Mercurial > repos > dereeper > pangenome_explorer
comparison Snakemake_files/Snakefile_cactus_heatmap_upset @ 3:e42d30da7a74 draft
Uploaded
author | dereeper |
---|---|
date | Thu, 30 May 2024 11:52:25 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
2:97e4e3e818b6 | 3:e42d30da7a74 |
---|---|
1 import glob | |
2 import os | |
3 import shutil | |
4 | |
5 import yaml | |
6 configfile: "config.yaml" | |
7 | |
8 | |
9 SAMPLES = [] | |
10 with open("config.yaml", "r") as yaml_file: | |
11 genome_data = yaml.safe_load(yaml_file) | |
12 for genome_name, genome_info in genome_data["input_genomes"].items(): | |
13 name = genome_info["name"] | |
14 SAMPLES.append(name) | |
15 | |
16 | |
17 rule all: | |
18 input: | |
19 "outputs/seqfile", | |
20 "outputs/cactus_outdir/output_cactus.sv.gfa.gz", | |
21 "outputs/pav_matrix.tsv", | |
22 "outputs/heatmap.svg.gz", | |
23 "outputs/rarefaction_curves.txt" | |
24 | |
25 rule get_data: | |
26 input: | |
27 "config.yaml" | |
28 output: | |
29 "outputs/seqfile", | |
30 expand("outputs/genomes/{sample}.fasta", sample=SAMPLES), | |
31 expand("outputs/genomes/{sample}.gff", sample=SAMPLES), | |
32 run: | |
33 with open(input[0], "r") as yaml_file, open(output[0], "w") as output_file: | |
34 genome_data = yaml.safe_load(yaml_file) | |
35 for genome_name, genome_info in genome_data["input_genomes"].items(): | |
36 fasta_file = genome_info["fasta"] | |
37 name = genome_info["name"] | |
38 gff_file = genome_info["gff3"] | |
39 shutil.copy(gff_file, "outputs/genomes/"+str(name)+".gff") | |
40 shutil.copy(fasta_file, "outputs/genomes/"+str(name)+".fasta") | |
41 output_file.write(f"{genome_name}\toutputs/genomes/"+str(name)+".fasta\n") | |
42 | |
43 | |
44 rule gffread: | |
45 input: | |
46 fasta = "outputs/genomes/{sample}.fasta", | |
47 gff = "outputs/genomes/{sample}.gff" | |
48 output: | |
49 "outputs/genomes/{sample}.nuc" | |
50 shell: | |
51 """ | |
52 gffread -x {output} -g {input.fasta} {input.gff} | |
53 """ | |
54 | |
55 rule cactus: | |
56 input: | |
57 expand("outputs/genomes/{sample}.fasta", sample=SAMPLES), | |
58 expand("outputs/genomes/{sample}.gff", sample=SAMPLES), | |
59 params: | |
60 reference=SAMPLES[0] | |
61 output: | |
62 gfasv="outputs/cactus_outdir/output_cactus.sv.gfa.gz", | |
63 gfafull="outputs/cactus_outdir/full.gfa" | |
64 shell: | |
65 """ | |
66 mkdir outputs/cactus_work | |
67 cactus-pangenome outputs/jobstore outputs/seqfile --outDir outputs/cactus_outdir --outName output_cactus --reference {params.reference} --workDir outputs/cactus_work --vcf --mapCores 12 --gfa clip full --viz | |
68 zcat outputs/cactus_outdir/output_cactus.full.gfa.gz >{output.gfafull} | |
69 """ | |
70 | |
71 | |
72 rule gfatools: | |
73 input: | |
74 "outputs/cactus_outdir/output_cactus.sv.gfa.gz" | |
75 output: | |
76 "outputs/cactus_outdir/output_cactus.sv.gfa.pangenome.fasta" | |
77 shell: | |
78 """ | |
79 gfatools gfa2fa -s {input} > {output} | |
80 """ | |
81 | |
82 rule minigraph: | |
83 input: | |
84 cds_fasta="outputs/genomes/{sample}.nuc", | |
85 gfa="outputs/cactus_outdir/output_cactus.sv.gfa.gz", | |
86 output: | |
87 gaf="outputs/genomes/{sample}.nuc.pangenome.gaf", | |
88 shell: | |
89 """ | |
90 minigraph -x lr {input.gfa} {input.cds_fasta} > {output.gaf} | |
91 """ | |
92 | |
93 rule odgi: | |
94 input: | |
95 "outputs/cactus_outdir/full.gfa" | |
96 output: | |
97 og="outputs/cactus_outdir/full.gfa.og", | |
98 png="outputs/cactus_outdir/full.gfa.png", | |
99 shell: | |
100 """ | |
101 odgi build -g {input} -o {output.og} | |
102 odgi viz -i {output.og} -o {output.png} | |
103 """ | |
104 | |
105 rule gaf2bed: | |
106 input: | |
107 "outputs/genomes/{sample}.nuc.pangenome.gaf" | |
108 output: | |
109 "outputs/genomes/{sample}.nuc.pangenome.gaf.bed", | |
110 shell: | |
111 """ | |
112 awk '{{print $6"\\t"$8"\\t"$9"\\t"$1}}' {input} >{output} | |
113 """ | |
114 | |
115 rule bedtools_intersect: | |
116 input: | |
117 strains="outputs/seqfile", | |
118 bedfiles=expand("outputs/genomes/{sample}.nuc.pangenome.gaf.bed", sample=SAMPLES) | |
119 output: | |
120 "outputs/pav_matrix.tsv", | |
121 shell: | |
122 """ | |
123 perl $PANEX_PATH/Perl/GeneratePAVfromBed.pl {input.strains} outputs/genomes {output} | |
124 """ | |
125 | |
126 rule heatmap_upset: | |
127 input: | |
128 pav="outputs/pav_matrix.tsv" | |
129 output: | |
130 heatmap="outputs/heatmap.svg.gz", | |
131 html="outputs/heatmap.svg.heatmap_plotly.html", | |
132 upsetr="outputs/upsetr.svg", | |
133 binpav="outputs/heatmap.svg.pangenes_01matrix.txt" | |
134 shell: | |
135 """ | |
136 perl $PANEX_PATH/Perl/GenerateHeatmapFromPAV.pl {input.pav} outputs/heatmap.svg | |
137 mv outputs/heatmap.svg.upsetr.svg {output.upsetr} | |
138 """ | |
139 | |
140 rule micropan: | |
141 input: | |
142 binpav="outputs/heatmap.svg.pangenes_01matrix.txt" | |
143 output: | |
144 txt="outputs/rarefaction_curves.txt", | |
145 pdf="outputs/rarefaction_curves.pdf", | |
146 svg="outputs/rarefaction_curves.svg", | |
147 heaps="outputs/heaps.tsv" | |
148 shell: | |
149 """ | |
150 Rscript $PANEX_PATH/R/micropan_rarefaction.R -f {input.binpav} -p {output.pdf} -a {output.heaps} -o {output.txt} | |
151 pdf2svg {output.pdf} {output.svg} | |
152 """ |