v7.7.0 release: Kraken added and multiQC fixed

example_of_result/20220120_res_CL14985_B4985_4_1645109072/reports/report.rmd → example_of_result/20220120_res_CL14985_B4985_4_1645462141/reports/report.rmd

@@ -228,6 +228,16 @@ Time loading reference: 00:00:00
 <br />Overall time: 00:00:00
 
 
+<br /><br />
+
+###  MultiQC
+
+
+Results are published in the [Report](./reports/multiqc_report.html) folder
+
+
+
+
 <br /><br />
 
 ###  Q20 filtering
@@ -360,7 +370,7 @@ In each sequence of length 40 <br />position 21 corresponds to the first nucleot
 </center>
 
 
-![Figure 8: test.fastq2_LEADING_16](./figures/logo_test.fastq2_LEADING_16.png){width=600}
+![Figure 8: test.fastq2_LEADING_0](./figures/logo_test.fastq2_LEADING_0.png){width=600}
 
 
 </center>
@@ -375,7 +385,7 @@ In each sequence of length 40 <br />position 21 corresponds to the first nucleot
 </center>
 
 
-![Figure 9: test.fastq2_LEADING_0](./figures/logo_test.fastq2_LEADING_0.png){width=600}
+![Figure 9: test.fastq2_LAGGING_0](./figures/logo_test.fastq2_LAGGING_0.png){width=600}
 
 
 </center>
@@ -390,7 +400,7 @@ In each sequence of length 40 <br />position 21 corresponds to the first nucleot
 </center>
 
 
-![Figure 10: test.fastq2_LAGGING_0](./figures/logo_test.fastq2_LAGGING_0.png){width=600}
+![Figure 10: test.fastq2_LEADING_16](./figures/logo_test.fastq2_LEADING_16.png){width=600}
 
 
 </center>
@@ -841,11 +851,11 @@ Full .nextflow.log is in: /mnt/c/Users/Gael/Documents/Git_projects/14985_loot<br
 
 
 Project (empty means no .git folder where the main.nf file is present):  loot https://gitlab.pasteur.fr/gmillot/14985_loot (fetch)
-<br />Git info (empty means no .git folder where the main.nf file is present):  v7.5.0-dirty
+<br />Git info (empty means no .git folder where the main.nf file is present):  v7.6.0-2-g005eedc277-dirty
 <br />Cmd line: nextflow run main.nf -resume
 <br />execution mode: local
 <br />Manifest's pipeline version: null
-<br />result path: /mnt/c/Users/Gael/Documents/Git_projects/14985_loot/results/20220120_res_CL14985_B4985_4_1645109072
+<br />result path: /mnt/c/Users/Gael/Documents/Git_projects/14985_loot/results/20220120_res_CL14985_B4985_4_1645462141
 <br />nextflow version: 21.04.2
 
 
@@ -862,7 +872,7 @@ workDir (directory where tasks temporary files are created): /mnt/c/Users/Gael/D
 
 USER VARIABLES:<br />
 
-out_path: /mnt/c/Users/Gael/Documents/Git_projects/14985_loot/results/20220120_res_CL14985_B4985_4_1645109072<br />
+out_path: /mnt/c/Users/Gael/Documents/Git_projects/14985_loot/results/20220120_res_CL14985_B4985_4_1645462141<br />
 in_path: /mnt/c/Users/Gael/Documents/Git_projects/14985_loot/dataset
 
 

example_of_result/20220120_res_CL14985_B4985_4_1645109072/reports/seq_around_insertion_report.txt → example_of_result/20220120_res_CL14985_B4985_4_1645462141/reports/seq_around_insertion_report.txt

@@ -12,7 +12,7 @@
 
 
 
-2022-02-17 14:41:48
+2022-02-21 16:52:41
 
 
 
@@ -31,7 +31,7 @@
 
 
 
-END TIME: 2022-02-17 14:41:48
+END TIME: 2022-02-21 16:52:42
 
 
 
@@ -118,7 +118,7 @@ loaded via a namespace (and not attached):
 
