def setup(self):
grace.status('Load depths')
self.sample_names = [ os.path.split(dirname)[1] for dirname in self.working_dirs ]
self.workspaces = [ working_directory.Working(dirname, must_exist=True) for dirname in self.working_dirs ]
self.depths = [ item.get_depths() for item in self.workspaces ]
#self.depths = list(legion.imap(lambda item: item.get_object('depths.pickle.gz'), self.workspaces, local=True))
self.any_pairs = any(item.param['any_pairs'] for item in self.workspaces)
grace.status('')
lengths = self.workspaces[0].get_reference().get_lengths()
self.chromosome_names = [ name for name, length in lengths ]
self.lengths = dict(lengths)
self.processes = [ ]
def run(self):
workspace = working_directory.Working(self.output_dir)
workspace.setup_reference(self.reference)
workspace.update_param(snp_cost = self.snp_cost)
#assert os.path.exists(self.reference), 'Reference file does not exist'
#reference_filename = workspace._object_filename('reference.fa')
#if os.path.exists(reference_filename):
# os.unlink(reference_filename)
#os.symlink(os.path.relpath(self.reference, self.output_dir), reference_filename)
bam_filename = io.abspath(self.output_dir, 'alignments.bam')
bam_prefix = io.abspath(self.output_dir, 'alignments')
if sam.is_bam(self.input):
sort_input_filename = self.input
temp_filename = None
else:
temp_filename = io.abspath(self.output_dir, 'temp.bam')
sort_input_filename = temp_filename
writer = io.Pipe_writer(temp_filename, ['samtools', 'view', '-S', '-b', '-'])
f = open(self.input, 'rb')
while True:
data = f.read(1<<20)
if not data: break
writer.write(data)
writer.close()
f.close()
grace.status('Sort')
#io.execute([
# 'samtools', 'sort', '-n', sort_input_filename, bam_prefix
#])
sam.sort_bam(sort_input_filename, bam_prefix, by_name=True)
if temp_filename is not None:
os.unlink(temp_filename)
grace.status('')
def run(self):
title1 = self.title1
title2 = self.title2
working1 = working_directory.Working(self.working_dir1)
working2 = working_directory.Working(self.working_dir2)
cutoff = self.cutoff
sequence_names = [
name for name, length in working1.get_reference().get_lengths()
]
if title1 is None:
title1 = working1.name
if title2 is None:
title2 = working2.name
n = 1
while significance([('A', n)], [('T', n)], 1.0) > cutoff:
n += 1
f = open(self.prefix + '.txt', 'wb')
print >> f, '%g\tsignificance cutoff' % cutoff
print >> f, '%d\tdepth required to call substitution (greater if there are errors in the reads)' % n
print >> f, 'Sequence\tPosition in reference\tChange type\tReference\t%s\t%s\tp-value (no correction for multiple testing)\t%s\t%s' % (
title1, title2, title1, title2)
for sequence_name in sequence_names:
filename1 = working1 / (
grace.filesystem_friendly_name(sequence_name) +
'-evidence.txt')
filename2 = working2 / (
grace.filesystem_friendly_name(sequence_name) +
'-evidence.txt')
for (pos1, ins1, sub1, ref1, conins1,
consub1), (pos2, ins2, sub2, ref2, conins2,
consub2) in itertools.izip(read_file(filename1),
read_file(filename2)):
assert pos1 == pos2 and ref1 == ref2
if pos1 % 1000 == 0:
grace.status('Testing %s %d' % (sequence_name, pos1))
dec_ins1 = io.decode_evidence(ins1)
dec_ins2 = io.decode_evidence(ins2)
if dec_ins1 and dec_ins2:
sig = significance(io.decode_evidence(ins1),
io.decode_evidence(ins2), cutoff)
if sig is not None and sig <= cutoff:
print >> f, '%s\t%d\t%s\t\t%s\t%s\t%g\t%s\t%s' % (
sequence_name, pos1, 'insertion-before', ins1,
ins2, sig, conins1, conins2)
f.flush()
dec_sub1 = io.decode_evidence(sub1)
dec_sub2 = io.decode_evidence(sub2)
if dec_sub1 and dec_sub2:
sig = significance(dec_sub1, dec_sub2, cutoff)
if sig is not None and sig <= cutoff:
if dec_sub1[0][0] == '-' or dec_sub2[0][0] == '-':
what = 'deletion'
elif dec_sub1[0][0] != dec_sub2[0][0]:
what = 'substitution'
else:
what = 'different mix'
print >> f, '%s\t%d\t%s\t%s\t%s\t%s\t%g\t%s\t%s' % (
sequence_name, pos1, what, ref1, sub1, sub2, sig,
consub1, consub2)
f.flush()
f.close()
grace.status('')
return 0
def nway_main(gbk_filename, use_indels, use_reference, give_evidence, give_consequences,
require_all, require_bisect, full_output, format, working_dirs, split_a, split_b, f=sys.stdout):
assert working_dirs, 'Need at least one working directory.'
