Merge branch 'tidy-params' into 'dev'

Tidy params

See merge request epi2melabs/workflows/wf-transcriptomes!283

README.md

@@ -10,10 +10,12 @@ This workflow analyses Oxford Nanopore long-read RNA sequencing data. It uses
 [`bambu`](https://bioconductor.org/packages/bambu/) to build and quantify
 transcript models, can optionally run
 [`SQANTI3`](https://github.com/ConesaLab/SQANTI3) for transcript classification
-and QC, and can optionally run
+and QC, can optionally run
 [`DESeq2`](https://bioconductor.org/packages/DESeq2/) and
 [`DEXSeq`](https://bioconductor.org/packages/DEXSeq/) for differential
-analysis.
+analysis, and will run
+[`modkit`](https://github.com/nanoporetech/modkit) for base modification
+pileups on aligned reads if relevant tags are present.
 
 The workflow supports:
 
@@ -23,6 +25,7 @@ The workflow supports:
 + optional transcript classification and QC with `SQANTI3`
 + differential gene expression with `DESeq2`
 + differential transcript usage with `DEXSeq`
++ base modification pileups with `modkit`
 
 The main transcriptome result is a shared `bambu` model built from all samples
 together. The workflow also produces separate per-sample transcriptomes, so
@@ -48,13 +51,13 @@ sections call out the main differences from the previous workflow version.
 
 Recommended requirements:
 
-+ CPUs = 16
++ CPUs = 32
-+ Memory = 64GB
++ Memory = 96GB
 
 Minimum requirements:
 
-+ CPUs = 8
++ CPUs = 12
-+ Memory = 32GB
++ Memory = 64GB
 
 Approximate run time: Varies with read depth and sample count; expect a small single-sample run to finish in under 30 minutes with the recommended resources.
 
@@ -117,7 +120,6 @@ nextflow run epi2me-labs/wf-transcriptomes \
 	--de_analysis \
 	--direct_rna \
 	--fastq 'wf-transcriptomes-demo/differential_expression_fastq' \
-	--minimap2_index_opts '-k 15' \
 	--ref_annotation 'wf-transcriptomes-demo/gencode.v22.annotation.chr20.gtf' \
 	--ref_genome 'wf-transcriptomes-demo/hg38_chr20.fa' \
 	--sample_sheet 'wf-transcriptomes-demo/sample_sheet.csv' \
@@ -187,14 +189,15 @@ main source of sample names for multiplexed runs and is required for
 + Every row must contain `barcode` and `alias`.
 + `barcode` must use the usual ONT-style naming such as `barcode01`,
   `barcode02`, and the values must be unique.
-+ `alias` is the user-facing sample name, must be unique, and must not begin
++ `alias` is the user-facing sample name, must be unique, must not begin
-  with the word `barcode`.
+  with the word `barcode` and may contain only letters, numbers, `.`, `_` or `-`.
 + If a `type` column is present, it must use one of:
   `test_sample`, `positive_control`, `negative_control`, or
   `no_template_control`.
 + If an `analysis_group` column is present, every row must have a value.
 + For `--de_analysis`, the sheet must also contain the primary condition
-  column, `condition` by default, plus any columns named in `--covariates`.
+  column (`condition` by default, overridable with `--condition_column`),
+  plus any columns named in `--covariates`.
 
 When multiplexed input folders are named by barcode, the workflow matches those
 folder names against the `barcode` column. If the folders are named by alias,
@@ -256,7 +259,7 @@ for DE/DTU.
 ### 7. Transcript sequence generation and QC
 
 Transcript FASTA files are derived from GTF plus genome using `gffread`.
-When `--skip_sqanti` is not set, `SQANTI3` classifies the cohort and per-sample
+`SQANTI3` classifies the cohort and per-sample
 transcriptomes and produces structural QC summaries. The cohort `SQANTI3`
 results live under `cohort/sqanti/`, while per-sample `SQANTI3`
 directories are published under `samples/<alias>/sqanti/`.
@@ -302,27 +305,26 @@ directories:
 
