def _write_table(self, samples, items):
names = [
'%s:%d' % (item.record.CHROM, item.record.POS) for item in items
]
sample_list = io.named_list_type(samples)
groups = []
locations_list = io.named_list_type(['CHROM', 'POS'])
locations = io.named_list_type(names, locations_list)([
locations_list([item.record.CHROM, item.record.POS])
for item in items
])
groups.append(('Location', locations))
genotypes = io.named_list_type(names, sample_list)([
sample_list([
describe_genotype(item2, item.variants)
for item2 in item.genotypes
]) for item in items
])
groups.append(('Genotype', genotypes))
if self.qualities:
qualities = io.named_list_type(names, sample_list)(
[sample_list(item.qualities) for item in items])
groups.append(('Quality', qualities))
if self.counts:
counts = io.named_list_type(names, sample_list)([
sample_list([
describe_counts(item2, item.variants)
for item2 in item.counts
]) for item in items
])
groups.append(('Count', counts))
annotation_list = io.named_list_type(['snpeff'])
annotations = io.named_list_type(names, annotation_list)([
annotation_list([
' /// '.join(item2[0] for item2 in item.snpeff
if selection.matches(self.snpeff_show, item2[1]))
]) for item in items
])
groups.append(('Annotation', annotations))
io.write_grouped_csv(self.prefix + '.csv', groups)
def _write_table(self, samples, items):
names = [ '%s:%d' % (item.record.CHROM, item.record.POS) for item in items ]
sample_list = io.named_list_type(samples)
groups = [ ]
locations_list = io.named_list_type(['CHROM','POS'])
locations = io.named_list_type(names, locations_list)([
locations_list([ item.record.CHROM, item.record.POS ])
for item in items
])
groups.append(('Location',locations))
genotypes = io.named_list_type(names,sample_list)([
sample_list([ describe_genotype(item2,item.variants) for item2 in item.genotypes ])
for item in items
])
groups.append(('Genotype',genotypes))
if self.qualities:
qualities = io.named_list_type(names,sample_list)([
sample_list(item.qualities)
for item in items
])
groups.append(('Quality',qualities))
if self.counts:
counts = io.named_list_type(names,sample_list)([
sample_list([ describe_counts(item2,item.variants) for item2 in item.counts ])
for item in items
])
groups.append(('Count',counts))
annotation_list = io.named_list_type(['snpeff'])
annotations = io.named_list_type(names, annotation_list)([
annotation_list([
' /// '.join(item2[0] for item2 in item.snpeff if selection.matches(self.snpeff_show, item2[1]))
])
for item in items
])
groups.append(('Annotation',annotations))
io.write_grouped_csv(self.prefix + '.csv', groups)
def run(self):
#assert not self.utr_only or self.utrs, '--utrs-only yes but no --utrs given'
# Reference genome
#chromosome_lengths = reference_directory.Reference(self.reference, must_exist=True).get_lengths()
chromosomes = collections.OrderedDict(io.read_sequences(self.reference))
def get_interpeak_seq(peaks):
start = min(item.transcription_stop for item in peaks)
end = max(item.transcription_stop for item in peaks)
if end-start > self.max_seq: return ''
if peaks[0].strand >= 0:
return chromosomes[peaks[0].seqid][start:end]
else:
return bio.reverse_complement(chromosomes[peaks[0].seqid][start:end])
def get_prepeak_seq(gene,peaks):
if gene.strand >= 0:
start = gene.utr_pos
end = min(item.transcription_stop for item in peaks)
if end-start > self.max_seq: return ''
return chromosomes[gene.seqid][start:end]
else:
start = max(item.transcription_stop for item in peaks)
end = gene.utr_pos
if end-start > self.max_seq: return ''
return bio.reverse_complement(chromosomes[gene.seqid][start:end])
# Normalization files
if self.norm_file:
norm_file = self.norm_file
else:
nesoni.Norm_from_counts(self.prefix+'-norm', self.counts).run()
norm_file = self.prefix+'-norm.csv'
norms = io.read_grouped_table(norm_file, [('All',str)])['All']
