Merge branch 'master' into i18n/hello-world-hello-nextflow

Author: mribeirodantas

.devcontainer/Dockerfile

@@ -0,0 +1,4 @@
+FROM ghcr.io/nextflow-io/training:latest
+
+ENV NXF_VER=24.10.0
+ENV NXF_EDGE=0

.devcontainer/devcontainer.json

@@ -1,10 +1,15 @@
 {
     "name": "nfcore",
-    "image": "ghcr.io/nextflow-io/training:latest",
+    "build": {
+        "dockerfile": "Dockerfile",
+        "context": ".."
+    },
     "remoteUser": "gitpod",
     "features": {
         "ghcr.io/devcontainers/features/docker-outside-of-docker:1": {}
     },
+    "workspaceFolder": "${localWorkspaceFolder}",
+    "workspaceMount": "source=${localWorkspaceFolder},target=${localWorkspaceFolder},type=bind",
     "remoteEnv": {
         "NXF_HOME": "/workspaces/.nextflow",
         "HOST_PROJECT_PATH": "${localWorkspaceFolder}"
@@ -32,5 +37,6 @@
             "label": "Application",
             "onAutoForward": "openPreview"
         }
-    }
+    },
+    "postCreateCommand": "mkdir -p /workspace && ln -s /workspaces /workspace/gitpod"
 }

.github/gitpod.Dockerfile

@@ -47,8 +47,8 @@ RUN curl -fSL https://github.com/seqeralabs/tower-agent/releases/latest/download
 USER gitpod
 
 # Uncomment if we need to pin the Nextflow version
-ENV NXF_EDGE=1
-ENV NXF_VER=24.02.0-edge
+ENV NXF_EDGE=0
+ENV NXF_VER=24.10.0
 
 # Install nextflow, nf-core, Mamba, and pytest-workflow
 RUN conda config --add channels defaults && \

.gitpod.yml

@@ -29,6 +29,8 @@ tasks:
       command: docker pull -q nextflow/rnaseq-nf
 
     - name: Start Nextflow Tutorial
+      env:
+          NXF_HOME: "/workspace/gitpod/.nextflow"
       command: |
           cd hello-nextflow
           source $HOME/.bashrc

docs/advanced/configuration.md

@@ -4,8 +4,8 @@ This is an aspect of Nextflow that can be confusing. There are multiple ways of
 
 This gives us two complications:
 
--   At which location should I be loading a configuration value?
--   Given a particular parameter, how do I know where it was set?
+- At which location should I be loading a configuration value?
+- Given a particular parameter, how do I know where it was set?
 
 ## Precedence
 
@@ -152,15 +152,15 @@ The most common use for dynamic process directives is to enable tasks that fail
 
 To enable this, two directives are needed:
 
--   `maxRetries`
--   `errorStrategy`
+- `maxRetries`
+- `errorStrategy`
 
 The `errorStrategy` directive determines what action Nextflow should take in the event of a task failure (a non-zero exit code). The available options are:
 
--   `terminate`: Nextflow terminates the execution as soon as an error condition is reported. Pending jobs are killed (default)
--   `finish`: Initiates an orderly pipeline shutdown when an error condition is raised, waiting the completion of any submitted job.
--   `ignore`: Ignores processes execution errors.
--   `retry`: Re-submit for execution a process returning an error condition.
+- `terminate`: Nextflow terminates the execution as soon as an error condition is reported. Pending jobs are killed (default)
+- `finish`: Initiates an orderly pipeline shutdown when an error condition is raised, waiting the completion of any submitted job.
+- `ignore`: Ignores processes execution errors.
+- `retry`: Re-submit for execution a process returning an error condition.
 
