Record types [wip]

Author: bentsherman

main.nf

@@ -21,15 +21,259 @@ include { PIPELINE_COMPLETION         } from './subworkflows/local/utils_nfcore_
 include { getGenomeAttribute          } from './subworkflows/local/utils_nfcore_methylseq_pipeline'
 include { METHYLSEQ                   } from './workflows/methylseq/'
 
+include { Sample                      } from './subworkflows/nf-core/fastq_align_dedup_bismark/main'
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     GENOME PARAMETER VALUES
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
-params.fasta         = getGenomeAttribute('fasta')
-params.fasta_index   = getGenomeAttribute('fasta_index')
-params.bwameth_index = getGenomeAttribute('bwameth')
-params.bismark_index = params.aligner == 'bismark_hisat' ? getGenomeAttribute('bismark_hisat2') : getGenomeAttribute('bismark')
+
+params {
+
+    // Path to comma-separated file containing information about the samples in the experiment.
+    input                        : String
+
+    // The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.
+    outdir                       : String
+
+    // Email address for completion summary.
+    email                        : String
+
+    // MultiQC report title. Printed as page header, used for filename if not otherwise specified.
+    multiqc_title                : String
+
+    // Save reference(s) to results directory
+    save_reference               : Boolean
+
+    // Save aligned intermediates to results directory
+    save_align_intermeds         : Boolean
+
+    // Bismark only - Save unmapped reads to FastQ files
+    unmapped                     : Boolean
+
+    // Save trimmed reads to results directory.
+    save_trimmed                 : Boolean
+
+    // Name of iGenomes reference.
+    genome                       : String
+
+    // Path to FASTA genome file
+    fasta                        : Path = getGenomeAttribute('fasta')
+
+    // Path to Fasta index file.
+    fasta_index                  : Path = getGenomeAttribute('fasta_index')
+
+    // Path to a directory containing a Bismark reference index.
+    bismark_index                : Path = params.aligner == 'bismark_hisat' ? getGenomeAttribute('bismark_hisat2') : getGenomeAttribute('bismark')
+
+    // bwameth index filename base
+    bwameth_index                : Path = getGenomeAttribute('bwameth')
+
+    // Do not load the iGenomes reference config.
+    igenomes_ignore              : Boolean
+
+    // The base path to the igenomes reference files
+    igenomes_base                : String = 's3://ngi-igenomes/igenomes/'
+
+    // Alignment tool to use.
+    aligner                      : String = 'bismark'
+
+    // Use BWA-MEM2 algorithm for BWA-Meth indexing and alignment.
+    use_mem2                     : Boolean = false
+
+    // Preset for working with PBAT libraries.
+    pbat                         : Boolean
+
+    // Turn on if dealing with MspI digested material.
+    rrbs                         : Boolean
+
+    // Run bismark in SLAM-seq mode.
+    slamseq                      : Boolean
+
+    // Preset for EM-seq libraries.
+    em_seq                       : Boolean
+
+    // Trimming preset for single-cell bisulfite libraries.
+    single_cell                  : Boolean
+
+    // Trimming preset for the Accel kit.
+    accel                        : Boolean
+
+    // Trimming preset for the Zymo kit.
+    zymo                         : Boolean
+
+    // Trim bases from the 5' end of read 1 (or single-end reads).
+    clip_r1                      : Integer = 0
+
+    // Trim bases from the 5' end of read 2 (paired-end only).
+    clip_r2                      : Integer = 0
+
+    // Trim bases from the 3' end of read 1 AFTER adapter/quality trimming.
+    three_prime_clip_r1          : Integer = 0
+
+    // Trim bases from the 3' end of read 2 AFTER adapter/quality trimming
+    three_prime_clip_r2          : Integer = 0
+
+    // Trim bases below this quality value from the 3' end of the read, ignoring high-quality G bases
+    nextseq_trim                 : Integer = 0
+
+    // Discard reads that become shorter than INT because of either quality or adapter trimming.
+    length_trim                  : Integer
+
+    // Skip presetting trimming parameters entirely
+    skip_trimming_presets        : Boolean = false
+
+    // Run alignment against all four possible strands.
+    non_directional              : Boolean
+
+    // Output stranded cytosine report, following Bismark's bismark_methylation_extractor step.
+    cytosine_report              : Boolean
+
+    // Turn on to relax stringency for alignment (set allowed penalty with --num_mismatches).
+    relax_mismatches             : Boolean
+
+    // 0.6 will allow a penalty of bp * -0.6 - for 100bp reads (bismark default is 0.2)
+    num_mismatches               : Float = 0.6
+
+    // Specify a minimum read coverage to report a methylation call
+    meth_cutoff                  : Integer
+
+    // Ignore read 2 methylation when it overlaps read 1
+    no_overlap                   : Boolean = true
+
+    // Ignore methylation in first n bases of 5' end of R1
+    ignore_r1                    : Integer = 0
+
+    // Ignore methylation in first n bases of 5' end of R2
+    ignore_r2                    : Integer = 2
+
+    // Ignore methylation in last n bases of 3' end of R1
+    ignore_3prime_r1             : Integer = 0
+
+    // Ignore methylation in last n bases of 3' end of R2
+    ignore_3prime_r2             : Integer = 2
+
+    // Supply a .gtf file containing known splice sites (bismark_hisat only).
+    known_splices                : String
+
+    // Allow soft-clipping of reads (potentially useful for single-cell experiments).
+    local_alignment              : Boolean
+
+    // The minimum insert size for valid paired-end alignments.
+    minins                       : Integer
+
+    // The maximum insert size for valid paired-end alignments.
+    maxins                       : Integer
+
+    // Sample is NOMe-seq or NMT-seq. Runs coverage2cytosine.
+    nomeseq                      : Boolean
+
+    // Merges methylation calls for every strand into a single, context dependent file.
+    comprehensive                : Boolean
+
+    // Call methylation in all three CpG, CHG and CHH contexts.
+    all_contexts                 : Boolean
+
+    // Merges methylation metrics of the Cytosines in a given context.
+    merge_context                : Boolean
+
+    // Specify a minimum read coverage for MethylDackel to report a methylation call.
+    min_depth                    : Integer = 0
+
+    // MethylDackel - ignore SAM flags
+    ignore_flags                 : Boolean
+
+    // Save files for use with methylKit
+    methyl_kit                   : Boolean
+
+    // A GFF or BED file containing the target regions which will be passed to Qualimap/Bamqc.
+    bamqc_regions_file           : String
+
+    // A BED file containing the target regions
+    target_regions_file          : String
+
+    // Run Picard CollectHsMetrics in the targeted analysis
+    collecthsmetrics             : Boolean
+
+    // Skip read trimming.
+    skip_trimming                : Boolean
+
+    // Skip deduplication step after alignment.
+    skip_deduplication           : Boolean
+
+    // Skip FastQC
+    skip_fastqc                  : Boolean
+
+    // Skip MultiQC
+    skip_multiqc                 : Boolean
+
+    // Run preseq/lcextrap tool
+    run_preseq                   : Boolean
+
+    // Run qualimap/bamqc tool
+    run_qualimap                 : Boolean
+
+    // Run advanced analysis for targeted methylation kits with enrichment of specific regions
+    run_targeted_sequencing      : Boolean
+
+    // Git commit id for Institutional configs.
+    custom_config_version        : String = 'master'
+
+    // Base directory for Institutional configs.
+    custom_config_base           : String = 'https://raw.githubusercontent.com/nf-core/configs/master'
+
+    // Institutional config name.
+    config_profile_name          : String
+
+    // Institutional config description.
+    config_profile_description   : String
+
+    // Institutional config contact information.
+    config_profile_contact       : String
+
+    // Institutional config URL link.
+    config_profile_url           : String
+
+    // Display version and exit.
+    version                      : Boolean
+
+    // Method used to save pipeline results to output directory.
+    publish_dir_mode             : String = 'copy'
+
+    // Email address for completion summary, only when pipeline fails.
+    email_on_fail                : String
+
+    // Send plain-text email instead of HTML.
+    plaintext_email              : Boolean
+
+    // File size limit when attaching MultiQC reports to summary emails.
+    max_multiqc_email_size       : String = '25.MB'
+
+    // Do not use coloured log outputs.
+    monochrome_logs              : Boolean
+
+    // Incoming hook URL for messaging service
+    hook_url                     : String
+
+    // Custom config file to supply to MultiQC.
+    multiqc_config               : String
+
+    // Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file
+    multiqc_logo                 : String
+
+    // Custom MultiQC yaml file containing HTML including a methods description.
+    multiqc_methods_description  : String
+
+    // Boolean whether to validate parameters against the schema at runtime
+    validate_params              : Boolean = true
+
+    // Base URL or local path to location of pipeline test dataset files
+    pipelines_testdata_base_path : String = 'https://raw.githubusercontent.com/nf-core/test-datasets/methylseq/'
+
+    // Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.
+    trace_report_suffix          : String
+}
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -43,27 +287,18 @@ params.bismark_index = params.aligner == 'bismark_hisat' ? getGenomeAttribute('b
 workflow NFCORE_METHYLSEQ {
 