workspaces = [ working_directory.Working(dirname, must_exist=True) for dirname in working_dirs ]
reference = workspaces[0].get_reference()
#if not annotation_filename:
# annotation_filename = reference.annotations_filename() #May still be None
if use_reference:
names = ['reference']
evidence_start = 1
else:
names = [ ]
evidence_start = 0
names.extend( norm_name(item) for item in working_dirs )
references = io.read_sequences(reference.reference_fasta_filename())
annotations = { }
if gbk_filename:
from Bio import SeqIO
for record in SeqIO.parse(io.open_possibly_compressed_file(gbk_filename),'genbank'):
sequence = record.seq.tostring()
features = [ item for item in record.features if item.type != 'source' ]
features.sort(key=lambda item: item.location.nofuzzy_start)
annotations[sequence] = features
iterator = reader(working_dirs, references, use_reference, annotations)
if not use_indels:
iterator = itertools.ifilter(has_no_indels, iterator)
if require_all or require_bisect or format == 'counts':
iterator = itertools.ifilter(fully_unambiguous, iterator)
if require_bisect:
iterator = itertools.ifilter(is_binary_partition, iterator)
if not require_bisect:
if full_output:
iterator = itertools.ifilter(not_boring_insertion, iterator)
else:
iterator = itertools.ifilter(is_interesting, iterator)
if split_a or split_b:
assert len(names) == len(set(names)), 'Two samples with the same name'
try:
split_a = [ names.index(norm_name(item)) for item in split_a ]
split_b = [ names.index(norm_name(item)) for item in split_b ]
except ValueError:
raise grace.Error('Sample to be split is not amongst samples given')
iterator = itertools.ifilter(is_split(split_a, split_b), iterator)
#if limit:
# iterator = itertools.islice(iterator, limit)
if format == 'table':
line = 'Reference\tPosition\tChange type'
line += '\t' + '\t'.join(names)
if give_evidence:
line += '\t' + '\t'.join(names[evidence_start:])
if give_consequences:
line += '\t' + '\t'.join(names[evidence_start:])
if annotations:
line += '\tAnnotations'
print >> f, line
for calls in iterator:
line = '%s\t%d\t%s\t%s' % (
calls.ref_name,
calls.ref_pos+1,
change_type(calls),
'\t'.join(item.consensus for item in calls.calls))
if give_evidence:
line += '\t' + '\t'.join(item.evidence for item in calls.calls[evidence_start:])
if give_consequences:
line += '\t' + '\t'.join(item.consequences for item in calls.calls[evidence_start:])
if annotations:
line += '\t' + describe_features(calls.features)
print >> f, line
elif format == 'compact':
for line in transpose_strings(names):
print >> f, line
print >> f
for calls in iterator:
if calls.is_insertion:
footer = '%12d.5 %s' % (calls.ref_pos, calls.ref_name)
else:
footer = '%12d %s' % (calls.ref_pos+1, calls.ref_name)
t = transpose_strings([ item.consensus for item in calls.calls ], '-', 1)
top = t[0] + ' ' + footer
if give_consequences:
consequences = [ ]
for call in calls.calls:
if call.consequences:
for item in call.consequences.split(', '):
item = ' '.join(item.split()[:3])
if item not in consequences: consequences.append(item)
if consequences:
top += ' ' + ' / '.join(sorted(consequences))
top += ' ' + describe_features(calls.features)
print >> f, top
for line in t[1:]:
print >> f, line
elif format == 'nexus':
buckets = [ [ ] for name in names ]
for calls in iterator:
for i, char in enumerate(partition_string(calls)):
buckets[i].append(char)
print >> f, '#NEXUS'
print >> f, 'begin taxa;'
print >> f, 'dimensions ntax=%d;' % len(names)
print >> f, 'taxlabels'
for name in names:
print >> f, name
print >> f, ';'
print >> f, 'end;'
print >> f, 'begin characters;'
print >> f, 'dimensions nchar=%d;' % len(buckets[0])
print >> f, 'format datatype=STANDARD symbols="ACGT-0123456789" missing=N;'
print >> f, 'matrix'
for name, bucket in itertools.izip(names, buckets):
print >> f, name, ''.join(bucket)
print >> f, ';'
print >> f, 'end;'
elif format == 'counts':
for line in transpose_strings(names):
print >> f, line
print >> f
counts = { }
for calls in iterator:
count_str = partition_string(calls)
if count_str not in counts:
counts[count_str] = 1
else:
counts[count_str] += 1
for count_str in sorted(counts, key=lambda x: (counts[x], x), reverse=True):
print >> f, '%s %d' % (transpose_strings(count_str)[0], counts[count_str])
else:
raise grace.Error('Unknown output format: ' + format)
def run(self):
#mincov, args = grace.get_option_value(args, '--mincov', int, 1)
#maxdiff, args = grace.get_option_value(args, '--maxdiff', int, 16)
#minsize, args = grace.get_option_value(args, '--minsize', int, 200)
#what, args = grace.get_option_value(args, '--what', as_core_or_unique, 'core')
#is_core = (what == 'core')
#
#grace.expect_no_further_options(args)
#
#if len(args) < 2:
# print >> sys.stderr, HELP
# raise grace.Help_shown()
#
#output_dir, working_dirs = args[0], args[1:]
#
##assert not path.exists(path.join(output_dir, 'reference.fa')), \
#assert not path.exists(path.join(output_dir, 'parameters')), \
# 'Output directory not given'
#
#if not path.exists(output_dir):
# os.mkdir(output_dir)
assert self.what in (
'core',
'unique'), 'Expected --what to be either "core" or "unique".'
