def do_summarize(args):
d = pandas.read_table(args.infile)
peaks = d[ d['MARKER'] == args.marker ]
stats = bin_stats(peaks)
for s in sorted(stats.keys()):
cout(stats[s].repr())
def align(self, parameters=None, anchor_pairs=None):
# sanity checks
if self.marker.code != 'ladder':
raise RuntimeError(
'E: align() must be performed on ladder channel!')
if parameters:
self.scan(parameters) # in case this channel hasn't been scanned
ladder = self.fsa.panel.get_ladder()
# prepare ladder qcfunc
if 'qcfunc' not in ladder:
ladder['qcfunc'] = algo.generate_scoring_function(
ladder['strict'], ladder['relax'])
start_time = time.process_time()
result = algo.align_peaks(self, parameters, ladder, anchor_pairs)
dpresult = result.dpresult
fsa = self.fsa
fsa.z = dpresult.z
fsa.rss = dpresult.rss
fsa.nladder = len(dpresult.sized_peaks)
fsa.score = result.score
fsa.duration = time.process_time() - start_time
fsa.status = const.assaystatus.aligned
fsa.ztranspose = dpresult.ztranspose
#import pprint; pprint.pprint(dpresult.sized_peaks)
#print(fsa.z)
cout('O: Score %3.2f | %5.2f | %d/%d | %s | %5.1f | %s' %
(fsa.score, fsa.rss, fsa.nladder, len(
ladder['sizes']), result.method, fsa.duration, fsa.filename))
def do_renamefsa(args, dbh):
cout('Renaming FSA files from input file: %s' % args.infile)
b = dbh.get_batch(args.batch)
inrows = csv.DictReader( open(args.infile),
delimiter = ',' if args.infile.endswith('.csv') else '\t' )
#next(inrows)
total_fsa = 0
line_counter = 1
for r in inrows:
line_counter += 1
#if not row[0] or row[0].startswith('#'):
# continue
if not (r['FILENAME'] and r['SAMPLE']) or '#' in [ r['FILENAME'][0], r['SAMPLE'][0] ]:
continue
try:
sample_code, fsa_filename, fsa_new_filename = r['SAMPLE'], r['FILENAME'], r['NEWNAME']
s = b.search_sample(sample_code)
a = s.assays.filter( dbh.Assay.filename == fsa_filename ).one()
a.filename = fsa_new_filename
except:
cerr('Error in executing line %d' % line_counter)
raise
def setup(session):
# create undefined marker
marker = schema.Marker( code = 'undefined', species = 'X' )
cout("INFO - marker 'undefined' created.")
session.add(marker)
# create ladder marker
marker = schema.Marker( code = 'ladder', species = 'X' )
cout("INFO - marker 'ladder' created.")
session.add(marker)
# create combined marker
marker = schema.Marker( code = 'combined', species = 'X' )
cout("INFO - marker 'combined' created.")
session.add(marker)
# create default panel
panel = schema.Panel( code = 'undefined' )
cout("INFO - panel 'undefined' created.")
session.add(panel)
# create default batch (for bin holder)
batch = schema.Batch( code = 'default' )
batch.assay_provider = ''
batch.species = 'X'
cout("INFO - batch 'default' created.")
session.add(batch)
def align(self, parameters=None, anchor_pairs=None):
# sanity checks
if self.marker.code != 'ladder':
raise RuntimeError('E: align() must be performed on ladder channel!')
