style: format shell blocks with snakefmt

.github/workflows/main.yml

@@ -4,7 +4,6 @@ on:
   push:
     branches: [main]
   pull_request:
-    branches: [main]
 
 jobs:
   # pixi test

workflow/rules/apply-model.smk

@@ -8,6 +8,10 @@ rule fire:
     output:
         cram="results/{sm}/{sm}-fire-{v}-filtered.cram",
         crai="results/{sm}/{sm}-fire-{v}-filtered.cram.crai",
+    benchmark:
+        "results/{sm}/additional-outputs-{v}/benchmarks/{sm}-fire-bam.txt"
+    conda:
+        DEFAULT_ENV
     threads: 32
     resources:
         mem_mb=32 * 1024,
@@ -17,10 +21,6 @@ rule fire:
         min_ave_msp_size=config.get("min_ave_msp_size", 10),
         use_ont=USE_ONT,
         flag=FILTER_FLAG,
-    benchmark:
-        "results/{sm}/additional-outputs-{v}/benchmarks/{sm}-fire-bam.txt"
-    conda:
-        DEFAULT_ENV
     shell:
         """
         samtools view -@ {threads} -u -F {params.flag} {input.bam} \
@@ -37,7 +37,7 @@ rule fire:
                 --input-fmt-option required_fields=0x1bff \
                 --write-index -o {output.cram}
 
-        # check if the cram file has zero reads 
+        # check if the cram file has zero reads
         reads_in_header=$(samtools view {output.cram} | head | wc -l || true)
         if [ $reads_in_header -eq 0 ]; then
             printf "\nNo reads passed filters exiting...\n\nPlease review https://fiberseq.github.io/quick-start.html to make sure the input BAM has been correctly processed.\n\n"
@@ -51,9 +51,9 @@ rule fire_sites_chrom:
         cram=rules.fire.output.cram,
     output:
         bed=temp("temp/{sm}/chrom/{v}-{chrom}.sorted.bed.gz"),
-    threads: 4
     conda:
         DEFAULT_ENV
+    threads: 4
     resources:
         mem_mb=16 * 1024,
     params:
@@ -62,13 +62,13 @@ rule fire_sites_chrom:
         """
         samtools view -@ {threads} -u {input.cram} {wildcards.chrom} \
             | {FT_EXE} fire -t {threads} --extract - \
-                | LC_ALL=C sort --parallel={threads} \
-                    -k1,1 -k2,2n -k3,3n -k4,4 \
-                | bioawk -tc hdr '$10<={params.min_fdr}' \
-                | (grep '\\S' || true) \
-                | (grep -v '^#' || true) \
-                | bgzip -@ {threads} \
-            > {output.bed}
+            | LC_ALL=C sort --parallel={threads} \
+                -k1,1 -k2,2n -k3,3n -k4,4 \
+            | bioawk -tc hdr '$10<={params.min_fdr}' \
+            | (grep '\\S' || true) \
+            | (grep -v '^#' || true) \
+            | bgzip -@ {threads} \
+                >{output.bed}
         """
 
 
@@ -79,12 +79,12 @@ rule fire_sites:
         ),
     output:
         bed="results/{sm}/additional-outputs-{v}/fire-peaks/{sm}-{v}-fire-elements.bed.gz",
-    threads: 1
     conda:
         DEFAULT_ENV
+    threads: 1
     shell:
         """
-        cat {input.beds} > {output.bed}
+        cat {input.beds} >{output.bed}
         """
 
