def test_18_filter_reads(self):
if ONLY and ONLY != '18':
return
if CHKTIME:
t0 = time()
for ali in ['map', 'sam']:
seed(1)
if 13436 == int(random()*100000):
same_seed = True
genome = generate_random_ali(ali)
genome_bis = parse_fasta('test.fa~', verbose=False)
self.assertEqual(genome, genome_bis)
else:
same_seed = False
genome = parse_fasta('test.fa~')
# PARSE SAM
if ali == 'map':
from pytadbit.parsers.map_parser import parse_map as parser
else:
try:
from pytadbit.parsers.sam_parser import parse_sam as parser
except ImportError:
print 'ERROR: PYSAM not found, skipping test\n'
continue
parser(['test_read1.%s~' % (ali)], ['test_read2.%s~' % (ali)],
'./lala1-%s~' % (ali), './lala2-%s~' % (ali), genome,
re_name='DPNII', mapper='GEM')
# GET INTERSECTION
from pytadbit.mapping import get_intersection
get_intersection('lala1-%s~' % (ali), 'lala2-%s~' % (ali),
'lala-%s~' % (ali))
# FILTER
masked = filter_reads('lala-%s~' % (ali), verbose=False,
fast=(ali=='map'))
self.assertEqual(masked[1]['reads'], 1000)
self.assertEqual(masked[2]['reads'], 1000)
self.assertEqual(masked[3]['reads'], 1000)
self.assertEqual(masked[4]['reads'], 1000)
if same_seed:
self.assertEqual(masked[5]['reads'], 1110)
self.assertEqual(masked[6]['reads'], 2332)
self.assertEqual(masked[7]['reads'], 0)
self.assertEqual(masked[8]['reads'], 141)
self.assertEqual(masked[10]['reads'], 1)
else:
self.assertTrue (masked[5]['reads'] > 1000)
self.assertEqual(masked[9]['reads'], 1000)
apply_filter('lala-map~', 'lala-map-filt~', masked, filters=[1],
reverse=True, verbose=False)
self.assertEqual(len([True for l in open('lala-map-filt~')
if not l.startswith('#')]), 1000)
d = plot_iterative_mapping('lala1-map~', 'lala2-map~')
self.assertEqual(d[0][1], 6000)
if CHKTIME:
self.assertEqual(True, True)
print '18', time() - t0
def test_18_filter_reads(self):
if ONLY and ONLY != '18':
return
if CHKTIME:
t0 = time()
for ali in ['map', 'sam']:
seed(1)
if 13436 == int(random()*100000):
same_seed = True
genome = generate_random_ali(ali)
genome_bis = parse_fasta('test.fa~', verbose=False)
self.assertEqual(genome, genome_bis)
else:
same_seed = False
genome = parse_fasta('test.fa~')
# PARSE SAM
if ali == 'map':
from pytadbit.parsers.map_parser import parse_map as parser
else:
try:
from pytadbit.parsers.sam_parser import parse_sam as parser
except ImportError:
print 'ERROR: PYSAM not found, skipping test\n'
continue
parser(['test_read1.%s~' % (ali)], ['test_read2.%s~' % (ali)],
'./lala1-%s~' % (ali), './lala2-%s~' % (ali), genome,
re_name='DPNII', mapper='GEM')
# GET INTERSECTION
from pytadbit.mapping import get_intersection
get_intersection('lala1-%s~' % (ali), 'lala2-%s~' % (ali),
'lala-%s~' % (ali))
# FILTER
masked = filter_reads('lala-%s~' % (ali), verbose=False,
fast=(ali=='map'))
self.assertEqual(masked[1]['reads'], 1000)
self.assertEqual(masked[2]['reads'], 1000)
self.assertEqual(masked[3]['reads'], 1000)
self.assertEqual(masked[4]['reads'], 1000)
if same_seed:
self.assertEqual(masked[5]['reads'], 1110)
self.assertEqual(masked[6]['reads'], 2332)
self.assertEqual(masked[7]['reads'], 0)
self.assertEqual(masked[8]['reads'], 141)
self.assertEqual(masked[10]['reads'], 1)
else:
self.assertTrue (masked[5]['reads'] > 1000)
self.assertEqual(masked[9]['reads'], 1000)
apply_filter('lala-map~', 'lala-map-filt~', masked, filters=[1],
reverse=True, verbose=False)
self.assertEqual(len([True for l in open('lala-map-filt~')
if not l.startswith('#')]), 1000)
d = plot_iterative_mapping('lala1-map~', 'lala2-map~')
self.assertEqual(d[0][1], 6000)
if CHKTIME:
self.assertEqual(True, True)
print '18', time() - t0
def test_18_filter_reads(self):
if ONLY and not "18" in ONLY:
return
if CHKTIME:
t0 = time()
for ali in ["map", "sam"]:
seed(1)
if 13436 == int(random()*100000):
same_seed = True
genome = generate_random_ali(ali)
genome_bis = parse_fasta("test.fa~", verbose=False)
self.assertEqual(genome, genome_bis)
else:
same_seed = False
genome = parse_fasta("test.fa~")
# PARSE SAM
if ali == "map":
from pytadbit.parsers.map_parser import parse_map as parser
else:
try:
from pytadbit.parsers.sam_parser import parse_sam as parser
except ImportError:
print "ERROR: PYSAM not found, skipping test\n"
continue
