Merge pull request #67 from seqeralabs/Final_changes_22Mar2022

Final changes 22 mar2022

.gitpod.yml

@@ -25,12 +25,13 @@ tasks:
     init: |
       echo 'init script' # runs during prebuild
       echo 'start script'
+
+      
+    command: |
       curl -s https://get.nextflow.io | bash
       chmod +x nextflow
       sudo mv nextflow /usr/local/bin/
       docker pull nextflow/rnaseq-nf
-      
-    command: |
       sudo apt install  -y tree
       sudo apt install  -y graphviz
       unset JAVA_TOOL_OPTIONS

asciidocs/rnaseq_pipeline.adoc

@@ -19,9 +19,9 @@ The script `script1.nf` defines the pipeline input parameters.
 
 [source,nextflow,linenums]
 ----
-params.reads = "$baseDir/data/ggal/*_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/*_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 
 println "reads: $params.reads"
 ----
@@ -45,10 +45,10 @@ that will be used as the pipeline output directory.
 ====
 [source,nextflow,linenums]
 ----
-params.reads = "$baseDir/data/ggal/*_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
-params.outdir = "$baseDir/myresults"
+params.reads = "$projectDir/data/ggal/*_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
+params.outdir = "results"
 ----
 ====
 
@@ -183,7 +183,7 @@ process index {
     input:
     ...
 ----
-Then check it worked, by looking at the script executed in the work directory. Look for the hexidecimal (e.g. work/7f/f285b80022d9f61e82cd7f90436aa4/), Then `cat` the .command.sh.
+Then check it worked, by looking at the script executed in the work directory. Look for the hexidecimal (e.g. work/7f/f285b80022d9f61e82cd7f90436aa4/), Then `cat` the `.command.sh` file.
 ====
 
 [discrete]
@@ -313,7 +313,7 @@ In this script, note how the `index_ch` channel, declared as output in the `inde
 is now used as a channel in the input section.
 
 Also, note how the second input is declared as a `tuple` composed by two elements:
-the `pair_id` and the `reads` in order to match the structure of the items emitted
+the `sample_id` and the `reads` in order to match the structure of the items emitted
 by the `read_pairs_ch` channel.
 
 
@@ -348,7 +348,7 @@ Add a https://www.nextflow.io/docs/latest/process.html#tag[tag] directive to the
 ====
 Add the following before the input declaration:
 ```
-  tag "Salmon on $pair_id"
+  tag "Salmon on $sample_id"
 ```
 ====
 
@@ -531,7 +531,7 @@ the following code:
 ----
   script:
   """
-  fastqc.sh "$pair_id" "$reads" 
+  fastqc.sh "$sample_id" "$reads" 
   """
 ----
 

asciidocs/setup.adoc

@@ -10,6 +10,7 @@ Nextflow can be used on any POSIX compatible system (Linux, OS X, Windows Subsys
 
 * Bash
 * http://www.oracle.com/technetwork/java/javase/downloads/index.html[Java 8 (or later, up to 15)]
+* Git
 
 *Optional requirements for this tutorial*:
 
@@ -40,7 +41,7 @@ Then ensure that the downloaded binary is executable:
 chmod +x nextflow
 ----
 
-or put the nextflow executable into your $PATH (e.g. /usr/bin)
+AND put the nextflow executable into your $PATH (e.g. /usr/local/bin)
 
 === Training material 
 
@@ -49,14 +50,7 @@ in the terminal:
 
 [source,bash,linenums]
 ----
-curl https://s3-eu-west-1.amazonaws.com/seqeralabs.com/public/nf-training.tar.gz | tar xvz
-----
-
-Or alternatively if you have `wget` instead of curl:
-
-[source,bash,linenums]
-----
-wget -q -O- https://s3-eu-west-1.amazonaws.com/seqeralabs.com/public/nf-training.tar.gz | tar xvz
+git clone https://github.com/seqeralabs/nf-training-public.git
 ----
 
 Check the correct installation of `nextflow` by running the following command: 
@@ -123,6 +117,10 @@ image::gitpod.welcome.png[]
 
 **The main window** allows you to view and edit files. Clicking on a file in the explorer will open it within the main window. We can also see the nf-training material in this window, but if you find the space too small you can open it separately in another browser window (https://training.seqera.io/). Finally, if you accidently close the Gitpod training window, you can reopen it by entering `gp preview https://training.seqera.io`.
 
+4. Saving your files in Gitpod to local machine.
+
+To save your files, choose your file of interest, then either use the left/top hand side bar (File/Save As...) or use you're keyboard shortcut to save as (On Mac: CMD, shift, s), then choose `Show local`. This will open up a explorer to choose where to save your file on your local machine.
+
 ### Reopening a Gitpod session
 
 Any running workspace will be automatically stopped after 30 minutes. You can open the environment again by going to https://gitpod.io/workspaces and finding your previous environment, then clicking the three dot button to the right, and selecting Open. 

