add rx to chip as an option

seqnado/cli.py

@@ -7,7 +7,7 @@
 
 
 @click.command(context_settings=dict(ignore_unknown_options=True))
-@click.argument("method", type=click.Choice(["atac", "chip", "rna", "snp", "chip-rx"]))
+@click.argument("method", type=click.Choice(["atac", "chip", "rna", "snp"]))
 @click.argument("cookiecutter_options", nargs=-1, type=click.UNPROCESSED)
 def cli_config(method, cookiecutter_options, help=False):
     """
@@ -55,7 +55,7 @@ def cli_design(method, files, output="design.csv"):
 @click.command(context_settings=dict(ignore_unknown_options=True))
 @click.argument(
     "method",
-    type=click.Choice(["atac", "chip", "rna", "snp", "chip-rx", "consensus-peaks"]),
+    type=click.Choice(["atac", "chip", "rna", "snp", "consensus-peaks"]),
 )
 @click.option("--version", help="Print version and exit", is_flag=True)
 @click.option("-c", "--cores", default=1, help="Number of cores to use", required=True)

seqnado/utils.py

@@ -272,7 +272,8 @@ def get_control_file(wc, design, assay, filetype):
 
 
 def define_output_files(
-    assay: Literal["ChIP", "ATAC", "RNA", "SNP", "ChIP-rx"],
+    assay: Literal["ChIP", "ATAC", "RNA", "SNP"],
+    chip_spikein_normalisation: bool = False,
     sample_names: list = None,
     pileup_method: list = None,
     peak_calling_method: list = None,
@@ -300,6 +301,15 @@ def define_output_files(
         analysis_output.append(hub_file)
 
     if assay in ["ChIP", "ATAC"]:
+        if chip_spikein_normalisation:
+            if assay == "ChIP":
+                assay_output.extend(
+                    [
+                        "seqnado_output/normalisation_factors.tsv",
+                        "seqnado_output/qc/full_fastqscreen_report.html",
+                    ]
+                )
+
         if make_bigwigs and pileup_method:
             assay_output.extend(
                 expand(
@@ -335,21 +345,7 @@ def define_output_files(
                     method=pileup_method,
                 )
             )
-    elif assay == "ChIP-rx":
-        assay_output.extend(
-            [
-                "seqnado_output/qc/full_fastqscreen_report.html",
-                *expand(
-                    "seqnado_output/qc/fastq_screen/{sample}_{read}_screen.html",
-                    sample=sample_names,
-                    read=["1", "2"],
-                ),
-                *expand(
-                    "seqnado_output/aligned/spikein/{sample}_stats.tsv",
-                    sample=sample_names,
-                ),
-            ]
-        )
+
 
     elif assay == "RNA":
         if make_bigwigs and pileup_method:

seqnado/workflow/config/cookiecutter_config/config_chip/cookiecutter.json

@@ -11,6 +11,13 @@
   "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/sequence/hg38.chrom.sizes",
   "indicies": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/bt2_index/hg38",
   "gtf": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/genes/hg38.ncbiRefSeq.gtf",
+  "chip_spikein_normalisation": [
+    "yes",
+    "no"
+  ],
+  "reference_genome": "hg38",
+  "spikein_genome": "dm6",
+  "fastq_screen_config": "/ceph/project/milne_group/shared/seqnado_reference/fastqscreen_reference/fastq_screen.conf",
   "read_type": [
     "paired",
     "single"

seqnado/workflow/config/cookiecutter_config/config_chip/{{cookiecutter.date}}_{{cookiecutter.project_id}}/config_chip.yml

@@ -12,6 +12,12 @@ genome:
 
 design: "design.csv"
 
+spikein:
+    chip_spikein_normalisation: "{{cookiecutter.chip_spikein_normalisation}}"
+    reference_genome: "{{cookiecutter.reference_genome}}"
+    spikein_genome: "{{cookiecutter.spikein_genome}}"
+    fastq_screen_config: "{{cookiecutter.fastq_screen_config}}"
+
 read_type: "{{cookiecutter.read_type}}"
 split_fastq: "{{cookiecutter.split_fastq}}"
 split_fastq_parts: "{{cookiecutter.split_fastq_parts}}"

seqnado/workflow/rules/chip_refnorm.smk

@@ -9,7 +9,7 @@ rule fastq_screen:
         fq_screen_txt="seqnado_output/qc/fastq_screen/{sample}_{read}_screen.txt",
     params:
         outdir="seqnado_output/qc/fastq_screen",
-        conf=config["genome"]["fastq_screen_config"],
+        conf=config["spikein"]["fastq_screen_config"],
         tmpdir="seqnado_output/qc/fastqc_raw/{sample}_{read}",
         basename=lambda wc, output: utils.get_fq_filestem(wc, samples=FASTQ_SAMPLES),
     threads: config["bowtie2"]["threads"]
@@ -49,6 +49,8 @@ use rule align_paired as align_paired_spikein with:
         fq2="seqnado_output/trimmed/{sample}_2.fastq.gz",
     output:
         bam=temp("seqnado_output/aligned/spikein/raw/{sample}.bam"),
+    params:
+        options="--no-mixed --no-discordant",
     log:
         "seqnado_output/logs/aligned_spikein/{sample}.log"
 
@@ -100,8 +102,8 @@ rule split_bam:
         exo_bam=temp("seqnado_output/aligned/spikein/{sample}_exo.bam"),
         stats="seqnado_output/aligned/spikein/{sample}_stats.tsv",
     params:
-        genome_prefix=config["genome"]["sample_genome"],
-        exo_prefix=config["genome"]["exo_genome"],
+        genome_prefix=config["spikein"]["reference_genome"],
+        exo_prefix=config["spikein"]["spikein_genome"],
         prefix="seqnado_output/aligned/spikein/{sample}",
         map_qual=30,
     log:"seqnado_output/logs/split_bam/{sample}.log"
@@ -120,3 +122,15 @@ rule move_ref_bam:
     shell:"""
     mv {input.bam} {output.bam}
     """
+
+rule calculate_normalisation_factors:
+    input:
+        expand(rules.split_bam.output.stats, sample=SAMPLE_NAMES),
+    output:
+        normalisation_table = "seqnado_output/normalisation_factors.tsv",
+        normalisation_factors = "seqnado_output/normalisation_factors.json",
+        scale_factors="seqnado_output/scaling_factors.json",
+    log:
+        "seqnado_output/logs/normalisation_factors.log"
+    script:
+        "../scripts/calculate_spikein_norm_orlando.py"