is_core = (self.what == 'core')
workspace = self.get_workspace()
for name, seq in io.read_sequences(
working_directory.Working(self.working_dirs[0]).get_reference(
).reference_fasta_filename()):
self.log.log(name + '\n')
friendly_name = grace.filesystem_friendly_name(name)
good = [True] * len(seq)
for working_dir in self.working_dirs:
if is_core:
suffix = '-depth.userplot'
else:
suffix = '-ambiguous-depth.userplot'
data = trivia.read_unstranded_userplot(
os.path.join(working_dir, friendly_name + suffix))
assert len(seq) == len(data)
for i in xrange(len(seq)):
if good[i]:
if is_core:
good[i] = data[i] >= self.mincov
else:
good[i] = data[i] < self.mincov
#Close holes
start = -self.maxdiff - 1
n_holes = 0
for i in xrange(len(seq)):
if good[i]:
if 0 < i - start <= self.maxdiff:
for j in xrange(start, i):
good[j] = True
n_holes += 1
start = i + 1
self.log.log('Closed ' + grace.pretty_number(n_holes) + ' holes\n')
f = open(workspace / ('%s-%s.fa' % (friendly_name, self.what)),
'wb')
io.write_fasta(
f, name, ''.join([(seq[i] if good[i] else 'N')
for i in xrange(len(seq))]))
f.close()
f = open(
workspace / ('%s-%s_masked.fa' % (friendly_name, self.what)),
'wb')
io.write_fasta(
f, name, ''.join([(seq[i] if good[i] else seq[i].lower())
for i in xrange(len(seq))]))
f.close()
f_good = open(
workspace / ('%s-%s_parts.fa' % (friendly_name, self.what)),
'wb')
f_nongood = open(
workspace / ('%s-non%s_parts.fa' % (friendly_name, self.what)),
'wb')
start = 0
n_good = [0]
n_good_bases = [0]
def emit(i):
if i - start < self.minsize: return
if good[start]:
n_good[0] += 1
n_good_bases[0] += i - start
io.write_fasta(f_good if good[start] else f_nongood,
'%s:%d..%d' % (name, start + 1, i),
seq[start:i])
for i in xrange(1, len(seq)):
if good[i] != good[start]:
emit(i)
start = i
emit(len(seq))
f_nongood.close()
f_good.close()
self.log.log(
grace.pretty_number(sum(good)) + ' bases are ' + self.what +
', of ' + grace.pretty_number(len(seq)) +
' in reference sequence\n')
self.log.log(
grace.pretty_number(n_good[0]) + ' parts at least ' +
grace.pretty_number(self.minsize) + ' bases long with ' +
grace.pretty_number(n_good_bases[0]) + ' total bases\n')
self.log.log('\n')
def run(self):
bams = []
reference = None
reference2 = None
extra = []
for sample in self.samples:
if sam.is_bam(sample):
bams.append(sample)
elif os.path.isdir(sample):
working = working_directory.Working(sample, True)
bams.append(working.get_filtered_sorted_bam())
extra.append('##sampleTags=' + ','.join(working.get_tags()))
if reference2 is None:
reference2 = working.get_reference(
).reference_fasta_filename()
elif io.is_sequence_file(sample):
assert reference is None, 'Only one reference FASTA file allowed.'
reference = sample
if reference is None:
reference = reference2
if reference is None:
raise grace.Error('No reference FASTA file given.')
with nesoni.Stage() as stage:
tempspace = stage.enter(workspace.tempspace())
if self.depth_limit:
with nesoni.Stage() as stage2:
for i in xrange(len(bams)):
sam.Bam_depth_limit(
tempspace / ('%d' % i),
bams[i],
depth=self.depth_limit).process_make(stage2)
bams[i] = tempspace / ('%d.bam' % i)
# FreeBayes claims to handle multiple bams, but it doesn't actually work
if len(bams) > 1:
sam.Bam_merge(tempspace / 'merged', bams=bams,
index=False).run()
bams = [tempspace / 'merged.bam']
command = [
'freebayes',
'-f',
reference,
'--ploidy',
str(self.ploidy),
'--pvar',
str(self.pvar),
] + self.freebayes_options + bams
self.log.log('Running: ' + ' '.join(command) + '\n')
f_out = stage.enter(open(self.prefix + '.vcf', 'wb'))
f_in = stage.enter(io.pipe_from(command))
done_extra = False
for line in f_in:
if not done_extra and not line.startswith('##'):
for extra_line in extra:
f_out.write(extra_line + '\n')
done_extra = True
f_out.write(line)
index_vcf(self.prefix + '.vcf')
def count_run(min_score, min_size, max_size, filter_mode, equalize, types,
locii, qualifiers, use_strand, merge_filename, limit,
output_prefix, filenames, log):
if filter_mode == 'poly':
use_bam_filename = 'alignments.bam'
use_only_top = True
use_only_monogamous = False
expect_multiple_alignments = True
elif filter_mode == 'mono':
use_bam_filename = 'alignments.bam'
use_only_top = True
use_only_monogamous = True
expect_multiple_alignments = True
else:
assert filter_mode == 'existing', 'Unrecognized filtering mode'
use_bam_filename = 'alignments_filtered.bam'
use_only_top = False
use_only_monogamous = False
expect_multiple_alignments = False
types = types.lower().split(',')
qualifiers = qualifiers.split(',')
if locii:
locii = locii.lower().split(',')
else:
locii = None
assert use_strand is not None, 'You must now explicitly specify --strand'
assert use_strand in ('pool', 'forward', 'reverse',
'both'), "Can't understand --strand specification."
