-
Notifications
You must be signed in to change notification settings - Fork 0
/
Snakefile
222 lines (195 loc) · 6.14 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
220
221
222
### Setting the rules applicable to all steps that come next. It defines where the input files are: make sure this information is accurate
rule all:
input:
auspice_tree = "auspice/addHereYourProjectName_tree.json",
auspice_meta = "auspice/addHereYourProjectName_meta.json"
input_fasta = "data/sequences.fasta",
input_metadata = "data/metadata.tsv",
reference = "config/reference.gb",
dropped_strains = "config/dropped_strains.txt",
colors = "config/colors.tsv",
lat_longs = "config/lat_longs.tsv",
auspice_config = "config/auspice_config.json"
### Excluding sequences included in dropped_strains
rule filter:
message:
"""
Filtering to
- excluding strains in {input.exclude}
"""
input:
sequences = input_fasta,
metadata = input_metadata,
exclude = dropped_strains
output:
sequences = "results/filtered.fasta"
params:
group_by = "country year month",
sequences_per_group = 20,
min_date = 1900
shell:
"""
augur filter \
--sequences {input.sequences} \
--metadata {input.metadata} \
--exclude {input.exclude} \
--output {output.sequences}
"""
### Aligning the sequences using MAFFT
rule align:
message:
"""
Aligning sequences to {input.reference}
- filling gaps with N
"""
input:
sequences = rules.filter.output.sequences,
reference = reference
output:
alignment = "results/aligned.fasta"
shell:
"""
augur align \
--sequences {input.sequences} \
--reference-sequence {input.reference} \
--output {output.alignment} \
--fill-gaps
"""
### Inferring Maximum Likelihood tree using the default software (IQTree)
rule tree:
message: "Building tree"
input:
alignment = rules.align.output.alignment
output:
tree = "results/tree_raw.nwk"
shell:
"""
augur tree \
--alignment {input.alignment} \
--output {output.tree}
"""
### Running TreeTime to estimate time for ancestral genomes
rule refine:
message:
"""
Refining tree
- estimate timetree
- use {params.coalescent} coalescent timescale
- estimate {params.date_inference} node dates
- filter tips more than {params.clock_filter_iqd} IQDs from clock expectation
"""
input:
tree = rules.tree.output.tree,
alignment = rules.align.output,
metadata = input_metadata
output:
tree = "results/tree.nwk",
node_data = "results/branch_lengths.json"
params:
coalescent = "opt",
date_inference = "marginal",
clock_filter_iqd = 4
shell:
"""
augur refine \
--tree {input.tree} \
--alignment {input.alignment} \
--metadata {input.metadata} \
--output-tree {output.tree} \
--output-node-data {output.node_data} \
--timetree \
--coalescent {params.coalescent} \
--date-confidence \
# --clock-filter-iqd {params.clock_filter_iqd} \
--date-inference {params.date_inference}
"""
### Reconstructing ancestral sequences and mutations
rule ancestral:
message: "Reconstructing ancestral sequences and mutations"
input:
tree = rules.refine.output.tree,
alignment = rules.align.output
output:
node_data = "results/nt_muts.json"
params:
inference = "joint"
shell:
"""
augur ancestral \
--tree {input.tree} \
--alignment {input.alignment} \
--output {output.node_data} \
--inference {params.inference}
"""
## Performing amino acid translation
rule translate:
message: "Translating amino acid sequences"
input:
tree = rules.refine.output.tree,
node_data = rules.ancestral.output.node_data,
reference = reference
output:
node_data = "results/aa_muts.json"
shell:
"""
augur translate \
--tree {input.tree} \
--ancestral-sequences {input.node_data} \
--reference-sequence {input.reference} \
--output {output.node_data} \
"""
### Inferring ancestral locations of genomes
rule traits:
message: "Inferring ancestral traits for {params.columns!s}"
input:
tree = rules.refine.output.tree,
metadata = input_metadata
output:
node_data = "results/traits.json",
params:
columns = "region country state"
shell:
"""
augur traits \
--tree {input.tree} \
--metadata {input.metadata} \
--output {output.node_data} \
--columns {params.columns} \
--confidence
"""
### Generating final results for visualisation with auspice
rule export:
message: "Exporting data files for for auspice"
input:
tree = rules.refine.output.tree,
metadata = input_metadata,
branch_lengths = rules.refine.output.node_data,
traits = rules.traits.output.node_data,
nt_muts = rules.ancestral.output.node_data,
aa_muts = rules.translate.output.node_data,
colors = colors,
lat_longs = lat_longs,
auspice_config = auspice_config
output:
auspice_tree = rules.all.input.auspice_tree,
auspice_meta = rules.all.input.auspice_meta
shell:
"""
augur export \
--tree {input.tree} \
--metadata {input.metadata} \
--node-data {input.branch_lengths} {input.traits} {input.nt_muts} {input.aa_muts} \
--colors {input.colors} \
--lat-longs {input.lat_longs} \
--auspice-config {input.auspice_config} \
--output-tree {output.auspice_tree} \
--output-meta {output.auspice_meta}
"""
### Clearing the working directory (only executed when needed)
rule clean:
message: "Removing directories: {params}"
params:
"results ",
"auspice"
shell:
"rm -rfv {params}"