Merge pull request #49 from sanger-tol/reworked_github_test

Reworked GitHub test

.github/workflows/ci.yml

@@ -48,10 +48,6 @@ jobs:
         run: |
           nextflow secrets set NCBI_API_KEY ${{ secrets.NCBI_API_KEY }}
 
-      - name: Download test data
-        run: |
-          curl https://tolit.cog.sanger.ac.uk/test-data/resources/genomeassembly/genomeassembly_test_data.tar.gz | tar xzf -
-
       - name: Setup apptainer
         uses: eWaterCycle/setup-apptainer@main
 
@@ -62,4 +58,4 @@ jobs:
 
       - name: Run pipeline with test data
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_github,singularity --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} -profile test,singularity --outdir ./results

assets/test.yaml

@@ -1,13 +1,16 @@
 dataset:
   id: baUndUnlc1
   illumina_10X:
-    reads: /lustre/scratch123/tol/resources/nextflow/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/10x/
+    reads:
+      - https://tolit.cog.sanger.ac.uk/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/10x/baUndUnlc1_S12_L002_R1_001.fastq.gz
+      - https://tolit.cog.sanger.ac.uk/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/10x/baUndUnlc1_S12_L002_R2_001.fastq.gz
+      - https://tolit.cog.sanger.ac.uk/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/10x/baUndUnlc1_S12_L002_I1_001.fastq.gz
   pacbio:
     reads:
-      - reads: /lustre/scratch124/tol/projects/darwin/users/kk16/development/test/test/HiFi.reads.BIG.fasta
+      - reads: https://tolit.cog.sanger.ac.uk/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/pacbio/fasta/HiFi.reads.fasta
   HiC:
     reads:
-      - reads: /lustre/scratch123/tol/resources/nextflow/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/hic-arima2/41741_2#7.sub.cram
+      - reads: https://tolit.cog.sanger.ac.uk/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/hic-arima2/41741_2%237.sub.cram
 hic_motif: GATC,GANTC,CTNAG,TTAA
 hic_aligner: bwamem2
 busco:
@@ -16,6 +19,6 @@ mito:
   species: Caradrina clavipalpis
   min_length: 15000
   code: 5
-  fam: /lustre/scratch124/tol/projects/darwin/users/cz3/organelle_asm/hmm_db/insecta_mito.fam
+  fam: https://github.com/c-zhou/OatkDB/raw/main/v20230921/insecta_mito.fam
 plastid:
-  fam: /lustre/scratch124/tol/projects/darwin/users/cz3/organelle_asm/hmm_db/acrogymnospermae_pltd.fam
+  fam: https://github.com/c-zhou/OatkDB/raw/main/v20230921/acrogymnospermae_pltd.fam

bin/generate_cram_csv.sh

@@ -12,8 +12,9 @@ for cram in "$@"; do
     rgline=$(samtools view -H $cram|grep "RG"|sed 's/\t/\\t/g'|sed "s/'//g")
 
     crampath=$(readlink -f ${cram})
+    craipath=$(readlink -f ${cram}.crai)
 
-    ncontainers=$(zcat ${crampath}.crai|wc -l)
+    ncontainers=$(zcat ${craipath} | wc -l)
     base=$(basename $cram .cram)
 
     from=0
@@ -22,15 +23,15 @@ for cram in "$@"; do
 
     while [ $to -lt $ncontainers ]
     do
-        echo $crampath,${crampath}.crai,${from},${to},${base},${chunkn},${rgline}
+        echo $crampath,${craipath},${from},${to},${base},${chunkn},${rgline}
         from=$((to+1))
         ((to+=10000))
         ((chunkn++))
     done
 
     if [ $from -le $ncontainers ]
     then
-        echo $crampath,${crampath}.crai,${from},${ncontainers},${base},${chunkn},${rgline}
+        echo $crampath,${craipath},${from},${ncontainers},${base},${chunkn},${rgline}
         ((chunkn++))
     fi
 done

