Create independent Snakemake language

lib/linguist/languages.yml

@@ -5292,7 +5292,6 @@ Python:
   - ".pyt"
   - ".pyw"
   - ".rpy"
-  - ".smk"
   - ".spec"
   - ".tac"
   - ".wsgi"
@@ -5302,7 +5301,6 @@ Python:
   - DEPS
   - SConscript
   - SConstruct
-  - Snakefile
   - wscript
   interpreters:
   - python
@@ -6411,6 +6409,21 @@ Smithy:
   extensions:
   - ".smithy"
   language_id: 1027892786
+Snakemake:
+  type: programming
+  group: Python
+  tm_scope: source.python
+  ace_mode: python
+  codemirror_mode: python
+  codemirror_mime_type: text/x-python
+  color: "#33c68a"
+  extensions:
+  - ".smk"
+  - ".snakefile"
+  filenames:
+  - Snakefile
+  aliases:
+  - snakefile
 Solidity:
   type: programming
   color: "#AA6746"

samples/Snakemake/Snakefile

@@ -0,0 +1,70 @@
+configfile: "config.yaml"
+
+
+rule all:
+    input:
+        "plots/quals.svg"
+
+
+def get_bwa_map_input_fastqs(wildcards):
+    return config["samples"][wildcards.sample]
+
+
+rule bwa_map:
+    input:
+        "data/genome.fa",
+        get_bwa_map_input_fastqs
+    output:
+        temp("mapped_reads/{sample}.bam")
+    params:
+        rg=r"@RG\tID:{sample}\tSM:{sample}"
+    log:
+        "logs/bwa_mem/{sample}.log"
+    threads: 8
+    shell:
+        "(bwa mem -R '{params.rg}' -t {threads} {input} | "
+        "samtools view -Sb - > {output}) 2> {log}"
+
+
+rule samtools_sort:
+    input:
+        "mapped_reads/{sample}.bam"
+    output:
+        protected("sorted_reads/{sample}.bam")
+    shell:
+        "samtools sort -T sorted_reads/{wildcards.sample} "
+        "-O bam {input} > {output}"
+
+
+rule samtools_index:
+    input:
+        "sorted_reads/{sample}.bam"
+    output:
+        "sorted_reads/{sample}.bam.bai"
+    shell:
+        "samtools index {input}"
+
+
+rule bcftools_call:
+    input:
+        fa="data/genome.fa",
+        bam=expand("sorted_reads/{sample}.bam", sample=config["samples"]),
+        bai=expand("sorted_reads/{sample}.bam.bai", sample=config["samples"])
+    output:
+        "calls/all.vcf"
+    params:
+        rate=config["prior_mutation_rate"]
+    log:
+        "logs/bcftools_call/all.log"
+    shell:
+        "(bcftools mpileup -f {input.fa} {input.bam} | "
+        "bcftools call -mv -P {params.rate} - > {output}) 2> {log}"
+
+
+rule plot_quals:
+    input:
+        "calls/all.vcf"
+    output:
+        "plots/quals.svg"
+    script:
+        "scripts/plot-quals.py"