feat: added wrappers (#46)

* fix: file paths after cluster migration

* fix: minimap2 indexing rule now uses wrapper

* fix: minimap2 mapping rule now uses wrapper

* fix: rule sam_view SAM to BAM now uses wrapper

* fix: sam_stats qc rule now uses wrapper

* fix: sam_sorts rule now uses wrapper

* fix: updated wrappers

* fix: updated samsort mem allocation

* fix: linting

config/config.yml

@@ -7,16 +7,16 @@ samples: samples.csv
 workflow: "workflow-transcriptome-de_phe"
 
 # this is the input directory. All samples are looked for in this directory
-inputdir: "/lustre/project/m2_zdvhpc/transcriptome_data"
+inputdir: "/lustre/project/nhr-zdvhpc/transcriptome_data"
 # Repository URL:
 repo: "https://github.com/snakemake-workflows/transriptome-differential-expression"
 
 ## Workflow-specific Parameters:
 
 # Genome fasta (absolute path)
-genome: "/lustre/miifs01/project/m2_zdvhpc/transcriptome_data/GCA_917627325.4_PGI_CHIRRI_v4_genomic.fa"
+genome: "/lustre/miifs01/project/nhr-zdvhpc/transcriptome_data/GCA_917627325.4_PGI_CHIRRI_v4_genomic.fa"
 # Annotation GFF/GTF (absolute path)
-annotation: "/lustre/miifs01/project/m2_zdvhpc/transcriptome_data/GCA_917627325.4_PGI_CHIRRI_v4_genomic.gff"
+annotation: "/lustre/miifs01/project/nhr-zdvhpc/transcriptome_data/GCA_917627325.4_PGI_CHIRRI_v4_genomic.gff"
 # these samples ought to contain all samples comprising of the
 
 # Minimum read length, put 0 if you want to proceed with all reads.
@@ -40,9 +40,21 @@ maximum_secondary: 100
 # Secondary score ratio (-p for minimap2)
 secondary_score_ratio: 1.0
 
+# Samtools view opts, "-b" creates BAM from SAM.
+sview_opts: "-b"
+
+# Samtools sort opts,
+ssort_opts: ""
+
 # Salmon library type
 salmon_libtype: "U"
 
+
+# QC options
+
+# Samtools stats opts
+sstats_opts: ""
+
 # Count filtering options - customize these according to your experimental design:
 
 # Genes expressed in minimum this many samples

workflow/Snakefile

@@ -68,7 +68,7 @@ rule filter_reads:
         ),
     output:
         temp("filter/{sample}_filtered.fq"),
-    message: 
+    message:
         f"Filtering with read length >= {config['min_length']}."
     log:
         "logs/filter_reads/{sample}.log",
@@ -80,40 +80,34 @@ rule filter_reads:
 
 rule build_minimap_index:  ## build minimap2 index
     input:
-        transcriptome=rules.genome_to_transcriptome.output,
+        target=rules.genome_to_transcriptome.output,
     output:
         index="index/transcriptome_index.mmi",
     params:
-        opts=config["minimap_index_opts"],
+        extra=config["minimap_index_opts"],
     log:
         "logs/minimap2/index.log",
     conda:
         "envs/env.yml"
-    shell:
-        """
-    minimap2 -t {resources.cpus_per_task} {params.opts} -ax map-ont -d {output.index} {input.transcriptome} 2> {log}
-    """
+    wrapper:
+        "v3.13.4/bio/minimap2/index"
 
 
 # mapping reads with minimap2
 rule map_reads:
     input:
-        index=rules.build_minimap_index.output.index,
-        fastq_filtered=rules.filter_reads.output,
+        target=rules.build_minimap_index.output.index,
+        query=rules.filter_reads.output,
     output:
         "alignments/{sample}.sam",
     log:
         "logs/minimap2/mapping_{sample}.log",
     params:
-        opts=config["minimap2_opts"],
-        msec=config["maximum_secondary"],
-        psec=config["secondary_score_ratio"],
+        extra=f"-p {config['secondary_score_ratio']} -N {config['maximum_secondary']} {config['minimap2_opts']}",
     conda:
         "envs/env.yml"
-    shell:
-        """
-    minimap2 -t {resources.cpus_per_task} -ax map-ont -p {params.psec} -N {params.msec} {params.opts} {input.index} {input.fastq} > {output} 2> {log}
-    """
+    wrapper:
+        "v3.13.4/bio/minimap2/aligner"
 
 
 rule sam_view:
@@ -123,10 +117,12 @@ rule sam_view:
         "sorted_alignments/{sample}.bam",
     log:
         "logs/samtools/samview_{sample}.log",
+    params:
+        extra=f'{config["sview_opts"]}',
     conda:
         "envs/env.yml"
-    shell:
-        "samtools view -@ {resources.cpus_per_task} -bS {input.sam} > {output} 2> {log}"
+    wrapper:
+        "v3.13.4/bio/samtools/view"
 
 
 rule sam_index:

workflow/profile/Mainz-MogonNHR/config.yaml

@@ -4,17 +4,22 @@ default-resources:
 
 set-resources:
     genome_to_transcriptome:
+        cpus_per_task: 1
+        mem_mb_per_cpu: 1800
+        runtime: "30m"
+
+    filter_reads:
         cpus_per_task: 1
         mem_mb_per_cpu: 1800
         runtime: "2h"
 
     build_minimap_index:
         cpus_per_task: 4
         mem_mb_per_cpu: 3600
-        runtime: "1h"
+        runtime: "30m"
 
     map_reads:
-        cpus_per_task: 40
+        cpus_per_task: 32
         mem_mb_per_cpu: 1800
         runtime: "3h"
         slurm_partition: "smallcpu" # needs benchmarking
@@ -36,7 +41,7 @@ set-resources:
 
     sam_sort:
         cpus_per_task: 4
-        mem_mb_per_cpu: 1800
+        mem_mb_per_cpu: 3600
         runtime: "2h"
 
     sam_view:

workflow/rules/qc.smk

@@ -118,10 +118,12 @@ rule sam_sort:
         "sorted_alignments/{sample}_sorted.bam",
     log:
         "logs/samtools/samsort_{sample}.log",
+    params:
+        extra=f'{config["ssort_opts"]}',
     conda:
         "../envs/env.yml"
-    shell:
-        "samtools sort -@ {resources.cpus_per_task} {input.sam} -o {output} -O bam &> {log}"
+    wrapper:
+        "v3.13.4/bio/samtools/sort"
 
 
 rule map_qc:
@@ -134,7 +136,7 @@ rule map_qc:
     conda:
         "../envs/env.yml"
     wrapper:
-        "v3.12.1/bio/qualimap/bamqc"
+        "v3.13.4/bio/qualimap/bamqc"
 
 
 rule compress_map_qc:
@@ -157,9 +159,9 @@ rule sam_stats:
         "QC/samstats/{sample}.txt",
     log:
         "logs/samtools/samstats_{sample}.log",
+    params:
+        extra=f'{config["sstats_opts"]}',
     conda:
         "../envs/env.yml"
-    shell:
-        """
-            samtools stats -@ {resources.cpus_per_task} {input.bam} > {output} 2> {log}
-        """
+    wrapper:
+        "v3.13.4/bio/samtools/stats"