if parameters:
self.scan( parameters ) # in case this channel hasn't been scanned
ladder = self.fsa.panel.get_ladder()
# prepare ladder qcfunc
if 'qcfunc' not in ladder:
ladder['qcfunc'] = algo.generate_scoring_function(
ladder['strict'], ladder['relax'] )
start_time = time.process_time()
result = algo.align_peaks(self, parameters, ladder, anchor_pairs)
dpresult = result.dpresult
fsa = self.fsa
fsa.z = dpresult.z
fsa.rss = dpresult.rss
fsa.nladder = len(dpresult.sized_peaks)
fsa.score = result.score
fsa.duration = time.process_time() - start_time
fsa.status = const.assaystatus.aligned
fsa.ztranspose = dpresult.ztranspose
#import pprint; pprint.pprint(dpresult.sized_peaks)
#print(fsa.z)
cout('O: Score %3.2f | %5.2f | %d/%d | %s | %5.1f | %s' %
(fsa.score, fsa.rss, fsa.nladder, len(ladder['sizes']), result.method,
fsa.duration, fsa.filename) )
def do_listpeaks(args, dbh):
assay_list = get_assay_list(args, dbh)
if args.marker:
markers = [dbh.get_marker(code) for code in args.marker.split(',')]
else:
markers = None
if markers:
cerr('Markers: %s' % ','.join(m.code for m in markers))
if args.outfile != '-':
out_stream = open(args.outfile, 'w')
else:
out_stream = sys.stdout
out_stream.write('SAMPLE\tFILENAME\tDYE\tRTIME\tHEIGHT\tSIZE\tSCORE\tID\n')
for (assay, sample_code) in assay_list:
cout('Sample: %s assay: %s' % (sample_code, assay.filename))
for channel in assay.channels:
if markers and channel.marker not in markers:
continue
cout('Marker => %s | %s [%d]' %
(channel.marker.code, channel.dye, len(channel.alleles)))
for p in channel.alleles:
out_stream.write('%s\t%s\t%s\t%d\t%d\t%5.3f\t%3.2f\t%d\n' %
(sample_code, assay.filename, channel.dye,
p.rtime, p.height, p.size, p.qscore, p.id))
def do_listpeaks( args, dbh ):
assay_list = get_assay_list( args, dbh )
if args.marker:
markers = [ dbh.get_marker( code ) for code in args.marker.split(',') ]
else:
markers = None
if markers:
cerr('Markers: %s' % ','.join( m.code for m in markers ))
if args.outfile != '-':
out_stream = open(args.outfile, 'w')
else:
out_stream = sys.stdout
out_stream.write('SAMPLE\tFILENAME\tDYE\tRTIME\tHEIGHT\tSIZE\tSCORE\tID\n')
for (assay, sample_code) in assay_list:
cout('Sample: %s assay: %s' % (sample_code, assay.filename))
for channel in assay.channels:
if markers and channel.marker not in markers:
continue
cout('Marker => %s | %s [%d]' % (channel.marker.code, channel.dye,
len(channel.alleles)))
for p in channel.alleles:
out_stream.write('%s\t%s\t%s\t%d\t%d\t%5.3f\t%3.2f\t%d\n' %
(sample_code, assay.filename, channel.dye, p.rtime, p.height, p.size, p.qscore, p.id)
)
def do_renamefsa(args, dbh):
cout('Renaming FSA files from input file: %s' % args.infile)
b = dbh.get_batch(args.batch)
inrows = csv.DictReader(
open(args.infile),
delimiter=',' if args.infile.endswith('.csv') else '\t')
#next(inrows)
total_fsa = 0
line_counter = 1
for r in inrows:
line_counter += 1
#if not row[0] or row[0].startswith('#'):
# continue
if not (r['FILENAME'] and r['SAMPLE']) or '#' in [
r['FILENAME'][0], r['SAMPLE'][0]
]:
continue
try:
sample_code, fsa_filename, fsa_new_filename = r['SAMPLE'], r[
'FILENAME'], r['NEWNAME']
s = b.search_sample(sample_code)
a = s.assays.filter(dbh.Assay.filename == fsa_filename).one()
a.filename = fsa_new_filename
except:
cerr('Error in executing line %d' % line_counter)
raise
def do_summarize(args):
d = pandas.read_table(args.infile)
peaks = d[d['MARKER'] == args.marker]
stats = bin_stats(peaks)
for s in sorted(stats.keys()):
cout(stats[s].repr())
def do_uploadfsa(args, dbh):
cout('Uploading FSA files from input file: %s' % args.infile)
b = dbh.get_batch(args.batch)
inrows = csv.DictReader(
open(args.infile),
delimiter=',' if args.infile.endswith('.csv') else '\t')
#next(inrows)
total_fsa = 0
line_counter = 1
for r in inrows:
line_counter += 1
#if not row[0] or row[0].startswith('#'):
# continue
if not (r['FILENAME'] and r['SAMPLE']) or '#' in [
r['FILENAME'][0], r['SAMPLE'][0]
]:
continue
#if len(row) < 3:
# cerr('ERR - line %d only has %d item(s)' % (line_counter, len(row)))
sample_code, fsa_filename, fsa_panel = r['SAMPLE'], r['FILENAME'], r[
'PANEL']
if r['OPTIONS']:
options = tokenize(r['OPTIONS'])
else:
options = None
try:
s = b.search_sample(sample_code)
if not s:
cerr('ERR - sample %s does not exist' % sample_code)
sys.exit(1)
with open(args.indir + '/' + fsa_filename, 'rb') as f:
trace = f.read()
a = s.add_fsa_assay(trace,
filename=fsa_filename,
panel_code=fsa_panel,
options=options,
species=args.species,
dbhandler=dbh)
cerr('INFO - sample: %s assay: %s panel: %s has been uploaded' %
(s.code, a.filename, fsa_panel))
except Exception as exc:
if not args.test:
raise
cerr('ERR - line %d' % line_counter)
cerr(' => %s' % str(exc))
def do_info(args, dbh):
traces = get_traces(args, dbh)
for abspath, trace in traces:
cout('I - trace: %s' % abspath)
cout('I - runtime: %s' % trace.get_run_start_time())
def align(self, parameters, ladder=None, anchor_pairs=None):
# sanity checks
if self.marker.code != 'ladder':
raise RuntimeError(
'E: align() must be performed on ladder channel!')
