_DEPHASED>
- <SIG_FILE_SUFFIX_NOT_DEPHASED>_sig.txt</SIG_FILE_SUFFIX_NOT_DEPHASED>
- <SOFTWARE_VERSION>@(#) Id: GERALD.pl,v 1.68.2.2 2007/06/13 11:08:49 km Exp</SOFTWARE_VERSION>
- <TILE_REGEX>s_[1-8]_[0-9][0-9][0-9][0-9]</TILE_REGEX>
- <TILE_ROOT>s</TILE_ROOT>
- <TIME_STAMP>Sat Apr 19 19:08:30 2008</TIME_STAMP>
- <TOOLS_DIR>/home/diane/proj/SolexaPipeline-0.2.2.6/Goat/../Gerald</TOOLS_DIR>
- <USE_BASES>all</USE_BASES>
- <WEB_DIR_ROOT>http://host.domain.com/yourshare/</WEB_DIR_ROOT>
-</ChipWideRunParameters>
-<LaneSpecificRunParameters>
- <ANALYSIS>
- <s_1>eland</s_1>
- <s_2>eland</s_2>
- <s_3>eland</s_3>
- <s_4>eland</s_4>
- <s_5>eland</s_5>
- <s_6>eland</s_6>
- <s_7>eland</s_7>
- <s_8>eland</s_8>
- </ANALYSIS>
- <ELAND_GENOME>
- <s_1>/g/dm3</s_1>
- <s_2>/g/equcab1</s_2>
- <s_3>/g/equcab1</s_3>
- <s_4>/g/canfam2</s_4>
- <s_5>/g/hg18</s_5>
- <s_6>/g/hg18</s_6>
- <s_7>/g/hg18</s_7>
- <s_8>/g/hg18</s_8>
- </ELAND_GENOME>
- <READ_LENGTH>
- <s_1>32</s_1>
- <s_2>32</s_2>
- <s_3>32</s_3>
- <s_4>32</s_4>
- <s_5>32</s_5>
- <s_6>32</s_6>
- <s_7>32</s_7>
- <s_8>32</s_8>
- </READ_LENGTH>
- <USE_BASES>
- <s_1>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_1>
- <s_2>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_2>
- <s_3>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_3>
- <s_4>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_4>
- <s_5>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_5>
- <s_6>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_6>
- <s_7>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_7>
- <s_8>YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY</s_8>
- </USE_BASES>
-</LaneSpecificRunParameters>
-</RunParameters>
-"""
- pathname = os.path.join(gerald_dir, 'config.xml')
- f = open(pathname,'w')
- f.write(config_xml)
- f.close()
def make_summary_htm(gerald_dir):
summary_htm="""<!--RUN_TIME Wed Jul 2 06:47:44 2008 -->
r2 = runfolder.PipelineRun(xml=xml)
self.failUnlessEqual(r1.name, r2.name)
- self.failIfEqual(r2.firecrest, None)
+ self.failIfEqual(r2.image_analysis, None)
self.failIfEqual(r2.bustard, None)
self.failIfEqual(r2.gerald, None)
--- /dev/null
+#!/usr/bin/env python
+
+from datetime import datetime, date
+import os
+import tempfile
+import shutil
+import unittest
+
+from htsworkflow.pipelines import ipar
+from htsworkflow.pipelines import bustard
+from htsworkflow.pipelines import gerald
+from htsworkflow.pipelines import runfolder
+from htsworkflow.pipelines.runfolder import ElementTree
+
+from htsworkflow.pipelines.test.simulate_runfolder import *
+
+
+def make_runfolder(obj=None):
+ """
+ Make a fake runfolder, attach all the directories to obj if defined
+ """
+ # make a fake runfolder directory
+ temp_dir = tempfile.mkdtemp(prefix='tmp_runfolder_')
+
+ runfolder_dir = os.path.join(temp_dir,
+ '080102_HWI-EAS229_0010_207BTAAXX')
+ os.mkdir(runfolder_dir)
+
+ data_dir = os.path.join(runfolder_dir, 'Data')
+ os.mkdir(data_dir)
+
+ ipar_dir = make_ipar_dir(data_dir)
+
+ matrix_dir = os.path.join(ipar_dir, 'Matrix')
+ os.mkdir(matrix_dir)
+ make_matrix(matrix_dir)
+
+ bustard_dir = os.path.join(ipar_dir,
+ 'Bustard1.8.28_12-04-2008_diane')
+ os.mkdir(bustard_dir)
+ make_phasing_params(bustard_dir)
+
+ gerald_dir = os.path.join(bustard_dir,
+ 'GERALD_12-04-2008_diane')
+ os.mkdir(gerald_dir)
+ make_gerald_config(gerald_dir)
+ make_summary100_htm(gerald_dir)
+ make_eland_results(gerald_dir)
+
+ if obj is not None:
+ obj.temp_dir = temp_dir
+ obj.runfolder_dir = runfolder_dir
+ obj.data_dir = data_dir
+ obj.image_analysis_dir = ipar_dir
+ obj.matrix_dir = matrix_dir
+ obj.bustard_dir = bustard_dir
+ obj.gerald_dir = gerald_dir
+
+