from Bio import Seq, SeqIO
annotation_filenames = []
bam_filenames = []
for arg in filenames:
if annotation.is_annotation_file(arg):
annotation_filenames.append(arg)
else:
bam_filenames.append(arg)
n_samples = len(bam_filenames)
titles = bam_filenames[:]
for i in xrange(len(bam_filenames)):
if os.path.isdir(bam_filenames[i]):
titles[i] = os.path.basename(bam_filenames[i])
if not annotation_filenames:
working = working_directory.Working(bam_filenames[i])
reference_filename = working.get_reference(
).annotations_filename()
if reference_filename is not None:
annotation_filenames.append(reference_filename)
bam_filenames[i] = os.path.join(bam_filenames[i], use_bam_filename)
assert bam_filenames, 'No reference alignments given'
merge = {}
merge_qualifiers = {}
if merge_filename is not None:
#First line gives qualifiers
#remaining lines give <qualifier> <qualifier...> <gene> <transcript> <transcript...>
f = open(merge_filename, 'rU')
qualifiers = f.readline().rstrip('\n').split('\t')
for line in f:
parts = line.rstrip('\n').split('\t')
if not parts: continue
for name in parts[len(qualifiers) + 1:]:
assert name not in merge, 'Duplicate feature name in merge file'
merge[name] = parts[len(qualifiers)]
merge_qualifiers[name] = parts[:len(qualifiers)]
f.close()
genes = {} # reference name -> gene index
feature_names = {} # feature_name -> number of occurrences
features = []
n_features = 0
chromosome_length = {}
for filename in bam_filenames:
headers = sam.bam_headers(filename)
for line in headers.split('\n'):
if not line: continue
parts = line.split('\t')
if parts[0] != '@SQ': continue
name = None
length = None
for part in parts[1:]:
if part.startswith('SN:'): name = part[3:]
if part.startswith('LN:'): length = int(part[3:])
assert name is not None and length is not None
if name in chromosome_length:
assert chromosome_length[name] == length
else:
chromosome_length[name] = length
for name in chromosome_length:
genes[name] = span_index.Span_index()
if annotation_filenames:
assert not merge, 'Merging not supported with annotation files'
for filename in annotation_filenames:
for feature in annotation.read_annotations(filename):
if feature.type.lower() not in types: continue
if (locii is not None and
('locus_tag' not in feature.attr
or feature.attr['locus_tag'].lower() not in locii)):
continue
f = Feature(n_samples)
f.name = feature.get_id()
if feature.type.lower() != 'cds' and len(types) > 1:
f.name = feature.type + ':' + f.name
feature_names[f.name] = feature_names.get(f.name, 0) + 1
if feature_names[f.name] > 1:
f.name += '/%d' % feature_names[f.name]
f.qualifiers = [
feature.attr.get(item, '') for item in qualifiers
]
f.length = feature.end - feature.start
assert feature.seqid in genes, 'Annotation for sequence that is not in BAM files'
genes[feature.seqid].insert(
Span_entry(feature.start, feature.end, feature.strand or 1,
f))
features.append(f)
else:
# Sequences as features
log.log(
'No annotation files given or found, using sequences as features\n'
)
name_feature = {} # (merged)name -> feature
for name in chromosome_length:
merged_name = merge.get(name, name)
if merged_name not in name_feature:
f = Feature(n_samples)
f.name = merged_name
f.length = length
f.qualifiers = merge_qualifiers.get(name,
('', ) * len(qualifiers))
n_features += 1
name_feature[merged_name] = f
features.append(f)
else:
f = name_feature[merged_name]
f.length = max(f.length, length) #...