ladder = self.fsa.panel.get_ladder()
# prepare ladder qcfunc
if 'qcfunc' not in ladder:
ladder['qcfunc'] = algo.generate_scoring_function(
ladder['strict'], ladder['relax'])
start_time = time.process_time()
result = algo.align_peaks(self, parameters, ladder, anchor_pairs)
dpresult = result.dpresult
fsa = self.fsa
fsa.z = dpresult.z
fsa.rss = dpresult.rss
fsa.nladder = len(dpresult.sized_peaks)
fsa.score = result.score
fsa.duration = time.process_time() - start_time
# set allele sizes from ladder steps
alleles = self.get_alleles()
alleles.sort(key=lambda x: x.rtime)
ladder_sizes = ladder['sizes']
ladder_sizes.sort()
for allele, ladder_size in zip(alleles, ladder_sizes):
allele.size = ladder_size
# check the allele method
method = parameters.allelemethod
if method == const.allelemethod.leastsquare:
fsa.allele_fit_func = algo.least_square(alleles, self.fsa.z)
elif method == const.allelemethod.cubicspline:
fsa.allele_fit_func = algo.cubic_spline(alleles)
elif method == const.allelemethod.localsouthern:
fsa.allele_fit_func = algo.local_southern(alleles)
else:
raise RuntimeError
#min_rtime = ladders[1].rtime
#max_rtime = ladders[-2].rtime
fsa.min_rtime = parameters.ladder.min_rtime
fsa.max_rtime = parameters.ladder.max_rtime
#import pprint; pprint.pprint(dpresult.sized_peaks)
#print(fsa.z)
if is_verbosity(4):
cout('O: Score %3.2f | %5.2f | %d/%d | %s | %5.1f | %s' %
(fsa.score, fsa.rss, fsa.nladder, len(ladder['sizes']),
result.method, fsa.duration, fsa.filename))
def do_corralleles(args, dbh):
from fatools.lib.analysis.correlation import correlate_alleles
query = get_query( args, dbh )
analytical_sets = query.get_filtered_analytical_sets()
for marker_code in analytical_sets.marker_ids:
report = correlate_alleles(analytical_sets[0], analytical_sets[1], marker=marker_code)
cout( make_correlate_report( report ) )
def do_initbatch(args, dbh):
b = dbh.Batch()
b.code = args.initbatch
b.species = args.species
b.assay_provider = args.assayprovider
# set default bin_batch to batch default
def_batch = dbh.get_batch('default')
b.bin_batch = def_batch
dbh.session.add(b)
cout('INFO: batch %s added.' % b.code)
def do_initbatch(args, dbh):
b = dbh.Batch()
b.code = args.initbatch
b.species = args.species
b.assay_provider = args.assayprovider
# set default bin_batch to batch default
def_batch = dbh.get_batch('default')
b.bin_batch = def_batch
dbh.session.add(b)
cout('INFO: batch %s added.' % b.code)
def do_export(args, dbh):
from fatools.lib.analytics.export import export
query = get_query( args, dbh )
analytical_sets = query.get_filtered_analytical_sets()
if analytical_sets.total_samples <= 0:
cexit('ERR - query does not yield any sample data')
else:
cerr('INFO - total sampel number: %d' % analytical_sets.total_samples)
output = export( analytical_sets, dbh, outfile = args.outfile, format = args.outformat )
cout('Done.')
