Fix symlink_files function to handle both paired

and single-end assays

seqnado/utils.py

@@ -687,7 +687,7 @@ def from_dataframe(cls, df: pd.DataFrame, simplified: bool = True, **kwargs):
         return cls(assays=experiments, **kwargs)
 
 
-def symlink_files(
+def symlink_files_paired(
     output_dir: pathlib.Path, assay: Union[AssayNonIP, AssayIP], assay_name: str
 ):
     r1_path_new = pathlib.Path(f"{output_dir}/{assay_name}_1.fastq.gz")
@@ -706,6 +706,18 @@ def symlink_files(
             logger.warning(f"Symlink for {r2_path_new} already exists.")
 
 
+def symlink_files_single(
+    output_dir: pathlib.Path, assay: Union[AssayNonIP, AssayIP], assay_name: str
+):
+    r1_path_new = pathlib.Path(f"{output_dir}/{assay_name}.fastq.gz")
+
+    if not r1_path_new.exists():
+        try:
+            r1_path_new.symlink_to(assay.r1.path.resolve())
+        except FileExistsError:
+            logger.warning(f"Symlink for {r1_path_new} already exists.")
+
+
 def symlink_fastq_files(
     design: Union[Design, DesignIP], output_dir: str = "seqnado_output/fastqs/"
 ) -> None:
@@ -717,18 +729,28 @@ def symlink_fastq_files(
 
     if isinstance(design, Design):
         for assay_name, assay in design.assays.items():
-            symlink_files(output_dir, assay, assay_name)
+            if assay.is_paired:
+                symlink_files_paired(output_dir, assay, assay_name)
+            else:
+                symlink_files_single(output_dir, assay, assay_name)
 
     elif isinstance(design, DesignIP):
         for experiment_name, experiment in design.assays.items():
             assay = experiment.ip_files
             assay_name = assay.name
-            symlink_files(output_dir, assay, assay_name)
+
+            if assay.is_paired:
+                symlink_files_paired(output_dir, assay, assay_name)
+            else:
+                symlink_files_single(output_dir, assay, assay_name)
 
             if experiment.control_files:
                 assay = experiment.control_files
                 assay_name = assay.name
-                symlink_files(output_dir, assay, assay_name)
+                if assay.is_paired:
+                    symlink_files_paired(output_dir, assay, assay_name)
+                else:
+                    symlink_files_single(output_dir, assay, assay_name)
 
 
 def define_output_files(

seqnado/workflow/rules/qc.smk

@@ -19,6 +19,14 @@ rule fastqc_raw_paired:
         "v3.0.1/bio/fastqc"
 
 
+rule fastqc_raw_single:
+    input:
+        "seqnado_output/fastqs/{sample}.fastq.gz",
+    output:
+        html="seqnado_output/qc/fastqc_raw/{sample}.html",
+        zip="seqnado_output/qc/fastqc_raw/{sample}_fastqc.zip",  # the suffix _fastqc.zip is necessary for multiqc to find the file. If not using multiqc, you are free to choose an arbitrary filename
+
+
 use rule fastqc_raw_paired as fastqc_trimmed_paired with:
     input:
         "seqnado_output/trimmed/{sample}_{read}.fastq.gz",
@@ -29,6 +37,16 @@ use rule fastqc_raw_paired as fastqc_trimmed_paired with:
         "seqnado_output/logs/fastqc_trimmed/{sample}_{read}.log",
 
 
+use rule fastqc_raw_single as fastqc_trimmed_single with:
+    input:
+        "seqnado_output/trimmed/{sample}.fastq.gz",
+    output:
+        html="seqnado_output/qc/fastqc_trimmed/{sample}.html",
+        zip="seqnado_output/qc/fastqc_trimmed/{sample}_fastqc.zip",  # the suffix _fastqc.zip is necessary for multiqc to find the file. If not using multiqc, you are free to choose an arbitrary filename
+    log:
+        "seqnado_output/logs/fastqc_trimmed/{sample}.log",
+
+
 rule samtools_stats:
     input:
         bam="seqnado_output/aligned/raw/{sample}.bam",
@@ -47,7 +65,9 @@ use rule samtools_stats as samtools_stats_filtered with:
     output:
         stats="seqnado_output/qc/alignment_filtered/{sample}.txt",
 
+
 if config["split_fastq"] == "False":
+
     rule multiqc:
         input:
             expand(
@@ -61,7 +81,10 @@ if config["split_fastq"] == "False":
                 read=[1, 2],
             ),
             expand("seqnado_output/qc/alignment_raw/{sample}.txt", sample=SAMPLE_NAMES),
-            expand("seqnado_output/qc/alignment_filtered/{sample}.txt", sample=SAMPLE_NAMES),
+            expand(
+                "seqnado_output/qc/alignment_filtered/{sample}.txt",
+                sample=SAMPLE_NAMES,
+            ),
         output:
             "seqnado_output/qc/full_qc_report.html",
         log:
@@ -71,6 +94,7 @@ if config["split_fastq"] == "False":
         shell:
             "multiqc -o seqnado_output/qc seqnado_output/qc -n full_qc_report.html --force > {log} 2>&1"
 
+
 def get_fastqc_files(*args, **kwargs):
     """Return a list of fastq files for a given sample name."""
     import pathlib
@@ -99,13 +123,24 @@ rule multiqc_raw:
         "multiqc -o seqnado_output/qc seqnado_output/qc/fastqc_raw -n fastq_raw_qc.html --force > {log} 2>&1"
 
 
+def get_trimmed_files(wc):
+    """Return a list of fastq files for a given sample name."""
+    import pathlib
+
+    fastqc_dir = pathlib.Path("seqnado_output/qc/fastqc_trimmed/")
+
+    fastqc_files = []
+    fq_files = pathlib.Path("seqnado_output/fastqs").glob("*.fastq.gz")
+    for fq_file in fq_files:
+        fastqc_file = fastqc_dir / (fq_file.stem.replace(".fastq", "") + ".html")
+        fastqc_files.append(str(fastqc_file))
+
+    return fastqc_files
+
+
 rule multiqc_trimmed:
     input:
-        expand(
-            "seqnado_output/qc/fastqc_trimmed/{sample}_{read}.html",
-            sample=SAMPLE_NAMES,
-            read=[1, 2],
-        ),
+        get_trimmed_files,
     output:
         "seqnado_output/qc/fastq_trimmed_qc.html",
     log:
@@ -162,3 +197,6 @@ rule multiqc_library_complexity:
         mem_mb=lambda wildcards, attempt: 2000 * 2**attempt,
     shell:
         "multiqc -o seqnado_output/qc seqnado_output/aligned/duplicates_removed -n library_complexity_qc.html --force > {log} 2>&1"
+
+
+ruleorder: fastqc_raw_paired > fastqc_raw_single > fastqc_trimmed_paired > fastqc_trimmed_single > samtools_stats > samtools_stats_filtered > multiqc_raw > multiqc_trimmed > multiqc_alignment_raw > multiqc_alignment_filtered > multiqc_library_complexity

seqnado/workflow/snakefile_chip

@@ -62,6 +62,7 @@ ANALYSIS_OUTPUT = seqnado.utils.define_output_files(
                                             **config
                                             )
 
+
 if config["spikein"]:
     include: "rules/chip_refnorm.smk"
     include: "rules/normalisation.smk"