 ################################ JOB END
 
-TIME: 2022-02-17 14:41:48
+TIME: 2022-02-21 16:52:42
 
 TOTAL TIME LAPSE: 0S
 

main.nf

@@ -30,7 +30,9 @@ ref_name = file("${ref_path}/${ref_file}").baseName
 primer = file(primer_fasta)
 ref = file("${ref_path}/${ref_file}")
 sum_of_2_nb = fivep_seq_nb.toInteger()+added_nb.toInteger()
-k2db = file("${kraken_db}")
+if(system_exec == 'slurm'){
+    k2db = file("${kraken_db}")
+}
 
 // end from the nextflow.config file
 
@@ -46,7 +48,9 @@ modules = params.modules // remove the dot -> can be used in bash scripts
 fastq_ch_test = file("${in_path}/${fastq_file}") // to test if exist below
 primer_ch_test = file("${primer_fasta}") // to test if exist below
 ref_ch_test = file("${ref_path}/${ref_file}") // to test if exist below
-k2db_ch_test = file("${kraken_db}") // to test if exist below
+if(system_exec == 'slurm'){
+    k2db_ch_test = file("${kraken_db}") // to test if exist below
+}
 
 //////// end Variables from config.file that need to be checked
 
@@ -73,9 +77,11 @@ if(system_exec == 'local' || system_exec == 'slurm'){
     if( ! file_exists3){
         error "\n\n========\n\nERROR IN NEXTFLOW EXECUTION\n\nINVALID ref_path: ${ref_path}\nOR ref_file: ${ref_file}\nPARAMETER IN nextflow.config FILE\n\nIF POINTING TO A DISTANT SERVER, CHECK THAT IT IS MOUNTED\n\n========\n\n"
     }
-    def file_exists4 = k2db_ch_test.exists()
-    if( ! file_exists4){
-        error "\n\n========\n\nERROR IN NEXTFLOW EXECUTION\n\nINVALID kraken db path: ${kraken_db}\nPARAMETER IN nextflow.config FILE\n\nIF POINTING TO A DISTANT SERVER, CHECK THAT IT IS MOUNTED\n\n========\n\n"
+    if(system_exec == 'slurm'){
+        def file_exists4 = k2db_ch_test.exists()
+        if( ! file_exists4){
+            error "\n\n========\n\nERROR IN NEXTFLOW EXECUTION\n\nINVALID kraken db path: ${kraken_db}\nPARAMETER IN nextflow.config FILE\n\nIF POINTING TO A DISTANT SERVER, CHECK THAT IT IS MOUNTED\n\n========\n\n"
+        }
     }
 }else{
     error "\n\n========\n\nERROR IN NEXTFLOW EXECUTION\n\nINVALID system_exec PARAMETER IN nextflow.config FILE: ${system_exec}\n\n========\n\n"
@@ -161,15 +167,22 @@ process kraken {
 
     input:
     file fastq from fastq_trim_ch3
-    file k2db
+    if(system_exec == 'slurm'){
+        file k2db
+    }
 
     output:
     file "${fastq.baseName}_kraken_std.txt" into krakenreports
 
     script:
+    if(system_exec == 'slurm')
     """
     kraken2 --db ${k2db} --threads ${task.cpus} --report ${fastq.baseName}_kraken_std.txt ${fastq} > ${fastq.baseName}.kraken2
     """
+    else
+    """
+    echo "No kraken analysis performed in local running" > ${fastq.baseName}_kraken_std.txt
+    """
 }
 
 
@@ -439,17 +452,20 @@ process bowtie2 { // section 24.1 of the labbook 20200707
 
 process multiQC{
     label "multiqc"
-    publishDir "${out_path}/reports", mode: 'copy', overwrite: false //
+    publishDir "${out_path}/reports", mode: 'copy', pattern: "multiqc_report.html", overwrite: false
 
     input:
     file "*" from fastqc_log_ch.mix(bowtie2_log_ch).mix(krakenreports).collect()
 
     output:
-    file "*.html"
+    file "multiqc_report.html" into multiqc_ch
+    file "report.rmd" into log_ch12
 
     script:
     """
-    multiqc .
+    multiqc . -n multiqc_report.html
+    echo -e "\\n\\n<br /><br />\\n\\n###  MultiQC\\n\\n" > report.rmd
+    echo -e "Results are published in the [Report](./reports/multiqc_report.html) folder\\n\\n" >> report.rmd
     """
 }
 