pair_norm_names = [ ]
pair_norms = [ ]
for i in xrange(len(norms)):
pair_norm_names.append(norms.keys()[i]+'-peak1')
pair_norms.append(norms.values()[i])
for i in xrange(len(norms)):
pair_norm_names.append(norms.keys()[i]+'-peak2')
pair_norms.append(norms.values()[i])
io.write_grouped_csv(
self.prefix+'-pairs-norm.csv',
[('All',io.named_list_type(pair_norm_names)(pair_norms))],
comments=['#Normalization'],
)
# Read data
annotations = list(annotation.read_annotations(self.parents))
if self.utrs:
utrs = list(annotation.read_annotations(self.utrs))
else:
utrs = [ ]
children = list(annotation.read_annotations(self.children))
count_table = io.read_grouped_table(self.counts, [
('Count',int),
('Tail_count',int),
('Tail',_float_or_none),
('Proportion',_float_or_none),
('Annotation',str)
])
counts = count_table['Count']
tail_counts = count_table['Tail_count']
proportions = count_table['Proportion']
tails = count_table['Tail']
samples = counts.value_type().keys()
sample_tags = { }
for line in count_table.comments:
if line.startswith('#sampleTags='):
parts = line[len('#sampleTags='):].split(',')
assert parts[0] not in sample_tags
sample_tags[parts[0]] = parts
for item in children:
item.weight = sum( counts[item.get_id()][name] * float(norms[name]['Normalizing.multiplier']) for name in samples )
parents = [ ]
id_to_parent = { }
for item in annotations:
if item.type != self.parent_type: continue
assert item.get_id() not in id_to_parent, 'Duplicate id in parent file: '+item.get_id()
parents.append(item)
id_to_parent[item.get_id()] = item
item.children = [ ]
#item.cds = [ ]
# Default utr
if item.strand >= 0:
item.utr_pos = item.end
else:
item.utr_pos = item.start
if 'three_prime_UTR_start' in item.attr:
if item.strand >= 0:
item.utr_pos = int(item.attr['three_prime_UTR_start'])-1
else:
item.utr_pos = int(item.attr['three_prime_UTR_start'])
for item in utrs:
assert item.attr['Parent'] in id_to_parent, 'Unknown gene '+item.attr['Parent']
id_to_parent[item.attr['Parent']].utr_pos = (item.start if item.strand >= 0 else item.end)
for item in children:
item.transcription_stop = item.end if item.strand >= 0 else item.start #End of transcription, 0-based, ie between-positions based
if 'Parent' in item.attr:
for item_parent in item.attr['Parent'].split(','):
parent = id_to_parent[item_parent]
parent.children.append(item)
for item in parents:
item.children.sort(key=_annotation_sorter)
relevant = list(item.children)
if self.utr_only:
#if item.strand <= 0:
# relative_utr_start = item.end - int(item.attr['three_prime_UTR_start'])
#else:
# relative_utr_start = int(item.attr['three_prime_UTR_start'])-1 - item.start
#
#def relative_start(peak):
# return item.end-peak.end if item.strand < 0 else peak.start-item.start
#relevant = [ peak for peak in relevant if relative_start(peak) >= relative_utr_start ]
relevant = [
peak for peak in relevant
if (peak.end >= item.utr_pos if item.strand >= 0 else peak.start <= item.utr_pos)
]
if self.top:
relevant.sort(key=lambda peak:peak.weight, reverse=True)
relevant = relevant[:self.top]
relevant.sort(key=_annotation_sorter)
item.relevant_children = relevant
# JSON output
j_data = { }
j_genes = j_data['genes'] = { }
j_genes['__comment__'] = 'start is 0-based'
j_genes['name'] = [ ]
j_genes['chromosome'] = [ ]
j_genes['strand'] = [ ]
j_genes['start'] = [ ]
j_genes['utr'] = [ ]
j_genes['end'] = [ ]
j_genes['gene'] = [ ]
j_genes['product'] = [ ]
j_genes['peaks'] = [ ]
j_genes['relevant_peaks'] = [ ]
#j_genes['cds'] = [ ]
#j_genes['cds_start'] = [ ]
#j_genes['cds_end'] = [ ]
for item in parents:
j_genes['name'].append( item.get_id() )
j_genes['chromosome'].append( item.seqid )
j_genes['strand'].append( item.strand )
j_genes['start'].append( item.start )
j_genes['utr'].append( item.utr_pos )
j_genes['end'].append( item.end )