 
@@ -93,9 +93,9 @@ rule fire_sites_index:
         bed=rules.fire_sites.output.bed,
     output:
         tbi=rules.fire_sites.output.bed + ".tbi",
-    threads: 1
     conda:
         DEFAULT_ENV
+    threads: 1
     shell:
         """
         tabix -p bed {input.bed}

workflow/rules/coverages.smk

@@ -10,18 +10,18 @@ rule genome_bedgraph:
     output:
         bg=temp("temp/{sm}/coverage/{sm}-{v}.bed.gz"),
         tbi=temp("temp/{sm}/coverage/{sm}-{v}.bed.gz.tbi"),
-    threads: 16
     shadow:
         "minimal"
     conda:
         DEFAULT_ENV
+    threads: 16
     shell:
-        """ 
+        """
         mosdepth -F 4 -f {input.ref} -t {threads} tmp {input.cram}
         bgzip -cd tmp.per-base.bed.gz \
-            | LC_ALL=C sort --parallel={threads} -k1,1 -k2,2n -k3,3n -k4,4  \
+            | LC_ALL=C sort --parallel={threads} -k1,1 -k2,2n -k3,3n -k4,4 \
             | bgzip -@ {threads} \
-        > {output.bg}
+                >{output.bg}
         tabix -f -p bed {output.bg}
         """
 
@@ -33,13 +33,13 @@ rule coverage:
         cov="results/{sm}/additional-outputs-{v}/coverage/{sm}-{v}-median-coverage.txt",
         minimum="results/{sm}/additional-outputs-{v}/coverage/{sm}-{v}-minimum-coverage.txt",
         maximum="results/{sm}/additional-outputs-{v}/coverage/{sm}-{v}-maximum-coverage.txt",
+    benchmark:
+        "results/{sm}/additional-outputs-{v}/benchmarks/coverage/{sm}.txt"
     conda:
         "../envs/python.yaml"
     threads: 1
     resources:
         mem_mb=64 * 1024,
-    benchmark:
-        "results/{sm}/additional-outputs-{v}/benchmarks/coverage/{sm}.txt"
     params:
         coverage_within_n_sd=COVERAGE_WITHIN_N_SD,
         min_coverage=MIN_COVERAGE,
@@ -57,18 +57,18 @@ rule fiber_locations_chromosome:
         crai=rules.fire.output.crai,
     output:
         bed=temp("temp/{sm}/coverage/{v}-{chrom}.fiber-locations.bed.gz"),
-    threads: 4
     conda:
         DEFAULT_ENV
+    threads: 4
     shell:
         """
         # get fiber locations
         (samtools view -@ {threads} -u {input.cram} {wildcards.chrom} \
             | {FT_EXE} extract -t {threads} -s --all - \
-            | hck -F '#ct' -F st -F en -F fiber -F strand -F HP ) \
+            | hck -F '#ct' -F st -F en -F fiber -F strand -F HP) \
             | (grep -v "^#" || true) \
             | bgzip -@ {threads} \
-        > {output.bed}
+                >{output.bed}
         """
 
 
@@ -91,24 +91,24 @@ rule fiber_locations:
         filtered_tbi=temp(
             "temp/{sm}/coverage/filtered-for-coverage/{v}-fiber-locations.bed.gz.tbi"
         ),
-    threads: 4
     conda:
         DEFAULT_ENV
+    threads: 4
     params:
         max_frac_overlap=0.2,
     shell:
         """
-        cat {input.fibers} > {output.bed}
+        cat {input.fibers} >{output.bed}
         tabix -f -p bed {output.bed}
-        
+
         # get filtered fiber locations
         MIN=$(cat {input.minimum})
         MAX=$(cat {input.maximum})
         bedtools intersect -header -sorted -v -f {params.max_frac_overlap} \
             -a {output.bed} \
             -b <(bgzip -cd {input.bg} | awk -v MAX="$MAX" -v MIN="$MIN" '$4 <= MIN || $4 >= MAX') \
-        | bgzip -@ {threads} \
-        > {output.filtered}
+            | bgzip -@ {threads} \
+                >{output.filtered}
         tabix -f -p bed {output.filtered}
         """
 
@@ -122,9 +122,9 @@ rule exclude_from_shuffle:
         fai=ancient(FAI),
     output:
         bed="results/{sm}/additional-outputs-{v}/coverage/exclude-from-shuffles.bed.gz",
-    threads: 4
     conda:
         DEFAULT_ENV
+    threads: 4
     params:
         exclude=lambda wc: " ".join(EXCLUDES) if EXCLUDES else "",
     shell:
@@ -139,7 +139,7 @@ rule exclude_from_shuffle:
             | bedtools sort \
             | bedtools merge \
             | bgzip -@ {threads} \
-        > {output.bed}
+                >{output.bed}
         """
 