conf/modules.config

@@ -358,6 +358,9 @@ process {
     // Set up of the polishing pipeline
     if (params.polishing_on) {
         withName: LONGRANGER_MKREF {
+            if(System.getenv('GITHUB_ACTION') != null ) {
+                container = "ghcr.io/sanger-tol/longranger:2.2.2-c4"
+            }
             publishDir = [
                 path: { "${params.outdir}/${meta.id}.${params.hifiasm}/polishing" },
                 mode: params.publish_dir_mode,
@@ -368,6 +371,9 @@ process {
         withName: LONGRANGER_ALIGN {
             // Keep in sync with `longranger_lsf_sanger.config`
             ext.args = "--disable-ui --nopreflight"
+            if(System.getenv('GITHUB_ACTION') != null ) {
+                container = "ghcr.io/sanger-tol/longranger:2.2.2-c4"
+            }
             publishDir = [
                 path: { "${params.outdir}/${meta.id}.${params.hifiasm}/polishing" },
                 mode: params.publish_dir_mode,
@@ -674,33 +680,4 @@ profiles {
             }
         }
     }
-
-    test_github {
-        process {
-            // Set up of the scaffolding pipeline
-            withName: 'YAHS' {
-                // Skip the initial assembly error correction step
-                ext.args = '-r 1000,2000,5000'
-            }
-
-            withName: '.*HIFIASM.*' {
-                // Skip bloom filter
-                ext.args = '--primary -f0'
-            }
-
-            withName: '.*OATK' {
-                // Set kmer size and minimal coverage
-                ext.args = "-k1001 -c5 -Ttmp"
-            }
-
-            if (params.polishing_on) {
-                withName: LONGRANGER_MKREF {
-                    container = "ghcr.io/sanger-tol/longranger:2.2.2-c4"
-                }
-                withName: LONGRANGER_ALIGN {
-                    container = "ghcr.io/sanger-tol/longranger:2.2.2-c4"
-                }
-            }
-        }
-    }
 }

conf/test.config

@@ -14,15 +14,14 @@ params {
     config_profile_name        = 'Test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
+    // Match resource limits with the ubuntu2204-4c runner
+    max_cpus   = 4
+    max_memory = '15.GB'
     max_time   = '6.h'
 
     // Input data
     input = "${projectDir}/assets/test.yaml"
     bed_chunks_polishing = 2
     organelles_on = true
-    polishing_on = true
     hifiasm_hic_on = true
 }

docs/usage.md

@@ -86,17 +86,12 @@ mito:
 The pipeline can be tested locally using a provided small test dataset:
 
 ```
-cd ${GENOMEASSEMBLY_TEST_DATA}
-curl https://darwin.cog.sanger.ac.uk/genomeassembly_test_data.tar.gz | tar xzf -
-
 git clone [email protected]:sanger-tol/genomeassembly.git
 cd genomeassembly/
-sed -i "s|/home/runner/work/genomeassembly/genomeassembly|${GENOMEASSEMBLY_TEST_DATA}|" assets/test_github.yaml
-nextflow run main.nf -profile test_github,singularity --outdir ${OUTDIR} {OTHER ARGUMENTS}
+nextflow run main.nf -profile test,singularity --outdir ${OUTDIR} {OTHER ARGUMENTS}
 ```
 
-These command line steps will download and decompress the test data first, then download the pipeline and modify YAML so that it matches dataset location in your file system.
-The last command line runs the test.
+These command line steps will download the pipeline and run the test.
 
 You should now be able to run the pipeline as you see fit.
 

modules/local/generate_cram_csv.nf

@@ -13,7 +13,7 @@ process GENERATE_CRAM_CSV {
         'biocontainers/samtools:1.17--h00cdaf9_0' }"
 
     input:
-    tuple val(meta), path(crampaths, stageAs: "?/*")
+    tuple val(meta), path(crampaths, stageAs: "?/*"), path(craipaths, stageAs: "?/*")
 
 
     output:
@@ -23,7 +23,7 @@ process GENERATE_CRAM_CSV {
     script:
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
-    generate_cram_csv.sh $crampaths >> ${prefix}_cram.csv
+    generate_cram_csv.sh $crampaths > ${prefix}_cram.csv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/longranger/align/main.nf

@@ -11,7 +11,7 @@ process LONGRANGER_ALIGN {
 
     input:
     tuple val(meta), path(reference)
-    path(fastqs)
+    path(fastqs, stageAs: "10X_inputs/*")
 
     output:
     tuple val(meta), path("${meta.id}/outs/possorted_bam.bam"), emit: bam
@@ -26,7 +26,7 @@ process LONGRANGER_ALIGN {
     def args = task.ext.args ?: ''
     def sample = "${meta.id}"
     """
-    longranger align --id=$sample --fastqs=$fastqs \
+    longranger align --id=$sample --fastqs=10X_inputs \
         --sample=$sample --reference=$reference \
         ${args}