remove split fastq from config and all rules

alsmith151 · Jan 26, 2024 · 01bb877 · 01bb877
1 parent abee85a
commit 01bb877
Show file tree

Hide file tree

Showing 10 changed files with 31 additions and 156 deletions.
diff --git a/docs/pipeline.md b/docs/pipeline.md
@@ -28,15 +28,6 @@ $ seqnado-config chip
   [6/23] chromosome_sizes (/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/sequence/hg38.chrom.sizes):
   [7/23] indicies (/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/bt2_index/hg38):
   [8/23] gtf (/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/genes/hg38.ncbiRefSeq.gtf):
-  [9/23] Select read_type
-    1 - paired
-    2 - single
-    Choose from [1/2] (1): 1
-  [10/23] Select split_fastq
-    1 - True
-    2 - False
-    Choose from [1/2] (1): 2
-  [11/23] split_fastq_parts (int):
   [12/23] Select remove_pcr_duplicates_method
     1 - picard
     2 - deeptools

diff --git a/seqnado/config.py b/seqnado/config.py
@@ -83,7 +83,6 @@ def setup_configuration(assay, genome, template_data):
     template_data['indicies'] = genome_dict[genome]['index']
     template_data['chromosome_sizes'] = genome_dict[genome]['chromosome_sizes']
     template_data['gtf'] = genome_dict[genome]['gtf']
-    template_data['read_type'] = get_user_input("What is your read type?", default="paired", choices=["paired", "single"])
 
     template_data['remove_blacklist'] = get_user_input("Do you want to remove blacklist regions? (yes/no)", default="yes", is_boolean=True)
     if template_data['remove_blacklist']:
@@ -114,11 +113,6 @@ def setup_configuration(assay, genome, template_data):
                 template_data['fastq_screen_config'] = get_user_input("Path to fastqscreen config:", default="/ceph/project/milne_group/shared/seqnado_reference/fastqscreen_reference/fastq_screen.conf")
     elif assay in ["atac", "rna"]:
         template_data['normalisation_method'] = "False"
-
-    template_data['split_fastq'] = get_user_input("Do you want to split FASTQ files? (yes/no)", default="no", is_boolean=True)
-    if template_data['split_fastq']:
-        template_data.update['split_fastq_parts'] = get_user_input("How many parts do you want to split the FASTQ files into?", default="4")
-
 
     template_data['make_bigwigs'] = get_user_input("Do you want to make bigwigs? (yes/no)", default="no", is_boolean=True)
     if template_data['make_bigwigs']:

diff --git a/seqnado/workflow/config/config.yaml.jinja b/seqnado/workflow/config/config.yaml.jinja
@@ -14,8 +14,6 @@ genome:
     chromosome_sizes: "{{chromosome_sizes}}"
     gtf: "{{gtf}}"
 
-read_type: "{{read_type}}"
-
 remove_blacklist: "{{remove_blacklist}}"
 blacklist: "{{blacklist}}"
 
@@ -30,9 +28,6 @@ spikein_options:
     spikein_genome: "{{spikein_genome}}"
     fastq_screen_config: "{{fastq_screen_config}}"
 
-split_fastq: "{{split_fastq}}"
-split_fastq_parts: "{{split_fastq_parts}}"
-
 make_bigwigs: "{{make_bigwigs}}"  
 pileup_method: "{{pileup_method}}"
 make_heatmaps: "{{make_heatmaps}}"

diff --git a/seqnado/workflow/rules/align.smk b/seqnado/workflow/rules/align.smk
@@ -1,28 +1,5 @@
 import seqnado.utils as utils
 
-if config["split_fastq"] == "False":
-    rule align_paired:
-        input:
-            fq1="seqnado_output/trimmed/{sample}_1.fastq.gz",
-            fq2="seqnado_output/trimmed/{sample}_2.fastq.gz",
-        params:
-            index=config["genome"]["indicies"],
-            options=utils.check_options(config["bowtie2"]["options"]),
-        output:
-            bam=temp("seqnado_output/aligned/raw/{sample}.bam"),
-        threads: config["bowtie2"]["threads"]
-        resources:
-            mem_mb=4000,
-        log:
-            "seqnado_output/logs/align/{sample}.log",
-        shell:
-            """bowtie2 -p {threads} -x {params.index} -1 {input.fq1} -2 {input.fq2} {params.options} 2> {log} |
-            samtools view -bS - > {output.bam} &&
-            samtools sort -@ {threads} -o {output.bam}_sorted {output.bam} >> {log} 2>&1 &&
-            mv {output.bam}_sorted {output.bam}
-            """
-
-
 rule align_paired:
     input:
         fq1="seqnado_output/trimmed/{sample}_1.fastq.gz",
@@ -34,8 +11,8 @@ rule align_paired:
         bam=temp("seqnado_output/aligned/raw/{sample}.bam"),
     threads: config["bowtie2"]["threads"]
     resources:
+        time=lambda wildcards, attempt: "0-{hours}:00:00".format(hours=4 * 2**(attempt-1)),
         mem_mb=4000,
-        time="0-04:00:00",
     log:
         "seqnado_output/logs/align/{sample}.log",
     shell:
@@ -45,7 +22,6 @@ rule align_paired:
            mv {output.bam}_sorted {output.bam}
         """
 