genes[name].insert(Span_entry(0, chromosome_length[name], 1, f))
log.log('%d features\n\n' % len(features))
for name in genes:
genes[name].prepare()
n_fragments = [0] * n_samples
n_fragments_aligned = [0] * n_samples
n_low_score = [0] * n_samples
n_something = [0] * n_samples
n_multiple = [0] * n_samples
n_span = [0] * n_samples
for i in xrange(n_samples):
for read_name, fragment_alignments, unmapped in sam.bam_iter_fragments(
bam_filenames[i],
'Counting sample %d of %d' % (i + 1, n_samples)):
n_fragments[i] += 1
if not fragment_alignments:
continue
n_fragments_aligned[i] += 1
feature_hits = [] # [ [ (feature, strand) ] ]
# Use only top scoring alignments
fragment_scores = [
sum(al.get_AS() for al in item) for item in fragment_alignments
]
best_score = max(fragment_scores)
if min_score is not None and best_score < min_score:
n_low_score[i] += 1
continue
if use_only_top:
cutoff = max(best_score, min_score)
else:
cutoff = min_score
fragment_alignments = [
item
for item, score in zip(fragment_alignments, fragment_scores)
if score >= cutoff
]
for alignments in fragment_alignments:
strand = -1 if alignments[0].flag & sam.FLAG_REVERSE else 1
start = min(item.pos - 1 for item in alignments)
end = max(item.pos + item.length - 1 for item in alignments)
length = end - start
if min_size is not None and length < min_size: continue
if max_size is not None and length > max_size: continue
rname = alignments[0].rname
strand = -1 if alignments[0].flag & sam.FLAG_REVERSE else 1
assert alignments[
0].rname in genes, 'Alignment refers to sequence not present in GENBANK file'
this_feature_hits = []
for item in genes[rname].get(start, end):
rel_strand = strand * item.strand
key = (item.feature, rel_strand)
if key in this_feature_hits: continue
this_feature_hits.append(key)
if not use_only_monogamous or len(
fragment_alignments) == 1:
item.feature.count[rel_strand][i] += 1
if this_feature_hits:
feature_hits.append(this_feature_hits)
if len(this_feature_hits) > 1:
for a in this_feature_hits:
for b in this_feature_hits:
if a[0] is b[0]: continue
a[0].common[(a[1], b[1])][b[0]] += 1
if len(feature_hits) > 0:
n_something[i] += 1
#else:
# print fragment_alignments
# print genes[fragment_alignments[0][0].rname].indexes
# print
if len(feature_hits) > 1:
n_multiple[i] += 1
for j in xrange(len(feature_hits)):
for k in xrange(len(feature_hits)):
if j == k: continue
for a in feature_hits[j]:
for b in feature_hits[k]:
if a[0] is b[0]: continue
a[0].ambiguous[(a[1], b[1])][b[0]] += 1
if any(len(item) > 1 for item in feature_hits): n_span[i] += 1
if limit is not None and n_fragments[i] >= limit: break
grace.status('')
#log.log('%s\n' % titles[i])
#log.log('%20s fragments\n' % grace.pretty_number(n_fragments[i]))
#log.log('%20s fragments aligned to the reference\n' % grace.pretty_number(n_fragments_aligned[i]))
#if n_low_score[i]:
# log.log('%20s had too low an alignment score, discarded\n' % grace.pretty_number(n_low_score[i]))
#log.log('%20s aligned to an annotated gene\n' % grace.pretty_number(n_something[i]))
#if expect_multiple_alignments or n_multiple[i]:
# log.log('%20s aligned to multiple genes\n' % grace.pretty_number(n_multiple[i]))
#log.log('%20s had an alignment that spanned multiple genes\n' % grace.pretty_number(n_span[i]))
#log.log('\n')
log.datum(titles[i], 'fragments', n_fragments[i])
log.datum(titles[i], 'fragments aligned to the reference',
n_fragments_aligned[i])
if n_low_score[i]:
log.datum(titles[i], 'had too low an alignment score, discarded',
n_low_score[i])
log.datum(titles[i], 'aligned to an annotated gene', n_something[i])
if expect_multiple_alignments or n_multiple[i]:
log.datum(titles[i], 'aligned to multiple genes', n_multiple[i])
log.datum(titles[i], 'had an alignment that spanned multiple genes',
n_span[i])
log.log('\n')
strandedness = []
for feature in features:
n_forward = sum(feature.count[1])
n_reverse = sum(feature.count[-1])
if n_forward + n_reverse < 5: continue
strandedness.append(
(n_forward - n_reverse) * 100.0 / (n_forward + n_reverse))
strandedness = sum(strandedness) / len(strandedness)
log.log(
'Strand specificity: %.0f%%\n'
' (~ -100%% reverse strand, ~ 0%% non-specific, ~ 100%% forward strand\n'
' Average over all features with at least 5 hits.)\n' % strandedness)
if use_strand == 'pool':
getters = [
lambda f:
(feature.name, add_lists(feature.count[1], feature.count[-1]),
add_defdicts(feature.common[(1, 1)], feature.common[
(1, -1)], feature.common[(-1, 1)], feature.common[(-1, -1)]),
