3
|
1 import glob
|
|
2 import os
|
|
3 import shutil
|
|
4 import re
|
|
5 import subprocess
|
|
6
|
|
7 import yaml
|
|
8 configfile: "config.yaml"
|
|
9
|
|
10
|
|
11 SAMPLES = []
|
|
12 with open("config.yaml", "r") as yaml_file:
|
|
13 genome_data = yaml.safe_load(yaml_file)
|
|
14 if "ids" in genome_data.keys():
|
|
15 for id in genome_data["ids"]:
|
|
16 SAMPLES.append(id)
|
|
17 if "input_genbanks" in genome_data.keys():
|
|
18 for gb_path in genome_data["input_genbanks"]:
|
|
19
|
|
20 cmd = "grep 'ACCESSION' "+gb_path
|
|
21 returned_value = subprocess.getoutput(cmd)
|
|
22 words = returned_value.split()
|
|
23 name = words[1]
|
|
24 #words = returned_value.split()
|
|
25 #SAMPLES.append(words[1])
|
|
26 words = gb_path.split("/")
|
|
27 genbank_file_name = words[-1]
|
|
28 x = genbank_file_name.replace(".", "_")
|
|
29 cmd = "sed -i 's/ACCESSION "+name+"/ACCESSION "+x+"/g' "+gb_path
|
|
30 subprocess.getoutput(cmd)
|
|
31
|
|
32 cmd_locus = "grep 'LOCUS' "+gb_path
|
|
33 returned_value = subprocess.getoutput(cmd_locus)
|
|
34 words_locus = returned_value.split()
|
|
35 name_locus = words_locus[1]
|
|
36 cmd = "sed -i 's/LOCUS "+name_locus+"/LOCUS "+x+"/' "+gb_path
|
|
37 subprocess.getoutput(cmd)
|
|
38
|
|
39 cmd = "grep 'ACCESSION' "+gb_path
|
|
40 returned_value = subprocess.getoutput(cmd)
|
|
41 words = returned_value.split()
|
|
42 SAMPLES.append(words[1])
|
|
43
|
|
44
|
|
45 rule final:
|
|
46 input:
|
|
47 "outputs/pav_matrix.csv",
|
|
48 "outputs/GCskew.txt",
|
|
49 "outputs/pav_matrix.tsv",
|
|
50 "outputs/heatmap.svg.gz",
|
|
51 "outputs/cog_output.txt",
|
|
52 "outputs/fastani.out",
|
|
53 "outputs/rarefaction_curves.txt"
|
|
54
|
|
55
|
|
56 rule ncbi_datasets:
|
|
57 input:
|
|
58 "config.yaml"
|
|
59 output:
|
|
60 expand("outputs/genomes/{sample}.fasta", sample=SAMPLES),
|
|
61 expand("outputs/genomes/{sample}.gb", sample=SAMPLES),
|
|
62 genomes="outputs/genomes/genomes.txt"
|
|
63 shell:
|
|
64 """
|
|
65 perl $PANEX_PATH/Perl/get_data.pl {input} outputs/genomes
|
|
66 """
|
|
67
|
|
68 rule gcskew:
|
|
69 input:
|
|
70 "outputs/genomes/{sample}.fasta"
|
|
71 output:
|
|
72 "outputs/genomes/{sample}.fasta.gcskew.txt"
|
|
73 shell:
|
|
74 """
|
|
75 python3 $PANEX_PATH/SkewIT/src/gcskew.py -i {input} -o {input}.gcskew.txt -k 1000 -w 1000
|
|
76 """
|
|
77
|
|
78 rule concat_gcskew:
|
|
79 input:
|
|
80 expand("outputs/genomes/{sample}.fasta.gcskew.txt", sample=SAMPLES)
|
|
81 output:
|
|
82 out2="outputs/GCskew.txt"
|
|
83 shell:
|
|
84 """
|
|
85 cat {input} >>{output.out2}
|
|
86 """
|
|
87
|
|
88 rule genbank2gff3:
|
|
89 input:
|
|
90 "outputs/genomes/{sample}.gb"
|
|
91 output:
|
|
92 gff1="outputs/genomes/{sample}.gb.gff",
|
|
93 gff2="outputs/genomes/{sample}.gb.rmdup.gff"
|
|
94 shell:
|
|
95 """
|
|
96 perl $PANEX_PATH/Perl/bp_genbank2gff3.pl -o outputs/genomes {input}
|
|
97 perl $PANEX_PATH/Perl/remove_duplicates_in_gff.pl {output.gff1} {output.gff2}
|
|
98 """
|
|
99
|
|