+class RunfolderTests(unittest.TestCase):
+ """
+ Test components of the runfolder processing code
+ which includes firecrest, bustard, and gerald
+ """
+ def setUp(self):
+ # attaches all the directories to the object passed in
+ make_runfolder(self)
+
+ def tearDown(self):
+ shutil.rmtree(self.temp_dir)
+
+ def test_ipar(self):
+ """
+ Construct a firecrest object
+ """
+ i = ipar.ipar(self.image_analysis_dir)
+ self.failUnlessEqual(i.version, '2.01.192.0')
+ self.failUnlessEqual(i.start, 1)
+ self.failUnlessEqual(i.stop, 37)
+
+ xml = i.get_elements()
+ # just make sure that element tree can serialize the tree
+ xml_str = ElementTree.tostring(xml)
+
+ i2 = ipar.IPAR(xml=xml)
+ self.failUnlessEqual(i.version, i2.version)
+ self.failUnlessEqual(i.start, i2.start)
+ self.failUnlessEqual(i.stop, i2.stop)
+ self.failUnlessEqual(i.date, i2.date)
+ self.failUnlessEqual(i.file_list(), i2.file_list())
+
+ def test_bustard(self):
+ """
+ construct a bustard object
+ """
+ b = bustard.bustard(self.bustard_dir)
+ self.failUnlessEqual(b.version, '1.8.28')
+ self.failUnlessEqual(b.date, date(2008,4,12))
+ self.failUnlessEqual(b.user, 'diane')
+ self.failUnlessEqual(len(b.phasing), 8)
+ self.failUnlessAlmostEqual(b.phasing[8].phasing, 0.0099)
+
+ xml = b.get_elements()
+ b2 = bustard.Bustard(xml=xml)
+ self.failUnlessEqual(b.version, b2.version)
+ self.failUnlessEqual(b.date, b2.date )
+ self.failUnlessEqual(b.user, b2.user)
+ self.failUnlessEqual(len(b.phasing), len(b2.phasing))
+ for key in b.phasing.keys():
+ self.failUnlessEqual(b.phasing[key].lane,
+ b2.phasing[key].lane)
+ self.failUnlessEqual(b.phasing[key].phasing,
+ b2.phasing[key].phasing)
+ self.failUnlessEqual(b.phasing[key].prephasing,
+ b2.phasing[key].prephasing)
+
+ def test_gerald(self):
+ # need to update gerald and make tests for it
+ g = gerald.gerald(self.gerald_dir)
+
+ self.failUnlessEqual(g.version,
+ '@(#) Id: GERALD.pl,v 1.68.2.2 2007/06/13 11:08:49 km Exp')
+ self.failUnlessEqual(g.date, datetime(2008,4,19,19,8,30))
+ self.failUnlessEqual(len(g.lanes), len(g.lanes.keys()))
+ self.failUnlessEqual(len(g.lanes), len(g.lanes.items()))
+
+
+ # list of genomes, matches what was defined up in
+ # make_gerald_config.
+ # the first None is to offset the genomes list to be 1..9
+ # instead of pythons default 0..8
+ genomes = [None, '/g/dm3', '/g/equcab1', '/g/equcab1', '/g/canfam2',
+ '/g/hg18', '/g/hg18', '/g/hg18', '/g/hg18', ]
+
+ # test lane specific parameters from gerald config file
+ for i in range(1,9):
+ cur_lane = g.lanes[str(i)]
+ self.failUnlessEqual(cur_lane.analysis, 'eland')
+ self.failUnlessEqual(cur_lane.eland_genome, genomes[i])
+ self.failUnlessEqual(cur_lane.read_length, '32')
+ self.failUnlessEqual(cur_lane.use_bases, 'Y'*32)
+
+ # test data extracted from summary file
+ clusters = [None,
+ (96483, 9074), (133738, 7938),
+ (152142, 10002), (15784, 2162),
+ (119735, 8465), (152177, 8146),
+ (84649, 7325), (54622, 4812),]
+
+ for i in range(1,9):
+ summary_lane = g.summary[str(i)]
+ self.failUnlessEqual(summary_lane.cluster, clusters[i])
+ self.failUnlessEqual(summary_lane.lane, str(i))
+
+ xml = g.get_elements()
+ # just make sure that element tree can serialize the tree
+ xml_str = ElementTree.tostring(xml)
+ g2 = gerald.Gerald(xml=xml)
+
+ # do it all again after extracting from the xml file
+ self.failUnlessEqual(g.version, g2.version)
+ self.failUnlessEqual(g.date, g2.date)
+ self.failUnlessEqual(len(g.lanes.keys()), len(g2.lanes.keys()))
+ self.failUnlessEqual(len(g.lanes.items()), len(g2.lanes.items()))
+
+ # test lane specific parameters from gerald config file
+ for i in range(1,9):
+ g_lane = g.lanes[str(i)]