add_defdicts(feature.ambiguous[(1, 1)], feature.ambiguous[
(1, -1)], feature.ambiguous[(-1, 1)], feature.ambiguous[
(-1, -1)]))
]
elif use_strand == 'forward':
getters = [
lambda f: (feature.name, feature.count[1], feature.common[
(1, 1)], feature.ambiguous[(1, 1)])
]
elif use_strand == 'reverse':
getters = [
lambda f: (feature.name, feature.count[-1], feature.common[
(-1, -1)], feature.ambiguous[(-1, -1)])
]
elif use_strand == 'both':
getters = [
lambda f: (feature.name, feature.count[1], feature.common[
(1, 1)], feature.ambiguous[(1, 1)]), lambda f:
(feature.name + 'r', feature.count[-1], feature.common[
(-1, -1)], feature.ambiguous[(-1, -1)])
]
total_hits = [0] * n_samples
for feature in features:
for getter in getters:
total_hits = add_lists(total_hits, getter(feature)[1])
if equalize:
min_hits = min(total_hits)
p = [float(min_hits) / item for item in total_hits]
total_hits = [min_hits] * n_samples
f = open(output_prefix + '.txt', 'wb')
#log.attach(open(output_prefix + '_log.txt', 'wb'))
print >> f, tab_encode(
['Feature'] + titles + ['RPKM ' + item for item in titles] +
['Length'] + qualifiers + ['On same fragment'] +
(['Ambiguous alignment'] if expect_multiple_alignments else []))
for feature in features:
for getter in getters:
feature_name, count, common, ambiguous = getter(feature)
if equalize:
count = [subsample(count[i], p[i]) for i in xrange(n_samples)]
rpkm = [
count[i] * 1.0e9 / feature.length / total_hits[i]
for i in xrange(n_samples)
]
common_str = ' '.join(
'%dx%s' % (item[1], item[0]) for item in sorted(
common.items(), key=lambda item: item[1], reverse=True))
ambiguous_str = ' '.join(
'%dx%s' % (item[1], item[0]) for item in sorted(
ambiguous.items(), key=lambda item: item[1], reverse=True))
print >> f, tab_encode(
[feature_name] + [str(item) for item in count] +
['%.2f' % item for item in rpkm] + [str(feature.length)] +
list(feature.qualifiers) + [common_str] +
([ambiguous_str] if expect_multiple_alignments else []))
f.close()
def run(self):
assert self.reads, 'No read files given.'
colorspace = [ io.is_colorspace(item) for item in self.reads ]
assert len(set(colorspace)) == 1, 'Mixture of colorspace and basespace reads is not currently supported.'
colorspace = colorspace[0]
#polya_dir = self.get_polya_dir()
working = working_directory.Working(self.output_dir, must_exist=False)
working.set_reference(self.reference)
reference = working.get_reference()
#polya_working = working_directory.Working(polya_dir, must_exist=False)
#polya_working.set_reference(self.reference)
clipped_prefix = working/'clipped_reads'
clipped_filename = clipped_prefix+('.csfastq.gz' if colorspace else '.fastq.gz')
raw_filename = working/'alignments_raw.sam.gz'
extended_filename = working/'alignments_extended.sam.gz'
#polya_filename = working/'alignments_filtered_polyA.sam.gz'
if colorspace:
self.clip_runs_colorspace(
filenames=self.reads,
prefix=clipped_prefix,
sample=working.name,
).make()
else:
self.clip_runs_basespace(
filenames=self.reads,
prefix=clipped_prefix,
sample=working.name,
).make()
cores = min(nesoni.coordinator().get_cores(), 8)
if colorspace:
nesoni.Execute(
command = reference.shrimp_command(cs=colorspace, parameters=[ clipped_filename ]) + [ '--qv-offset', '33' ],
execution_options = [ '-N', str(cores) ],
output=raw_filename,
cores=cores,
prefix=working/'run_alignment'
).make()
else:
nesoni.Execute(
command = [
'bowtie2',
'--rg-id', '1',
'--rg', 'SM:'+working.name,
'--sensitive-local',
'-k', '10', #Up to 10 alignments per read
'-x', reference.get_bowtie_index_prefix(),
'-U', clipped_filename,
],
execution_options = [ '--threads', str(cores) ],
output=raw_filename,
cores=cores,
prefix=working/'run_alignment'
).make()
if colorspace:
extend_sam.Extend_sam_colorspace(
input=raw_filename,
output=extended_filename,
reads=self.reads,
reference_filenames=[ reference.reference_fasta_filename() ],
).make()
else:
extend_sam.Extend_sam_basespace(
input=raw_filename,
output=extended_filename,
clips=[ clipped_prefix+'.clips.gz' ],
reference_filenames=[ reference.reference_fasta_filename() ],
prop_a = self.extension_prop_a
).make()
nesoni.Import(
input=extended_filename,
output_dir=self.output_dir,
reference=[ self.reference ],
).make()
self.get_filter_action().make()
#Tail_only(
# input=working/'alignments_filtered.bam',
# output=polya_filename,
#).make()
#nesoni.Import(
# input=polya_filename,
# output_dir=polya_dir,
# reference=[ self.reference ],
#).make()
