def main():
args = docopt(__doc__)
fasta_f = args['--infile']
bam_fs = args['--bam']
cas_fs = args['--cas']
prefix = args['--output']
estimate_cov_flag = True if not args['--calculate_cov'] else False
# Make covLibs
cov_libs = [BtCore.CovLibObj('bam' + str(idx), 'bam', lib_f) for idx, lib_f in enumerate(bam_fs)] + \
[BtCore.CovLibObj('cas' + str(idx), 'cas', lib_f) for idx, lib_f in enumerate(cas_fs)]
if not (cov_libs):
BtLog.error('31')
blobDb = BtCore.BlobDb('cov')
blobDb.version = interface.__version__
blobDb.parseFasta(fasta_f, None)
blobDb.parseCoverage(covLibObjs=cov_libs, estimate_cov=estimate_cov_flag, prefix=prefix)
def main():
args = docopt(__doc__)
fasta_f = args['--infile']
bam_fs = args['--bam']
cas_fs = args['--cas']
sam_fs = args['--sam']
prefix = args['--output']
no_base_cov_flag = args['--no_base_cov']
# Make covLibs
cov_libs = [BtCore.CovLibObj('bam' + str(idx), 'bam', lib_f) for idx, lib_f in enumerate(bam_fs)] + \
[BtCore.CovLibObj('sam' + str(idx), 'sam', lib_f) for idx, lib_f in enumerate(sam_fs)] + \
[BtCore.CovLibObj('cas' + str(idx), 'cas', lib_f) for idx, lib_f in enumerate(cas_fs)]
if not (cov_libs):
BtLog.error('31')
blobDb = BtCore.BlobDb('cov')
blobDb.version = blobtools.__version__
blobDb.parseFasta(fasta_f, None)
blobDb.parseCoverage(covLibObjs=cov_libs, no_base_cov=no_base_cov_flag, prefix=prefix)
def main():
#print(data_dir)
args = docopt(__doc__)
blobdb_f = args['--input']
prefix = args['--out']
ranks = args['--rank']
taxrule = args['--taxrule']
hits_flag = args['--hits']
seq_list_f = args['--list']
concoct = args['--concoct']
cov = args['--cov']
notable = args['--notable']
experimental = args['--experimental']
# Does blobdb_f exist ?
if not isfile(blobdb_f):
BtLog.error('0', blobdb_f)
out_f = BtIO.getOutFile(blobdb_f, prefix, None)
# Are ranks sane ?
if 'all' in ranks:
temp_ranks = RANKS[0:-1]
ranks = temp_ranks[::-1]
else:
for rank in ranks:
if rank not in RANKS:
BtLog.error('9', rank)
# Does seq_list file exist?
seqs = []
if (seq_list_f):
if isfile(seq_list_f):
seqs = BtIO.parseList(seq_list_f)
else:
BtLog.error('0', seq_list_f)
# Load BlobDb
blobDb = BtCore.BlobDb('new')
print(BtLog.status_d['9'] % (blobdb_f))
blobDb.load(blobdb_f)