100 rule roary:
|
|
101 input:
|
|
102 expand("outputs/genomes/{sample}.gb.rmdup.gff", sample=SAMPLES)
|
|
103 params:
|
|
104 identity=80
|
|
105 output:
|
|
106 pav="outputs/pav_matrix.csv",
|
|
107 newick="outputs/accessory_binary_genes.fa.newick"
|
|
108 shell:
|
|
109 """
|
|
110 roary -f outputs/roary_outdir -i {params.identity} outputs/genomes/*gb.rmdup.gff
|
|
111 cp -rf outputs/roary_outdir/gene_presence_absence.csv {output.pav}
|
|
112 cp -rf outputs/roary_outdir/accessory_binary_genes.fa.newick {output.newick}
|
|
113 """
|
|
114
|
|
115 rule convert_matrix:
|
|
116 input:
|
|
117 pav="outputs/pav_matrix.csv"
|
|
118 output:
|
|
119 "outputs/pav_matrix.tsv"
|
|
120 shell:
|
|
121 """
|
|
122 perl $PANEX_PATH/Perl/ConvertRoaryMatrix.pl outputs/genomes {input} {output} outputs/genomes/strains.txt
|
|
123 """
|
|
124
|
|
125 rule cog:
|
|
126 input:
|
|
127 pav="outputs/pav_matrix.tsv"
|
|
128 output:
|
|
129 cog="outputs/cog_output.txt",
|
|
130 cogstat="outputs/cog_stats.txt",
|
|
131 cogstat2="outputs/cog_stats2.txt",
|
|
132 cogofclusters="outputs/cog_of_clusters.txt"
|
|
133 shell:
|
|
134 """
|
|
135 perl $PANEX_PATH/Perl/GetCogOfCluster.pl {input} outputs/genomes {output.cog} {output.cogstat} {output.cogstat2} {output.cogofclusters} outputs/genomes/strains.txt
|
|
136 """
|
|
137
|
|
138 rule heatmap_upset:
|
|
139 input:
|
|
140 pav="outputs/pav_matrix.tsv"
|
|
141 output:
|
|
142 heatmap="outputs/heatmap.svg.gz",
|
|
143 html="outputs/heatmap.svg.heatmap_plotly.html",
|
|
144 upsetr="outputs/upsetr.svg",
|
|
145 binpav="outputs/heatmap.svg.pangenes_01matrix.txt"
|
|
146 shell:
|
|
147 """
|
|
148 perl $PANEX_PATH/Perl/GenerateHeatmapFromPAV.pl {input.pav} outputs/heatmap.svg
|
|
149 mv outputs/heatmap.svg.upsetr.svg {output.upsetr}
|
|
150 """
|
|
151
|
|
152 rule micropan:
|
|
153 input:
|
|
154 binpav="outputs/heatmap.svg.pangenes_01matrix.txt"
|
|
155 output:
|
|
156 txt="outputs/rarefaction_curves.txt",
|
|
157 pdf="outputs/rarefaction_curves.pdf",
|
|
158 svg="outputs/rarefaction_curves.svg",
|
|
159 heaps="outputs/heaps.tsv"
|
|
160 shell:
|
|
161 """
|
|
162 Rscript $PANEX_PATH/R/micropan_rarefaction.R -f {input.binpav} -p {output.pdf} -a {output.heaps} -o {output.txt}
|
|
163 pdf2svg {output.pdf} {output.svg}
|
|
164 """
|
|
165
|
|
166 rule fastani:
|
|
167 input:
|
|
168 "outputs/genomes/genomes.txt"
|
|
169 output:
|
|
170 out="outputs/fastani.out",
|
|
171 matrix="outputs/fastani.out.matrix",
|
|
172 completematrix="outputs/fastani.out.matrix.complete",
|
|
173 pdf="outputs/fastani.out.pdf",
|
|
174 svg="outputs/fastani.out.svg"
|
|
175 shell:
|
|
176 """
|
|
177 fastANI --rl {input} --ql {input} -o {output.out} -t 4 --matrix
|
|
178 perl $PANEX_PATH/Perl/convertANI.pl {output.matrix} outputs/genomes/genomes2.txt >{output.completematrix}
|
|
179 Rscript $PANEX_PATH/R/heatmap_ani.R -f {output.completematrix} -o {output.pdf}
|
|
180 pdf2svg {output.pdf} {output.svg}
|
|
181 """
|
|
182
|