feat: RNA trimming for arriba

config/config.yaml

@@ -131,6 +131,10 @@ fastp_pe:
   # Default enabled trimming parameters for fastp. Specified for clarity.
   extra: "--trim_poly_g --qualified_quality_phred 15 --unqualified_percent_limit 40 --n_base_limit 5 --length_required 15"
 
+fastp_pe_arriba:
+  container: "docker://hydragenetics/fastp:0.20.1"
+  extra: "--max_len1 100"
+
 fastqc:
   container: "docker://hydragenetics/fastqc:0.11.9"
 

config/resources.yaml

@@ -22,6 +22,11 @@ fastp_pe:
   mem_mb: 30720
   mem_per_cpu: 6144
 
+fastp_pe_arriba:
+  threads: 5
+  mem_mb: 30720
+  mem_per_cpu: 6144
+
 fuseq_wes:
   threads: 2
   mem_mb: 12288

requirements.txt

@@ -1,6 +1,6 @@
 hydra-genetics==0.15.0
 pandas>=1.3.1
-snakemake==7.13.0
+snakemake==7.18.0
 singularity==3.0.0
 jinja2==3.0.1
 networkx

workflow/Snakefile

@@ -60,6 +60,60 @@ module prealignment:
 use rule * from prealignment as prealignment_*
 
 
+use rule fastp_pe from prealignment as prealignment_fastp_pe_arriba with:
+    output:
+        trimmed=temp(
+            [
+                "prealignment/fastp_pe_arriba/{sample}_{type}_{flowcell}_{lane}_{barcode}_fastq1.fastq.gz",
+                "prealignment/fastp_pe_arriba/{sample}_{type}_{flowcell}_{lane}_{barcode}_fastq2.fastq.gz",
+            ]
+        ),
+        html="prealignment/fastp_pe_arriba/{sample}_{type}_{flowcell}_{lane}_{barcode}_fastp.html",
+        json="prealignment/fastp_pe_arriba/{sample}_{type}_{flowcell}_{lane}_{barcode}_fastp.json",
+    params:
+        adapters=lambda wildcards: " --adapter_sequence {} --adapter_sequence_r2 {} ".format(
+            *get_fastq_adapter(units, wildcards).split(",")
+        ),
+        extra=config.get("fastp_pe_arriba", {}).get("extra", ""),
+    log:
+        "prealignment/fastp_pe_arriba/{sample}_{type}_{flowcell}_{lane}_{barcode}_fastq.fastq.gz.log",
+    benchmark:
+        repeat(
+            "prealignment/fastp_pe_arriba/{sample}_{type}_{flowcell}_{lane}_{barcode}_fastq.fastq.gz.benchmark.tsv",
+            config.get("fastp_pe_arriba", {}).get("benchmark_repeats", 1),
+        )
+    resources:
+        mem_mb=config.get("fastp_pe_arriba", {}).get("mem_mb", config["default_resources"]["mem_mb"]),
+        mem_per_cpu=config.get("fastp_pe_arriba", {}).get("mem_per_cpu", config["default_resources"]["mem_per_cpu"]),
+        partition=config.get("fastp_pe_arriba", {}).get("partition", config["default_resources"]["partition"]),
+        threads=config.get("fastp_pe_arriba", {}).get("threads", config["default_resources"]["threads"]),
+        time=config.get("fastp_pe_arriba", {}).get("time", config["default_resources"]["time"]),
+    threads: config.get("fastp_pe_arriba", {}).get("threads", config["default_resources"]["threads"])
+
+
+use rule merged from prealignment as prealignment_merged_arriba with:
+    input:
+        fastq=merged_input_arriba,
+    output:
+        fastq=temp("prealignment/merged_arriba/{sample}_{type}_{read}.fastq.gz"),
+    log:
+        "prealignment/merged_arriba/{sample}_{type}_{read}.fastq.gz.log",
+    benchmark:
+        repeat(
+            "prealignment/merged_arriba/{sample}_{type}_{read}.fastq.gz.benchmark.tsv",
+            config.get("merged_arriba", {}).get("benchmark_repeats", 1),
+        )
+    resources:
+        mem_mb=config.get("merged_arriba", {}).get("mem_mb", config["default_resources"]["mem_mb"]),
+        mem_per_cpu=config.get("merged_arriba", {}).get("mem_per_cpu", config["default_resources"]["mem_per_cpu"]),
+        partition=config.get("merged_arriba", {}).get("partition", config["default_resources"]["partition"]),
+        threads=config.get("merged_arriba", {}).get("threads", config["default_resources"]["threads"]),
+        time=config.get("merged_arriba", {}).get("time", config["default_resources"]["time"]),
+    threads: config.get("merged_arriba", {}).get("threads", config["default_resources"]["threads"])
+    container:
+        config.get("merged_arriba", {}).get("container", config["default_container"])
+
+
 module alignment:
     snakefile:
         get_module_snakefile(config, "hydra-genetics/alignment", path="workflow/Snakefile", tag="v0.3.1")
@@ -71,6 +125,10 @@ use rule * from alignment as alignment_*
 
 
 use rule star from alignment as alignment_star with:
+    input:
+        fq1="prealignment/merged_arriba/{sample}_{type}_fastq1.fastq.gz",
+        fq2="prealignment/merged_arriba/{sample}_{type}_fastq2.fastq.gz",
+        idx=config.get("star", {}).get("genome_index", ""),
     params:
         extra=lambda wildcards: "%s %s"
         % (

workflow/rules/common.smk

@@ -70,6 +70,14 @@ wildcard_constraints:
     type="N|T|R",
 
 
+merged_input_arriba = lambda wildcards: expand(
+    "prealignment/fastp_pe_arriba/{{sample}}_{{type}}_{flowcell_lane_barcode}_{{read}}.fastq.gz",
+    flowcell_lane_barcode=[
+        "{}_{}_{}".format(unit.flowcell, unit.lane, unit.barcode) for unit in get_units(units, wildcards, wildcards.type)
+    ],
+)
+
+
 def compile_output_list(wildcards):
     output_files = []
     types = set([unit.type for unit in units.itertuples()])