parser(["test_read1.%s~" % (ali)], ["test_read2.%s~" % (ali)],
"./lala1-%s~" % (ali), "./lala2-%s~" % (ali), genome,
re_name="DPNII", mapper="GEM")
# GET INTERSECTION
from pytadbit.mapping import get_intersection
get_intersection("lala1-%s~" % (ali), "lala2-%s~" % (ali),
"lala-%s~" % (ali))
# FILTER
masked = filter_reads("lala-%s~" % (ali), verbose=False,
fast=(ali=="map"))
self.assertEqual(masked[1]["reads"], 1000)
self.assertEqual(masked[2]["reads"], 1000)
self.assertEqual(masked[3]["reads"], 1000)
self.assertEqual(masked[4]["reads"], 1000)
if same_seed:
self.assertEqual(masked[5]["reads"], 1110)
self.assertEqual(masked[6]["reads"], 2332)
self.assertEqual(masked[7]["reads"], 0)
self.assertEqual(masked[8]["reads"], 141)
self.assertEqual(masked[10]["reads"], 1)
else:
self.assertTrue (masked[5]["reads"] > 1000)
self.assertEqual(masked[9]["reads"], 1000)
apply_filter("lala-map~", "lala-map-filt~", masked, filters=[1],
reverse=True, verbose=False)
self.assertEqual(len([True for l in open("lala-map-filt~")
if not l.startswith("#")]), 1000)
d = plot_iterative_mapping("lala1-map~", "lala2-map~")
self.assertEqual(d[0][1], 6000)
if CHKTIME:
self.assertEqual(True, True)
print "18", time() - t0
def test_18_filter_reads(self):
if ONLY and ONLY != "18":
return
if CHKTIME:
t0 = time()
for ali in ["map", "sam"]:
seed(1)
if 13436 == int(random() * 100000):
same_seed = True
genome = generate_random_ali(ali)
genome_bis = parse_fasta("test.fa~", verbose=False)
self.assertEqual(genome, genome_bis)
else:
same_seed = False
genome = parse_fasta("test.fa~")
# PARSE SAM
if ali == "map":
from pytadbit.parsers.map_parser import parse_map as parser
else:
try:
from pytadbit.parsers.sam_parser import parse_sam as parser
except ImportError:
print "ERROR: PYSAM not found, skipping test\n"
continue
parser(
["test_read1.%s~" % (ali)],
["test_read2.%s~" % (ali)],
"./lala1-%s~" % (ali),
"./lala2-%s~" % (ali),
genome,
re_name="DPNII",
mapper="GEM",
)
# GET INTERSECTION
from pytadbit.mapping import get_intersection
get_intersection("lala1-%s~" % (ali), "lala2-%s~" % (ali), "lala-%s~" % (ali))
# FILTER
masked = filter_reads("lala-%s~" % (ali), verbose=False, fast=(ali == "map"))
self.assertEqual(masked[1]["reads"], 1000)
self.assertEqual(masked[2]["reads"], 1000)
self.assertEqual(masked[3]["reads"], 1000)
self.assertEqual(masked[4]["reads"], 1000)
if same_seed:
self.assertEqual(masked[5]["reads"], 1110)
self.assertEqual(masked[6]["reads"], 2332)
self.assertEqual(masked[7]["reads"], 0)
self.assertEqual(masked[8]["reads"], 141)
self.assertEqual(masked[10]["reads"], 1)
else:
self.assertTrue(masked[5]["reads"] > 1000)
self.assertEqual(masked[9]["reads"], 1000)
apply_filter("lala-map~", "lala-map-filt~", masked, filters=[1], reverse=True, verbose=False)
self.assertEqual(len([True for l in open("lala-map-filt~") if not l.startswith("#")]), 1000)
d = plot_iterative_mapping("lala1-map~", "lala2-map~")
self.assertEqual(d[0][1], 6000)
if CHKTIME:
self.assertEqual(True, True)
print "18", time() - t0
plt.rcParams['font.weight'] = 'medium'
#plt.rcParams['font.family'] = 'sans-serif'
#plt.rcParams['font.sans-serif'] = 'Arial'
plt.rcParams['lines.linewidth'] = 2.0
plt.rcParams['legend.numpoints'] = 1
plt.rcParams['legend.frameon'] = False
plt.rcParams['savefig.bbox'] = 'tight'
# Plot: fraction of mapped reads
infiles = [maps1, maps2]
pair_id = infiles[0].split("/")[-1].replace("_read1_map.tsv", "")
outfile = '%s/%s_plot_proportion_mapped_reads.png' % (POSTMAPPING_PLOTS,
pair_id)
reads_mapped_per_iteration = plot_iterative_mapping(
fnam1=infiles[0],
fnam2=infiles[1],
total_reads=n_reads_trimmed,
savefig=outfile)
reads_mapped_per_iteration = pd.DataFrame.from_dict(reads_mapped_per_iteration)
reads_mapped_per_iteration.columns = ['read1', 'read2']
fraction_mapped_read1 = list(
reads_mapped_per_iteration['read1'])[-1] / float(n_reads_trimmed)
fraction_mapped_read2 = list(
reads_mapped_per_iteration['read2'])[-1] / float(n_reads_trimmed)
fraction_mapped_str = ",".join(
[str(i) for i in [fraction_mapped_read1, fraction_mapped_read2]])
# Plot: distribution of dangling-end lengths
plt.rcParams['font.size'] = 12
infile = '%s/%s_both_map.tsv' % (PROCESSED, pair_id)
outfile = '%s/%s_plot_distribution_dangling_ends_lengths.png' % (