 ## Input parameters
 
-### Input Options
+### Main Options
 
 | Nextflow parameter name  | Type | Description | Help | Default |
 |--------------------------|------|-------------|------|---------|
 | fastq | string | FASTQ reads to analyse. | You can provide a single FASTQ, a folder of FASTQs, or a multiplexed folder containing one sub-folder per sample or barcode. |  |
 | bam | string | BAM or uBAM reads to analyse. | You can provide a single BAM or uBAM, a folder of BAMs, or a multiplexed folder containing one sub-folder per sample or barcode. |  |
-| analyse_unclassified | boolean | Include unclassified reads from multiplexed input directories. |  | False |
-| analyse_fail | boolean | Include fail reads from multiplexed input directories. |  | False |
-| fastq_chunk | integer | Maximum number of reads per ingress chunk. | Useful mainly for testing or for splitting very large inputs into smaller pieces. |  |
-
-
-### Reference Options
-
-| Nextflow parameter name  | Type | Description | Help | Default |
-|--------------------------|------|-------------|------|---------|
 | ref_genome | string | Reference genome FASTA. | Required in both discover and fixed_annotation modes. |  |
 | ref_annotation | string | Reference transcript annotation in GTF or GFF format. | Required in both discover and fixed_annotation modes. |  |
 | transcriptome_mode | string | How bambu should prepare the transcriptome model. | Use discover for reference-guided transcript discovery and quantification, or fixed_annotation for quantification only against the supplied annotation. | discover |
 | direct_rna | boolean | Set this for direct RNA sequencing libraries. |  | False |
 
 
+### Read Filtering Options
+
+| Nextflow parameter name  | Type | Description | Help | Default |
+|--------------------------|------|-------------|------|---------|
+| analyse_unclassified | boolean | Include unclassified reads from multiplexed input directories. |  | False |
+| analyse_fail | boolean | Include fail reads from bam_fail and fastq_fail folders found in sample folders on the input path. |  | False |
+
+
 ### Sample Options
 
 | Nextflow parameter name  | Type | Description | Help | Default |
@@ -331,7 +333,7 @@ directories:
 | sample | string | Single sample name for singleplexed input or to restrict multiplexed analysis to one sample. |  |  |
 
 
-### Analysis Options
+### Differential Expression Analysis Options
 
 | Nextflow parameter name  | Type | Description | Help | Default |
 |--------------------------|------|-------------|------|---------|
@@ -355,12 +357,9 @@ directories:
 |--------------------------|------|-------------|------|---------|
 | threads | integer | Thread count to use for the core workflow processes. |  | 4 |
 | mod_codes | string | Comma-separated modified base codes to pass to modkit pileup. | Provide values accepted by `modkit pileup --modified-bases`, for example `A:a,C:m`. If omitted, the workflow infers `primary_base:mod_code` pairs from the BAM with `modkit modbam check-tags`. |  |
-| minimap2_opts | string | Extra command-line options to pass to minimap2. |  |  |
 | force_alignment | boolean | Force re-alignment of input BAM files. | Read alignment is skipped if the existing sequence names in the aligned BAM match the provided reference. Enable this if the existing alignments used incorrect minimap2 presets (e.g. missing --splice or direct RNA settings). | False |
 | ndr | number | Optional bambu novel discovery rate override. |  |  |
-| skip_sqanti | boolean | Skip SQANTI3 transcript classification and QC. |  | False |
 | sqanti_skip_orf | boolean | Skip ORF prediction during SQANTI3 QC. |  | True |
-| sqanti_extra_args | string | Extra command-line options to pass to SQANTI3. |  |  |
 
 
 
@@ -407,8 +406,8 @@ Output files may be aggregated including information for all samples or provided
 | DTU failure diagnostic | de_analysis/{{ contrast }}/DTU_ANALYSIS_FAILED.txt | Diagnostic details when DEXSeq fails for a contrast. | aggregated |
 | Multiple-testing warning | de_analysis/MULTIPLE_TESTING_WARNING.txt | Family-wise error-rate note generated when multiple contrasts are tested. | aggregated |
 | IGV configuration | igv.json | JSON configuration for viewing the aligned BAMs in IGV. | aggregated |
-| Reference FASTA index | igv_reference/{{ ref_genome_file }}.fai | FAI index for the reference genome published for IGV. | aggregated |
+| Reference FASTA index | reference/{{ ref_genome_file }}.fai | FAI index for the reference genome published for IGV. | aggregated |
-| Reference GZI index | igv_reference/{{ ref_genome_file }}.gzi | GZI index for a compressed reference genome published for IGV. | aggregated |
+| Reference GZI index | reference/{{ ref_genome_file }}.gzi | GZI index for a compressed reference genome published for IGV. | aggregated |
 
