Chapter 11 - our final Snakefile - review and discussion

Here's the final Snakefile:

ACCESSIONS = ["GCF_000017325.1",
              "GCF_000020225.1",
              "GCF_000021665.1",
              "GCF_008423265.1"]

rule all:
    input:
        "compare.mat.matrix.png"

rule sketch_genome:
    input:
        "genomes/{accession}.fna.gz",
    output:
        "{accession}.fna.gz.sig",
    shell: """
        sourmash sketch dna -p k=31 {input} --name-from-first
    """

rule compare_genomes:
    input:
        expand("{acc}.fna.gz.sig", acc=ACCESSIONS),
    output:
        "compare.mat"
    shell: """
        sourmash compare {input} -o {output}
    """

rule plot_comparison:
    message: "compare all input genomes using sourmash"
    input:
        "compare.mat"
    output:
        "compare.mat.matrix.png"
    shell: """
        sourmash plot {input}
    """

@@ add discussion!