blobDb.version = interface.__version__
# Is taxrule sane and was it computed?
if (blobDb.hitLibs) and taxrule not in blobDb.taxrules:
BtLog.error('11', taxrule, blobDb.taxrules)
# view(s)
viewObjs = []
print(BtLog.status_d['14'])
if not (notable):
tableView = None
if len(blobDb.hitLibs) > 1:
tableView = BtCore.ViewObj(name="table",
out_f=out_f,
suffix="%s.table.txt" % (taxrule),
body=[])
else:
tableView = BtCore.ViewObj(name="table",
out_f=out_f,
suffix="table.txt",
body=[])
viewObjs.append(tableView)
if not experimental == 'False':
meta = {}
if isfile(experimental):
meta = BtIO.readYaml(experimental)
experimentalView = BtCore.ExperimentalViewObj(name="experimental",
view_dir=out_f,
blobDb=blobDb,
meta=meta)
viewObjs.append(experimentalView)
if (concoct):
concoctTaxView = None
concoctCovView = None
if len(blobDb.hitLibs) > 1:
concoctTaxView = BtCore.ViewObj(
name="concoct_tax",
out_f=out_f,
suffix="%s.concoct_taxonomy_info.csv" % (taxrule),
body=dict())
concoctCovView = BtCore.ViewObj(
name="concoct_cov",
out_f=out_f,
suffix="%s.concoct_coverage_info.tsv" % (taxrule),
body=[])
else:
concoctTaxView = BtCore.ViewObj(name="concoct_tax",
out_f=out_f,
suffix="concoct_taxonomy_info.csv",
body=dict())
concoctCovView = BtCore.ViewObj(name="concoct_cov",
out_f=out_f,
suffix="concoct_coverage_info.tsv",
body=[])
viewObjs.append(concoctTaxView)
viewObjs.append(concoctCovView)
if (cov):
for cov_lib_name, covLibDict in blobDb.covLibs.items():
out_f = BtIO.getOutFile(covLibDict['f'], prefix, None)
covView = BtCore.ViewObj(name="covlib",
out_f=out_f,
suffix="cov",
body=[])
blobDb.view(viewObjs=[covView],
ranks=None,
taxrule=None,
hits_flag=None,
seqs=None,
cov_libs=[cov_lib_name],
progressbar=True)
if (viewObjs):
#for viewObj in viewObjs:
# print(viewObj.name)
blobDb.view(viewObjs=viewObjs,
ranks=ranks,
taxrule=taxrule,
hits_flag=hits_flag,
seqs=seqs,
cov_libs=[],
progressbar=True)
print(BtLog.status_d['19'])
refcov_dict = {}
if (refcov_f):
refcov_dict = BtPlot.parseRefCov(refcov_f)
catcolour_dict = {}
if (catcolour_f) and (c_index):
BtLog.error('24')
elif (catcolour_f):
catcolour_dict = BtPlot.parseCatColour(catcolour_f)
else:
pass
# Load BlobDb
print BtLog.status_d['9'] % blobdb_f
blobDB = bt.BlobDb('new')
blobDB.load(blobdb_f)
title = blobDB.title
if plot_title:
plot_title = title
# Is taxrule sane and was it computed?
if taxrule not in blobDB.taxrules:
BtLog.error('11', taxrule, blobDB.taxrules)
data_dict, max_cov, cov_libs, cov_libs_total_reads = blobDB.getPlotData(
rank, min_length, hide_nohits, taxrule, c_index, catcolour_dict)
plotObj = BtPlot.PlotObj(data_dict, cov_libs, cov_libs_total_reads)
plotObj.exclude_groups = exclude_groups
plotObj.format = format
def main():
args = docopt(__doc__)
args = BtPlot.check_input(args)
blobdb_f = args['--infile']
rank = args['--rank']
min_length = int(args['--length'])
max_group_plot = int(args['--plotgroups'])
hide_nohits = args['--nohit']
taxrule = args['--taxrule']
c_index = args['--cindex']
exclude_groups = args['--exclude']
labels = args['--label']
colour_f = args['--colours']
refcov_f = args['--refcov']
catcolour_f = args['--catcolour']
multiplot = args['--multiplot']
out_prefix = args['--out']
sort_order = args['--sort']
sort_first = args['--sort_first']
hist_type = args['--hist']
no_title = args['--notitle']
ignore_contig_length = args['--noscale']
format_plot = args['--format']
no_plot_blobs = args['--noblobs']
no_plot_reads = args['--noreads']
legend_flag = args['--legend']
cumulative_flag = args['--cumulative']
cov_lib_selection = args['--lib']
filelabel = args['--filelabel']
exclude_groups = BtIO.parseCmdlist(exclude_groups)
refcov_dict = BtIO.parseReferenceCov(refcov_f)
user_labels = BtIO.parseCmdLabels(labels)
catcolour_dict = BtIO.parseCatColour(catcolour_f)
colour_dict = BtIO.parseColours(colour_f)
# Load BlobDb
print BtLog.status_d['9'] % blobdb_f
blobDb = BtCore.BlobDb('blobplot')
blobDb.version = blobtools.__version__
blobDb.load(blobdb_f)
# Generate plot data
print BtLog.status_d['18']