j_genes['gene'].append( item.attr.get('Name',item.attr.get('gene','')) )
j_genes['product'].append( item.attr.get('Product',item.attr.get('product','')) )
j_genes['peaks'].append( [ item2.get_id() for item2 in item.children ] )
j_genes['relevant_peaks'].append( [ item2.get_id() for item2 in item.relevant_children ] )
#j_genes['cds'].append( item.cds )
#j_genes['cds_start'].append( item.cds_start )
#j_genes['cds_end'].append( item.cds_end )
j_peaks = j_data['peaks'] = { }
j_peaks['__comment__'] = 'start is 0-based'
j_peaks['name'] = [ ]
j_peaks['chromosome'] = [ ]
j_peaks['strand'] = [ ]
j_peaks['start'] = [ ]
j_peaks['end'] = [ ]
j_peaks['parents'] = [ ]
j_peaks['counts'] = [ ]
j_peaks['tail_lengths'] = [ ]
j_peaks['proportion_tailed'] = [ ]
for item in children:
j_peaks['name'].append( item.get_id() )
j_peaks['chromosome'].append( item.seqid )
j_peaks['strand'].append( item.strand )
j_peaks['start'].append( item.start )
j_peaks['end'].append( item.end )
j_peaks['parents'].append( item.attr['Parent'].split(',') if 'Parent' in item.attr else [ ])
j_peaks['counts'].append( counts[item.get_id()].values() )
j_peaks['tail_lengths'].append( count_table['Tail'][item.get_id()].values() )
j_peaks['proportion_tailed'].append( count_table['Proportion'][item.get_id()].values() )
j_samples = j_data['samples'] = { }
j_samples['name'] = [ ]
j_samples['tags'] = [ ]
j_samples['normalizing_multiplier'] = [ ]
for name in samples:
j_samples['name'].append(name)
j_samples['tags'].append(sample_tags[name])
j_samples['normalizing_multiplier'].append(float(norms[name]['Normalizing.multiplier']))
j_chromosomes = j_data['chromosomes'] = { }
j_chromosomes['name'] = [ ]
j_chromosomes['length'] = [ ]
for name, seq in chromosomes.iteritems():
j_chromosomes['name'].append(name)
j_chromosomes['length'].append(len(seq))
with open(self.prefix + '.json','wb') as f:
json.dump(j_data, f)
# Output paired peak file
output_comments = [ '#Counts' ]
output_samples = [ ]
for item in samples:
output_samples.append(item+'-peak1')
output_comments.append('#sampleTags=' + ','.join([item+'-peak1','peak1']+sample_tags.get(item,[])))
for item in samples:
output_samples.append(item+'-peak2')
output_comments.append('#sampleTags=' + ','.join([item+'-peak2','peak2']+sample_tags.get(item,[])))
output_names = [ ]
output_counts = [ ]
output_tail_counts = [ ]
output_proportions = [ ]
output_tails = [ ]
output_annotation_fields = [ 'gene', 'product', 'mean_tail_1', 'mean_tail_2', 'chromosome', 'strand',
'transcription_stops' ] #, 'interpeak_seq', ]
output_annotations = [ ]
for item in parents:
peaks = item.relevant_children
for i in xrange(len(peaks)-1):
for j in xrange(i+1, len(peaks)):
id_i = peaks[i].get_id()
id_j = peaks[j].get_id()
id_pair = item.get_id() + '-'+id_i+'-'+id_j
output_names.append(id_pair)
row = [ ]
row.extend(counts[id_i].values())
row.extend(counts[id_j].values())
output_counts.append(filter(_text,row))
row = [ ]
row.extend(tail_counts[id_i].values())
row.extend(tail_counts[id_j].values())
output_tail_counts.append(filter(_text,row))
row = [ ]
row.extend(proportions[id_i].values())
row.extend(proportions[id_j].values())
output_proportions.append(filter(_text,row))
row = [ ]
row.extend(tails[id_i].values())
row.extend(tails[id_j].values())
output_tails.append(filter(_text,row))
output_annotations.append([
item.attr.get('Name',item.attr.get('gene','')),
item.attr.get('Product',item.attr.get('product','')),
count_table['Annotation'][id_i]['mean-tail'],
count_table['Annotation'][id_j]['mean-tail'],
item.seqid,
str(item.strand),
'%d, %d' % (peaks[i].transcription_stop,peaks[j].transcription_stop),
#get_interpeak_seq([peaks[i],peaks[j]]),
])
#output_count_table = io.named_matrix_type(output_names,output_samples)(output_counts)
io.write_grouped_csv(
self.prefix + '-pairs.csv',
