diff --git a/SUBMIT_CONFIG/slurm/cluster.yaml b/SUBMIT_CONFIG/slurm/cluster.yaml
index 42cab37fdae39abc715a26e813eafc73891dbd73..5019c6644e774fa53bc50ead8c6d493e298463b3 100644
--- a/SUBMIT_CONFIG/slurm/cluster.yaml
+++ b/SUBMIT_CONFIG/slurm/cluster.yaml
@@ -340,7 +340,7 @@ nanoplot_hifi:
longQC_hifi:
jobname: GEP.{rule}.{wildcards.sample}.{wildcards.readCounter}.{wildcards.smrtornot}
- mem_mb: 12000
+ mem_mb: 96000
time: "04:00:05"
multiqc_hifi:
diff --git a/Snakefile b/Snakefile
index 8facab1a486aa77c36de36c112cd96027312ba58..4c6e19c3cd762f1f2c45b2be7d1a1acde4ed2ee7 100644
--- a/Snakefile
+++ b/Snakefile
@@ -139,7 +139,7 @@ elif set(['sample', 'hifi_reads', 'meryl_kmer_size','trimSMRTbell', 'fastQC']).i
samples=samples.set_index(['sample','readCounter'])
longqc_dir = "tools/LongQC"
-
+ sequencing_type = "pb-sequel" if config["use_pacbio"] else "ont-rapid"
ruleAllQCFiles=[]
### TODO change this column in a generic QC analysis. (both nanoplot and and longqc running)
diff --git a/configuration/config.yaml b/configuration/config.yaml
index a57dadd97e844e96c029e5a5f7b5e269105bc35a..c681466efa94c20d8e5753f2cc76f8ba53952187 100644
--- a/configuration/config.yaml
+++ b/configuration/config.yaml
@@ -1,13 +1,16 @@
### PATH TO WHERE YOU WANT YOUR RESULTS FOR THIS RUN STORED - WILL BE AUTOMATICALLY CREATED IF IT DOESN'T EXIST ###
-Results: "/home/valentina/Desktop/test_gep/results_test_new"
+Results: "/home/valentina/Desktop/test_gep/results_test_new_11"
### FULL PATH TO YOUR SAMPLESHEET ###
-samplesTSV: "/home/valentina/Desktop/test_gep/build_hifi_example.tsv"
+samplesTSV: "/home/valentina/Desktop/test_gep/build_nano_example.tsv"
### PATH TO DEFINE RESOURCES FILE - DO NOT CHANGE UNLESS YOU WISH TO USE IN A DIFFERENT LOCATION ####
resources: "configuration/define_resources.yaml"
-### With EAR=True the ERGA Assembly Report is automatically generated from the analysis
-EAR: False
smudgeplot: False
kmer_plot_flat: False
+use_pacbio: True
+run_longqc: True
+
+### With EAR=True the ERGA Assembly Report is automatically generated from the analysis
+EAR: False
diff --git a/configuration/define_resources.yaml b/configuration/define_resources.yaml
index 4383973ccbc36fbb9f4f7f509d186158d682911d..f72dbe865397f682b38072b6a8a20208487f9cf7 100644
--- a/configuration/define_resources.yaml
+++ b/configuration/define_resources.yaml
@@ -186,3 +186,8 @@ merylUnion_hifi:
mem_mb: 96000
time: "12:00:00"
threads: 12
+
+install_longqc:
+ mem_mb: 4000
+ time: "01:00:00"
+ threads: 1
diff --git a/rules/build_hifi.smk b/rules/build_hifi.smk
index e3e9aaa5910ba20456df060b4dc56305cb35409d..f9508ab7a3fed3aa298e2e4de708fdb913d38120 100644
--- a/rules/build_hifi.smk
+++ b/rules/build_hifi.smk
@@ -69,7 +69,7 @@ rule trimSMRTBellAdapters_hifi:
log:
os.path.join(config['Results'], "0_buildDatabases/{sample}/hifiReads/logs/trimSMRTbell.{readCounter}.log")
priority:
- 15
+ 2
conda:
os.path.join(workflow.basedir, "envs/UNZIP_and_QC.yaml")
shell:
@@ -110,11 +110,18 @@ rule fastQC_hifi:
(fastqc {input} -o {params.folder2out} -t {threads}) &> {log}
"""
+def longqc_input(wildcards):
+ # if longqc is disactivated by the user, this input function return the output of nanoplot rather than the longQC one
+ if config["run_longqc"]:
+ return os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/longQC/web_summary.html")
+ else:
+ return os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/nanoplot/NanoPlot-report.html")
+
rule multiQC_hifi:
input:
lambda wildcards: expand(os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/fastqc/{readCounter}.{smrtornot}_fastqc.html"), sample=wildcards.sample, readCounter=dictReadCounter[wildcards.sample], smrtornot=dictSamples[wildcards.sample][1]),