 
 

docs/02_introduction.md

@@ -2,10 +2,12 @@ This workflow analyses Oxford Nanopore long-read RNA sequencing data. It uses
 [`bambu`](https://bioconductor.org/packages/bambu/) to build and quantify
 transcript models, can optionally run
 [`SQANTI3`](https://github.com/ConesaLab/SQANTI3) for transcript classification
-and QC, and can optionally run
+and QC, can optionally run
 [`DESeq2`](https://bioconductor.org/packages/DESeq2/) and
 [`DEXSeq`](https://bioconductor.org/packages/DEXSeq/) for differential
-analysis.
+analysis, and will run
+[`modkit`](https://github.com/nanoporetech/modkit) for base modification
+pileups on aligned reads if relevant tags are present.
 
 The workflow supports:
 
@@ -15,6 +17,7 @@ The workflow supports:
 + optional transcript classification and QC with `SQANTI3`
 + differential gene expression with `DESeq2`
 + differential transcript usage with `DEXSeq`
++ base modification pileups with `modkit`
 
 The main transcriptome result is a shared `bambu` model built from all samples
 together. The workflow also produces separate per-sample transcriptomes, so

docs/03_compute_requirements.md

@@ -1,12 +1,12 @@
 Recommended requirements:
 
-+ CPUs = 16
++ CPUs = 32
-+ Memory = 64GB
++ Memory = 96GB
 
 Minimum requirements:
 
-+ CPUs = 8
++ CPUs = 12
-+ Memory = 32GB
++ Memory = 64GB
 
 Approximate run time: Varies with read depth and sample count; expect a small single-sample run to finish in under 30 minutes with the recommended resources.
 

docs/04_install_and_run.md

@@ -50,7 +50,6 @@ nextflow run epi2me-labs/wf-transcriptomes \
 	--de_analysis \
 	--direct_rna \
 	--fastq 'wf-transcriptomes-demo/differential_expression_fastq' \
-	--minimap2_index_opts '-k 15' \
 	--ref_annotation 'wf-transcriptomes-demo/gencode.v22.annotation.chr20.gtf' \
 	--ref_genome 'wf-transcriptomes-demo/hg38_chr20.fa' \
 	--sample_sheet 'wf-transcriptomes-demo/sample_sheet.csv' \

docs/06_pipeline_overview.md

@@ -32,14 +32,15 @@ main source of sample names for multiplexed runs and is required for
 + Every row must contain `barcode` and `alias`.
 + `barcode` must use the usual ONT-style naming such as `barcode01`,
   `barcode02`, and the values must be unique.
-+ `alias` is the user-facing sample name, must be unique, and must not begin
++ `alias` is the user-facing sample name, must be unique, must not begin
-  with the word `barcode`.
+  with the word `barcode` and may contain only letters, numbers, `.`, `_` or `-`.
 + If a `type` column is present, it must use one of:
   `test_sample`, `positive_control`, `negative_control`, or
   `no_template_control`.
 + If an `analysis_group` column is present, every row must have a value.
 + For `--de_analysis`, the sheet must also contain the primary condition
-  column, `condition` by default, plus any columns named in `--covariates`.
+  column (`condition` by default, overridable with `--condition_column`),
+  plus any columns named in `--covariates`.
 