@@ -470,7 +486,7 @@ process Q20 { // section 24.2 of the labbook 20200707
     file "read_nb_before" into bow_read_nb_ch
     file "read_nb_after" into q20_read_nb_ch
     file "q20_report.txt"
-    file "report.rmd" into log_ch12
+    file "report.rmd" into log_ch13
 
     script:
     """
@@ -498,7 +514,7 @@ process no_soft_clipping { // section 24.4 of the labbook 20200707
     file bam from q20_ch1
 
     output:
-    file "report.rmd" into log_ch13
+    file "report.rmd" into log_ch14
 
     script:
     """
@@ -524,7 +540,7 @@ process duplicate_removal { // section 24.5 of the labbook 20200707. Warning: US
     file "${file_name}_q20_nodup.bam" into dup_ch1, dup_ch2
     file "dup_read_nb" into dup_read_nb_ch
     file "dup_report.txt"
-    file "report.rmd" into log_ch14
+    file "report.rmd" into log_ch15
 
     script:
     """
@@ -543,7 +559,7 @@ process report1 {
     val file_name
 
     output:
-    file "report.rmd" into log_ch15
+    file "report.rmd" into log_ch16
 
     script:
     """
@@ -635,7 +651,7 @@ process insertion { // section 24.7 of the labbook 20200707
     output:
     file "${file_name}.pos" into orient_ch1, orient_ch2
     file "insertion_report.txt"
-    file "report.rmd" into log_ch16
+    file "report.rmd" into log_ch17
 
     script:
     """
@@ -780,7 +796,7 @@ process report2 {
     val insertion_dist
 
     output:
-    file "report.rmd" into log_ch17
+    file "report.rmd" into log_ch18
 
     script:
     """
@@ -839,7 +855,7 @@ process global_logo { // 24.9.3 of the labbook 20200707
     output:
     file "global_logo_${file_name}.png" into fig_ch7
     file "global_logo_report.txt"
-    file "report.rmd" into log_ch18
+    file "report.rmd" into log_ch19
 
     script:
     """
@@ -871,7 +887,7 @@ process final_insertion_files { // 44.1 of the labbook 20201210
     file "${file_name}_annot.pos" into pos_ch1
     file "${file_name}_annot_insertion.freq"
     file "final_insertion_files_report.txt"
-    file "report.rmd" into log_ch19
+    file "report.rmd" into log_ch20
 
     script:
     """
@@ -903,7 +919,7 @@ process motif { // 43 of the labbook 20201209
     file "motif_sites.pos" into motif_ch
     file "motif_report.txt"
     file "{head,table}*.txt" into motif_table_ch // warning: several files
-    file "report.rmd" into log_ch20
+    file "report.rmd" into log_ch21
 
     script:
     """
@@ -946,7 +962,7 @@ process random_insertion { // sections 44 of the labbook 20201210
     file "obs_rd_insertions.pos" into obs_rd_insertions_pos_ch1
     file "obs_rd_insertions.freq" into obs_rd_insertions_freq_ch1
     file "random_insertion_report.txt"
-    file "report.rmd" into log_ch21
+    file "report.rmd" into log_ch22
 
     script:
     """
@@ -1000,7 +1016,7 @@ process plot_insertion { // sections 24.7.2 and 45 of the labbook 20200520
     output:
     file "*.png" into fig_ch9 // warning: several files
     file "plot_insertion_report.txt"
-    file "report.rmd" into log_ch22
+    file "report.rmd" into log_ch23
 
     script:
     """
@@ -1062,7 +1078,7 @@ process backup {
     output:
     file "${config_file}" // warning message if we use file config_file
     file "${log_file}" // warning message if we use file log_file
-    file "report.rmd" into log_ch23
+    file "report.rmd" into log_ch24
 
     script:
     """
@@ -1078,7 +1094,7 @@ process workflowVersion { // create a file with the workflow version in out_path
     cache 'false'
 
     output:
-    file "report.rmd" into log_ch24
+    file "report.rmd" into log_ch25
 