[
('Count',io.named_matrix_type(output_names,output_samples)(output_counts)),
('Tail_count',io.named_matrix_type(output_names,output_samples)(output_tail_counts)),
('Proportion',io.named_matrix_type(output_names,output_samples)(output_proportions)),
('Tail',io.named_matrix_type(output_names,output_samples)(output_tails)),
('Annotation',io.named_matrix_type(output_names,output_annotation_fields)(output_annotations)),
],
comments=output_comments,
)
# # Chi Sq tests
#
# #for id in relation:
# # peaks = relation[id]
# # if len(peaks) < 2: continue
#
# mats = [ ]
# genes = [ ]
# products = [ ]
# mean_tails = [ ]
# prop_tails = [ ]
#
# peak_names = [ ]
# chromosome_names = [ ]
# strands = [ ]
# transcription_stops = [ ]
# interpeak_seqs = [ ]
# prepeak_seqs = [ ]
#
# for parent in parents:
# id = parent.get_id()
# peaks = parent.relevant_children
# if len(peaks) < 2: continue
#
# matrix = [ ]
# for item in peaks:
# matrix.append(counts[item.get_id()].values())
#
# mats.append(
# runr.R_literal(id) + ' = ' +
# runr.R_literal(matrix)
# )
#
# genes.append(parent.attr.get('Name',parent.attr.get('gene','')))
# products.append(parent.attr.get('Product',parent.attr.get('product','')))
#
# def format_mean(s):
# if s == 'NA': return 'NA'
# return '%.1f' % float(s)
# mean_tails.append(', '.join( format_mean(count_table['Annotation'][item.get_id()]['mean-tail']) for item in peaks ))
#
# def format_prop(s):
# if s == 'NA': return 'NA'
# return '%.2f' % float(s)
# prop_tails.append(', '.join( format_prop(count_table['Annotation'][item.get_id()]['proportion-with-tail']) for item in peaks ))
#
# peak_names.append(', '.join(item.get_id() for item in peaks))
# chromosome_names.append(parent.seqid)
# strands.append(parent.strand)
# transcription_stops.append(', '.join(str(item.transcription_stop) for item in peaks))
# interpeak_seqs.append(get_interpeak_seq(peaks))
# prepeak_seqs.append(get_prepeak_seq(parent,peaks))
#
# #if len(mats) >= 10: break
#
# text = 'cat("Loading data into R+\n")\n'
# text += 'data <- list(\n' + ',\n'.join(mats) + ')\n'
# text += CHISQ
#
# runr.run_script(text,
# OUTPUT_FILENAME=self.prefix+'.csv',
# GENES = genes,
# PRODUCTS = products,
# MEAN_TAILS = mean_tails,
# PROP_TAILS = prop_tails,
# PEAK_NAMES = peak_names,
# CHROMOSOME_NAMES = chromosome_names,
# STRANDS = strands,
# TRANSCRIPTION_STOPS = transcription_stops,
# INTERPEAK_SEQS = interpeak_seqs,
# PREPEAK_SEQS = prepeak_seqs,
# )
#
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[:]
tags = []
for i in xrange(len(bam_filenames)):
if os.path.isdir(bam_filenames[i]):
working = working_directory.Working(bam_filenames[i])
titles[i] = working.name
tags.append(working.get_tags())
if not annotation_filenames:
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) / max(1, len(strandedness))
log.log(
'Strand specificity score: %.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
comments = ['#Counts'] + ['#sampleTags=' + ','.join(item) for item in tags]
names = []
count_type = io.named_list_type(titles)
counts = []
#rpkm_type = io.named_list_type(titles)
#rpkms = [ ]
annotation_type = io.named_list_type(['Length'] + qualifiers)
annotations = []
alignment_type = io.named_list_type(
['On same fragment'] +
['Ambiguous alignment'] if expect_multiple_alignments else [])
alignments = []
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)
# )
common_str = count_encode(common)
ambiguous_str = count_encode(ambiguous)
names.append(feature_name)
counts.append(count_type(count))
#rpkms.append(rpkm_type(rpkm))
annotations.append(
annotation_type([str(feature.length)] +
list(feature.qualifiers)))
alignments.append(
alignment_type(
[common_str] +
[ambiguous_str] if expect_multiple_alignments else []))
groups = [
('Count', io.named_list_type(names, count_type)(counts)),