 When multiplexed input folders are named by barcode, the workflow matches those
 folder names against the `barcode` column. If the folders are named by alias,
@@ -101,7 +102,7 @@ for DE/DTU.
 ### 7. Transcript sequence generation and QC
 
 Transcript FASTA files are derived from GTF plus genome using `gffread`.
-When `--skip_sqanti` is not set, `SQANTI3` classifies the cohort and per-sample
+`SQANTI3` classifies the cohort and per-sample
 transcriptomes and produces structural QC summaries. The cohort `SQANTI3`
 results live under `cohort/sqanti/`, while per-sample `SQANTI3`
 directories are published under `samples/<alias>/sqanti/`.

docs/07_input_parameters.md

@@ -1,24 +1,23 @@
-### Input Options
+### Main Options
 
 | Nextflow parameter name  | Type | Description | Help | Default |
 |--------------------------|------|-------------|------|---------|
 | fastq | string | FASTQ reads to analyse. | You can provide a single FASTQ, a folder of FASTQs, or a multiplexed folder containing one sub-folder per sample or barcode. |  |
 | bam | string | BAM or uBAM reads to analyse. | You can provide a single BAM or uBAM, a folder of BAMs, or a multiplexed folder containing one sub-folder per sample or barcode. |  |
-| analyse_unclassified | boolean | Include unclassified reads from multiplexed input directories. |  | False |
-| analyse_fail | boolean | Include fail reads from multiplexed input directories. |  | False |
-| fastq_chunk | integer | Maximum number of reads per ingress chunk. | Useful mainly for testing or for splitting very large inputs into smaller pieces. |  |
-
-
-### Reference Options
-
-| Nextflow parameter name  | Type | Description | Help | Default |
-|--------------------------|------|-------------|------|---------|
 | ref_genome | string | Reference genome FASTA. | Required in both discover and fixed_annotation modes. |  |
 | ref_annotation | string | Reference transcript annotation in GTF or GFF format. | Required in both discover and fixed_annotation modes. |  |
 | transcriptome_mode | string | How bambu should prepare the transcriptome model. | Use discover for reference-guided transcript discovery and quantification, or fixed_annotation for quantification only against the supplied annotation. | discover |
 | direct_rna | boolean | Set this for direct RNA sequencing libraries. |  | False |
 
 
+### Read Filtering Options
+
+| Nextflow parameter name  | Type | Description | Help | Default |
+|--------------------------|------|-------------|------|---------|
+| analyse_unclassified | boolean | Include unclassified reads from multiplexed input directories. |  | False |
+| analyse_fail | boolean | Include fail reads from bam_fail and fastq_fail folders found in sample folders on the input path. |  | False |
+
+
 ### Sample Options
 
 | Nextflow parameter name  | Type | Description | Help | Default |
@@ -27,7 +26,7 @@
 | sample | string | Single sample name for singleplexed input or to restrict multiplexed analysis to one sample. |  |  |
 
 
-### Analysis Options
+### Differential Expression Analysis Options
 
 | Nextflow parameter name  | Type | Description | Help | Default |
 |--------------------------|------|-------------|------|---------|
@@ -51,11 +50,8 @@
 |--------------------------|------|-------------|------|---------|
 | threads | integer | Thread count to use for the core workflow processes. |  | 4 |
 | mod_codes | string | Comma-separated modified base codes to pass to modkit pileup. | Provide values accepted by `modkit pileup --modified-bases`, for example `A:a,C:m`. If omitted, the workflow infers `primary_base:mod_code` pairs from the BAM with `modkit modbam check-tags`. |  |
-| minimap2_opts | string | Extra command-line options to pass to minimap2. |  |  |
 | force_alignment | boolean | Force re-alignment of input BAM files. | Read alignment is skipped if the existing sequence names in the aligned BAM match the provided reference. Enable this if the existing alignments used incorrect minimap2 presets (e.g. missing --splice or direct RNA settings). | False |
 | ndr | number | Optional bambu novel discovery rate override. |  |  |
-| skip_sqanti | boolean | Skip SQANTI3 transcript classification and QC. |  | False |
 | sqanti_skip_orf | boolean | Skip ORF prediction during SQANTI3 QC. |  | True |
-| sqanti_extra_args | string | Extra command-line options to pass to SQANTI3. |  |  |
 
