-
Notifications
You must be signed in to change notification settings - Fork 0
/
Snakefile
219 lines (202 loc) · 7.37 KB
/
Snakefile
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
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
import os.path
import re
import subprocess
from snakemake.remote.HTTP import RemoteProvider as HTTPRemoteProvider
HTTP = HTTPRemoteProvider()
# For testing, parse the yaml file (this is automatically done by Snakemake)
#import yaml
#with open("config/config.yaml", 'r') as ymlfile: config = yaml.safe_load(ymlfile)
configfile: "config/config.yaml"
# Find the maximum number of cores available to a single node on SLURM,
# or if we aren't in a SLURM environment, how many we have on the local machine.
try:
maxthreads = max([int(x) for x in re.findall(r'\d+', subprocess.check_output(["sinfo", "-O", "cpus"]).decode())])
except FileNotFoundError:
maxthreads = int(subprocess.check_output("nproc").decode())
#### Reference databases ####
# generate taxonomy translation files
localrules: translate_references
rule translate_references:
output:
expand("{outdir}/{db}.{region}.{method}.fasta.gz",
outdir = config['outdir'],
db = ['warcup', 'unite_single', 'unite_nosingle'],
region = ['ITS'],
method = ['sintax', 'dada2']),
expand("{outdir}/{db}.{region}.{method}.fasta.gz",
outdir = config['outdir'],
db = ['rdp_train', 'silva_parc', 'silva_ref', 'silva_nr99'],
region = ['LSU'],
method = ['sintax', 'dada2'])
input:
expand("{refdir}/{dbname}.{type}",
refdir = config['refdir'],
dbname = ['rdp_train', 'warcup', 'unite_single', 'unite_nosingle',
'silva_parc', 'silva_ref', 'silva_nr99'],
type = ['fasta.gz', 'pre.sed']),
"{rdir}/taxonomy.R".format_map(config),
regions = config["regions_file"],
tedersoo = "{refdir}/Tedersoo_Eukarya_classification.xlsx".format_map(config),
tedersoo_add = config['tedersoo_add'],
tedersoo_patch = config['tedersoo_patch'],
script = "{rdir}/make_taxonomy.R".format_map(config)
resources:
walltime = 60
conda: "{condadir}/drake.yaml".format_map(config)
log: "{logdir}/translate_references.log".format_map(config)
script: "{rdir}/make_taxonomy.R".format_map(config)
def unite_url(wildcards) :
return config['unite_{which}_url'.format(which = wildcards.which)]
def unite_md5(wildcards) :
return config['unite_{which}_md5'.format(which = wildcards.which)]
def unite_basename(wildcards) :
return os.path.basename(unite_url(wildcards))
def unite_filename(wildcards) :
return config['unite_{which}_filename'.format(which = wildcards.which)]
# Download the Unite database, without global and 97% singletons
localrules: unite_download
rule unite_download:
output: "{refdir}/unite_{{which}}.fasta.gz".format_map(config)
wildcard_constraints:
which = "(no)?single"
params:
url = unite_url,
zipfile = unite_basename,
md5 = unite_md5,
fasta = unite_filename
shadow: "shallow"
shell:
"""
wget {params.url}
echo {params.md5} {params.zipfile} | md5sum -c -
mkdir -p $(dirname {output})
tar -xzf {params.zipfile} {params.fasta}
gzip -c9 {params.fasta} > {output}
"""
# Download the Unite+INSD database
localrules: unite_insd_download
rule unite_insd_download:
output: "{refdir}/unite_insd.fasta.gz".format_map(config)
params:
url = config['unite_insd_url'],
md5 = config['unite_insd_md5'],
fasta = os.path.basename(config['unite_insd_url'])
shadow: "shallow"
shell:
"""
wget {params.url}