def do_corralleles(args, dbh):
from fatools.lib.analysis.correlation import correlate_alleles
query = get_query(args, dbh)
analytical_sets = query.get_filtered_analytical_sets()
for marker_code in analytical_sets.marker_ids:
report = correlate_alleles(analytical_sets[0],
analytical_sets[1],
marker=marker_code)
cout(make_correlate_report(report))
def do_allelesummary(args, dbh):
from fatools.lib.analytics.summary import summarize_alleles, plot_alleles
query = get_query(args, dbh)
analytical_sets = query.get_filtered_analytical_sets()
report = summarize_alleles(analytical_sets)
cout(make_sample_report(analytical_sets.get_sample_sets()))
cout(make_allele_report(report, dbh))
if args.outplot:
plot_alleles(report, args.outplot)
def do_allelesummary(args, dbh):
from fatools.lib.analytics.summary import summarize_alleles, plot_alleles
query = get_query( args, dbh )
analytical_sets = query.get_filtered_analytical_sets()
report = summarize_alleles( analytical_sets )
cout( make_sample_report( analytical_sets.get_sample_sets() ) )
cout( make_allele_report(report, dbh) )
if args.outplot:
plot_alleles( report, args.outplot )
def do_showsample(args, dbh):
from fatools.lib.const import channelstatus
batch = dbh.get_batch(args.batch)
for code in args.sample.split(','):
sample = batch.search_sample(code)
cout('Sample: %s' % sample.code)
for fsa in sample.assays:
marker_codes = [ c.marker.code for c in fsa.channels
if c.status == channelstatus.assigned]
cout(' % 3d - %s | %s | %s' %
(fsa.id, fsa.filename, fsa.panel.code, ','.join(marker_codes)) )
def do_uploadfsa(args, dbh):
cout('Uploading FSA files from input file: %s' % args.infile)
b = dbh.get_batch(args.batch)
inrows = csv.DictReader( open(args.infile),
delimiter = ',' if args.infile.endswith('.csv') else '\t' )
#next(inrows)
total_fsa = 0
line_counter = 1
for r in inrows:
line_counter += 1
#if not row[0] or row[0].startswith('#'):
# continue
if not (r['FILENAME'] and r['SAMPLE']) or '#' in [ r['FILENAME'][0], r['SAMPLE'][0] ]:
continue
#if len(row) < 3:
# cerr('ERR - line %d only has %d item(s)' % (line_counter, len(row)))
sample_code, fsa_filename, fsa_panel = r['SAMPLE'], r['FILENAME'], r['PANEL']
if r['OPTIONS']:
options = tokenize( r['OPTIONS'] )
else:
options = None
try:
s = b.search_sample(sample_code)
if not s:
cerr('ERR - sample %s does not exist' % sample_code)
sys.exit(1)
with open( args.indir + '/' + fsa_filename, 'rb') as f:
trace = f.read()
a = s.add_fsa_assay( trace, filename=fsa_filename, panel_code = fsa_panel,
options = options, species = args.species, dbhandler = dbh)
cerr('INFO - sample: %s assay: %s panel: %s has been uploaded' %
(s.code, a.filename, fsa_panel))
except Exception as exc:
if not args.test:
raise
cerr('ERR - line %d' % line_counter)
cerr(' => %s' % str(exc))
def do_export(args, dbh):
from fatools.lib.analytics.export import export
query = get_query(args, dbh)
analytical_sets = query.get_filtered_analytical_sets()
if analytical_sets.total_samples <= 0:
cexit('ERR - query does not yield any sample data')
else:
cerr('INFO - total sampel number: %d' % analytical_sets.total_samples)
output = export(analytical_sets,
dbh,
outfile=args.outfile,
format=args.outformat)
cout('Done.')
