Test profile setup

assets/samplesheet.csv

@@ -1,3 +1,5 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+id,data_directory,mt_cc_rm_genes
+0dpa,./assets/test_data/0dpa/,./auxillaryGeneFiles/danioRerio.aux.features.csv
+1dpa,./assets/test_data/1dpa/,./auxillaryGeneFiles/danioRerio.aux.features.csv
+2dpa,./assets/test_data/2dpa/,./auxillaryGeneFiles/danioRerio.aux.features.csv
+4dpa,./assets/test_data/4dpa/,./auxillaryGeneFiles/danioRerio.aux.features.csv

assets/segmentation.csv

@@ -0,0 +1,37 @@
+id,kidney,spleen,lungs,all
+Old_O1_kidney_88w_rep1,true,false,false,true
+Old_O1_lung_88w_rep1,false,false,true,true
+Old_O1_lung_88w_rep2,false,false,true,true
+Old_O1_spleen_88w_rep1,false,true,false,true
+Old_O1_spleen_88w_rep2,false,true,false,true
+Old_O2_kidney_91w_rep1,true,false,false,true
+Old_O2_kidney_91w_rep2,true,false,false,true
+Old_O2_lung_91w_rep1,false,false,true,true
+Old_O2_lung_91w_rep2,false,false,true,true
+Old_O2_spleen_91w_rep1,false,true,false,true
+Old_O2_spleen_91w_rep2,false,true,false,true
+Old_O3_kidney_93w_rep1,true,false,false,true
+Old_O3_lung_93w_rep1,false,false,true,true
+Old_O3_spleen_93w_rep1,false,true,false,true
+Old_O3_spleen_93w_rep2,false,true,false,true
+Young_Y1_kidney_29w_rep1,true,false,false,true
+Young_Y1_kidney_29w_rep2,true,false,false,true
+Young_Y1_spleen_29w_rep1,false,true,false,true
+Young_Y3_kidney_31w_rep1,true,false,false,true
+Young_Y3_kidney_31w_rep2,true,false,false,true
+Young_Y3_lung_31w_rep1,false,false,true,true
+Young_Y3_lung_31w_rep2,false,false,true,true
+Young_Y3_spleen_31w_rep1,false,true,false,true
+Young_Y3_spleen_31w_rep2,false,true,false,true
+Young_Y4_kidney_34w_rep1,true,false,false,true
+Young_Y4_kidney_34w_rep2,true,false,false,true
+Young_Y4_lung_34w_rep1,false,false,true,true
+Young_Y4_lung_34w_rep2,false,false,true,true
+Young_Y4_spleen_34w_rep1,false,true,false,true
+Young_Y4_spleen_34w_rep2,false,true,false,true
+Young_Y5_kidney_34w_rep1,true,false,false,true
+Young_Y5_kidney_34w_rep2,true,false,false,true
+Young_Y5_lung_34w_rep1,false,false,true,true
+Young_Y5_lung_34w_rep2,false,false,true,true
+Young_Y5_spleen_34w_rep1,false,true,false,true
+Young_Y5_spleen_34w_rep2,false,true,false,true

conf/test.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/scscape -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/scscape -profile test<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */
@@ -14,16 +14,40 @@ params {
     config_profile_name        = 'Test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
+
+    segmentation_sheet = "${projectDir}/assets/segmentation.csv"
+    gene_identifier = "gene_name"
+    min_cells = 3
+    min_features = 200
+
+    nfeature_lower = 10
+    nfeature_upper = 0
+    ncount_lower = 10
+    ncount_upper = 0
+    max_mito_pct = 10
+
+    vars_2_regress = "nCount_RNA,nFeature_RNA,percent.mt,S.Score,G2M.Score"
+
+    features_2_scale = "VF"
+    scale_method = "SCT"
+
+    pcMax = null
+
+    integration_method = Harmony
+
+    resolutions = "0.05,0.1,0.3,0.5,0.7,0.9,1.2,1.5"
+
+    makeLoupe = true
+    eula_agreement = "Agree"
+
     // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
+    max_cpus   = 4
+    max_memory = '10.GB'
     max_time   = '6.h'
 
     // Input data
     // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
     // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
+    input  = "${projectDir}/assets/samplesheet.csv"
 