echo {params.md5} {params.fasta} | md5sum -c -
mkdir -p $(dirname {output})
mv {params.fasta} {output}
"""
# Download the RDP fungal LSU training set
# This will also convert all sequences from RNA (Uu) to DNA (Tt)
localrules: rdp_download
rule rdp_download:
output:
fasta = "{refdir}/rdp_train.fasta.gz".format_map(config),
taxa = "{refdir}/rdp_train.taxa.txt".format_map(config)
params:
url = config['rdp_url'],
md5 = config['rdp_md5'],
zipfile = os.path.basename(config['rdp_url']),
fasta = config['rdp_filename'],
taxa = config['rdp_taxa']
shadow: "shallow"
shell:
"""
wget {params.url}
echo {params.md5} {params.zipfile} | md5sum -c -
mkdir -p $(dirname {output.fasta})
unzip {params.zipfile} {params.fasta} {params.taxa}
sed '/^>/!y/uU/tT/' <{params.fasta} | gzip -c9 > {output.fasta}
mv {params.taxa} {output.taxa}
"""
# Download the RDP fungal LSU database
# This will also convert all sequences from RNA (Uu) to DNA (Tt)
localrules: rdp_full_download
rule rdp_full_download:
output:
fasta = "{refdir}/rdp_28S.fasta.gz".format_map(config)
params:
url = config['rdp_full_url'],
fasta = os.path.basename(config['rdp_full_url']),
md5 = config['rdp_full_md5']
shadow: "shallow"
shell:
"""
wget {params.url}
echo {params.md5} {params.fasta} | md5sum -c -
mkdir -p $(dirname {output.fasta})
zcat {params.fasta} |
sed '/^>/!y/uU/tT/' |
gzip -c9 >{output.fasta}
"""
# Download the Warcup fungal ITS training set
localrules: warcup_download
rule warcup_download:
output:
fasta = "{refdir}/warcup.fasta.gz".format_map(config),
taxa = "{refdir}/warcup.taxa.txt".format_map(config)
params:
url = config['warcup_url'],
basename = os.path.basename(config['warcup_url']),
md5 = config['warcup_md5'],
filename = config['warcup_filename'],
taxa = config['warcup_taxa']
shadow: "shallow"
shell:
"""
wget {params.url}
echo {params.md5} {params.basename} | md5sum -c -
mkdir -p $(dirname {output.fasta})
unzip {params.basename} {params.filename} {params.taxa}
gzip -c9 {params.filename} > {output.fasta}
mv {params.taxa} {output.taxa}
"""
def silva_url(wildcards) :
return config['silva_{which}_url'.format(which = wildcards.which)]
def silva_md5(wildcards) :
return config['silva_{which}_md5'.format(which = wildcards.which)]
def silva_basename(wildcards) :
return os.path.basename(silva_url(wildcards))
# Download SILVA
# also extract Eukaryotes only, and transcribe RNA to DNA
rule silva_download:
output:
fasta = "{refdir}/silva_{{which}}.fasta.gz".format_map(config)
params:
url = silva_url,
md5 = silva_md5,
basename = silva_basename
wildcard_constraints:
which = "(parc|ref|nr99)"
shadow: "shallow"
conda: "config/vsearch.yaml"
shell:
"""
wget {params.url}
echo {params.md5} {params.basename} | md5sum -c -
mkdir -p $(dirname {output.fasta})
zcat {params.basename} |
tr ' ' '$' |
vsearch --fastx_getseqs - --label_word Eukaryota --fastaout - |
tr '$' ' ' |
sed '/^>/!y/Uu/Tt/' |
gzip -c >{output.fasta}
"""
# Download Eukarya classification system proposed by Tedersoo
localrules: tedersoo_classification
rule tedersoo_classification:
output: "{refdir}/Tedersoo_Eukarya_classification.xlsx".format_map(config)
params:
url = config['tedersoo_url'],
filename = os.path.basename(config['tedersoo_url']),
md5 = config['tedersoo_md5']
shadow: "shallow"
shell:
"""
wget {params.url}
echo {params.md5} {params.filename} | md5sum -c -
mv {params.filename} {output}
"""