Dsl2 new test configs

conf/test_default.config

@@ -0,0 +1,64 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/eager -profile test_default,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+// TO DO: Change name to test.config once migration is complete.
+params {
+    config_profile_name             = 'Test profile'
+    config_profile_description      = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input                           = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
+
+    // Genome references
+    fasta                           = params.pipelines_testdata_base_path + 'eager/reference/Mammoth/Mammoth_MT_Krause.fasta'
+
+    // Preprocessing
+    preprocessing_tool              = 'adapterremoval'
+
+    // Sharding FASTQ
+    run_fastq_sharding              = true
+    fastq_shard_size                = 5000
+
+    // Mapping
+    mapping_tool                    = 'bwaaln'
+    skip_qualimap                   = false
+
+    // BAM filtering
+    run_bamfiltering                = true
+    bamfiltering_minreadlength      = 30
+    bamfiltering_mappingquality     = 37
+    deduplication_tool              = 'markduplicates'
+
+    // PreSeq
+    mapstats_preseq_mode            = 'c_curve'
+
+    // Damage calculation
+    damagecalculation_tool          = 'damageprofiler'
+    skip_qualimap                   = false
+
+    // Genotyping
+    genotyping_tool                 = 'ug'
+
+    // Metagenomic screening
+    run_metagenomics                = true
+    metagenomics_profiling_tool     = 'metaphlan'
+    metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/metaphlan/metaphlan4_database.tar.gz'
+    metagenomics_run_postprocessing = true
+}

conf/test_humanpopgen.config

@@ -0,0 +1,62 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/eager -profile test_humanpopgen,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+
+    // To avoid pipeline failure due to not having X reads and to not have overcrowded datasets in the test
+    withName: ANGSD_CONTAMINATION {
+        errorStrategy  = { task.exitStatus in [134] ? 'ignore' : 'finish' }
+    }
+}
+
+params {
+    config_profile_name                = 'Test human popgen profile'
+    config_profile_description         = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input                              = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
+
+    // Genome references
+    fasta                              = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
+
+    // Mapping
+    mapping_tool                       = 'bowtie2'
+    convert_inputbam                    = true
+
+    // BAM filtering
+    run_bamfiltering                   = true
+    bamfiltering_minreadlength         = 30
+    bamfiltering_mappingquality        = 37
+
+    // Damage
+    damagecalculation_tool             = 'mapdamage'
+    run_trim_bam                       = true
+
+    // Contamination
+    run_mtnucratio                     = true
+    run_contamination_estimation_angsd = true
+
+    // Genotyping
+    genotyping_tool                    = 'pileupcaller'
+    genotyping_pileupcaller_bedfile    = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
+    genotyping_pileupcaller_snpfile    = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K_covered_in_JK2067_downsampled_s0.1.numeric_chromosomes.snp'
+
+    //Sex Determination
+    run_sexdeterrmine                  = true
+    sexdeterrmine_bedfile              = params.pipelines_testdata_base_path + 'eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
+
+}

conf/test_microbial.config

@@ -0,0 +1,58 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/eager -profile test_microbial,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name             = 'Test microbial profile'
+    config_profile_description      = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input                           = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_PE_only_v3.tsv'
+
+    // Genome references
+    fasta_sheet                     = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
+
+
+    // Preprocessing
+    sequencing_qc_tool              = 'falco'
+    preprocessing_excludeunmerged   = true
+
+    // Mapping
+    mapping_tool                    = 'circularmapper'
+
+    // BAM filtering
+    deduplication_tool              = "dedup"
+    run_bamfiltering                = true
+    bamfiltering_minreadlength      = 30
+    bamfiltering_mappingquality     = 37
+
+    // Metagenomics
+    run_metagenomics                = true
+    metagenomics_profiling_tool     = 'krakenuniq'
+    metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/krakenuniq/testdb-krakenuniq.tar.gz'
+    run_host_removal                = true
+
+    // Manipulate Damage
+    run_mapdamage_rescaling         = true
+
+    // Genotyping
+    genotyping_tool                 = 'freebayes'
+
+
+}

conf/test_modern.config

@@ -0,0 +1,50 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/eager -profile test_modern,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name             = 'Test modern profile'
+    config_profile_description      = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input                           = params.pipelines_testdata_base_path + 'eager/testdata/Human/human_design_bam_eager3.tsv'
+
+    // Genome references
+    fasta                           = params.pipelines_testdata_base_path + 'eager/reference/Human/hs37d5_chr21-MT.fa.gz'
+
+
+    // Preprocessing
+    sequencing_qc_tool              = 'falco'
+    preprocessing_tool              = 'fastp'
+    convert_inputbam                = true
+
+    // Mapping
+    mapping_tool                    = 'bwamem'
+
+    // Metagenomics
+    run_metagenomics                = true
+    metagenomics_complexity_tool    = 'prinseq'
+    metagenomics_profiling_tool     = 'kraken2'
+    metagenomics_profiling_database = params.pipelines_testdata_base_path + 'eager/databases/kraken/eager_test.tar.gz'
+    metagenomics_run_postprocessing = true
+
+    // Genotyping
+    genotyping_tool                 = 'hc'
+
+}

conf/test_shortdna.config

@@ -0,0 +1,51 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/eager -profile test_shortdna,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name                = 'Test very short DNA profile'
+    config_profile_description         = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input  = params.pipelines_testdata_base_path + 'eager/testdata/Mammoth/samplesheet_v3.tsv'
+
+    // Genome references
+    fasta_sheet                        = params.pipelines_testdata_base_path + 'eager/reference/reference_sheet_multiref.csv'
+
+    // Mapping
+    // TO DO: Change when mapAD is there.
+    // mapping_tool                    = 'mapad'
+
+    // Metagenomics
+    run_metagenomics                   = true
+    metagenomics_complexity_tool       = 'bbduk'
+    metagenomics_profiling_tool        = 'malt'
+    metagenomics_profiling_database    = params.pipelines_testdata_base_path + '/eager/databases/malt/eager_test.tar.gz'
+    metagenomics_run_postprocessing    = true
+    metagenomics_maltextract_taxonlist = params.pipelines_testdata_base_path + '/eager/testdata/Mammoth/maltextract/MaltExtract_list.txt'
+    metagenomics_maltextract_ncbidir   = 'https://github.com/rhuebler/HOPS/raw/external/Resources/'
+
+    // Manioulate Damage
+    run_pmd_filtering                  = true
+
+    // Genotyping
+    genotyping_tool                    = 'angsd'
+
+
+}

nextflow.config

@@ -384,15 +384,20 @@ profiles {
     test_full {
         includeConfig 'conf/test_full.config'
     }
-    test            { includeConfig 'conf/test.config'           }
-    test_full       { includeConfig 'conf/test_full.config'      }
-    test_nothing    { includeConfig 'conf/test_nothing.config'   }
-    test_humanbam   { includeConfig 'conf/test_humanbam.config'  }
-    test_multiref   { includeConfig 'conf/test_multiref.config'  }
-    test_kraken2    { includeConfig 'conf/test_kraken2.config'   }
-    test_malt       { includeConfig 'conf/test_malt.config'      }
-    test_krakenuniq { includeConfig 'conf/test_krakenuniq.config'}
-    test_metaphlan  { includeConfig 'conf/test_metaphlan.config' }
+    test             { includeConfig 'conf/test.config'             }
+    test_full        { includeConfig 'conf/test_full.config'        }
+    test_nothing     { includeConfig 'conf/test_nothing.config'     }
+    test_humanbam    { includeConfig 'conf/test_humanbam.config'    }
+    test_multiref    { includeConfig 'conf/test_multiref.config'    }
+    test_kraken2     { includeConfig 'conf/test_kraken2.config'     }
+    test_malt        { includeConfig 'conf/test_malt.config'        }
+    test_krakenuniq  { includeConfig 'conf/test_krakenuniq.config'  }
+    test_metaphlan   { includeConfig 'conf/test_metaphlan.config'   }
+    test_default     { includeConfig 'conf/test_default.config'     }
+    test_modern      { includeConfig 'conf/test_modern.config'      }
+    test_microbial   { includeConfig 'conf/test_microbial.config'   }
+    test_shortdna    { includeConfig 'conf/test_shortdna.config'    }
+    test_humanpopgen { includeConfig 'conf/test_humanpopgen.config' }
 }
 
 // Load nf-core custom profiles from different Institutions

subworkflows/local/utils_nfcore_eager_pipeline/main.nf

@@ -215,7 +215,7 @@ def validateInputParameters() {
     if ( !params.fasta                                     && !params.fasta_sheet ) { exit 1, "[nf-core/eager] ERROR: Neither FASTA file --fasta nor reference sheet --fasta_sheet have been provided."}
     if ( params.fasta                                      && params.fasta_sheet ) { exit 1, "[nf-core/eager] ERROR: A FASTA file --fasta and a reference sheet --fasta_sheet have been provided. These parameters are mutually exclusive."}
     if ( params.preprocessing_adapterlist                  && params.preprocessing_skipadaptertrim ) { log.warn("[nf-core/eager] WARNING: --preprocessing_skipadaptertrim will override --preprocessing_adapterlist. Adapter trimming will be skipped!") }
-    if ( params.deduplication_tool == 'dedup'              && ! params.preprocessing_excludeunmerged ) { exit 1, "[nf-core/eager] ERROR: Dedup can only be used on collapsed (i.e. merged) PE reads. For all other cases, please set --deduplication_tool to 'markduplicates'."}
+    if ( params.deduplication_tool == 'dedup'              && ! params.preprocessing_excludeunmerged ) { exit 1, "[nf-core/eager] ERROR: Dedup can only be used on collapsed (i.e. merged) PE reads without singletons. If you want to use Dedup, please provide --preprocessing_excludeunmerged. For all other cases, please set --deduplication_tool to 'markduplicates'."}
     if ( params.bamfiltering_retainunmappedgenomicbam      && params.bamfiltering_mappingquality > 0  ) { exit 1, ("[nf-core/eager] ERROR: You cannot both retain unmapped reads and perform quality filtering, as unmapped reads have a mapping quality of 0. Pick one or the other functionality.") }
     if ( params.genotyping_source == 'trimmed'             && ! params.run_trim_bam                   ) { exit 1, ("[nf-core/eager] ERROR: --genotyping_source cannot be 'trimmed' unless BAM trimming is turned on with `--run_trim_bam`.") }
     if ( params.genotyping_source == 'pmd'                 && ! params.run_pmd_filtering              ) { exit 1, ("[nf-core/eager] ERROR: --genotyping_source cannot be 'pmd' unless PMD-filtering is ran.") }