     take:
-    samplesheet // channel: samplesheet read in from --input
+    ch_samples: Channel<Sample>
 
     main:
 
-
-    //
-    // Initialize file channels or values based on params
-    //
-    ch_fasta                = params.fasta         ? channel.fromPath(params.fasta).map{ it -> [ [id:it.baseName], it ] } : channel.empty()
-    ch_or_val_fasta_index   = params.fasta_index   ? channel.fromPath(params.fasta_index).map{ it -> [ [id:it.baseName], it ] } : []
-    ch_or_val_bismark_index = params.bismark_index ? channel.fromPath(params.bismark_index).map{ it -> [ [id:it.baseName], it ] } : []
-    ch_or_val_bwameth_index = params.bwameth_index ? channel.fromPath(params.bwameth_index).map{ it -> [ [id:it.baseName], it ] } : []
-
     //
     // SUBWORKFLOW: Prepare any required reference genome indices
     //
     FASTA_INDEX_BISMARK_BWAMETH(
-        ch_fasta,
-        ch_or_val_fasta_index,
-        ch_or_val_bismark_index,
-        ch_or_val_bwameth_index,
+        params.fasta,
+        params.fasta_index,
+        params.bismark_index,
+        params.bwameth_index,
         params.aligner,
         params.collecthsmetrics,
         params.use_mem2
@@ -74,15 +309,16 @@ workflow NFCORE_METHYLSEQ {
     //
 
     METHYLSEQ (
-        samplesheet,
+        ch_samples,
         FASTA_INDEX_BISMARK_BWAMETH.out.fasta,
         FASTA_INDEX_BISMARK_BWAMETH.out.fasta_index,
         FASTA_INDEX_BISMARK_BWAMETH.out.bismark_index,
         FASTA_INDEX_BISMARK_BWAMETH.out.bwameth_index,
+        params
     )
 
     emit:
-    multiqc_report = METHYLSEQ.out.multiqc_report // channel: [ path(multiqc_report.html )  ]
+    multiqc_report = METHYLSEQ.out.multiqc_report
 
 }
 /*
@@ -98,6 +334,7 @@ workflow {
     // SUBWORKFLOW: Run initialisation tasks
     //
     PIPELINE_INITIALISATION (
+        params.input,
         params.version,
         params.validate_params,
         params.monochrome_logs,