#('RPKM', io.named_list_type(names,rpkm_type)(rpkms)),
('Annotation', io.named_list_type(names,
annotation_type)(annotations)),
('Alignment', io.named_list_type(names, alignment_type)(alignments)),
]
io.write_grouped_csv(output_prefix + '.csv',
groups,
rowname_name='Feature',
comments=comments)
def run(self):
#assert not self.utr_only or self.utrs, '--utrs-only yes but no --utrs given'
# Reference genome
#chromosome_lengths = reference_directory.Reference(self.reference, must_exist=True).get_lengths()
chromosomes = collections.OrderedDict(io.read_sequences(
self.reference))
def get_interpeak_seq(peaks):
start = min(item.transcription_stop for item in peaks)
end = max(item.transcription_stop for item in peaks)
if end - start > self.max_seq: return ''
if peaks[0].strand >= 0:
return chromosomes[peaks[0].seqid][start:end]
else:
return bio.reverse_complement(
chromosomes[peaks[0].seqid][start:end])
def get_prepeak_seq(gene, peaks):
if gene.strand >= 0:
start = gene.utr_pos
end = min(item.transcription_stop for item in peaks)
if end - start > self.max_seq: return ''
return chromosomes[gene.seqid][start:end]
else:
start = max(item.transcription_stop for item in peaks)
end = gene.utr_pos
if end - start > self.max_seq: return ''
return bio.reverse_complement(
chromosomes[gene.seqid][start:end])
# Normalization files
if self.norm_file:
norm_file = self.norm_file
else:
nesoni.Norm_from_counts(self.prefix + '-norm', self.counts).run()
norm_file = self.prefix + '-norm.csv'
norms = io.read_grouped_table(norm_file, [('All', str)])['All']
pair_norm_names = []
pair_norms = []
for i in xrange(len(norms)):
pair_norm_names.append(norms.keys()[i] + '-peak1')
pair_norms.append(norms.values()[i])
for i in xrange(len(norms)):
pair_norm_names.append(norms.keys()[i] + '-peak2')
pair_norms.append(norms.values()[i])
io.write_grouped_csv(
self.prefix + '-pairs-norm.csv',
[('All', io.named_list_type(pair_norm_names)(pair_norms))],
comments=['#Normalization'],
)
# Read data
annotations = list(annotation.read_annotations(self.parents))
if self.utrs:
utrs = list(annotation.read_annotations(self.utrs))
else:
utrs = []
children = list(annotation.read_annotations(self.children))
count_table = io.read_grouped_table(self.counts,
[('Count', int),
('Tail_count', int),
('Tail', _float_or_none),
('Proportion', _float_or_none),
('Annotation', str)])
counts = count_table['Count']
tail_counts = count_table['Tail_count']
proportions = count_table['Proportion']
tails = count_table['Tail']
samples = counts.value_type().keys()
sample_tags = {}
for line in count_table.comments:
if line.startswith('#sampleTags='):
parts = line[len('#sampleTags='):].split(',')
assert parts[0] not in sample_tags
sample_tags[parts[0]] = parts
for item in children:
item.weight = sum(counts[item.get_id()][name] *
float(norms[name]['Normalizing.multiplier'])
for name in samples)
parents = []
id_to_parent = {}
for item in annotations:
if item.type != self.parent_type: continue
assert item.get_id(
) not in id_to_parent, 'Duplicate id in parent file: ' + item.get_id(
)
parents.append(item)
id_to_parent[item.get_id()] = item
item.children = []
#item.cds = [ ]
# Default utr
if item.strand >= 0:
item.utr_pos = item.end
else:
item.utr_pos = item.start
if 'three_prime_UTR_start' in item.attr:
if item.strand >= 0:
item.utr_pos = int(item.attr['three_prime_UTR_start']) - 1
else:
item.utr_pos = int(item.attr['three_prime_UTR_start'])
for item in utrs:
assert item.attr[
'Parent'] in id_to_parent, 'Unknown gene ' + item.attr['Parent']
id_to_parent[item.attr['Parent']].utr_pos = (
item.start if item.strand >= 0 else item.end)
for item in children:
item.transcription_stop = item.end if item.strand >= 0 else item.start #End of transcription, 0-based, ie between-positions based
if 'Parent' in item.attr and item.attr.get(
