conf.py 3.58 KB
Newer Older
aknecht2's avatar
aknecht2 committed
1
2
import string

3
4
5
6
7
8
# Module directory
job_modules = "jobs/modules/"

# Job params directory
job_params = "jobs/params/"

9
10
11
# Job wrappers directory
job_wrappers = "jobs/wrappers/"

12
13
14
# Job scripts directory
job_scripts = "jobs/scripts/"

15
16
17
18
19
20
21
22
23
24
25
26
# SYSTEM PATH, probably /bin
system_path = "/bin/"

# System commands mv, cp, sort, zcat, awk e.t.c
system_commands = [
    "mv",
    "cp",
    "sort",
    "zcat",
    "awk"
]

27
28
29
30
31
32
# Current align tools
align_tools = [
    "bwa",
    "bowtie2"
]

33
# Current peak calling tools
34
35
peak_tools = [
    "spp",
36
    "macs2",
37
    "gem",
38
    "peakranger",
39
40
41
42
    "ccat",
    "zerone",
    "hiddendomains",
    "pepr"
43
44
]

45
46
47
48
49
50
# Peak_type validation
peak_types = {
    "spp": ["narrow", "broad"],
    "macs2": ["narrow", "broad"],
    "gem": ["narrow"],
    "peakranger": ["narrow"],
51
52
53
54
    "ccat": ["broad"],
    "zerone": ["broad"],
    "hiddendomains": ["broad"],
    "pepr": ["narrow", "broad"]
55
56
}

57
58
# File extensions
file_extensions = {
59
    "genome_index": ["fa", "fna"],
60
    "fastq": ["fastq", "fastq.gz"],
61
    "sai": ["sai"],
62
63
    "sam": ["sam"],
    "bam": ["bam"],
64
    "bed": ["bed", "peak", "region", "narrowPeak", "broadPeak", "tagAlign", "narrowPeak.gz", "broadPeak.gz"],
65
    "bwa_genome": ["amb", "ann", "bwt", "pac", "sa"],
66
    "bowtie2_genome": ["1.bt2", "2.bt2", "3.bt2", "4.bt2", "rev.1.bt2", "rev.2.bt2"],
aknecht2's avatar
aknecht2 committed
67
    "quality": ["quality"],
68
69
    "qc": ["qc"],
    "pdf": ["pdf"],
70
    "ccscore": ["ccscore"],
71
72
    "xls": ["xls"],
    "yaml": ["yaml"],
Adam Caprez's avatar
Adam Caprez committed
73
    "result": ["bed", "narrowPeak", "broadPeak", "tagAlign", "bam"],
74
    "txt": ["txt"],
75
    "chrom_sizes": ["sizes"],
76
    "read_dist" : ["txt"],
77
78
79
    "plaintext": ["txt", "md"],
    "ccat_conf": ["txt", "conf"],
    "log": ["log"]
80
}
aknecht2's avatar
aknecht2 committed
81
file_extensions["any"] = list(string.ascii_lowercase)
82

Adam Caprez's avatar
Adam Caprez committed
83
84
# list of resources that can be specified per job (step) in
# the workflow and corresponding Pegasus profile info
85
86
87
88
89
90
91
92
resources = {
    "walltime": {
        "namespace": "globus",
        "key": "maxwalltime"
    },
    "memory": {
        "namespace": "condor",
        "key": "request_memory"
93
94
    },
    "cores": {
aknecht2's avatar
aknecht2 committed
95
        "namespace": "pegasus",
96
        "key": "cores"
97
98
99
100
    },
    "nodes": {
        "namespace": "pegasus",
        "key": "nodes"
101
    }
Adam Caprez's avatar
Adam Caprez committed
102
103
}

104
105
# Defines the types of input / output arguments
# argument -> Any non file argument
106
107
#   string -> Any string argument
#   numeric -> Numeric arguments.
108
# file -> Any file argument that isn't redirected
109
110
111
#   file -> Normal file arguments.
#   stdout -> Any file argument that is redirected from stdout
#   stderr -> Any file argument that is redirected from stderr
112
113
# list -> For variable argument inputs
#   list -> Currently a list of files.
114
argument_types = {
115
    "argument": ["string", "numeric"],
116
117
    "file": ["file", "rawfile", "stdout", "stderr"],
    "list": ["list"]
118
119
120
121
122
}

# Defines information about arguments
argument_keys = {
    "required": ["type", "changeable", "has_value"],
123
    "optional": ["required", "default", "file_type", "path"]
124
125
126
127
128
129
}

# workflow_job keys
job_keys = {
    "required": ["inputs", "additional_inputs", "outputs", "command", "arguments"] + resources.keys(),
    "optional": []
130
}
131

132
133
# param keys
param_keys = {
134
135
    "required": [],
    "optional": ["arguments"] + resources.keys()
136
137
}

138
139
140
141
142
file_list_keys = {
    "required": ["name", "type"],
    "optional": ["file_type"]
}

143
144
# workflow order
workflow = ["align", "remove_duplicates", "peak_calling"]
145
146
147
148
149
150
151
152
153
154
155
156

# genome info
genomes = {
    "bwa": {
        "base_file": file_extensions["genome_index"],
        "additional_files": file_extensions["bwa_genome"]
    },
    "bowtie2": {
        "base_file": file_extensions["genome_index"],
        "additional_files": file_extensions["bowtie2_genome"]
    }
}