 

docs/08_outputs.md

@@ -36,5 +36,5 @@ Output files may be aggregated including information for all samples or provided
 | DTU failure diagnostic | de_analysis/{{ contrast }}/DTU_ANALYSIS_FAILED.txt | Diagnostic details when DEXSeq fails for a contrast. | aggregated |
 | Multiple-testing warning | de_analysis/MULTIPLE_TESTING_WARNING.txt | Family-wise error-rate note generated when multiple contrasts are tested. | aggregated |
 | IGV configuration | igv.json | JSON configuration for viewing the aligned BAMs in IGV. | aggregated |
-| Reference FASTA index | igv_reference/{{ ref_genome_file }}.fai | FAI index for the reference genome published for IGV. | aggregated |
+| Reference FASTA index | reference/{{ ref_genome_file }}.fai | FAI index for the reference genome published for IGV. | aggregated |
-| Reference GZI index | igv_reference/{{ ref_genome_file }}.gzi | GZI index for a compressed reference genome published for IGV. | aggregated |
+| Reference GZI index | reference/{{ ref_genome_file }}.gzi | GZI index for a compressed reference genome published for IGV. | aggregated |

nextflow.config

@@ -21,17 +21,12 @@ params {
 
     analyse_unclassified = false
     analyse_fail = false
-    fastq_chunk = null
 
     threads = 4
     mod_codes = null
-    minimap2_index_opts = ""
-    minimap2_opts = ""
     force_alignment = false
     ndr = null
-    skip_sqanti = false
     sqanti_skip_orf = true
-    sqanti_extra_args = ""
 
     aws_image_prefix = null
     aws_queue = null
@@ -52,7 +47,6 @@ params {
             "--de_analysis",
             "--direct_rna",
             "--fastq 'wf-transcriptomes-demo/differential_expression_fastq'",
-            "--minimap2_index_opts '-k 15'",
             "--ref_annotation 'wf-transcriptomes-demo/gencode.v22.annotation.chr20.gtf'",
             "--ref_genome 'wf-transcriptomes-demo/hg38_chr20.fa'",
             "--sample_sheet 'wf-transcriptomes-demo/sample_sheet.csv'",