"Relation") != "Antisense":
for item_parent in item.attr['Parent'].split(','):
parent = id_to_parent[item_parent]
parent.children.append(item)
for item in parents:
item.children.sort(key=_annotation_sorter)
relevant = list(item.children)
if self.utr_only:
#if item.strand <= 0:
# relative_utr_start = item.end - int(item.attr['three_prime_UTR_start'])
#else:
# relative_utr_start = int(item.attr['three_prime_UTR_start'])-1 - item.start
#
#def relative_start(peak):
# return item.end-peak.end if item.strand < 0 else peak.start-item.start
#relevant = [ peak for peak in relevant if relative_start(peak) >= relative_utr_start ]
#relevant = [
# peak for peak in relevant
# if (peak.end >= item.utr_pos if item.strand >= 0 else peak.start <= item.utr_pos)
# ]
relevant = [
peak for peak in relevant
if peak.attr.get("Relation") == "3'UTR"
]
if self.top:
relevant.sort(key=lambda peak: peak.weight, reverse=True)
relevant = relevant[:self.top]
relevant.sort(key=_annotation_sorter)
item.relevant_children = relevant
# JSON output
j_data = {}
j_genes = j_data['genes'] = {}
j_genes['__comment__'] = 'start is 0-based'
j_genes['name'] = []
j_genes['chromosome'] = []
j_genes['strand'] = []
j_genes['start'] = []
j_genes['utr'] = []
j_genes['end'] = []
j_genes['gene'] = []
j_genes['product'] = []
j_genes['peaks'] = []
j_genes['relevant_peaks'] = []
#j_genes['cds'] = [ ]
#j_genes['cds_start'] = [ ]
#j_genes['cds_end'] = [ ]
for item in parents:
j_genes['name'].append(item.get_id())
j_genes['chromosome'].append(item.seqid)
j_genes['strand'].append(item.strand)
j_genes['start'].append(item.start)
j_genes['utr'].append(item.utr_pos)
j_genes['end'].append(item.end)
j_genes['gene'].append(
item.attr.get('Name', item.attr.get('gene', '')))
j_genes['product'].append(
item.attr.get('Product', item.attr.get('product', '')))
j_genes['peaks'].append(
[item2.get_id() for item2 in item.children])
j_genes['relevant_peaks'].append(
[item2.get_id() for item2 in item.relevant_children])
#j_genes['cds'].append( item.cds )
#j_genes['cds_start'].append( item.cds_start )
#j_genes['cds_end'].append( item.cds_end )
j_peaks = j_data['peaks'] = {}
j_peaks['__comment__'] = 'start is 0-based'
j_peaks['name'] = []
j_peaks['chromosome'] = []
j_peaks['strand'] = []
j_peaks['start'] = []
j_peaks['end'] = []
j_peaks['parents'] = []
j_peaks['counts'] = []
j_peaks['tail_lengths'] = []
j_peaks['proportion_tailed'] = []
for item in children:
j_peaks['name'].append(item.get_id())
j_peaks['chromosome'].append(item.seqid)
j_peaks['strand'].append(item.strand)
j_peaks['start'].append(item.start)
j_peaks['end'].append(item.end)
j_peaks['parents'].append(item.attr['Parent'].split(',')
if 'Parent' in item.attr else [])
j_peaks['counts'].append(counts[item.get_id()].values())
j_peaks['tail_lengths'].append(
count_table['Tail'][item.get_id()].values())
j_peaks['proportion_tailed'].append(
count_table['Proportion'][item.get_id()].values())
j_samples = j_data['samples'] = {}
j_samples['name'] = []
j_samples['tags'] = []
j_samples['normalizing_multiplier'] = []
for name in samples:
j_samples['name'].append(name)
j_samples['tags'].append(sample_tags[name])
j_samples['normalizing_multiplier'].append(
float(norms[name]['Normalizing.multiplier']))
j_chromosomes = j_data['chromosomes'] = {}
j_chromosomes['name'] = []
j_chromosomes['length'] = []
for name, seq in chromosomes.iteritems():
j_chromosomes['name'].append(name)
j_chromosomes['length'].append(len(seq))
with open(self.prefix + '.json', 'wb') as f:
json.dump(j_data, f)
# Output paired peak file
output_comments = ['#Counts']
output_samples = []
for item in samples:
output_samples.append(item + '-peak1')
output_comments.append('#sampleTags=' +
','.join([item + '-peak1', 'peak1'] +
sample_tags.get(item, [])))
for item in samples:
output_samples.append(item + '-peak2')
