cut and tag updates

Author: DanHUMassMed

.gitignore

@@ -2,7 +2,7 @@
 .nextflow/
 **/data/
 **/results/
-work/
+**/work/
 **/deseq_out
 **/__pycache__
 

arf1_rnaseq/conf/experiment.config

@@ -9,7 +9,8 @@ params {
     run_get_dropbox_data       = false
     run_fastqc                 = false
     run_trimmomatic            = false
-    run_rnaseq_rsem            = true
+    run_trim_galore            = true
+    run_rnaseq_rsem            = false
     run_rnaseq_salmon          = false
     run_deseq_rsem             = false
     run_deseq_rsem_report      = false

arf1_rnaseq/run.sh

@@ -1,2 +1,3 @@
 #!/bin/bash
 nextflow -c conf/experiment.config run ../../RNA-Seq-Nextflow -resume -bg -with-tower -N [email protected]
+#nextflow -c conf/experiment.config run ../../Cut-and-Tag-Nextflow -bg -with-tower -N [email protected]

cut_tag_trial/conf/experiment.config

@@ -4,22 +4,18 @@ params {
     data_remote = "cut_tag_trial"
     experiment  = "cut_tag_trial"
 
-    run_create_star_rsem_index = false
-    run_create_salmon_index    = false
     run_get_dropbox_data       = false
-    run_fastqc                 = true
-    run_trimmomatic            = false
-    run_rnaseq_rsem            = false
-    run_rnaseq_salmon          = false
-    run_deseq_rsem             = false
-    run_deseq_rsem_report      = false
-    run_wormcat                = false
-    run_overview_report        = false
+    run_fastqc                 = false
+    run_trim_galore            = false
 
-    fastq_single = "${launchDir}/data/fastq/*.fastq.gz"
+    run_cut_and_tag            = true
 
-    trimmomatic_control='"HEADCROP:10"'
 
-    report_config = "${launchDir}/conf/experiment1.json"
+    fastq_paired = "${launchDir}/data/fastq/*_R{1,2}.fastq.gz"
+
+
+    genome = 'WBcel235'
+    //genome = 'ce10'
+    sample_sheet = "${launchDir}/conf/samplesheet.csv" 
 
 }

cut_tag_trial/conf/samplesheet.csv

@@ -0,0 +1,4 @@
+group,replicate,fastq_1,fastq_2,control
+h3k4me3,1,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-1_R1.fastq.gz,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-1_R2.fastq.gz,igg_ctrl 
+h3k4me3,2,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-2_R1.fastq.gz,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-2_R2.fastq.gz,igg_ctrl
+igg_ctrl,1,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV_noAb_R1.fastq.gz,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV_noAb_R2.fastq.gz,

cut_tag_trial/nf-core/find_non_sys.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+FIND=$1
+find ./work -name "$FIND" -exec ls -F {} \;|grep -v '@'

cut_tag_trial/nf-core/nextflow.config

@@ -0,0 +1,26 @@
+params {
+    max_cpus   = 48
+    max_memory = '768.GB'
+    max_time   = '48.h'
+ 
+    lsf_opts = ''
+    schema_ignore_params = 'genomes,lsf_opts'
+    validationSchemaIgnoreParams = "genomes,lsf_opts,schema_ignore_params"
+}
+ 
+singularity {
+  enabled = true
+  autoMounts = true
+}
+ 
+process {
+  executor = 'lsf'
+  clusterOptions = params.lsf_opts
+}
+ 
+executor {
+  perTaskReserve = false
+  perJobMemLimit = true
+}
+ 
+ 

cut_tag_trial/nf-core/params.json

@@ -0,0 +1,8 @@
+{
+    "input": "samplesheet.csv",
+    "outdir": "results",
+    "genome": "WBcel235",
+    "max_memory": "500.GB",
+    "max_cpus": 48,
+    "max_time": "48.h"
+}

cut_tag_trial/nf-core/run.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+nextflow run nf-core/cutandrun -r 3.2.1 -params-file params.json -resume -bg -with-tower

cut_tag_trial/nf-core/samplesheet.csv

@@ -0,0 +1,4 @@
+group,replicate,fastq_1,fastq_2,control
+h3k4me3,1,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-1_R1.fastq.gz,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-1_R2.fastq.gz,igg_ctrl 
+h3k4me3,2,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-2_R1.fastq.gz,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV-cn-2_R2.fastq.gz,igg_ctrl
+igg_ctrl,1,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV_noAb_R1.fastq.gz,/home/daniel.higgins-umw/project_data/Walker_Lab/cut_tag_trial/data/fastq/EV_noAb_R2.fastq.gz,

cut_tag_trial/nf-core/search.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+SEARCH="BOWTIE2_TARGET"
+rm found*.sh
+count=1
+for d in `find ./work -name .command.sh`;
+do 
+    found=`cat $d|grep ${SEARCH}`;
+    if [ -n "$found" ];
+    then
+        echo $d;
+        echo $found;
+        cat $d >found${count}.sh;
+        count=$((count + 1))
+    fi
+
+done
+

cut_tag_trial/run.sh

@@ -1,2 +1,2 @@
 #!/bin/bash
-nextflow -c conf/experiment.config run ../../RNA-Seq-Nextflow -resume -bg -with-tower -N [email protected]
+nextflow -c conf/experiment.config run ../../Cut-and-Tag-Nextflow -resume -bg -with-tower -N [email protected]

cut_tag_trial/separate-interleaved.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+if [ -z "$1" ]; then
+    echo "Usage: separate_and_compress_fastq <input_interleaved.fastq.gz>"
+    return 1
+fi
+
+zcat "$1" | awk 'NR%8==1 || NR%8==2 || NR%8==4 || NR%8==5 {print}' | gzip > output_R1.fastq.gz
+zcat "$1" | awk 'NR%8==3 || NR%8==6 || NR%8==7 || NR%8==0 {print}' | gzip > output_R2.fastq.gz
+
+echo "Interleaved FASTQ file separated into R1 and R2 files: output_R1.fastq.gz and output_R2.fastq.gz"
+
+