os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/nanoplot/NanoPlot-report.html"),
- os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/longQC/web_summary.html")
+ longqc_input
params:
folder2qc=os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/fastqc/"),
folder2qc2=os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/nanoplot/"),
@@ -145,7 +152,7 @@ rule merylCount_hifi:
log:
os.path.join(config['Results'], "0_buildDatabases/{sample}/hifiReads/logs/meryl_hifi_count.{readCounter}.{kmer}.{smrtornot}.log")
priority:
- 10
+ 1
conda:
os.path.join(workflow.basedir, "envs/MER_STATS.yaml")
shell:
@@ -155,7 +162,9 @@ rule merylCount_hifi:
rule merylUnion_hifi:
input:
- lambda wildcards: expand(os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/merylDb/{readCounter}_hifi_dB.{smrtornot}.{kmer}.meryl/"), sample=wildcards.sample, readCounter=dictReadCounter[wildcards.sample], kmer=dictSamples[wildcards.sample][0], smrtornot=dictSamples[wildcards.sample][1])
+ db = lambda wildcards: expand(os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/merylDb/{readCounter}_hifi_dB.{smrtornot}.{kmer}.meryl/"), sample=wildcards.sample, readCounter=dictReadCounter[wildcards.sample], kmer=dictSamples[wildcards.sample][0], smrtornot=dictSamples[wildcards.sample][1]),
+ output_nanoplot = os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/nanoplot/NanoPlot-report.html"),
+ output_longqc = longqc_input
params:
kmer = "{kmer}",
removeReadDIR_trimmed=os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/temp_trimReads/"),
@@ -170,12 +179,12 @@ rule merylUnion_hifi:
log:
os.path.join(config['Results'], "0_buildDatabases/{sample}/hifiReads/logs/meryl_hifi_combine.{sample}.{kmer}.log")
priority:
- 10
+ 1
conda:
os.path.join(workflow.basedir, "envs/MER_STATS.yaml")
shell:
"""
- (meryl union-sum {input} output {output}) &> {log}
+ (meryl union-sum {input.db} output {output}) &> {log}
rm -r {params.removeReadDIR_trimmed}
rm -r {params.removeReadDIR_unzipped}
"""
@@ -194,6 +203,8 @@ rule NanoPlot:
time=resource['nanoplot_hifi']['time'],
log:
os.path.join(config['Results'], "0_buildDatabases/{sample}/hifiReads/logs/nanoplot.log")
+ priority:
+ 2
conda:
os.path.join(workflow.basedir, "envs/UNZIP_and_QC.yaml")
shell:
@@ -206,7 +217,8 @@ rule longQC:
fastq = lambda wildcards: expand(os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/temp_trimReads/{readCounter}.{smrtornot}.fastq"), sample=wildcards.sample, readCounter=dictReadCounter[wildcards.sample], smrtornot=dictSamples[wildcards.sample][1]),
path_lonqqc = os.path.join(longqc_dir,"longQC.py")
params:
- folder2out=os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/longQC/")
+ folder2out=os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/longQC/"),
+ sequencing_type = sequencing_type
output:
os.path.join(config['Results'],"0_buildDatabases/{sample}/hifiReads/QC/longQC/web_summary.html")
threads:
@@ -216,13 +228,14 @@ rule longQC:
time=resource['longQC_hifi']['time'],
log:
os.path.join(config['Results'], "0_buildDatabases/{sample}/hifiReads/logs/longQC.log")
+ priority:
+ 2
conda:
os.path.join(workflow.basedir, "envs/LONGQC.yaml")
shell:
"""
- ## TODO making either pacbio or nanopore for -x
- rmdir {params.folder2out}
- (python tools/LongQC/longQC.py sampleqc -x pb-sequel -o {params.folder2out} {input.fastq}) &> {log}
+ rm -r {params.folder2out}
+ (python tools/LongQC/longQC.py sampleqc -x {params.sequencing_type} -o {params.folder2out} {input.fastq}) &> {log}
"""
rule install_longqc: