Add fasta to picard/collectalignmentsummarymetrics (#8392)

* Update bioconda version

* Add ability to use a reference genome

* Add meta map for fasta input

* Update modules/nf-core/picard/collectalignmentsummarymetrics/meta.yml

---------

Co-authored-by: Simon Pearce <24893913+SPPearce@users.noreply.github.com>

Author: randombenj

modules/nf-core/picard/collectalignmentsummarymetrics/environment.yml

@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - "bioconda::picard=3.3.0"
+  - bioconda::picard=3.4.0

modules/nf-core/picard/collectalignmentsummarymetrics/main.nf

@@ -8,7 +8,8 @@ process PICARD_COLLECTALIGNMENTSUMMARYMETRICS {
         'biocontainers/picard:3.3.0--hdfd78af_0' }"
 
     input:
-    tuple val(meta), path(bam)
+    tuple val(meta),  path(bam)
+    tuple val(meta2), path(fasta)
 
     output:
     tuple val(meta), path("*.txt"), emit: metrics
@@ -20,6 +21,7 @@ process PICARD_COLLECTALIGNMENTSUMMARYMETRICS {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = fasta ? "--REFERENCE_SEQUENCE ${fasta}" : ""
 
     def avail_mem = 3072
     if (!task.memory) {
@@ -33,6 +35,7 @@ process PICARD_COLLECTALIGNMENTSUMMARYMETRICS {
         CollectAlignmentSummaryMetrics \\
         --INPUT $bam \\
         --OUTPUT ${prefix}.txt \\
+        ${reference} \\
         $args
 
     cat <<-END_VERSIONS > versions.yml

modules/nf-core/picard/collectalignmentsummarymetrics/meta.yml

@@ -23,6 +23,15 @@ input:
         type: file
         description: BAM/CRAM/SAM file
         pattern: "*.{bam,cram,sam}"
+  - - meta2:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. [ id:'test', single_end:false ]
+    - fasta:
+        type: file
+        description: Fasta file
+        pattern: "*.{fasta}"
 output:
   - metrics:
       - meta:

modules/nf-core/picard/collectalignmentsummarymetrics/tests/main.nf.test

@@ -15,10 +15,39 @@ nextflow_process {
             process {
                 """
                 input[0] = [
-				    [ id:'test', single_end:false ], // meta map
-				    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
-				]
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
+                ]
+                input[1] = [[], []]
+                """
+            }
+        }
 
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    file(process.out.metrics[0][1]).readLines()[5..8],
+                    process.out.versions
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("test-picard-collectalignmentsummarymetrics - with reference") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
+                ]
+                input[1] = [
+                    [ id:'test', single_end:false ], // meta map
+                    [file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)]
+                ]
                 """
             }
         }
@@ -27,10 +56,10 @@ nextflow_process {
             assertAll(
                 { assert process.success },
                 { assert snapshot(
-					file(process.out.metrics[0][1]).readLines()[5..8],
-					process.out.versions
-					).match()
-				}
+                    file(process.out.metrics[0][1]).readLines()[5..8],
+                    process.out.versions
+                    ).match()
+                }
             )
         }
     }
@@ -41,10 +70,10 @@ nextflow_process {
             process {
                 """
                 input[0] = [
-				    [ id:'test', single_end:false ], // meta map
-				    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
-				]
-
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
+                ]
+                input[1] = [[], []]
                 """
             }
         }
@@ -57,4 +86,4 @@ nextflow_process {
         }
     }
 
-}
+}

modules/nf-core/picard/collectalignmentsummarymetrics/tests/main.nf.test.snap

@@ -13,9 +13,27 @@
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.5"
+            "nextflow": "24.10.6"
         },
-        "timestamp": "2025-04-13T14:35:05.248694"
+        "timestamp": "2025-05-05T15:13:47.554135117"
+    },
+    "test-picard-collectalignmentsummarymetrics - with reference": {
+        "content": [
+            [
+                "## METRICS CLASS\tpicard.analysis.AlignmentSummaryMetrics",
+                "CATEGORY\tTOTAL_READS\tPF_READS\tPCT_PF_READS\tPF_NOISE_READS\tPF_READS_ALIGNED\tPCT_PF_READS_ALIGNED\tPF_ALIGNED_BASES\tPF_HQ_ALIGNED_READS\tPF_HQ_ALIGNED_BASES\tPF_HQ_ALIGNED_Q20_BASES\tPF_HQ_MEDIAN_MISMATCHES\tPF_MISMATCH_RATE\tPF_HQ_ERROR_RATE\tPF_INDEL_RATE\tMEAN_READ_LENGTH\tSD_READ_LENGTH\tMEDIAN_READ_LENGTH\tMAD_READ_LENGTH\tMIN_READ_LENGTH\tMAX_READ_LENGTH\tMEAN_ALIGNED_READ_LENGTH\tREADS_ALIGNED_IN_PAIRS\tPCT_READS_ALIGNED_IN_PAIRS\tPF_READS_IMPROPER_PAIRS\tPCT_PF_READS_IMPROPER_PAIRS\tBAD_CYCLES\tSTRAND_BALANCE\tPCT_CHIMERAS\tPCT_ADAPTER\tPCT_SOFTCLIP\tPCT_HARDCLIP\tAVG_POS_3PRIME_SOFTCLIP_LENGTH\tSAMPLE\tLIBRARY\tREAD_GROUP",
+                "FIRST_OF_PAIR\t100\t100\t1\t0\t100\t1\t13884\t99\t13735\t12777\t0\t0.004249\t0.004296\t0.000432\t138.97\t22.059357\t150\t1\t72\t151\t138.84\t97\t0.97\t4\t0.04\t0\t0.48\t0\t0\t0.000935\t0\t6.5\t\t\t",
+                "SECOND_OF_PAIR\t100\t100\t1\t0\t97\t0.97\t13517\t97\t13517\t12630\t0\t0.002885\t0.002885\t0.000296\t137.48\t23.672633\t150\t1\t53\t151\t135.17\t97\t1\t1\t0.010309\t0\t0.515464\t0\t0\t0.000655\t0\t0\t\t\t"
+            ],
+            [
+                "versions.yml:md5,6861b381e5b887f0d331e45166feeb04"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.6"
+        },
+        "timestamp": "2025-05-05T15:13:56.775995067"
     },
     "test-picard-collectalignmentsummarymetrics-stub": {
         "content": [
@@ -48,8 +66,8 @@
         ],
         "meta": {
             "nf-test": "0.9.2",
-            "nextflow": "24.10.5"
+            "nextflow": "24.10.6"
         },
-        "timestamp": "2025-04-13T14:31:59.598201"
+        "timestamp": "2025-05-05T15:15:16.790101044"
     }
 }