def do_parallel_find_peaks( channel_list, peakdb ):
import concurrent.futures, pickle
cerr('I: Processing channel(s)')
total = len(channel_list)
counter = 0
with concurrent.futures.ProcessPoolExecutor() as executor:
for (tag, peaks) in executor.map( find_peaks_p, channel_list ):
if peakdb:
peakdb.Put(tag.encode(), pickle.dumps(peaks))
else:
cout('== channel %s\n' % tag )
cout(str(peaks))
counter += 1
cerr('I: [%d/%d] channel %s => %d peak(s)' % (counter, total, tag, len(peaks)))
def do_importpanel(args, dbh):
panels = yaml.load( open(args.infile) )
for code, panel in panels.items():
if panel['code'] != code:
cerr('ERR: code for panel %s is not consistent!' % code)
sys.exit(1)
p = dbh.new_panel()
p.update( panel )
if args.update:
db_p = p.sync(dbh.session)
cout("INFO: panel %s sync'd." % db_p.code)
else:
dbh.session.add(p)
cout("INFO: panel %s added." % p.code)
def do_importpanel(args, dbh):
panels = yaml.load(open(args.infile))
for code, panel in panels.items():
if panel['code'] != code:
cerr('ERR: code for panel %s is not consistent!' % code)
sys.exit(1)
p = dbh.new_panel()
p.update(panel)
if args.update:
db_p = p.sync(dbh.session)
cout("INFO: panel %s sync'd." % db_p.code)
else:
dbh.session.add(p)
cout("INFO: panel %s added." % p.code)
def do_viewpeakcachedb(args, dbh):
from leveldb import LevelDB
from collections import defaultdict
ldb = LevelDB(args.peakcachedb, create_if_missing=False)
batches = defaultdict(int)
for key in ldb.RangeIter(include_value=False):
batch_code = bytes(key.split(b'|', 1)[0])
batches[batch_code] += 1
cout('Peakcache DB: %s' % args.peakcachedb)
for (k, v) in batches.items():
cout('\t%s\t%4d' % (k.decode(), v))
def do_showsample(args, dbh):
from fatools.lib.const import channelstatus
batch = dbh.get_batch(args.batch)
for code in args.sample.split(','):
sample = batch.search_sample(code)
cout('Sample: %s' % sample.code)
for fsa in sample.assays:
marker_codes = [
c.marker.code for c in fsa.channels
if c.status == channelstatus.assigned
]
cout(
' % 3d - %s | %s | %s' %
(fsa.id, fsa.filename, fsa.panel.code, ','.join(marker_codes)))
def do_parallel_find_peaks( channel_list, peakdb ):
import concurrent.futures, pickle
cerr('I: Processing channel(s)')
total = len(channel_list)
counter = 0
with concurrent.futures.ProcessPoolExecutor() as executor:
for (tag, peaks) in executor.map( find_peaks_p, channel_list ):
if peakdb:
peakdb.Put(tag.encode(), pickle.dumps(peaks))
else:
cout('== channel %s\n' % tag )
cout(str(peaks))
counter += 1
cerr('I: [%d/%d] channel %s => %d peak(s)' % (counter, total, tag, len(peaks)))
def do_viewpeakcachedb(args, dbh):
from leveldb import LevelDB
from collections import defaultdict
ldb = LevelDB(args.peakcachedb, create_if_missing=False)
batches = defaultdict(int)
for key in ldb.RangeIter(include_value=False):
batch_code = bytes(key.split(b'|', 1)[0])
batches[batch_code] += 1
cout('Peakcache DB: %s' % args.peakcachedb)
for (k,v) in batches.items():
cout('\t%s\t%4d' % (k.decode(),v))
def do_viewbin(args, dbh):
if not args.marker:
cexit('ERR - please provide marker code')
markers = [ dbh.get_marker(code) for code in args.marker.split(',') ]
batch = dbh.get_batch( args.batch or 'default')
for m in markers:
cout('Marker: %s' % m.label)
cout(' Bin Mean 25%P 75%P Width')
cout(' ====================================')
for binset in m.get_bin(batch).sortedbins:
cout(' %3d %5.2f %5.2f %5.2f %4.2f' %
(binset[0], binset[1], binset[2], binset[3], binset[3] - binset[2]))
def do_viewbin(args, dbh):
if not args.marker:
cexit('ERR - please provide marker code')
markers = [dbh.get_marker(code) for code in args.marker.split(',')]
batch = dbh.get_batch(args.batch or 'default')
for m in markers:
cout('Marker: %s' % m.label)
cout(' Bin Mean 25%P 75%P Width')
cout(' ====================================')
for binset in m.get_bin(batch).sortedbins:
cout(' %3d %5.2f %5.2f %5.2f %4.2f' %
(binset[0], binset[1], binset[2], binset[3],
binset[3] - binset[2]))
def do_showbatches(args, dbh):
cout('Available batch(es):')
batches = dbh.get_batches(None)
for batch in batches:
cout(' %s' % batch.code)
def do_initsample(args, dbh):
if not args.batch:
cerr('ERR: batch code must be supplied!')