-
 rule align_single:
     input:
         fq1="seqnado_output/trimmed/{sample}.fastq.gz",
@@ -55,6 +31,7 @@ rule align_single:
     output:
         bam=temp("seqnado_output/aligned/raw/{sample}.bam"),
     resources:
+        time=lambda wildcards, attempt: "0-{hours}:00:00".format(hours=4 * 2**(attempt-1)),
         mem_mb=4000,
     threads: config["bowtie2"]["threads"]
     log:

diff --git a/seqnado/workflow/rules/fastq_split.smk b/seqnado/workflow/rules/fastq_split.smk
diff --git a/seqnado/workflow/rules/qc.smk b/seqnado/workflow/rules/qc.smk
@@ -70,33 +70,33 @@ use rule samtools_stats as samtools_stats_filtered with:
         stats="seqnado_output/qc/alignment_filtered/{sample}.txt",
 
 
-if config["split_fastq"] == "False":
-
-    rule multiqc:
-        input:
-            expand(
-                "seqnado_output/qc/fastqc_raw/{sample}_{read}_fastqc.html",
-                sample=SAMPLE_NAMES,
-                read=[1, 2],
-            ),
-            expand(
-                "seqnado_output/qc/fastqc_trimmed/{sample}_{read}_fastqc.html",
-                sample=SAMPLE_NAMES,
-                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,
-            ),
-        output:
-            "seqnado_output/qc/full_qc_report.html",
-        log:
-            "seqnado_output/logs/multiqc.log",
-        resources:
-            mem_mb=lambda wildcards, attempt: 2000 * 2**attempt,
-        shell:
-            "multiqc -o seqnado_output/qc seqnado_output/qc -n full_qc_report.html --force > {log} 2>&1"
+
+
+rule multiqc:
+    input:
+        expand(
+            "seqnado_output/qc/fastqc_raw/{sample}_{read}_fastqc.html",
+            sample=SAMPLE_NAMES,
+            read=[1, 2],
+        ),
+        expand(
+            "seqnado_output/qc/fastqc_trimmed/{sample}_{read}_fastqc.html",
+            sample=SAMPLE_NAMES,
+            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,
+        ),
+    output:
+        "seqnado_output/qc/full_qc_report.html",
+    log:
+        "seqnado_output/logs/multiqc.log",
+    resources:
+        mem_mb=lambda wildcards, attempt: 2000 * 2**attempt,
+    shell:
+        "multiqc -o seqnado_output/qc seqnado_output/qc -n full_qc_report.html --force > {log} 2>&1"
 
 
 def get_fastqc_files(*args, **kwargs):

diff --git a/seqnado/workflow/snakefile_snp b/seqnado/workflow/snakefile_snp
@@ -34,12 +34,8 @@ else:
 
 DESIGN = FASTQ_SAMPLES.design
 SAMPLE_NAMES = FASTQ_SAMPLES.sample_names_all
-if config["split_fastq"]:
-    include: "rules/fastq_split.smk" 
-else:
-    include: "rules/fastq_trim.smk"
-    include: "rules/align.smk"
-
+include: "rules/fastq_trim.smk"
+include: "rules/align.smk"
 include: "rules/alignment_post_processing.smk"
 include: "rules/hub.smk"
 include: "rules/qc.smk"

diff --git a/tests/test_atac.py b/tests/test_atac.py
@@ -106,12 +106,10 @@ def user_inputs(
         "chromsizes": chromsizes,
         "gtf": f"{data_path}/genome/chr21.gtf",
         "blacklist": f"{data_path}/genome/hg19-blacklist.v2.chr21.bed.gz",
-        "read_type": "paired",
         "remove_blacklist": "yes",
         "remove_pcr_duplicates": "yes",
         "remove_pcr_duplicates_method": "picard",
         "shift_atac_reads": "yes",
-        "split_fastq": "no",
         "make_bigwigs": "yes",
         "pileup_method": "deeptools",
         "make_heatmaps": "yes",

diff --git a/tests/test_chip.py b/tests/test_chip.py
@@ -106,12 +106,10 @@ def user_inputs(
         "chromsizes": chromsizes,
         "gtf": f"{data_path}/genome/chr21.gtf",
         "blacklist": f"{data_path}/genome/hg19-blacklist.v2.chr21.bed.gz",
-        "read_type": "paired",
         "remove_blacklist": "yes",
         "remove_pcr_duplicates": "yes",
         "remove_pcr_duplicates_method": "picard",
         "spikein": "no",
-        "split_fastq": "no",
         "make_bigwigs": "yes",
         "pileup_method": "deeptools",
         "make_heatmaps": "yes",

diff --git a/tests/test_rna.py b/tests/test_rna.py
@@ -117,10 +117,8 @@ def user_inputs(
         "chromsizes": chromsizes,
         "gtf": f"{data_path}/genome/chr21.gtf",
         "blacklist": f"{data_path}/genome/hg19-blacklist.v2.chr21.bed.gz",
-        "read_type": "paired",
         "remove_blacklist": "yes",
         "remove_pcr_duplicates": "no",
-        "split_fastq": "no",
         "make_bigwigs": "yes",
         "pileup_method": "deeptools",
         "make_heatmaps": "yes",