 If the `errorStrategy` is "retry", then it will retry up to the value of `maxRetries` times.
 

docs/advanced/grouping.md

@@ -256,9 +256,9 @@ process GenotypeOnInterval {
     tuple val(meta), path(bam), path(bed)
 
     output:
-    tuple val(meta), path("genotyped.bam")
+    tuple val(meta), path("genotyped.vcf")
 
-    "cat $bam $bed > genotyped.bam"
+    "cat $bam $bed > genotyped.vcf"
 }
 ```
 
@@ -282,12 +282,12 @@ Finally, we can combine these genotyped bams back using `groupTuple` and another
 ```groovy linenums="1"
 process MergeGenotyped {
     input:
-    tuple val(meta), path("input/in_*_.bam")
+    tuple val(meta), path("input/in_*_.vcf")
 
     output:
-    tuple val(meta), path("merged.genotyped.bam")
+    tuple val(meta), path("merged.genotyped.vcf")
 
-    "cat input/*.bam > merged.genotyped.bam"
+    "cat input/*.vcf > merged.genotyped.vcf"
 }
 ```
 
@@ -331,12 +331,12 @@ MapReads( samples, reference )
 This will return us six bam files - a tumor and normal pair for each of the three samples:
 
 ```output title="Final channel output"
-[[id:sampleB, type:normal], merged.genotyped.bam]
-[[id:sampleB, type:tumor], merged.genotyped.bam]
-[[id:sampleA, type:normal], merged.genotyped.bam]
-[[id:sampleA, type:tumor], merged.genotyped.bam]
-[[id:sampleC, type:normal], merged.genotyped.bam]
-[[id:sampleC, type:tumor], merged.genotyped.bam]
+[[id:sampleB, type:normal], merged.genotyped.vcf]
+[[id:sampleB, type:tumor], merged.genotyped.vcf]
+[[id:sampleA, type:normal], merged.genotyped.vcf]
+[[id:sampleA, type:tumor], merged.genotyped.vcf]
+[[id:sampleC, type:normal], merged.genotyped.vcf]
+[[id:sampleC, type:tumor], merged.genotyped.vcf]
 ```
 
 If we would like to save the output of our `MergeGenotyped` process, we can "publish" the outputs of a process using the `publishDir` directive. We will cover this in more detail on day 2, but try modifying the `MergeGenotyped` process to include the directive:
@@ -346,52 +346,54 @@ process MergeGenotyped {
     publishDir 'results/genotyped'
 
     input:
-    tuple val(meta), path("input/in_*_.bam")
+    tuple val(meta), path("input/in_*_.vcf")
 
     output:
-    tuple val(meta), path("merged.genotyped.bam")
+    tuple val(meta), path("merged.genotyped.vcf")
 
-    "cat input/*.bam > merged.genotyped.bam"
+    "cat input/*.vcf > merged.genotyped.vcf"
 }
 ```
 
 This will publish all of the files in the `output` block of this process to the `results/genotyped` directory.
 
 !!! exercise
-Inspect the contents of the `results` directory. Does this match what you were expecting? What is missing here?
+
+    Inspect the contents of the `results` directory. Does this match what you were expecting? What is missing here?
 
     Can you modify the `MergeGenotyped` process to ensure we are capturing all of the expected output files?
 
     ??? solution
+
         One solution might be to modify the `script` block to ensure that each file has a unique name:
 
         ```groovy
         process MergeGenotyped {
             publishDir 'results/genotyped'
 
             input:
-            tuple val(meta), path("input/in_*_.bam")
+            tuple val(meta), path("input/in_*_.vcf")
 
             output:
-            tuple val(meta), path("*.bam")
+            tuple val(meta), path("*.vcf")
 
-            "cat input/*.bam > ${meta.id}.${meta.type}.genotyped.bam"
+            "cat input/*.vcf > ${meta.id}.${meta.type}.genotyped.vcf"
         }
         ```
 
         Another option might be to use the `saveAs` argument to the `publishDir` directive:
 
         ```groovy
         process MergeGenotyped {
-            publishDir 'results/genotyped', saveAs: { "${meta.id}.${meta.type}.genotyped.bam" }
+            publishDir 'results/genotyped', saveAs: { "${meta.id}.${meta.type}.genotyped.vcf" }
 
             input:
-            tuple val(meta), path("input/in_*_.bam")
+            tuple val(meta), path("input/in_*_.vcf")
 
             output:
-            tuple val(meta), path("merged.genotyped.bam")
+            tuple val(meta), path("merged.genotyped.vcf")
 
-            "cat input/*.bam > merged.genotyped.bam"
+            "cat input/*.vcf > merged.genotyped.vcf"
         }
         ```
 

docs/advanced/index.md

@@ -16,23 +16,23 @@ Let's get started!
 