# This shouldn't actually filter out any alignments.
# We do it to produce depth of coverage plots
# and position-sorted BAM files.
#self.get_polya_filter_action().make()
nesoni.Tag(self.output_dir, tags=self.tags).make()
#nesoni.Tag(polya_dir, tags=self.tags).make()
if self.delete_files:
# Delete unneeded files
os.unlink(clipped_prefix+'.state')
os.unlink(clipped_filename)
os.unlink(working/'alignments.bam')
os.unlink(working/'alignments_filtered.bam')
os.unlink(working/'run_alignment.state')
os.unlink(raw_filename)
os.unlink(extended_filename)
def run(self):
assert self.extension is not None, '--extension must be specified'
# Also allow simply the analyse-polya-batch directory
working_dirs = []
for item in self.working_dirs:
state_filename = os.path.join(item, 'analyse-polya-batch.state')
if not os.path.exists(state_filename):
working_dirs.append(item)
else:
with open(state_filename, 'rb') as f:
state = pickle.load(f)
for sample in state.samples:
working_dirs.append(
os.path.join(item, 'samples', sample.output_dir))
work = self.get_workspace()
if self.reuse:
pickle_workspace = workspace.Workspace(
os.path.join(self.reuse, 'pickles'))
else:
pickle_workspace = workspace.Workspace(work / 'pickles')
plot_workspace = workspace.Workspace(work / 'plots')
pickle_filenames = []
file_prefix = self.file_prefix
if file_prefix and not file_prefix.endswith('-'):
file_prefix += '-'
with nesoni.Stage() as stage:
for dir in working_dirs:
working = working_directory.Working(dir, must_exist=True)
pickle_filenames.append(pickle_workspace / working.name +
'.pickle.gz')
if self.reuse: continue
Tail_count(
pickle_workspace / working.name,
working_dir=dir,
annotations=self.annotations,
types=self.types,
parts=self.parts,
extension=self.extension,
).process_make(stage)
assert len(set(pickle_filenames)) == len(
pickle_filenames), "Duplicate sample name."
with nesoni.Stage() as stage:
Aggregate_tail_counts(output_dir=self.output_dir,
pickles=pickle_filenames,
tail=self.tail,
adaptor=self.adaptor).process_make(stage)
nesoni.Norm_from_counts(
prefix=work / 'norm',
counts_filename=work / 'counts.csv',
).make()
similarity = nesoni.Similarity(
prefix=plot_workspace / 'similarity',
counts=work / 'counts.csv',
)
plot_pooleds = [
Plot_pooled(
prefix=plot_workspace / 'pooled-heatmap',
aggregate=self.output_dir,
#min_tails = min_tails,
min_tails=1,
top=100,
)
#for min_tails in (20,50,100,200,500,1000,2000)
]
#plot_comparisons = [
# Plot_comparison(
# prefix = plot_workspace/('comparison-min-tails-%d-min-span-%.1f' % (min_tails,min_span)),
# aggregate = self.output_dir,
# min_tails = min_tails,
# min_span = min_span,
# )
# for min_tails in [50,100,200,500]
# for min_span in [2,4,8,10,15,20,25,30]
# ]
#
heatmaps = [
nesoni.Heatmap(
prefix=plot_workspace / ('heatmap-min-fold-%.1f' % fold),
counts=work / 'counts.csv',
norm_file=work / 'norm.csv',
min_span=math.log(fold) / math.log(2.0),
) for fold in [1.5, 2.0, 4.0, 6.0, 8.0, 10.0, 20.0, 30.0, 40.0]
]
with nesoni.Stage() as stage:
similarity.process_make(stage)
for action in plot_pooleds + heatmaps: #+ plot_comparisons:
action.process_make(stage)
r = reporting.Reporter(
work / 'report',
self.title,
file_prefix,
style=web.style(),
)
similarity.report(r)
r.heading('Poly(A) tail length distribution')
r.p('This plot shows the distribution of lengths of poly(A) tail sequence in top expressed features. '
'Its main purpose is to assess data quality. '
'If the plot has many bright spots there may be many identical reads, possibly due to non-random digestion.'
)
r.p('Only reads with a poly(A) sequence of four or more bases are used.'
)
for heatmap in plot_pooleds:
r.report_heatmap(heatmap)
r.heading('Heatmaps')
r.p('Genes were selected based '
'on there being at least some fold change difference between '
'some pair of samples.')
for heatmap in heatmaps:
r.report_heatmap(heatmap)
#r.heading('Average poly(A) tail length and its relation to expression levels')
#
#r.p(
# 'Only reads with a poly(A) sequence of four or more bases was included in the averages.'
# )
#
#r.p(
# 'Genes were selected based on there being at least a certain number of reads with poly(A) sequence in <i>each</i> sample (min-tails), '
