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
|
#start
import sys
import os
import glob
#config params:
#+) input=<directory_containing_per_sample_sums (format per file (tabs): chrm,start,end,sum)
#+) staging=<directory_to_put_intermediate_files>
#+) sample_ids_file=<file_with_studyID_sampleID_sampleID2_mappings>
#optional:
#+) existing_sums=<file_with_original_coordinates/annotations_in_SAME_ORDER_as_sums_files>
#+) pigz_threads=<#_of_threads_to_use_for_final_pasted_file_compression>
#+) prefix=<additional_type_prefix_for_files_paste>
FILES=['%sall.samples.pasted.gz' % config['prefix']]
main_script_path=os.path.join(workflow.basedir)
SCRIPTS={'find':os.path.join(main_script_path,'find_new_files.sh'),'group':os.path.join(main_script_path,'group_sums.sh'),'paste':os.path.join(main_script_path,'paste_sums.sh')}
#initial coords/annotations (e.g. exons.bed.w_header.gz in Monorail)
if 'existing_sums' not in config:
config['existing_sums']=""
#how many threads to allow pigz when doing the final single file compression
if 'pigz_threads' not in config:
config['pigz_threads']=4
wildcard_constraints:
study_group_num="[0-9a-zA-Z]{2}",
run_group_num="[0-9a-zA-Z]{2}",
#prefix example: 'dn.' (for APA sites) or empty string
type=config['prefix']+"all"
rule all:
input:
expand("{file}", file=FILES)
###exon SUM pasting rules
rule find_sums:
input:
config['input'],
config['sample_ids_file']
output:
config['staging'] + '/{type}.groups.manifest'
params:
staging=config['staging'],
script_path=SCRIPTS['find'],
type=lambda wildcards: wildcards.type
shell:
"{params.script_path} {input[0]} {input[1]} {params.staging} {params.type} .tsv"
rule group_sums:
input:
config['staging'] + '/{type}.groups.manifest'
output:
config['staging'] + '/{type}.{study_group_num}.{run_group_num}.grouped'
params:
study_group_num=lambda wildcards: wildcards.study_group_num,
run_group_num=lambda wildcards: wildcards.run_group_num,
staging=config['staging'],
script_path=SCRIPTS['group'],
type=lambda wildcards: wildcards.type
shell:
"{params.script_path} {params.staging}/{params.type}.{params.study_group_num}.{params.run_group_num}.manifest {output} convert_to_int"
#do a rule instantiation per *run* low-order name grouping to do hierarchical pastes
rule paste_sums_per_group:
input:
config['staging'] + '/{type}.{study_group_num}.{run_group_num}.grouped'
output:
config['staging'] + '/{type}.{study_group_num}.{run_group_num}.pasted'
params:
study_group_num=lambda wildcards: wildcards.study_group_num,
run_group_num=lambda wildcards: wildcards.run_group_num,
staging=config['staging'],
script_path=SCRIPTS['paste'],
type=lambda wildcards: wildcards.type,
pigz_threads=0
shell:
"{params.script_path} {params.staging}/{params.type}.{params.study_group_num}.{params.run_group_num}.manifest {output} {params.pigz_threads}"
def get_pasted_sum_files(wildcards):
study_loworder = wildcards.study_group_num
fin = open(config['sample_ids_file'], "r")
lines = fin.read().split('\n')
fin.close()
return [config['staging']+"/%s.%s.%s.pasted" % (wildcards.type, f.split('\t')[0][-2:], f.split('\t')[1][-2:]) for f in lines[:-1]]
#return [config['staging']+"/%s.%s.%s.pasted" % (wildcards.type, f.split('/')[-3], f.split('/')[-1]) for f in glob.glob(config['input']+'/%s/*??' % (study_loworder))]
rule collect_pasted_sums:
input:
get_pasted_sum_files
output:
config['staging'] + '/{type}.{study_group_num}.pasted.files.list'
params:
study_group_num=lambda wildcards: wildcards.study_group_num,
staging=config['staging'],
type=lambda wildcards: wildcards.type
shell:
"ls {params.staging}/{params.type}.{params.study_group_num}.??.pasted > {output}"
rule paste_sums_per_study_group:
input:
config['staging'] + '/{type}.{study_group_num}.pasted.files.list'
output:
os.path.join(config['staging'], '{type}.{study_group_num}.pasted')
params:
study_group_num=lambda wildcards: wildcards.study_group_num,
staging=config['staging'],
script_path=SCRIPTS['paste'],
existing_sums=config['existing_sums'],
type=lambda wildcards: wildcards.type,
pigz_threads=0
shell:
"{params.script_path} {input} {output} {params.pigz_threads} dont_get_ids"
def get_study_pasted_sum_files(wildcards):
fin = open(config['sample_ids_file'], "r")
lines = fin.read().split('\n')
fin.close()
return [config['staging']+"/%s.%s.pasted" % (wildcards.type, f.split('\t')[0][-2:]) for f in lines[:-1]]
#return [config['staging']+"/%s.%s.pasted" % (wildcards.type, f.split('/')[-1]) for f in glob.glob(config['input']+'/??')]
rule collect_study_pasted_sums:
input:
get_study_pasted_sum_files
output:
config['staging'] + '/{type}.groups.pasted.files.list'
params:
staging=config['staging'],
type=lambda wildcards: wildcards.type
shell:
"ls {params.staging}/{params.type}.??.pasted > {output}"
rule paste_sums_final:
input:
config['staging'] + '/{type}.groups.pasted.files.list'
output:
'{type}.samples.pasted.gz'
params:
staging=config['staging'],
script_path=SCRIPTS['paste'],
existing_sums=config['existing_sums'],
type=lambda wildcards: wildcards.type,
pigz_threads = config['pigz_threads']
shell:
"{params.script_path} {input} {output} {params.pigz_threads} dont_get_ids {params.existing_sums}"
|
