Merge branch 'CW-7274' into 'dev'

Add force alignment option [CW-7274]

Closes CW-7274

See merge request epi2melabs/workflows/wf-transcriptomes!299

README.md

@@ -356,6 +356,7 @@ 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 |

docs/07_input_parameters.md

@@ -52,6 +52,7 @@
 | 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 |

lib/common.nf

@@ -80,7 +80,7 @@ process minimap2_alignment {
               path("bamstats_results"),
               emit: alignment
     script:
-        String reset_cmd_body = "samtools reset -x tp,cm,s1,s2,NM,MD,AS,SA,ms,nn,ts,cg,cs,dv,de,rl"
+        String reset_cmd_body = "samtools reset -x tp,cm,s1,s2,NM,MD,AS,SA,ms,nn,ts,cg,cs,dv,de,rl,zd"
         String fastq_cmd_body = "samtools fastq -T '*'"
         // Default required threads is 6
         // Samtools x3 and bamstats will all be single threaded

lib/ingress.nf

@@ -337,6 +337,7 @@ def fastq_ingress(Map arguments, aln_ref_ch = null)
  *  - "alignment_threads": number of threads to use for alignment process (default: 6)
  *  - "output_xam_fmt": alignment output format, `bam` outputs an BAM file with index (.bam, .bai),
        `cram` outputs a CRAM file with index (.cram, .crai)
+*   - "force_alignment": boolean. Run alignment regardless of inputs.
  * @param aln_ref_ch: optional channel with a reference tuple (ref, ref_idx) to align against.
  *  If provided alignment will be attempted if inputs are unaligned or not already aligned to this ref.
  * @return: channel of `[Map(alias, barcode, type, ...), Path|null, Path|null]`.
@@ -357,6 +358,7 @@ def xam_ingress(Map arguments, aln_ref_ch = null)
             "return_fastq": false,
             "fastcat_extra_args": "",
             "fastq_chunk": null,
+            "force_alignment": false,
         ]
     )
     margs["fastq_chunk"] ?= 0  // cant pass null through channel
@@ -427,7 +429,7 @@ def xam_ingress(Map arguments, aln_ref_ch = null)
         alignment_fork = ch_check_bams
         | branch {
             meta, paths ->
-                to_align: (meta.is_unaligned == true) && (meta.has_reads == true)
+                to_align: (meta.is_unaligned || margs.force_alignment) && meta.has_reads
                 noalign: true
         }
         if (margs["output_xam_fmt"] == "bam"){

main.nf

@@ -304,6 +304,7 @@ workflow {
     } else {
         samples = xam_ingress([
             "input": params.bam,
+            "force_alignment": params.force_alignment,
         ] + ingress_args, ref_genome)
     }
     analysis_samples = samples

nextflow.config

@@ -27,6 +27,7 @@ params {
     mod_codes = null
     minimap2_index_opts = ""
     minimap2_opts = ""
+    force_alignment = false
     ndr = null
     skip_sqanti = false
     sqanti_skip_orf = true

nextflow_schema.json

@@ -194,6 +194,12 @@
           "default": "",
           "description": "Extra command-line options to pass to minimap2."
         },
+        "force_alignment" : {
+          "type": "boolean",
+          "default": false,
+          "description": "Force re-alignment of input BAM files.",
+          "help_text": "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)."
+        },
         "ndr": {
           "type": "number",
           "description": "Optional bambu novel discovery rate override."