data_dict, min_cov, max_cov, cov_lib_dict = blobDb.getPlotData(
rank, min_length, hide_nohits, taxrule, c_index, catcolour_dict)
plotObj = BtPlot.PlotObj(data_dict, cov_lib_dict, cov_lib_selection,
'blobplot', sort_first)
plotObj.exclude_groups = exclude_groups
plotObj.version = blobDb.version
plotObj.format = format_plot
plotObj.max_cov = max_cov
plotObj.min_cov = min_cov
plotObj.no_title = no_title
plotObj.multiplot = multiplot
plotObj.hist_type = hist_type
plotObj.ignore_contig_length = ignore_contig_length
plotObj.max_group_plot = max_group_plot
plotObj.legend_flag = legend_flag
plotObj.cumulative_flag = cumulative_flag
# order by which to plot (should know about user label)
plotObj.group_order = BtPlot.getSortedGroups(data_dict, sort_order,
sort_first)
# labels for each level of stats
plotObj.labels.update(plotObj.group_order)
# plotObj.group_labels is dict that contains labels for each group : all/other/user_label
if (user_labels):
for group, label in user_labels.items():
plotObj.labels.add(label)
plotObj.group_labels = {group: set() for group in plotObj.group_order}
plotObj.relabel_and_colour(colour_dict, user_labels)
plotObj.compute_stats()
plotObj.refcov_dict = refcov_dict
# Plotting
info_flag = 1
out_f = ''
for cov_lib in plotObj.cov_libs:
plotObj.ylabel = "Coverage"
plotObj.xlabel = "GC proportion"
if (filelabel):
plotObj.ylabel = basename(cov_lib_dict[cov_lib]['f'])
out_f = "%s.%s.%s.p%s.%s.%s" % (blobDb.title, taxrule, rank,
max_group_plot, hist_type, min_length)
if catcolour_dict:
out_f = "%s.%s" % (out_f, "catcolour")
if ignore_contig_length:
out_f = "%s.%s" % (out_f, "noscale")
if c_index:
out_f = "%s.%s" % (out_f, "c_index")
if exclude_groups:
out_f = "%s.%s" % (out_f, "exclude_" + "_".join(exclude_groups))
if labels:
out_f = "%s.%s" % (out_f, "userlabel_" + "_".join(
set([name for name in user_labels.values()])))
out_f = "%s.%s" % (out_f, "blobplot")
if (plotObj.cumulative_flag):
out_f = "%s.%s" % (out_f, "cumulative")
if (plotObj.multiplot):
out_f = "%s.%s" % (out_f, "multiplot")
out_f = BtIO.getOutFile(out_f, out_prefix, None)
if not (no_plot_blobs):
plotObj.plotScatter(cov_lib, info_flag, out_f)
info_flag = 0
if not (no_plot_reads) and (
plotObj.cov_libs_total_reads_dict[cov_lib]):
# prevent plotting if --noreads or total_reads == 0
plotObj.plotBar(cov_lib, out_f)
plotObj.write_stats(out_f)
nodesDB_f = os.path.join(main_dir, nodesDB_f)
if not os.path.isfile(nodesDB_f) and not ((names_f) and (nodes_f)):
BtLog.error('3')
if not (hit_fs):
BtLog.error('18')
# can FASTA parser deal with assemblies
if not fasta_type in ASSEMBLY_TYPES:
BtLog.error('2', ",".join(ASSEMBLY_TYPES[1:]))
# Is coverage provided?
if not (fasta_type) and not bam_fs and not sam_fs and not cov_fs and not cas_fs:
BtLog.error('1')
cov_libs = [bt.CovLibObj('bam' + str(idx), 'bam', lib_f) for idx, lib_f in enumerate(bam_fs)] + \
[bt.CovLibObj('sam' + str(idx), 'sam', lib_f) for idx, lib_f in enumerate(sam_fs)] + \
[bt.CovLibObj('cas' + str(idx), 'cas', lib_f) for idx, lib_f in enumerate(cas_fs)] + \
[bt.CovLibObj('cov' + str(idx), 'cov', lib_f) for idx, lib_f in enumerate(cov_fs)]
# Create BlobDB object
blobDb = bt.BlobDb(title)
# Parse FASTA
blobDb.parseFasta(fasta_f, fasta_type)
# Parse coverage
blobDb.parseCovs(cov_libs)
# Parse Tax
hitLibs = [bt.hitLibObj('tax' + str(idx), 'tax', lib_f) for idx, lib_f in enumerate(hit_fs)]
blobDb.parseHits(hitLibs)
def validate_input_create(main_dir, args):
'''
Accepts:
- main_dir
- docopt args
Returns:
- title
- fasta_f
- fasta_type
- cov_libs
- hit_libs
- nodesDB_f
- taxrules
- out_f
'''
ASSEMBLY_TYPES = [None, 'spades', 'soap', 'abyss', 'velvet']
fasta_f = args['--infile']
fasta_type = args['--type']
sam_fs = args['--sam']
bam_fs = args['--bam']
cov_fs = args['--cov']
cas_fs = args['--cas']
hit_fs = args['--taxfile']
out_f = args['--out']
if (out_f):
out_f = "%s.%s" % (os.path.basename(out_f), "BlobDB.json")
else:
out_f = "%s" % ("BlobDB.json")
nodesDB_f = args['--db']
names_f = args['--names']
nodes_f = args['--nodes']
taxrules = args['--taxrule']
