feat(rule): add Split N CIGAR rule

workflow/Snakefile

@@ -2,7 +2,7 @@ import glob
 import os
 
 
-configfile: ".test/config/config.yml"
+configfile: "config/config.yml"
 
 
 # Access the data folder from the config
@@ -16,17 +16,17 @@ reference_dict = f"{reference}.dict"
 sample_files = glob.glob(os.path.join(data_folder, "*.bam"))
 samples = [os.path.basename(f).replace(".bam", "") for f in sample_files]
 
-read_groups = [f"results/grouped/{sample}.bam" for sample in samples]
-deduped_files = [f"results/dedup/{sample}.bam" for sample in samples]
+splitted_files = [f"results/split/{sample}.bam" for sample in samples]
 
 
 rule all:
     input:
-        deduped_files,
+        splitted_files,
         reference_idx,
         reference_dict,
 
 
 include: "rules/add_or_replace_rg.smk"
 include: "rules/mark_duplicates.smk"
 include: "rules/index_genome.smk"
+include: "rules/split_n_cigar_reads.smk"

workflow/rules/split_n_cigar_reads.smk

@@ -0,0 +1,17 @@
+rule splitncigarreads:
+    input:
+        bam="results/dedup/{sample}.bam",
+        ref=reference,
+        idx=reference_idx,
+        dict=reference_dict,
+    output:
+        temp("results/split/{sample}.bam"),
+    log:
+        "logs/splitNCIGARreads/{sample}.log",
+    params:
+        extra="",  # optional
+        java_mem_overhead_mb=512,  # Specify overhead for non-heap memory
+    resources:
+        mem_mb=4096,  # Total memory available for the rule
+    wrapper:
+        "v3.12.1/bio/gatk/splitncigarreads"