-
Notifications
You must be signed in to change notification settings - Fork 2
/
mappability.py
156 lines (129 loc) · 6.75 KB
/
mappability.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
import gtf
import trim
from Sequencing import fastq, genomes
from Sequencing.annotation import Annotation_factory
from Sequencing.Parallel import map_reduce
import os
import ribosome_profiling_experiment
import positions
import pysam
from Serialize import read_positions
from collections import defaultdict
artifical_annotation_fields = [
('transcript_name', 's'),
('position', '06d'),
]
artifical_annotation = Annotation_factory(artifical_annotation_fields)
def make_artificial_reads(transcript,
fragment_length,
read_length,
adapter_sequence,
region_fetcher,
common_buffer,
):
transcript_sequence = transcript.retrieve_sequence(region_fetcher,
left_buffer=common_buffer,
right_buffer=common_buffer + fragment_length,
)
# Needs to include one non-Solexa value for automatic encoding recognition.
high_quals = fastq.encode_sanger([25] + [30]*(read_length - 1))
for i, transcript_position in enumerate(range(-common_buffer, transcript.CDS_length + common_buffer)):
annotation = artifical_annotation(transcript_name=transcript.name,
position=transcript_position,
)
fragment_sequence = transcript_sequence[i:i + fragment_length]
if '-' in fragment_sequence:
# skip fragments that run off the edge of a reference sequence
continue
full_sequence = fragment_sequence + adapter_sequence
read = fastq.Read(annotation.identifier, full_sequence[:read_length], high_quals)
yield read
adapter_sequences = {'linker': trim.smRNA_linker + trim.truseq_R2_rc}
class MappabilityExperiment(ribosome_profiling_experiment.RibosomeProfilingExperiment):
num_stages = 1
specific_work = [
['record_uniqueness'],
]
specific_results_files = [
('uniqueness', read_positions, '{name}_uniqueness.hdf5'),
]
specific_outputs = [
['uniqueness'],
]
def __init__(self, **kwargs):
super(MappabilityExperiment, self).__init__(**kwargs)
self.adapter_sequence = adapter_sequences[self.adapter_type]
self.fragment_length = int(kwargs['fragment_length'])
self.common_buffer = 100
print self.work
def get_reads(self):
CDSs, _ = self.get_CDSs()
region_fetcher = genomes.build_region_fetcher(self.file_names['genome'],
load_references=True,
)
for transcript in CDSs:
reads = make_artificial_reads(transcript,
self.fragment_length,
self.max_read_length,
self.adapter_sequence,
region_fetcher,
self.common_buffer,
)
for read in reads:
yield read
def record_uniqueness(self):
CDSs, _ = self.get_CDSs()
uniqueness = {}
transcripts = {}
# For any genomic position that participates in a transcript, this will
# contain a mapping to a set of all transcripts it participates in.
genomic_to_all_transcripts = defaultdict(set)
for transcript in CDSs:
landmarks = {'start': 0,
'start_codon': transcript.transcript_start_codon,
'stop_codon': transcript.transcript_stop_codon,
'end': transcript.transcript_length,
}
uniqueness[transcript.name] = {self.fragment_length: positions.PositionCounts(landmarks, self.common_buffer, self.common_buffer)}
transcript.build_coordinate_maps(left_buffer=self.common_buffer, right_buffer=self.common_buffer)
transcripts[transcript.name] = transcript
for genomic_position, transcript_position in transcript.genomic_to_transcript.iteritems():
full_position = (transcript.seqname, transcript.strand, genomic_position)
genomic_to_all_transcripts[full_position].add((transcript.name, transcript_position))
bam_file = pysam.Samfile(self.file_names['accepted_hits'])
for read in bam_file:
# If this read was incorrectly trimmed, don't record it.
if read.qlen != self.fragment_length:
continue
annotation = artifical_annotation.from_prefix_identifier(read.qname)
true_transcript = transcripts[annotation['transcript_name']]
true_position = annotation['position']
strand = '-' if read.is_reverse else '+'
if strand == '+':
five_prime = read.pos
else:
five_prime = read.aend - 1
full_mapped_position = (bam_file.getrname(read.tid), strand, five_prime)
if read.mapq < 50:
# Flag the true source of the read as nonunique.
uniqueness[true_transcript.name][self.fragment_length]['start_codon', true_position] = 2
# Hopefully redundantly, flag the position actually mapped to as
# nonunqiue.
for transcript_name, transcript_position in genomic_to_all_transcripts[full_mapped_position]:
uniqueness[transcript_name][self.fragment_length]['start_codon', transcript_position] = 2
else:
# Check that any read with a MAPQ of 50 is to the expected position.
full_true_position = (true_transcript.seqname,
true_transcript.strand,
true_transcript.transcript_to_genomic[true_position],
)
if read.mapq == 50 and (full_mapped_position != full_true_position):
raise ValueError(full_mapped_position, full_true_position)
# As long as this hasn't been mapped to by some other fragment,
# mark it as unique.
if uniqueness[true_transcript.name][self.fragment_length]['start_codon', true_position] == 0:
uniqueness[true_transcript.name][self.fragment_length]['start_codon', true_position] = 1
self.write_file('uniqueness', uniqueness)
if __name__ == '__main__':
script_path = os.path.realpath(__file__)
map_reduce.controller(MappabilityExperiment, script_path)