sys.exit(1)
b = dbh.Batch.search(args.batch, dbh.session)
cout('INFO - using batch code: %s' % b.code)
name, ext = os.path.splitext( args.infile )
if ext in [ '.csv', '.tab', '.tsv' ]:
delim = ',' if ext == '.csv' else '\t'
dict_samples, errlog, sample_codes = b.get_sample_class().csv2dict(
open(args.infile), with_report=True, delimiter = delim )
if dict_samples is None:
cout('Error processing sample info file')
cout('\n'.join(errlog))
cexit('Terminated!')
elif ext in ['.json', '.yaml']:
payload = yaml.load( open(args.infile) )
sample_codes = payload['codes']
dict_samples = payload['samples']
inserted=0
updated=0
# get default location and subject first (to satisfy RDBMS constraints)
null_location = dbh.search_location(auto=True)
#null_subject = dbh.search_subject('null', auto=True) ## <- this shouldn't be here !!
session = dbh.session()
with session.no_autoflush:
for sample_code in sample_codes:
d_sample = dict_samples[sample_code]
db_sample = b.search_sample( sample_code )
if not db_sample:
db_sample = b.add_sample( sample_code )
inserted += 1
cout('INFO - sample: %s added.' % db_sample.code)
db_sample.location = null_location
#db_sample.subject = null_subject
#print(d_sample)
#dbh.session().flush( [db_sample] )
else:
cout('INFO - sample: %s being updated...' % db_sample.code)
updated += 1
db_sample.update( d_sample )
session.flush( [db_sample] )
cout('INFO - inserted new %d sample(s), updated %d sample(s)' %
(inserted, updated))
return
inrows = csv.reader( open(args.infile),
delimiter = ',' if args.infile.endswith('.csv') else '\t' )
next(inrows) # discard the 1st line
counter = 0
for row in inrows:
s = b.add_sample( row[0] )
counter += 1
cout('INFO - sample: %s added.' % s.code)
cout('INFO - number of new sample(s): %d' % counter)
def do_samplesummary(args, dbh):
query = get_query(args, dbh)
sample_sets = query.get_filtered_sample_sets()
cout(make_sample_report(sample_sets))
def do_samplesummary(args, dbh):
query = get_query( args, dbh )
sample_sets = query.get_filtered_sample_sets()
cout( make_sample_report(sample_sets) )
def do_clearassay(args, dbh):
cout('Clearing assay...')
def do_initsample(args, dbh):
if not args.batch:
cerr('ERR: batch code must be supplied!')
sys.exit(1)
b = dbh.Batch.search(args.batch, dbh.session)
cout('INFO - using batch code: %s' % b.code)
name, ext = os.path.splitext(args.infile)
if ext in ['.csv', '.tab', '.tsv']:
delim = ',' if ext == '.csv' else '\t'
dict_samples, errlog, sample_codes = b.get_sample_class().csv2dict(
open(args.infile), with_report=True, delimiter=delim)
if dict_samples is None:
cout('Error processing sample info file')
cout('\n'.join(errlog))
cexit('Terminated!')
elif ext in ['.json', '.yaml']:
payload = yaml.load(open(args.infile))
sample_codes = payload['codes']
dict_samples = payload['samples']
inserted = 0
updated = 0
# get default location and subject first (to satisfy RDBMS constraints)
null_location = dbh.search_location(auto=True)
#null_subject = dbh.search_subject('null', auto=True) ## <- this shouldn't be here !!