nf-training/script1.nf

@@ -1,5 +1,5 @@
-params.reads = "$baseDir/data/ggal/gut_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/gut_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 
 println "reads: $params.reads"

nf-training/script2.nf

@@ -1,9 +1,9 @@
 /* 
  * pipeline input parameters 
  */
-params.reads = "$baseDir/data/ggal/*_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/*_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 params.outdir = "results"
 
 log.info """\

nf-training/script3.nf

@@ -1,9 +1,9 @@
 /* 
  * pipeline input parameters 
  */
-params.reads = "$baseDir/data/ggal/gut_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/gut_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 params.outdir = "results"
 
 log.info """\

nf-training/script4.nf

@@ -1,9 +1,9 @@
 /* 
  * pipeline input parameters 
  */
-params.reads = "$baseDir/data/ggal/gut_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/gut_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 params.outdir = "results"
 
 log.info """\
@@ -43,14 +43,14 @@ process quantification {
 
     input:
     path salmon_index from index_ch
-    tuple pair_id, path(reads) from read_pairs_ch
+    tuple val(sample_id), path(reads) from read_pairs_ch
 
     output:
-    path pair_id into quant_ch
+    path sample_id into quant_ch
 
     script:
     """
-    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $pair_id
+    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $sample_id
     """
 }
 

nf-training/script5.nf

@@ -1,9 +1,9 @@
 /* 
  * pipeline input parameters 
  */
-params.reads = "$baseDir/data/ggal/gut_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/gut_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 params.outdir = "results"
 
 log.info """\
@@ -43,29 +43,29 @@ process quantification {
 
     input:
     path salmon_index from index_ch
-    tuple pair_id, path(reads) from read_pairs_ch
+    tuple val(sample_id), path(reads) from read_pairs_ch
 
     output:
-    path pair_id into quant_ch
+    path sample_id into quant_ch
 
     script:
     """
-    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $pair_id
+    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $sample_id
     """
 }
 
 process fastqc {
-    tag "FASTQC on $pair_id"
+    tag "FASTQC on $sample_id"
 
     input:
-    tuple pair_id, path(reads) from read_pairs_ch
+    tuple sample_id, path(reads) from read_pairs_ch
 
     output:
-    path "fastqc_${pair_id}_logs" into fastqc_ch
+    path "fastqc_${sample_id}_logs" into fastqc_ch
 
     script:
     """
-    mkdir fastqc_${pair_id}_logs
-    fastqc -o fastqc_${pair_id}_logs -f fastq -q ${reads}
+    mkdir fastqc_${sample_id}_logs
+    fastqc -o fastqc_${sample_id}_logs -f fastq -q ${reads}
     """  
 }

nf-training/script6.nf

@@ -1,9 +1,9 @@
 /* 
  * pipeline input parameters 
  */
-params.reads = "$baseDir/data/ggal/gut_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/gut_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 params.outdir = "results"
 
 log.info """\
@@ -40,34 +40,34 @@ Channel
     .into { read_pairs_ch; read_pairs2_ch } 
 
 process quantification {
-    tag "$pair_id"
+    tag "$sample_id"
 
     input:
     path salmon_index from index_ch
-    tuple pair_id, path(reads) from read_pairs_ch
+    tuple val(sample_id), path(reads) from read_pairs_ch
 
     output:
-    path pair_id into quant_ch
+    path sample_id into quant_ch
 
     script:
     """
-    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $pair_id
+    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $sample_id
     """
 }
 
 process fastqc {
-    tag "FASTQC on $pair_id"
+    tag "FASTQC on $sample_id"
 
     input:
-    tuple pair_id, path(reads) from read_pairs2_ch
+    tuple val(sample_id), path(reads) from read_pairs2_ch
 
     output:
-    path "fastqc_${pair_id}_logs" into fastqc_ch
+    path "fastqc_${sample_id}_logs" into fastqc_ch
 
     script:
     """
-    mkdir fastqc_${pair_id}_logs
-    fastqc -o fastqc_${pair_id}_logs -f fastq -q ${reads}
+    mkdir fastqc_${sample_id}_logs
+    fastqc -o fastqc_${sample_id}_logs -f fastq -q ${reads}
     """  
 }  
 

nf-training/script7.nf

@@ -1,9 +1,9 @@
 /* 
  * pipeline input parameters 
  */
-params.reads = "$baseDir/data/ggal/gut_{1,2}.fq"
-params.transcriptome_file = "$baseDir/data/ggal/transcriptome.fa"
-params.multiqc = "$baseDir/multiqc"
+params.reads = "$projectDir/data/ggal/gut_{1,2}.fq"
+params.transcriptome_file = "$projectDir/data/ggal/transcriptome.fa"
+params.multiqc = "$projectDir/multiqc"
 params.outdir = "results"
 
 log.info """\
@@ -40,35 +40,35 @@ Channel
     .into { read_pairs_ch; read_pairs2_ch } 
 
 process quantification {
-    tag "$pair_id"
+    tag "$sample_id"
 
     input:
     path salmon_index from index_ch
-    tuple pair_id, path(reads) from read_pairs_ch
+    tuple val(sample_id), path(reads) from read_pairs_ch
 
     output:
-    path pair_id into quant_ch
+    path sample_id into quant_ch
 
     script:
     """
-    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $pair_id
+    salmon quant --threads $task.cpus --libType=U -i $salmon_index -1 ${reads[0]} -2 ${reads[1]} -o $sample_id
     """
 }
 
 process fastqc {
-    tag "FASTQC on $pair_id"
+    tag "FASTQC on $sample_id"
 
     input:
-    tuple pair_id, path(reads) from read_pairs2_ch
+    tuple val(sample_id), path(reads) from read_pairs2_ch
 
     output:
-    path "fastqc_${pair_id}_logs" into fastqc_ch
+    path "fastqc_${sample_id}_logs" into fastqc_ch
 
 
     script:
     """
-    mkdir fastqc_${pair_id}_logs
-    fastqc -o fastqc_${pair_id}_logs -f fastq -q ${reads}
+    mkdir fastqc_${sample_id}_logs
+    fastqc -o fastqc_${sample_id}_logs -f fastq -q ${reads}
     """  
 }