toying with some nf-schema functionality, making small additions, removing dangling subworkflows

Author: number-25

CITATIONS.md

@@ -36,7 +36,7 @@
 
 - [alfred](https://www.gear-genomics.com/docs/alfred/)
 
-  >  Rausch, T., Fritz, M.H., Korbel, J.O. and Benes, V. Alfred: interactive multi-sample BAM alignment statistics, feature counting and feature annotation for long- and short-read sequencing. Bioinformatics. 2019 Jul 15;35(14):2489-2491. https://doi.org/10.1093/bioinformatics/bty1007
+  > Rausch, T., Fritz, M.H., Korbel, J.O. and Benes, V. Alfred: interactive multi-sample BAM alignment statistics, feature counting and feature annotation for long- and short-read sequencing. Bioinformatics. 2019 Jul 15;35(14):2489-2491. https://doi.org/10.1093/bioinformatics/bty1007
 
 - [ngs-bits](https://github.com/imgag/ngs-bits/tree/master)
 

README.md

@@ -21,6 +21,8 @@ Nanopore Technologies (ONT) libraries. It is recommended to provide raw FASTQ
 files to the pipeline, however, it will also accept already mapped sequencing
 reads in BAM format. These are provided to the samplesheet as input.
 
+The general flow of the pipeline is as follows;
+
 <!-- nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 
@@ -60,7 +62,7 @@ CONTROL1,2,data/long_reads_2.fastq.gz
 ```
 
 Each row represents a fastq file. Replicate refers to a technical replicate, biological replicates should be named uniquely. Be sure to pay attention to sample naming, in
-order to avoid duplication and file overwriting.
+order to avoid duplication and file overwriting. The replicate field is optional, the other two are mandatory.
 
 The basic reference files required to run the pipeline are 1) a genome in fasta format, and 2) a transcriptome annotation in gtf format. It is advised that the files be gzipped, but it is fine if they are not.
 

assets/email_template.html

@@ -13,6 +13,7 @@
 params {
     config_profile_name             = 'Test profile'
     config_profile_description      = 'Minimal test dataset to check pipeline function'
+    config_profile_url              = "https://github.com/number-25/LongTranscriptomics/blob/dev/conf/test.config"
 
     // Limit resources so that this can run on GitHub Actions
     max_cpus                        = 2
@@ -44,12 +45,12 @@ params {
     skip_bam_qc                     = false
     skip_nanoq                      = false
     skip_sequali                    = false
-    skip_alredy                     = false
+    skip_alfred                     = false
     skip_cramino                    = false
     skip_samtools_flagstat          = false
     skip_ngs_bits                   = true
     ngs_bits_skip_contamination     = true // default: [false]
-    ngs_bits_build                  = 'non_human' // options: [hg38, hg19, non_human]
+    ngs_bits_build                  = 'hg38' // options: [hg38, hg19, non_human]
     cramino_min_length              = 0 // minimum re
     skip_jaccard                    = true
     skip_flair                      = true
@@ -67,22 +68,21 @@ params {
     // TRANSCRIPT QUANTIFICATION
     skip_transcript_quantification  = false
     skip_oarfish                    = false
-    skip_transigner                 = false
     skip_sqanti_all                 = true
     skip_gffcompare                 = false
     extra_gffcompare_options        = null
     skip_sqanti_qc                  = true
     sqanti_qc_reference             = 'human'
     sqanti_qc_cage                  = true
-    sqanti_qc_cage_path             = '/path/to/cage'
+    sqanti_qc_cage_path             = null
     sqanti_qc_polyA_sites           = true
-    sqanti_qc_polyA_sites_path      = 'path/to/polyA'
+    sqanti_qc_polyA_sites_path      = null
     sqanti_qc_polyA_motif           = true
-    sqanti_qc_polyA_motif_path      = 'path/to/polyA/path'
+    sqanti_qc_polyA_motif_path      = null
     sqanti_qc_intron_junctions      = true
-    sqanti_qc_intron_path           = 'path/to/intro/path'
+    sqanti_qc_intron_path           = null
     extra_sqanti_qc_options         = null
-
+    help                            = false
 }
 
 includeConfig "../modules/local/isoquant/isoquant/test_nextflow.config"

conf/test.config

@@ -66,7 +66,6 @@ params {
     // TRANSCRIPT QUANTIFICATION
     skip_transcript_quantification  = false
     skip_oarfish                    = false
-    skip_transigner                 = false
     // TRANSCRIPTOME ASSESSMENT
     skip_gffcompare                 = false
     extra_gffcompare_options        = null
@@ -82,4 +81,5 @@ params {
     sqanti_qc_intron_junctions      = false
     sqanti_qc_intron_path           = null
     extra_sqanti_qc_options         = null
+    help                            = false
 }

conf/test_full.config

@@ -24,11 +24,11 @@ CONTROL1,1,data/long_reads_1.fastq.gz
 CONTROL1,2,data/long_reads_2.fastq.gz
 ```
 