nextflow_schema.json

@@ -9,16 +9,15 @@
   "url": "https://github.com/epi2me-labs/wf-transcriptomes",
   "type": "object",
   "definitions": {
-    "input_options": {
+    "main_options": {
-      "title": "Input Options",
+      "title": "Main Options",
       "type": "object",
-      "description": "Parameters for ingesting read data.",
+      "description": "Parameters for read ingestion, and setting reference and transcriptome construction mode.",
       "properties": {
         "fastq": {
           "type": "string",
           "format": "path",
           "title": "FASTQ",
-          "demo_data": "${projectDir}/test_data/smoke/reads.fastq",
           "description": "FASTQ reads to analyse.",
           "help_text": "You can provide a single FASTQ, a folder of FASTQs, or a multiplexed folder containing one sub-folder per sample or barcode."
         },
@@ -28,49 +27,10 @@
           "description": "BAM or uBAM reads to analyse.",
           "help_text": "You can provide a single BAM or uBAM, a folder of BAMs, or a multiplexed folder containing one sub-folder per sample or barcode."
         },
-        "analyse_unclassified": {
-          "type": "boolean",
-          "default": false,
-          "description": "Include unclassified reads from multiplexed input directories."
-        },
-        "analyse_fail": {
-          "type": "boolean",
-          "default": false,
-          "description": "Include fail reads from multiplexed input directories."
-        },
-        "fastq_chunk": {
-          "type": "integer",
-          "description": "Maximum number of reads per ingress chunk.",
-          "help_text": "Useful mainly for testing or for splitting very large inputs into smaller pieces."
-        }
-      },
-      "allOf": [
-        {
-          "oneOf": [
-            {
-              "required": [
-                "fastq"
-              ]
-            },
-            {
-              "required": [
-                "bam"
-              ]
-            }
-          ]
-        }
-      ]
-    },
-    "reference_options": {
-      "title": "Reference Options",
-      "type": "object",
-      "description": "Reference files and transcriptome construction mode.",
-      "properties": {
         "ref_genome": {
           "type": "string",
           "format": "file-path",
           "title": "Reference genome",
-          "demo_data": "${projectDir}/test_data/smoke/reference.fa",
           "description": "Reference genome FASTA.",
           "help_text": "Required in both discover and fixed_annotation modes."
         },
@@ -78,7 +38,6 @@
           "type": "string",
           "format": "file-path",
           "title": "Reference annotation",
-          "demo_data": "${projectDir}/test_data/smoke/annotation.gtf",
           "description": "Reference transcript annotation in GTF or GFF format.",
           "help_text": "Required in both discover and fixed_annotation modes."
         },
@@ -102,8 +61,41 @@
         "ref_genome",
         "ref_annotation",
         "transcriptome_mode"
+      ],
+      "allOf": [
+        {
+          "oneOf": [
+            {
+              "required": [
+                "fastq"
+              ]
+            },
+            {
+              "required": [
+                "bam"
+              ]
+            }
+          ]
+        }
       ]
     },
+    "filter_options": {
+      "title": "Read Filtering Options",
+      "type": "object",
+      "description": "Options for filtering input reads.",
+      "properties": {
+        "analyse_unclassified": {
+          "type": "boolean",
+          "default": false,
+          "description": "Include unclassified reads from multiplexed input directories."
+        },
+        "analyse_fail": {
+          "type": "boolean",
+          "default": false,
+          "description": "Include fail reads from bam_fail and fastq_fail folders found in sample folders on the input path."
+        }
+      }
+    },
     "sample_options": {
       "title": "Sample Options",
       "type": "object",
@@ -113,7 +105,6 @@
           "type": "string",
           "format": "file-path",
           "title": "Sample sheet",
-          "demo_data": "${projectDir}/test_data/smoke/sample_sheet.csv",
           "description": "CSV file describing barcodes, aliases, and optional experimental design columns.",
           "help_text": "For multiplexed runs, the sample sheet should contain both barcode and alias. For differential analysis it must also contain alias, the condition column, and any extra columns named in `--covariates`."
         },
@@ -123,8 +114,8 @@
         }
       }
     },
-    "analysis_options": {
+    "de_analysis_options": {
-      "title": "Analysis Options",
+      "title": "Differential Expression Analysis Options",
       "type": "object",
       "description": "Parameters controlling DGE and DTU analyses.",
       "properties": {
@@ -188,17 +179,6 @@
           "description": "Comma-separated modified base codes to pass to modkit pileup.",
           "help_text": "Provide values accepted by `modkit pileup --modified-bases`, for example `A:a,C:m`. If omitted, the workflow infers `primary_base:mod_code` pairs from the BAM with `modkit modbam check-tags`."
         },
-        "minimap2_index_opts": {
-          "type": "string",
-          "default": "",
-          "hidden": true,
-          "description": "Legacy compatibility parameter forwarded to minimap2 index generation."
-        },
-        "minimap2_opts": {
-          "type": "string",
-          "default": "",
-          "description": "Extra command-line options to pass to minimap2."
-        },
         "force_alignment" : {
           "type": "boolean",
           "default": false,
@@ -209,20 +189,10 @@
           "type": "number",
           "description": "Optional bambu novel discovery rate override."
         },
-        "skip_sqanti": {
-          "type": "boolean",
-          "default": false,
-          "description": "Skip SQANTI3 transcript classification and QC."
-        },
         "sqanti_skip_orf": {
           "type": "boolean",
           "default": true,
           "description": "Skip ORF prediction during SQANTI3 QC."
-        },
-        "sqanti_extra_args": {
-          "type": "string",
-          "default": "",
-          "description": "Extra command-line options to pass to SQANTI3."
         }
       }
     },
@@ -261,16 +231,16 @@
   },
   "allOf": [
     {
-      "$ref": "#/definitions/input_options"
+      "$ref": "#/definitions/main_options"
     },
     {
-      "$ref": "#/definitions/reference_options"
+      "$ref": "#/definitions/filter_options"
     },
     {
       "$ref": "#/definitions/sample_options"
     },
     {
-      "$ref": "#/definitions/analysis_options"
+      "$ref": "#/definitions/de_analysis_options"
     },
     {
       "$ref": "#/definitions/output_options"
@@ -304,12 +274,12 @@
   },
   "resources": {
     "recommended": {
-      "cpus": 16,
+      "cpus": 32,
-      "memory": "64GB"
+      "memory": "96GB"
     },
     "minimum": {
-      "cpus": 8,
+      "cpus": 12,
-      "memory": "32GB"
+      "memory": "64GB"
     },
     "run_time": "Varies with read depth and sample count; expect a small single-sample run to finish in under 30 minutes with the recommended resources.",
     "arm_support": false