+ g2_lane = g2.lanes[str(i)]
+ self.failUnlessEqual(g_lane.analysis, g2_lane.analysis)
+ self.failUnlessEqual(g_lane.eland_genome, g2_lane.eland_genome)
+ self.failUnlessEqual(g_lane.read_length, g2_lane.read_length)
+ self.failUnlessEqual(g_lane.use_bases, g2_lane.use_bases)
+
+ # test (some) summary elements
+ for i in range(1,9):
+ g_summary = g.summary[str(i)]
+ g2_summary = g2.summary[str(i)]
+ self.failUnlessEqual(g_summary.cluster, g2_summary.cluster)
+ self.failUnlessEqual(g_summary.lane, g2_summary.lane)
+
+ g_eland = g.eland_results
+ g2_eland = g2.eland_results
+ for lane in g_eland.keys():
+ self.failUnlessEqual(g_eland[lane].reads,
+ g2_eland[lane].reads)
+ self.failUnlessEqual(len(g_eland[lane].mapped_reads),
+ len(g2_eland[lane].mapped_reads))
+ for k in g_eland[lane].mapped_reads.keys():
+ self.failUnlessEqual(g_eland[lane].mapped_reads[k],
+ g2_eland[lane].mapped_reads[k])
+
+ self.failUnlessEqual(len(g_eland[lane].match_codes),
+ len(g2_eland[lane].match_codes))
+ for k in g_eland[lane].match_codes.keys():
+ self.failUnlessEqual(g_eland[lane].match_codes[k],
+ g2_eland[lane].match_codes[k])
+
+
+ def test_eland(self):
+ dm3_map = { 'chrUextra.fa' : 'dm3/chrUextra.fa',
+ 'chr2L.fa': 'dm3/chr2L.fa',
+ 'Lambda.fa': 'Lambda.fa'}
+ genome_maps = { '1':dm3_map, '2':dm3_map, '3':dm3_map, '4':dm3_map,
+ '5':dm3_map, '6':dm3_map, '7':dm3_map, '8':dm3_map }
+ eland = gerald.eland(self.gerald_dir, genome_maps=genome_maps)
+
+ for i in range(1,9):
+ lane = eland[str(i)]
+ self.failUnlessEqual(lane.reads, 4)
+ self.failUnlessEqual(lane.sample_name, "s")
+ self.failUnlessEqual(lane.lane_id, unicode(i))
+ self.failUnlessEqual(len(lane.mapped_reads), 3)
+ self.failUnlessEqual(lane.mapped_reads['Lambda.fa'], 1)
+ self.failUnlessEqual(lane.mapped_reads['dm3/chr2L.fa'], 1)
+ self.failUnlessEqual(lane.match_codes['U1'], 2)
+ self.failUnlessEqual(lane.match_codes['NM'], 1)
+
+ xml = eland.get_elements()
+ # just make sure that element tree can serialize the tree
+ xml_str = ElementTree.tostring(xml)
+ e2 = gerald.ELAND(xml=xml)
+
+ for i in range(1,9):
+ l1 = eland[str(i)]
+ l2 = e2[str(i)]
+ self.failUnlessEqual(l1.reads, l2.reads)
+ self.failUnlessEqual(l1.sample_name, l2.sample_name)
+ self.failUnlessEqual(l1.lane_id, l2.lane_id)
+ self.failUnlessEqual(len(l1.mapped_reads), len(l2.mapped_reads))
+ self.failUnlessEqual(len(l1.mapped_reads), 3)
+ for k in l1.mapped_reads.keys():
+ self.failUnlessEqual(l1.mapped_reads[k],
+ l2.mapped_reads[k])
+
+ self.failUnlessEqual(len(l1.match_codes), 9)
+ self.failUnlessEqual(len(l1.match_codes), len(l2.match_codes))
+ for k in l1.match_codes.keys():
+ self.failUnlessEqual(l1.match_codes[k],
+ l2.match_codes[k])
+
+ def test_runfolder(self):
+ runs = runfolder.get_runs(self.runfolder_dir)
+
+ # do we get the flowcell id from the filename?
+ self.failUnlessEqual(len(runs), 1)
+ self.failUnlessEqual(runs[0].name, 'run_207BTAAXX_2008-10-30.xml')
+
+ # do we get the flowcell id from the FlowcellId.xml file
+ make_flowcell_id(self.runfolder_dir, '207BTAAXY')
+ runs = runfolder.get_runs(self.runfolder_dir)
+ self.failUnlessEqual(len(runs), 1)
+ self.failUnlessEqual(runs[0].name, 'run_207BTAAXY_2008-10-30.xml')
+
+ r1 = runs[0]
+ xml = r1.get_elements()
+ xml_str = ElementTree.tostring(xml)
+
+ r2 = runfolder.PipelineRun(xml=xml)
+ self.failUnlessEqual(r1.name, r2.name)
+ self.failIfEqual(r2.image_analysis, None)
+ self.failIfEqual(r2.bustard, None)
+ self.failIfEqual(r2.gerald, None)
+
+
+def suite():
+ return unittest.makeSuite(RunfolderTests,'test')
+
+if __name__ == "__main__":
+ unittest.main(defaultTest="suite")
+
projects / htsworkflow.git / commitdiff