forked from jeffhussmann/ribosomes
/
TL_seq_experiment.py
149 lines (123 loc) · 6.27 KB
/
TL_seq_experiment.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
import os
import pysam
from Sequencing.Parallel import map_reduce
from Sequencing import mapping_tools, fastq, sam, utilities
from Serialize import read_positions
import positions
import visualize
import rna_experiment
class TLSeqExperiment(rna_experiment.RNAExperiment):
num_stages = 2
specific_results_files = [
('bam', 'bam', '{name}.bam'),
]
specific_figure_files = [
]
specific_outputs = [
[#'bam',
],
['read_positions',
'metagene_positions',
],
]
specific_work = [
[#'preprocess',
#'map_tophat',
#'combine_mappings',
],
['get_read_positions',
'get_metagene_positions',
]
]
specific_cleanup = [
[],
['plot_starts_and_ends',
],
]
def __init__(self, **kwargs):
super(TLSeqExperiment, self).__init__(**kwargs)
def preprocess(self):
''' tophat can't handle named pipes, so need to make a file. '''
reads = self.get_reads()
total_reads = 0
with open(self.file_names['preprocessed_reads'], 'w') as preprocessed_file:
for read in reads:
total_reads += 1
record = fastq.make_record(*read)
preprocessed_file.write(record)
self.summary.extend(
[('Total reads', total_reads),
],
)
def map_tophat(self):
mapping_tools.map_tophat([self.file_names['preprocessed_reads']],
self.file_names['bowtie2_index_prefix'],
self.file_names['genes'],
self.file_names['transcriptome_index'],
self.file_names['tophat_dir'],
no_sort=True,
)
def get_read_positions(self):
piece_CDSs, max_gene_length = self.get_CDSs()
gene_infos = positions.get_Transcript_position_counts(self.merged_file_names['bam'],
piece_CDSs,
relevant_lengths=[],
left_buffer=500,
right_buffer=500,
)
self.read_positions = {name: info['five_prime_positions']
for name, info in gene_infos.iteritems()}
self.write_file('read_positions', self.read_positions)
def get_metagene_positions(self):
piece_CDSs, max_gene_length = self.get_CDSs()
read_positions = self.load_read_positions()
metagene_positions = positions.compute_metagene_positions(piece_CDSs,
read_positions,
max_gene_length,
)
self.write_file('metagene_positions', metagene_positions)
def plot_starts_and_ends(self):
metagene_positions = self.read_file('metagene_positions')
visualize.plot_metagene_positions(metagene_positions,
self.figure_file_names['starts_and_ends'],
['all'],
)
def combine_mappings(self):
num_unmapped = 0
num_nonunique = 0
num_unique = 0
mappings = pysam.Samfile(self.file_names['accepted_hits'])
unmapped = pysam.Samfile(self.file_names['unmapped_bam'])
merged = sam.merge_by_name(mappings, unmapped)
grouped = utilities.group_by(merged, lambda m: m.qname)
alignment_sorter = sam.AlignmentSorter(mappings.references,
mappings.lengths,
self.file_names['bam'],
)
with alignment_sorter:
for qname, group in grouped:
unmapped = any(m.is_unmapped for m in group)
if unmapped:
num_unmapped += 1
continue
nonunique = len(group) > 1 or any(m.mapq < 40 for m in group)
if nonunique:
num_nonunique += 1
else:
num_unique += 1
for mapping in group:
alignment_sorter.write(mapping)
self.summary.extend(
[('Unmapped', num_unmapped),
('Nonunique', num_nonunique),
('Unique', num_unique),
],
)
def get_total_eligible_reads(self):
summary_pairs = self.read_file('summary')
summary_dict = {name: values[0] for name, values in summary_pairs}
total_mapped_reads = summary_dict['Nonunique'] + summary_dict['Unique']
return total_mapped_reads
if __name__ == '__main__':
script_path = os.path.realpath(__file__)
map_reduce.controller(TLSeqExperiment, script_path)