     script:
     """
@@ -1114,7 +1130,7 @@ process print_report { // section 8.8 of the labbook 20200520
     input:
     val file_name
     val cute_path
-    file report from log_ch0.concat(log_ch1,log_ch2, log_ch3, log_ch4, log_ch5, log_ch6, log_ch7, log_ch8, log_ch9, log_ch10, log_ch11, log_ch12, log_ch13, log_ch14, log_ch15, log_ch16, log_ch17, log_ch18, log_ch19, log_ch20, log_ch21, log_ch22, log_ch23, log_ch24).collectFile(name: 'report.rmd', sort: false)
+    file report from log_ch0.concat(log_ch1,log_ch2, log_ch3, log_ch4, log_ch5, log_ch6, log_ch7, log_ch8, log_ch9, log_ch10, log_ch11, log_ch12, log_ch13, log_ch14, log_ch15, log_ch16, log_ch17, log_ch18, log_ch19, log_ch20, log_ch21, log_ch22, log_ch23, log_ch24, log_ch25).collectFile(name: 'report.rmd', sort: false)
     tuple val ("stat_tempo_name"), file ("stat_tempo") from stat_fastq_5p_filter_ch2
     file table from motif_table_ch // warning: several files
     file png1 from fig_ch1
@@ -1126,6 +1142,7 @@ process print_report { // section 8.8 of the labbook 20200520
     file png7 from fig_ch7
     file png8 from fig_ch8.collect() // warning: several files
     file png9 from fig_ch9.collect() // warning: several files
+    file html from multiqc_ch
 
     output:
     file "report.html"
@@ -1142,6 +1159,7 @@ process print_report { // section 8.8 of the labbook 20200520
     cp ${table} ./files/ # this is to get hard files, not symlinks
     cp ${png1} ${png2} ${png3} ${png4} ${png5} ${png6} ${png7} ${png8} ${png9} ./figures/ # Warning several files
     cp ${png1} ./reports/nf_dag.png # trick to delude the knitting during the print report
+    cp ${html} ./reports/ # this is to get hard files, not symlinks
     print_report.R "${cute_path}" "report_file.rmd" "print_report.txt"
     """
 }

nextflow.config

@@ -73,7 +73,7 @@ env {
 //////// variables that will be used below (and potentially in the main.nf file)
 
 //// must be also exported
-system_exec = 'slurm' // the system that runs the workflow. Either 'local' or 'slurm'
+system_exec = 'local' // the system that runs the workflow. Either 'local' or 'slurm'
 //docker_exe = true // true for docker and false for singularity
 //out_path="/mnt/c/Users/Gael/Desktop" // where the report file will be saved. Example report_path = '.' for where the main.nf run is executed or report_path = '/mnt/c/Users/Gael/Desktop' 
 out_path="$baseDir/results" // where the report file will be saved. Example report_path = '.' for where the main.nf run is executed or report_path = '/mnt/c/Users/Gael/Desktop' 
@@ -159,10 +159,16 @@ dag {
 singularity {
     enabled = true
     autoMounts = true // automatically mounts host paths in the executed container
+    runOptions = '--no-home'
     //runOptions = '--home $HOME:/home/$USER --bind /pasteur' // provide any extra command line options supported by the singularity exec. HEre, fait un bind de tout /pasteur dans /pasteur du container. Sinon pas d accès
-    cacheDir = 'singularity' // name of the directory where remote Singularity images are stored. When rerun, the exec directly uses these without redownloading them. When using a computing cluster it must be a shared folder accessible to all computing nodes
+    if(system_exec == 'slurm'){
+        cacheDir = '/pasteur/zeus/projets/p01/BioIT/gmillot/14985_loot/singularity' // name of the directory where remote Singularity images are stored. When rerun, the exec directly uses these without redownloading them. When using a computing cluster it must be a shared folder accessible to all computing nodes
+    }else{
+        cacheDir = 'singularity'
+    }
 }
 
+
 //////// end Scopes
 
 
@@ -195,11 +201,12 @@ process {
         cpus=1 // only used when name = "local" in the executor part above
         memory='3G' // only used when name = "local" in the executor part above
     }
-
-    withLabel: kraken{
-        container="evolbioinfo/kraken:v2.0.8-beta"
-        cpus=20
-        memory='100G'
+    if(system_exec == 'slurm'){
+        withLabel: kraken{
+            container="evolbioinfo/kraken:v2.0.8-beta"
+            cpus=20
+            memory='100G'
+        }
     }
 
     withLabel: fastqc {