title = args['--title'] if (args['--title']) else out_f
# Do files exist ?
files = [
x for x in list([fasta_f] + sam_fs + bam_fs + cov_fs + cas_fs +
[names_f] + [nodes_f] + hit_fs) if x is not None
]
for f in files:
if not os.path.isfile(f):
BtLog.error('0', f)
# Is taxonomy provided?
if nodesDB_f == "data/nodesDB.txt":
nodesDB_f = os.path.join(main_dir, nodesDB_f)
if not os.path.isfile(nodesDB_f) and not ((names_f) and (nodes_f)):
BtLog.error('3')
if not (hit_fs):
BtLog.error('18')
# can FASTA parser deal with assemblies
if not fasta_type in ASSEMBLY_TYPES:
BtLog.error('2', ",".join(ASSEMBLY_TYPES[1:]))
# Is coverage provided?
if not (fasta_type
) and not bam_fs and not sam_fs and not cov_fs and not cas_fs:
BtLog.error('1')
cov_libs = [bt.CovLibObj('bam' + str(idx), 'bam', lib_f) for idx, lib_f in enumerate(bam_fs)] + \
[bt.CovLibObj('sam' + str(idx), 'sam', lib_f) for idx, lib_f in enumerate(sam_fs)] + \
[bt.CovLibObj('cas' + str(idx), 'cas', lib_f) for idx, lib_f in enumerate(cas_fs)] + \
[bt.CovLibObj('cov' + str(idx), 'cov', lib_f) for idx, lib_f in enumerate(cov_fs)]
hit_libs = [
bt.hitLibObj('tax' + str(idx), 'tax', lib_f)
for idx, lib_f in enumerate(hit_fs)
]
return title, fasta_f, fasta_type, cov_libs, hit_libs, taxrules, nodesDB_f, nodes_f, names_f, out_f
import lib.BtIO as BtIO
import lib.BtInput as BtInput
import os.path
if __name__ == '__main__':
main_dir = os.path.dirname(__file__)
#print data_dir
args = docopt(__doc__)
#print args
title, fasta_f, fasta_type, cov_libs, hit_libs, taxrules, nodesDB_f, nodes_f, names_f, out_f = BtInput.validate_input_create(main_dir, args)
# Create BlobDB object
blobDb = bt.BlobDb(title)
# Parse FASTA
blobDb.parseFasta(fasta_f, fasta_type)
# Parse Tax
blobDb.parseHits(hit_libs)
# Parse nodesDB
nodesDB, nodesDB_f = BtIO.getNodesDB(nodes=nodes_f, names=names_f, nodesDB=nodesDB_f)
blobDb.nodesDB_f = nodesDB_f
if not os.path.isfile(nodesDB_f):
print BtLog.status_d['5'] % nodesDB_f
BtIO.writeNodesDB(nodesDB, nodesDB_f)
def main():
#main_dir = dirname(__file__)
args = docopt(__doc__)
fasta_f = args['--infile']
fasta_type = args['--type']
bam_fs = args['--bam']
cov_fs = args['--cov']
cas_fs = args['--cas']
hit_fs = args['--hitsfile']
prefix = args['--out']
nodesDB_f = args['--db']
names_f = args['--names']
estimate_cov_flag = True if not args['--calculate_cov'] else False
nodes_f = args['--nodes']
taxrules = args['--taxrule']
try:
min_bitscore_diff = float(args['--min_diff'])
min_score = float(args['--min_score'])
except ValueError():
BtLog.error('45')
tax_collision_random = args['--tax_collision_random']
title = args['--title']
# outfile
out_f = BtIO.getOutFile("blobDB", prefix, "json")
if not (title):
title = out_f
# coverage
if not (fasta_type) and not bam_fs and not cov_fs and not cas_fs:
BtLog.error('1')
cov_libs = [BtCore.CovLibObj('bam' + str(idx), 'bam', lib_f) for idx, lib_f in enumerate(bam_fs)] + \
[BtCore.CovLibObj('cas' + str(idx), 'cas', lib_f) for idx, lib_f in enumerate(cas_fs)] + \