output_definition.json

@@ -268,12 +268,12 @@
       "filepath": "igv.json",
       "title": "IGV configuration",
       "description": "JSON configuration for viewing the aligned BAMs in IGV.",
-      "mime-type": "text/json",
+      "mime-type": "application/json",
       "optional": true,
       "type": "aggregated"
     },
     "reference-index": {
-      "filepath": "igv_reference/{{ ref_genome_file }}.fai",
+      "filepath": "reference/{{ ref_genome_file }}.fai",
       "title": "Reference FASTA index",
       "description": "FAI index for the reference genome published for IGV.",
       "mime-type": "text/tab-separated-values",
@@ -281,7 +281,7 @@
       "type": "aggregated"
     },
     "reference-gzi-index": {
-      "filepath": "igv_reference/{{ ref_genome_file }}.gzi",
+      "filepath": "reference/{{ ref_genome_file }}.gzi",
       "title": "Reference GZI index",
       "description": "GZI index for a compressed reference genome published for IGV.",
       "mime-type": "application/octet-stream",

subworkflows/transcriptome.nf

@@ -151,7 +151,6 @@ process runJointSqanti {
         path "cohort", emit: dir
         path "cohort/classification_summary.tsv", emit: summary
     script:
-        String extra = params.sqanti_extra_args ?: ""
         String skip_orf = params.sqanti_skip_orf ? "--skipORF" : ""
     """
     mkdir cohort
@@ -164,8 +163,7 @@ process runJointSqanti {
         --report skip \
         -t ${task.cpus} \
         -d cohort \
-        -o cohort \
+        -o cohort
-        ${extra}
     workflow-glue summarise_sqanti --sqanti_dir cohort \
         --output cohort/classification_summary.tsv
     """
@@ -187,7 +185,6 @@ process runPerSampleSqanti {
         tuple val(meta), path("${meta.alias}"), emit: dir
         tuple val(meta), path("${meta.alias}/classification_summary.tsv"), emit: summary
     script:
-        String extra = params.sqanti_extra_args ?: ""
         String skip_orf = params.sqanti_skip_orf ? "--skipORF" : ""
     """
     mkdir "${meta.alias}"
@@ -200,8 +197,7 @@ process runPerSampleSqanti {
         --report skip \
         -t ${task.cpus} \
         -d "${meta.alias}" \
-        -o "${meta.alias}" \
+        -o "${meta.alias}"
-        ${extra}
     workflow-glue summarise_sqanti --sqanti_dir "${meta.alias}" \
         --output "${meta.alias}/classification_summary.tsv"
     """
@@ -321,19 +317,16 @@ workflow transcriptome {
         )
         sample_fastas = buildSampleTranscriptomeFasta(sample_bambu_real.gtf, ref_genome)
 
-        if (params.skip_sqanti) {
+       
-            joint_sqanti_dir = Channel.empty()
+        joint_sqanti = runJointSqanti(
-            sample_sqanti_dirs = Channel.empty()
+            joint_bambu_real.gtf.map { meta, gtf -> gtf },
-        } else {
+            analysis_annotation,
-            joint_sqanti = runJointSqanti(
+            ref_genome
-                joint_bambu_real.gtf.map { meta, gtf -> gtf },
+        )
-                analysis_annotation,
+        sample_sqanti = runPerSampleSqanti(sample_bambu_real.gtf, analysis_annotation, ref_genome)
-                ref_genome
+        joint_sqanti_dir = joint_sqanti.dir
-            )
+        sample_sqanti_dirs = sample_sqanti.dir
-            sample_sqanti = runPerSampleSqanti(sample_bambu_real.gtf, analysis_annotation, ref_genome)
+
-            joint_sqanti_dir = joint_sqanti.dir
-            sample_sqanti_dirs = sample_sqanti.dir
-        }
 
     emit:
         annotation = analysis_annotation