# 'and on there being at least some amount of difference in average tail length between samples (min-span).'
# )
#
#for heatmap in plot_comparisons:
# r.report_heatmap(heatmap)
r.close()
def run(self):
assert self.extension is not None, '--extension must be specified'
#workspace = self.get_workspace()
workspace = working_directory.Working(self.working_dir,
must_exist=True)
if self.annotations == None:
reference = workspace.get_reference()
annotations_filename = reference.annotations_filename()
else:
annotations_filename = self.annotations
types = [item.lower() for item in self.types.split(',')]
parts = self.parts or self.types
parts = [item.lower() for item in parts.split(',')]
all_annotations = list(
annotation.read_annotations(annotations_filename))
annotation.link_up_annotations(all_annotations)
for item in all_annotations:
item.primary = None
annotations = [
item for item in all_annotations if item.type.lower() in types
]
part_annotations = []
seen = set()
queue = [(item, item) for item in annotations]
while queue:
primary, item = queue.pop()
if item.type.lower() in parts:
assert item.primary is None, "Feature with multiple parents"
item.primary = primary
key = (id(primary), item.start, item.end, item.seqid,
item.strand)
# Ignore duplicate exons (many isoforms will have the same exons)
if key not in seen:
seen.add(key)
part_annotations.append(item)
queue.extend((primary, item2) for item2 in item.children)
del seen
del all_annotations
self.log.log('%d annotations\n' % len(annotations))
self.log.log('%d part annotations\n' % len(part_annotations))
#assert annotations, 'No annotations of specified types in file'
for item in part_annotations:
this_extension = self.extension
if "max_extension" in item.attr:
this_extension = min(this_extension,
int(item.attr["max_extension"]))
if item.strand >= 0:
item.tail_pos = item.end
item.end += this_extension
else:
item.tail_pos = item.start
item.start -= this_extension
for item in annotations:
item.hits = [] # [ (tail_length, adaptor_bases) ]
index = span_index.index_annotations(part_annotations)
for alignment in sam.Bam_reader(workspace /
'alignments_filtered_sorted.bam'):
if alignment.is_unmapped or alignment.is_secondary or alignment.is_supplementary:
continue
start = alignment.reference_start
end = alignment.reference_end
alignment_length = end - start
strand = -1 if alignment.flag & sam.FLAG_REVERSE else 1
fragment_feature = annotation.Annotation(
seqid=alignment.reference_name,
start=start,
end=end,
strand=strand)
if strand >= 0:
tail_pos = end
else:
tail_pos = start
tail_length = 0
adaptor_bases = 0
for item in alignment.extra:
if item.startswith('AN:i:'):
tail_length = int(item[5:])
elif item.startswith('AD:i:'):
adaptor_bases = int(item[5:])
hits = index.get(fragment_feature, same_strand=True)
if hits:
gene = min(
hits,
key=lambda gene:
(abs(tail_pos - gene.tail_pos), gene.primary.get_id()))
# Nearest by tail_pos
# failing that, by id to ensure a deterministic choice
gene.primary.hits.append((tail_length, adaptor_bases))
for item in annotations:
del item.parents
del item.children
del item.primary
f = io.open_possibly_compressed_writer(self.prefix + '.pickle.gz')
pickle.dump((workspace.name, workspace.get_tags(), annotations), f,
pickle.HIGHEST_PROTOCOL)
f.close()
def run(self):
working_dirs = []
peaks_file = self.peaks_file
for item in self.working_dirs:
state_filename = os.path.join(item, 'analyse-polya-batch.state')
if not os.path.exists(state_filename):
working_dirs.append(item)
else:
with open(state_filename, 'rb') as f:
state = pickle.load(f)
for sample in state.samples:
working_dirs.append(
os.path.join(item, 'samples', sample.output_dir))
if not peaks_file:
peaks_file = os.path.join(self.pipeline_dir, "peaks",
"relation-child.gff")
sample_names = [os.path.split(dirname)[1] for dirname in working_dirs]
workspaces = [
working_directory.Working(dirname, must_exist=True)
for dirname in working_dirs
]
workspace = self.get_workspace()
with open(workspace / "index.html", "wb") as f:
web.emit(
f, "igv.html",
dict(
SAMPLES=json.dumps(sample_names),
HAVE_NORM=json.dumps(bool(self.norm_file)),
TITLE=self.title,
))
bams = [item / "alignments_filtered_sorted.bam" for item in workspaces]
for i in xrange(len(sample_names)):
io.symbolic_link(bams[i], workspace / (sample_names[i] + ".bam"))
io.symbolic_link(bams[i] + ".bai",
workspace / (sample_names[i] + ".bam.bai"))
io.symbolic_link(peaks_file, workspace / "peaks.gff")
if self.norm_file:
mults = io.read_grouped_table(self.norm_file)['All']
norm_mult = [
float(mults[name]['Normalizing.multiplier'])
for name in sample_names
]
with nesoni.Stage() as stage:
Bam_to_bigwig(
workspace / "total",
bam_files=bams,
what="ambiguity,span,3p,polyaspan,polya3p",
).process_make(stage)
for i in xrange(len(sample_names)):
for scale_desc, scale in \
[("raw",1.0)] + \
([("norm",norm_mult[i])] if self.norm_file else []):
Bam_to_bigwig(workspace /
(sample_names[i] + "-" + scale_desc),
bam_files=[bams[i]],
what='span,3p,polyaspan,polya3p',
scale=scale).process_make(stage)