[BtCore.CovLibObj('cov' + str(idx), 'cov', lib_f) for idx, lib_f in enumerate(cov_fs)]
# taxonomy
hit_libs = [
BtCore.HitLibObj('tax' + str(idx), 'tax', lib_f)
for idx, lib_f in enumerate(hit_fs)
]
# Create BlobDB object
blobDb = BtCore.BlobDb(title)
blobDb.version = interface.__version__
# Parse FASTA
blobDb.parseFasta(fasta_f, fasta_type)
# Parse nodesDB OR names.dmp, nodes.dmp
nodesDB_default = join(dirname(abspath(__file__)), "../data/nodesDB.txt")
nodesDB, nodesDB_f = BtIO.parseNodesDB(nodes=nodes_f,
names=names_f,
nodesDB=nodesDB_f,
nodesDBdefault=nodesDB_default)
blobDb.nodesDB_f = nodesDB_f
# Parse similarity hits
if (hit_libs):
blobDb.parseHits(hit_libs)
if not taxrules:
if len(hit_libs) > 1:
taxrules = ['bestsum', 'bestsumorder']
else:
taxrules = ['bestsum']
blobDb.computeTaxonomy(taxrules, nodesDB, min_score, min_bitscore_diff,
tax_collision_random)
else:
print(BtLog.warn_d['0'])
# Parse coverage
blobDb.parseCoverage(covLibObjs=cov_libs,
estimate_cov=estimate_cov_flag,
prefix=prefix)
# Generating BlobDB and writing to file
print(BtLog.status_d['7'] % out_f)
BtIO.writeJson(blobDb.dump(), out_f)
def validate_input_create(main_dir, args):
'''
Accepts:
- main_dir
- docopt args
Returns:
- title
- fasta_f
- fasta_type
- cov_libs
- hit_libs
- nodesDB_f
- taxrules
- out_f
'''
ASSEMBLY_TYPES = [None, 'spades', 'soap', 'abyss', 'velvet']
fasta_f = args['--infile']
fasta_type = args['--type']
sam_fs = args['--sam']
bam_fs = args['--bam']
cov_fs = args['--cov']
cas_fs = args['--cas']
hit_fs = args['--taxfile']
out_f = args['--out']
if (out_f):
out_f = "%s.%s" % (os.path.basename(out_f), "BlobDB.json")
else:
out_f = "%s" % ("BlobDB.json")
nodesDB_f = args['--db']
names_f = args['--names']
nodes_f = args['--nodes']
taxrules = args['--taxrule']
title = args['--title'] if (args['--title']) else out_f
# Do files exist ?
files = [x for x in list([fasta_f] + sam_fs + bam_fs + cov_fs + cas_fs + [names_f] + [nodes_f] + hit_fs) if x is not None]
for f in files:
if not os.path.isfile(f):
BtLog.error('0', f)
# Is taxonomy provided?
if nodesDB_f == "data/nodesDB.txt":
nodesDB_f = os.path.join(main_dir, nodesDB_f)
if not os.path.isfile(nodesDB_f) and not ((names_f) and (nodes_f)):
BtLog.error('3')
if not (hit_fs):
BtLog.error('18')
# can FASTA parser deal with assemblies
if not fasta_type in ASSEMBLY_TYPES:
BtLog.error('2', ",".join(ASSEMBLY_TYPES[1:]))
# Is coverage provided?
if not (fasta_type) and not bam_fs and not sam_fs and not cov_fs and not cas_fs:
BtLog.error('1')
cov_libs = [bt.CovLibObj('bam' + str(idx), 'bam', lib_f) for idx, lib_f in enumerate(bam_fs)] + \
[bt.CovLibObj('sam' + str(idx), 'sam', lib_f) for idx, lib_f in enumerate(sam_fs)] + \
[bt.CovLibObj('cas' + str(idx), 'cas', lib_f) for idx, lib_f in enumerate(cas_fs)] + \
[bt.CovLibObj('cov' + str(idx), 'cov', lib_f) for idx, lib_f in enumerate(cov_fs)]
hit_libs = [bt.hitLibObj('tax' + str(idx), 'tax', lib_f) for idx, lib_f in enumerate(hit_fs)]
return title, fasta_f, fasta_type, cov_libs, hit_libs, taxrules, nodesDB_f, nodes_f, names_f, out_f