Mercurial > repos > dereeper > pangenome_explorer
diff Snakemake_files/Snakefile_pggb_heatmap_upset @ 3:e42d30da7a74 draft
Uploaded
author | dereeper |
---|---|
date | Thu, 30 May 2024 11:52:25 +0000 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Snakemake_files/Snakefile_pggb_heatmap_upset Thu May 30 11:52:25 2024 +0000 @@ -0,0 +1,115 @@ +import glob +import os +import shutil + +import yaml +configfile: "config.yaml" + + +SAMPLES = [] +with open("config.yaml", "r") as yaml_file: + genome_data = yaml.safe_load(yaml_file) + for genome_name, genome_info in genome_data["input_genomes"].items(): + name = genome_info["name"] + SAMPLES.append(name) + + +rule all: + input: + "outputs/seqfile", + "outputs/pggb_out/all_genomes.fa.smooth.final.gfa", + "outputs/pav_matrix.tsv", + "outputs/heatmap.svg.gz", + "outputs/rarefaction_curves.txt" + +rule get_data: + input: + "config.yaml" + output: + "outputs/seqfile", + expand("outputs/genomes/{sample}.fasta", sample=SAMPLES), + expand("outputs/genomes/{sample}.gff", sample=SAMPLES), + run: + with open(input[0], "r") as yaml_file, open(output[0], "w") as output_file: + genome_data = yaml.safe_load(yaml_file) + for genome_name, genome_info in genome_data["input_genomes"].items(): + fasta_file = genome_info["fasta"] + name = genome_info["name"] + output_file.write(f"{genome_name}\t{genome_name}\t{fasta_file}\n") + cmd = "sed 's/>/>"+str(name)+"#/g' "+fasta_file+" >outputs/genomes/"+str(name)+".fasta" + os.system(cmd) + gff_file = genome_info["gff3"] + shutil.copy(gff_file, "outputs/genomes/"+str(name)+".gff") + +rule pggb: + input: + expand("outputs/genomes/{sample}.fasta", sample=SAMPLES), + expand("outputs/genomes/{sample}.gff", sample=SAMPLES), + output: + gfa="outputs/pggb_out/all_genomes.fa.smooth.final.gfa", + png1="outputs/pggb_out/all_genomes.fa.lay.draw.png", + png2="outputs/pggb_out/all_genomes.fa.og.viz_multiqc.png", + shell: + """ + cat outputs/genomes/*fasta >outputs/genomes/all_genomes.fa + samtools faidx outputs/genomes/all_genomes.fa + reference=$(head -1 outputs/genomes/strains.txt | awk '{{print $2}}') + pggb -i outputs/genomes/all_genomes.fa -o outputs/pggb_out -V $reference -m + mv outputs/pggb_out/all_genomes.*smooth.final.gfa {output.gfa} + mv outputs/pggb_out/all_genomes.*lay.draw.png {output.png1} + mv outputs/pggb_out/all_genomes.fa.*.og.viz_multiqc.png {output.png2} + """ + +rule create_gene_paths: + input: + gff="outputs/genomes/{sample}.gff", + gfa="outputs/pggb_out/all_genomes.fa.smooth.final.gfa", + output: + basename="outputs/genomes/{sample}.gene_segments", + gene_length="outputs/genomes/{sample}.gene_segments.gene_length.txt", + bed="outputs/genomes/{sample}.gene_segments.bed", + shell: + """ + perl $PANEX_PATH/Perl/CreateGenePathsFromGFA.pl {input.gfa} {input.gff} {output.basename} + """ + +rule bedtools_intersect: + input: + samples="outputs/seqfile", + bedfiles=expand("outputs/genomes/{sample}.gene_segments.bed", sample=SAMPLES) + params: + identity=30 + output: + "outputs/pav_matrix.tsv", + shell: + """ + perl $PANEX_PATH/Perl/GeneratePAVfromBed.pl {input.samples} outputs/genomes {output} {params.identity} + """ + +rule heatmap_upset: + input: + pav="outputs/pav_matrix.tsv" + output: + heatmap="outputs/heatmap.svg.gz", + html="outputs/heatmap.svg.heatmap_plotly.html", + upsetr="outputs/upsetr.svg", + binpav="outputs/heatmap.svg.pangenes_01matrix.txt" + shell: + """ + perl $PANEX_PATH/Perl/GenerateHeatmapFromPAV.pl {input.pav} outputs/heatmap.svg + mv outputs/heatmap.svg.upsetr.svg {output.upsetr} + """ + +rule micropan: + input: + binpav="outputs/heatmap.svg.pangenes_01matrix.txt" + output: + txt="outputs/rarefaction_curves.txt", + pdf="outputs/rarefaction_curves.pdf", + svg="outputs/rarefaction_curves.svg", + heaps="outputs/heaps.tsv" + shell: + """ + Rscript $PANEX_PATH/R/micropan_rarefaction.R -f {input.binpav} -p {output.pdf} -a {output.heaps} -o {output.txt} + pdf2svg {output.pdf} {output.svg} + """