 By the end of this course you should:
 
--   Describe commonly used and well understood operators
--   Apply good practices for the propagation of metadata
--   Group and split channels
--   Apply Groovy helper classes to Nextflow scripts
--   Sensibly structure workflows
--   Apply layers of configuration to a workflow
+- Describe commonly used and well understood operators
+- Apply good practices for the propagation of metadata
+- Group and split channels
+- Apply Groovy helper classes to Nextflow scripts
+- Sensibly structure workflows
+- Apply layers of configuration to a workflow
 
 ## Audience & prerequisites
 
 Please note that this is **not** a beginner's workshop and familiarity with Nextflow, the command line, and common file formats is assumed.
 
 **Prerequisites**
 
--   A GitHub account
--   Experience with command line
--   Familiarity with Nextflow and Groovy
--   An understanding of common file formats
+- A GitHub account
+- Experience with command line
+- Familiarity with Nextflow and Groovy
+- An understanding of common file formats
 
 ## Follow the training video
 

docs/advanced/introduction.md

@@ -14,23 +14,23 @@ Let's get started!
 
 By the end of this course you should:
 
--   Describe commonly used and well understood operators
--   Apply good practices for the propagation of metadata
--   Group and split channels
--   Apply Groovy helper classes to Nextflow scripts
--   Sensibly structure workflows
--   Apply layers of configuration to a workflow
+- Describe commonly used and well understood operators
+- Apply good practices for the propagation of metadata
+- Group and split channels
+- Apply Groovy helper classes to Nextflow scripts
+- Sensibly structure workflows
+- Apply layers of configuration to a workflow
 
 ## Audience & prerequisites
 
 Please note that this is **not** a beginner's workshop and familiarity with Nextflow, the command line, and common file formats is assumed.
 
 **Prerequisites**
 
--   A GitHub account
--   Experience with command line
--   Familiarity with Nextflow and Groovy
--   An understanding of common file formats
+- A GitHub account
+- Experience with command line
+- Familiarity with Nextflow and Groovy
+- An understanding of common file formats
 
 ## Follow the training video
 

docs/advanced/metadata.md

@@ -2,8 +2,8 @@
 
 A central challenge in a lot of batch-style computation is how to ensure the metadata describing a file remains with the file. Two good rules for handling metadata in Nextflow are:
 
--   Metadata should be explicit - be extremely wary of metadata encoded in filenames
--   Metadata should travel through channels with the data in a tuple element.
+- Metadata should be explicit - be extremely wary of metadata encoded in filenames
+- Metadata should travel through channels with the data in a tuple element.
 
 ## Metadata Import
 

docs/advanced/support.md

@@ -3,6 +3,6 @@ title: Support
 description: Advanced Nextflow Training Workshop
 ---
 
--   Nextflow official documentation is available at [www.nextflow.io/docs/latest](https://www.nextflow.io/docs/latest/)
--   If you have questions, ask on the Seqera Community Forum at [http://community.seqera.io/](http://community.seqera.io/)
--   If you want to chat about Nextflow or plugin development, check the Nextflow Slack at [https://www.nextflow.io/slack-invite.html](https://www.nextflow.io/slack-invite.html)
+- Nextflow official documentation is available at [www.nextflow.io/docs/latest](https://www.nextflow.io/docs/latest/)
+- If you have questions, ask on the Seqera Community Forum at [http://community.seqera.io/](http://community.seqera.io/)
+- If you want to chat about Nextflow or plugin development, check the Nextflow Slack at [https://www.nextflow.io/slack-invite.html](https://www.nextflow.io/slack-invite.html)