-| Column                    | Description                                                              |
-| ------------------------- | ------------------------------------------------------------------------ |
-| `sample`                  | Sample name.                                                             |
-| `replicate`               | Technical replicate number                                               |
-| `read_path`               | Full path to fastq reads.                                                |
+| Column      | Description                |
+| ----------- | -------------------------- |
+| `sample`    | Sample name.               |
+| `replicate` | Technical replicate number |
+| `read_path` | Full path to fastq reads.  |
 
 An [example samplesheet](../assets/samplesheet.csv) has been provided with the pipeline.
 

docs/usage.md

@@ -10,72 +10,37 @@
 
 nextflow.enable.dsl = 2
 
-/*
-========================================================================================
-    VALIDATE & PRINT PARAMETER SUMMARY
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-//WorkflowMain.initialise(workflow, params, log)
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-//include { DIRECTRNA } from './workflows/directrna'
-//include { PREPARE_REFERENCE } from './subworkflows/local/prepare_reference'
-//include { PIPELINE_INITIALISATION } from 'subworkflows/local/utils_nfcore_directrna_pipeline'
-//include { PIPELINE_COMPLETION     } from 'subworkflows/local/utils_nfcore_directrna_pipeline'
-//include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_directrna_pipeline'
-
-/*
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    GENOME PARAMETER VALUES
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-*/
-
-//nf-core: Remove this line if you don't need a FASTA file
-//   This is an example of how to use getGenomeAttribute() to fetch parameters
-//   from igenomes.config using `--genome`
-//params.genome_fasta = getGenomeAttribute('fasta')
-
-    //
-    // SUBWORKFLOW: Prepare reference genome files
-    //
-    //PREPARE_REFERENCE
-
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     NAMED WORKFLOWS FOR PIPELINE
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { DIRECTRNA } from './workflows/directrna'
+include { DIRECTRNA             } from './workflows/directrna'
+include { validateParameters    } from 'plugin/nf-schema'
+include { paramsSummaryLog      } from 'plugin/nf-schema'
 
-//
-// WORKFLOW: Run main analysis pipeline depending on type of input
-//
 workflow{
-    DIRECTRNA ()
-        //samplesheet
-    }
-    //take:
-    //samplesheet // channel: samplesheet read in from --input
-
-    //main:
 
     //
-    // WORKFLOW: Run pipeline
+    // nf-scheme validations
     //
 
+    validateParameters()
+    log.info paramsSummaryLog(workflow)
+
+    if (params.help) {
+        log.info paramsHelp(
+            beforeText: "Welcome to LongTranscriptomics, I see you are seeking help.",
+            afterText: "Farewell, hopefully this was helpful.",
+            command: "nextflow run . -profile <profile> --outdir <outdir>",
+        )
+        exit 0
+    }
 
-    //emit:
-    //multiqc_report = DIRECTRNA.out.multiqc_report // channel: /path/to/multiqc_report.html
 
-//}
+    DIRECTRNA ()
+}
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN MAIN WORKFLOW
@@ -98,18 +63,6 @@ workflow {
         params.outdir,
         params.input
     )
-
-    //
-    // WORKFLOW: Run main workflow
-    //
-    //MEDGEN_DIRECTRNA (
-    //    PIPELINE_INITIALISATION.out.samplesheet
-    )
-
-    //
-    // SUBWORKFLOW: Run completion tasks
-    //
-
     PIPELINE_COMPLETION (
         params.email,
         params.email_on_fail,