output_comments.append('#sampleTags=' +
','.join([item + '-peak2', 'peak2'] +
sample_tags.get(item, [])))
output_names = []
output_counts = []
output_tail_counts = []
output_proportions = []
output_tails = []
output_annotation_fields = [
'gene', 'product', 'biotype', 'mean_tail_1', 'mean_tail_2',
'chromosome', 'strand', 'transcription_stops'
] #, 'interpeak_seq', ]
output_annotations = []
for item in parents:
peaks = item.relevant_children
for i in xrange(len(peaks) - 1):
for j in xrange(i + 1, len(peaks)):
id_i = peaks[i].get_id()
id_j = peaks[j].get_id()
id_pair = item.get_id() + '-' + id_i + '-' + id_j
output_names.append(id_pair)
row = []
row.extend(counts[id_i].values())
row.extend(counts[id_j].values())
output_counts.append(filter(_text, row))
row = []
row.extend(tail_counts[id_i].values())
row.extend(tail_counts[id_j].values())
output_tail_counts.append(filter(_text, row))
row = []
row.extend(proportions[id_i].values())
row.extend(proportions[id_j].values())
output_proportions.append(filter(_text, row))
row = []
row.extend(tails[id_i].values())
row.extend(tails[id_j].values())
output_tails.append(filter(_text, row))
output_annotations.append([
item.attr.get('Name', item.attr.get('gene', '')),
item.attr.get('Product', item.attr.get('product', '')),
item.attr.get('Biotype', ''),
count_table['Annotation'][id_i]['mean-tail'],
count_table['Annotation'][id_j]['mean-tail'],
item.seqid,
str(item.strand),
'%d, %d' % (peaks[i].transcription_stop,
peaks[j].transcription_stop),
#get_interpeak_seq([peaks[i],peaks[j]]),
])
#output_count_table = io.named_matrix_type(output_names,output_samples)(output_counts)
io.write_grouped_csv(
self.prefix + '-pairs.csv',
[
('Count', io.named_matrix_type(output_names,
output_samples)(output_counts)),
('Tail_count',
io.named_matrix_type(output_names,
output_samples)(output_tail_counts)),
('Proportion',
io.named_matrix_type(output_names,
output_samples)(output_proportions)),
('Tail', io.named_matrix_type(output_names,
output_samples)(output_tails)),
('Annotation',
io.named_matrix_type(
output_names,
output_annotation_fields)(output_annotations)),
],
comments=output_comments,
)
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[:]
tags = [ ]
for i in xrange(len(bam_filenames)):
if os.path.isdir(bam_filenames[i]):
working = working_directory.Working(bam_filenames[i])
titles[i] = working.name
tags.append(working.get_tags())
if not annotation_filenames:
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) / max(1,len(strandedness))
log.log('Strand specificity score: %.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
comments = [ '#Counts' ] + [
'#sampleTags='+','.join(item)
for item in tags
]
names = [ ]
count_type = io.named_list_type(titles)
counts = [ ]
#rpkm_type = io.named_list_type(titles)
#rpkms = [ ]
annotation_type = io.named_list_type([ 'Length' ] + qualifiers)
annotations = [ ]
alignment_type = io.named_list_type(
[ 'On same fragment' ] +
[ 'Ambiguous alignment' ]
if expect_multiple_alignments
else [ ]
)
alignments = [ ]
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)
# )
common_str = count_encode(common)
ambiguous_str = count_encode(ambiguous)
names.append(feature_name)
counts.append(count_type(count))
#rpkms.append(rpkm_type(rpkm))
annotations.append(annotation_type([ str(feature.length) ] + list(feature.qualifiers)))
alignments.append(alignment_type([ common_str ] + [ ambiguous_str ] if expect_multiple_alignments else [ ]))
groups = [
('Count', io.named_list_type(names,count_type)(counts)),
#('RPKM', io.named_list_type(names,rpkm_type)(rpkms)),
('Annotation', io.named_list_type(names,annotation_type)(annotations)),
('Alignment', io.named_list_type(names,alignment_type)(alignments)),
]
io.write_grouped_csv(output_prefix + '.csv', groups, rowname_name='Feature', comments=comments)