 
@@ -154,12 +154,12 @@ rule unreliable_coverage_regions:
         bed_tbi="results/{sm}/additional-outputs-{v}/coverage/unreliable-coverage-regions.bed.gz.tbi",
         tmp=temp("temp/{sm}/additional-outputs-{v}/unreliable-coverage-regions.bed"),
         bb="results/{sm}/trackHub-{v}/bb/unreliable-coverage-regions.bb",
+    conda:
+        DEFAULT_ENV
     threads: 4
     params:
         min_len=MIN_UNRELIABLE_COVERAGE_LEN,
         bed3_as=workflow.source_path("../templates/bed3.as"),
-    conda:
-        DEFAULT_ENV
     shell:
         """
         MIN=$(cat {input.minimum})
@@ -170,15 +170,15 @@ rule unreliable_coverage_regions:
             | bedtools merge -i - \
             | awk '$3-$2 >= {params.min_len}' \
             | bgzip -@ {threads} \
-        > {output.bed}
+                >{output.bed}
 
         # bigbed
         # for some reason bigtools gives a too many files open error when reading from stdin
-        bedtools merge -i {output.bed} > {output.tmp}
+        bedtools merge -i {output.bed} >{output.tmp}
         bigtools bedtobigbed \
-                -s start -a {params.bed3_as} \
-                {output.tmp} {input.fai} {output.bb}
+            -s start -a {params.bed3_as} \
+            {output.tmp} {input.fai} {output.bb}
 
-        # index 
+        # index
         tabix -f -p bed {output.bed}
         """

workflow/rules/decorated-reads.smk

@@ -11,20 +11,20 @@ rule decorate_fibers_chromosome:
     output:
         bed=temp("temp/{sm}/decorate/{v}-{chrom}.bed.gz"),
         decorated=temp("temp/{sm}/decorate/{v}-{chrom}.dec.bed.gz"),
-    threads: 4
-    resources:
-        mem_mb=get_mem_mb,
     # the following steps can take a while so this helps the pipeline start this earlier.
     priority: 10
     conda:
         DEFAULT_ENV
+    threads: 4
+    resources:
+        mem_mb=get_mem_mb,
     shell:
         """
         samtools view -@ {threads} -u {input.cram} {wildcards.chrom} \
             | {FT_EXE} track-decorators -t {threads} --bed12 {output.bed} \
             | sort -k1,1 -k2,2n -k3,3n -k4,4 \
             | bgzip -@ {threads} \
-        > {output.decorated}
+                >{output.decorated}
         """
 
 
@@ -41,12 +41,12 @@ rule decorate_fibers_1:
         bb="results/{sm}/trackHub-{v}/bb/fire-fibers.bb",
     benchmark:
         "results/{sm}/additional-outputs-{v}/benchmarks/decorate_fibers_1/{sm}.txt"
-    threads: 8
-    resources:
-        runtime=240,
     priority: 10
     conda:
         DEFAULT_ENV
+    threads: 8
+    resources:
+        runtime=240,
     params:
         bed_as=workflow.source_path("../templates/bed12_filter.as"),
         nzooms=NZOOMS,
@@ -79,12 +79,12 @@ rule decorate_fibers_2:
         #bed=temp("temp/{sm}/trackHub-{v}/bb/fire-fiber-decorators.bed.gz"),
     benchmark:
         "results/{sm}/additional-outputs-{v}/benchmarks/decorate_fibers_2/{sm}.txt"
-    threads: 8
-    resources:
-        runtime=60 * 16,
     priority: 10
     conda:
         DEFAULT_ENV
+    threads: 8
+    resources:
+        runtime=60 * 16,
     params:
         dec_as=workflow.source_path("../templates/decoration.as"),
         nzooms=NZOOMS,