-    // Genome references
-    genome = 'R64-1-1'
 }

modules/local/feature_naming/feature_naming.nf

@@ -0,0 +1,45 @@
+process FEATURE_NAMING {
+
+    tag "${meta.id}"
+    label 'process_low'
+
+    conda "conda-forge::python=3.9.5"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/python:3.9--1' :
+        'quay.io/rgrindle/convert_gn_nms:latest' }"
+
+    input:
+    tuple val(meta), path(sample_files)
+    tuple val(meta), path(gene_list)
+
+    output:
+    tuple val(meta), path (sample_files), path ("AuxGeneList.csv"), emit: data
+    path("versions.yml"), emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+
+    while true; do
+        sleep 1
+    done
+    convert.py ${sample_files}/features.tsv.gz $gene_list
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        BASH: \$(echo \$(bash --version) )
+    END_VERSIONS
+    """
+
+    stub:
+    """
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        BASH: \$(echo \$(bash --version) )
+    END_VERSIONS
+    """
+
+}
+

segmentation.csv

@@ -1,5 +1,5 @@
-id,00_dpa,04_dpa,all
-00_dpa_1,true,false,true
-00_dpa_2,true,false,true
-04_dpa_1,false,true,true
-04_dpa_2,false,true,true
+id,early,late,all
+0dpa,true,false,true
+1dpa,true,false,true
+2dpa,false,true,true
+4dpa,false,true,true

subworkflows/local/input_check.nf

@@ -2,7 +2,7 @@
 // Check input samplesheet and get read channels
 //
 
-include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check'
+include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check/samplesheet_check'
 
 workflow INPUT_CHECK {
     take:

workflows/scscape.nf

@@ -37,18 +37,18 @@ ch_multiqc_custom_methods_description = params.multiqc_methods_description ? fil
 // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
 //
 include { INPUT_CHECK          } from '../subworkflows/local/input_check'
-include { MAKE_SEURAT          } from '../modules/local/makeseurat.nf'
-include { NORMALIZE_QC         } from '../modules/local/normalize_qc.nf'
-include { FIND_DOUBLETS        } from '../modules/local/doubletfinder.nf'
-include { MERGE_SO             } from '../modules/local/merge.nf'
-include { MERGE_SO as SCALE_SO } from '../modules/local/merge.nf'
-include { RUN_PCA as PCA_MULT  } from '../modules/local/runpca.nf'
-include { RUN_PCA as PCA_SING  } from '../modules/local/runpca.nf'
-include { INTEGRATION          } from '../modules/local/integration.nf'
-include { FIND_NN_CLUSTER      } from '../modules/local/find_NN_clusters.nf'
-include { DISPLAY_REDUCTION    } from '../modules/local/plotting.nf'
-include { GZIP                 } from '../modules/local/gzip.nf'
-include { FEATURE_NAMING       } from '../modules/local/feature_naming.nf'
+include { MAKE_SEURAT          } from '../modules/local/makeseurat/makeseurat.nf'
+include { NORMALIZE_QC         } from '../modules/local/normalize_qc/normalize_qc.nf'
+include { FIND_DOUBLETS        } from '../modules/local/doubletfinder/doubletfinder.nf'
+include { MERGE_SO             } from '../modules/local/merge/merge.nf'
+include { MERGE_SO as SCALE_SO } from '../modules/local/merge/merge.nf'
+include { RUN_PCA as PCA_MULT  } from '../modules/local/runpca/runpca.nf'
+include { RUN_PCA as PCA_SING  } from '../modules/local/runpca/runpca.nf'
+include { INTEGRATION          } from '../modules/local/integration/integration.nf'
+include { FIND_NN_CLUSTER      } from '../modules/local/find_NN_clusters/find_NN_clusters.nf'
+include { DISPLAY_REDUCTION    } from '../modules/local/plotting/plotting.nf'
+include { GZIP                 } from '../modules/local/gzip/gzip.nf'
+include { FEATURE_NAMING       } from '../modules/local/feature_naming/feature_naming.nf'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -135,18 +135,26 @@ workflow SCSCAPE {
             ch_updated_meta.map { [ it[0], it[1] ] },
             ch_updated_meta.map { [ it[0], it[2] ] }
         )
-    }
-
-
-    ch_init_rds = MAKE_SEURAT (
+        ch_init_rds = MAKE_SEURAT (
         ch_updated_features.data.map{ [ it[0], it[1] ] },
         ch_updated_features.data.map{ [ it[0], it[2] ] },
         params.min_cells,
         params.min_features,
         params.gene_identifier
-    )
-    ch_init_rds.rds.join(ch_updated_meta).set { ch_init_rds_meta }
-    ch_validation_log.mix(ch_init_rds.log).set{ ch_validation_log }
+        )
+        ch_init_rds.rds.join(ch_updated_meta).set { ch_init_rds_meta }
+        ch_validation_log.mix(ch_init_rds.log).set{ ch_validation_log }
+    } else {
+        ch_init_rds = MAKE_SEURAT (
+        ch_updated_meta.map{ [ it[0], it[1] ] },
+        ch_updated_meta.map{ [ it[0], it[2] ] },
+        params.min_cells,
+        params.min_features,
+        params.gene_identifier
+        )
+        ch_init_rds.rds.join(ch_updated_meta).set { ch_init_rds_meta }
+        ch_validation_log.mix(ch_init_rds.log).set{ ch_validation_log }
+    }
 
     ch_normalized_qc = NORMALIZE_QC (
         ch_init_rds_meta.map { [it[0], it[1]] },