session = dbh.session()
with session.no_autoflush:
for sample_code in sample_codes:
d_sample = dict_samples[sample_code]
db_sample = b.search_sample(sample_code)
if not db_sample:
db_sample = b.add_sample(sample_code)
inserted += 1
cout('INFO - sample: %s added.' % db_sample.code)
db_sample.location = null_location
#db_sample.subject = null_subject
#print(d_sample)
#dbh.session().flush( [db_sample] )
else:
cout('INFO - sample: %s being updated...' % db_sample.code)
updated += 1
db_sample.update(d_sample)
session.flush([db_sample])
cout('INFO - inserted new %d sample(s), updated %d sample(s)' %
(inserted, updated))
return
inrows = csv.reader(
open(args.infile),
delimiter=',' if args.infile.endswith('.csv') else '\t')
next(inrows) # discard the 1st line
counter = 0
for row in inrows:
s = b.add_sample(row[0])
counter += 1
cout('INFO - sample: %s added.' % s.code)
cout('INFO - number of new sample(s): %d' % counter)
def do_showbatches(args, dbh):
cout('Available batch(es):')
batches = dbh.get_batches(None)
for batch in batches:
cout(' %s' % batch.code)
def initdb(self, create_table=True):
if create_table:
schema.Base.metadata.create_all(self.engine)
from fatools.lib.sqlmodels.setup import setup
setup(self.session)
cout('Database at %s has been initialized.' % self.dbfile)
def initdb(self, create_table = True):
if create_table:
schema.Base.metadata.create_all(self.engine)
from fatools.lib.sqlmodels.setup import setup
setup( self.session )
cout('Database at %s has been initialized.' % self.dbfile)
def do_clearassay(args, dbh):
cout('Clearing assay...')
def do_listpeaks(args, fsa_list, dbh):
if args.outfile != '-':
out_stream = open(args.outfile, 'w')
else:
out_stream = sys.stdout
if args.peaks_format == 'standard':
out_stream.write(
'SAMPLE\tFILENAME \tDYE\tRTIME\tSIZE\tHEIGHT\tAREA\tSCORE\n')
elif args.peaks_format == 'peakscanner':
out_stream.write(
"Dye/Sample Peak,Sample File Name,Type,Size,Height,Area in Point,Area in BP,Corrected Area in BP,Data Point,Begin Point,"
)
if args.merge:
out_stream.write(
"Begin BP,End Point,End BP,Width in Point,Width in BP,Score,Peak Group,User Comments,User Edit\n"
)
else:
out_stream.write(
"Begin BP,End Point,End BP,Width in Point,Width in BP,Score,User Comments,User Edit\n"
)
else:
raise RuntimeError("Unknown value for args.peaks_format")
out_stream.close()
for (fsa, fsa_index) in fsa_list:
cverr(3, 'D: calling FSA %s' % fsa.filename)
markers = fsa.panel.data['markers']
if args.outfile != '-':
out_stream = open(args.outfile, 'a')
else:
out_stream = sys.stdout
for channel in fsa.channels:
if channel.is_ladder():
color = markers['x/ladder']['filter']
else:
color = markers['x/' + channel.dye]['filter']
alleles = channel.get_alleles(broad_peaks_only=False)
if is_verbosity(4):
cout('Marker => %s | %s [%d]' %
(channel.marker.code, channel.dye, len(alleles)))
cout("channel has alleles :", len(alleles))
i = 1
smeared_alleles = channel.smeared_alleles
if (not args.merge) or channel.is_ladder():
for p in alleles:
if args.peaks_format == 'standard':
out_stream.write(
'%6s\t%10s\t%3s\t%d\t%d\t%5i\t%3.2f\t%3.2f\n' %
(fsa_index, fsa.filename[:-4], color, p.rtime,
p.size, p.height, p.area, p.qscore))
else:
out_stream.write(
'"%s, %i",%s, %s, %f, %i, %i, %i, %i, %i, %i, %f, %i, %f, %i, %f, %f,,\n'
% (color, i, fsa.filename, p.type, p.size,
p.height, p.area, p.area_bp, p.area_bp_corr,
p.rtime, p.brtime, p.begin_bp, p.ertime,
p.end_bp, p.wrtime, p.width_bp, p.qscore))
i = i + 1
else:
if is_verbosity(4):
cout('Marker => %s | %s [%d]' %
(channel.marker.code, channel.dye,
len(smeared_alleles)))
cout("channel has smeared alleles :", len(smeared_alleles))
i = 1
for p in smeared_alleles:
out_stream.write(
'"%s, %i", %s, %s, %f, %i, %i, %i, %i, %i, %i, %f, %i, %f, %i, %f, %f, %i,,\n'
% (color, i, fsa.filename, p.type, p.size, p.height,
p.area, p.area_bp, p.area_bp_corr, p.rtime,
p.brtime, p.begin_bp, p.ertime, p.end_bp, p.wrtime,
p.width_bp, p.qscore, p.group))
i = i + 1
out_stream.close()
