add support for star transcriptome_aln

Author: lindaxiang

payload-gen-rna-alignment/main.nf

@@ -55,7 +55,7 @@ params.genome_build = ""
 
 process payloadGenRnaAlignment {
   container "${params.container ?: container[params.container_registry ?: default_container_registry]}:${params.container_version ?: version}"
-  publishDir "${params.publish_dir}/${task.process.replaceAll(':', '_')}", mode: "copy", enabled: params.publish_dir
+  publishDir "${params.publish_dir}/${task.process.replaceAll(':', '_')}", mode: "copy", enabled: params.publish_dir ? true : false
 
   cpus params.cpus
   memory "${params.mem} GB"

payload-gen-rna-alignment/main.py

@@ -150,7 +150,7 @@ def get_files_info(file_to_upload, date_str, seq_experiment_analysis_dict, align
     submitter_rg_id = None
     if re.match(r'^genome.merged.+?(cram|cram\.crai|bam|bam\.bai)$', file_to_upload): 
       file_type = 'genome_aln'
-    elif re.match(r'^transcriptome.merged.+?(cram|cram\.crai|bam|bam\.bai)$', file_to_upload): 
+    elif re.match(r'.+?_Aligned\.toTranscriptome\.out\.bam$', file_to_upload): 
       file_type = 'transcriptome_aln'
     elif re.match(r'^chimeric.merged.+?(cram|cram\.crai|bam|bam\.bai)$', file_to_upload): 
       file_type = 'chimeric_aln'
@@ -282,8 +282,8 @@ def main():
                         help="Input analysis for sequencing experiment", type=str)
     parser.add_argument("-t", "--analysis_type", dest="analysis_type", required=True, help="Specify analysis_type")
     parser.add_argument("-l", "--aligner", dest="aligner", default=None, help="Provide RNA-Seq aligner if files_to_upload are generated from alignment results. Default=None")
-    parser.add_argument("-g", "--genome_annotation", dest="genome_annotation", default="GENCODE v38", help="RNA-Seq alignment genome annotation")
-    parser.add_argument("-b", "--genome_build", dest="genome_build", default="GRCh38_hla_decoy_ebv", help="RNA-Seq alignment genome build")
+    parser.add_argument("-g", "--genome_annotation", dest="genome_annotation", default="GENCODE v40", help="RNA-Seq alignment genome annotation")
+    parser.add_argument("-b", "--genome_build", dest="genome_build", default="GRCh38_Verily_v1", help="RNA-Seq alignment genome build")
     parser.add_argument("-w", "--wf_name", dest="wf_name", required=True, help="Workflow name")
     parser.add_argument("-v", "--wf_version", dest="wf_version", required=True, help="Workflow version")
     parser.add_argument("-r", "--wf_run", dest="wf_run", required=True, help="Workflow run ID")

payload-gen-rna-alignment/tests/expected/expected.test-job-6.out.json

@@ -0,0 +1,80 @@
+{
+  "analysisType": {
+    "name": "sequencing_alignment"
+  },
+  "studyId": "TEST-PRO",
+  "workflow": {
+    "workflow_name": "RNA Seq Alignment",
+    "workflow_version": "0.2.0",
+    "genome_build": "GRCh38_Verily_v1",
+    "genome_annotation": "GENCODE v40",
+    "run_id": "pedantic_brenner",
+    "session_id": "b65970c3-192f-40dc-99f1-aedba8b987fe",
+    "inputs": [
+      {
+        "analysis_type": "sequencing_experiment",
+        "input_analysis_id": null
+      }
+    ]
+  },
+  "files": [
+    {
+      "fileSize": 51177,
+      "fileMd5sum": "f1c42eb0bc3aa8dc83cc3acac8632484",
+      "fileAccess": "controlled",
+      "info": {
+        "data_category": "Sequencing Reads",
+        "data_subtypes": [
+          "Transcriptome Alignment"
+        ],
+        "analysis_tools": [
+          "STAR"
+        ]
+      },
+      "fileName": "TEST-PRO.DO001.SA001.rna-seq.20221118.star.transcriptome_aln.bam",
+      "fileType": "BAM",
+      "dataType": "Aligned Reads"
+    }
+  ],
+  "samples": [
+    {
+      "submitterSampleId": "donor1_sample1_id",
+      "matchedNormalSubmitterSampleId": "sample1_normal",
+      "sampleType": "RNA",
+      "specimen": {
+        "submitterSpecimenId": "donor1_sample1",
+        "tumourNormalDesignation": "tumor",
+        "specimenTissueSource": "simulated",
+        "specimenType": "simulated"
+      },
+      "donor": {
+        "submitterDonorId": "donor1",
+        "gender": "male"
+      }
+    }
+  ],
+  "experiment": {
+    "submitter_sequencing_experiment_id": "TEST_EXP",
+    "sequencing_center": "SIM",
+    "platform": "ILLUMINA",
+    "platform_model": "Polyester",
+    "experimental_strategy": "RNA-Seq",
+    "sequencing_date": "2021-04-21"
+  },
+  "read_group_count": 1,
+  "read_groups": [
+    {
+      "submitter_read_group_id": "S01L1",
+      "read_group_id_in_bam": null,
+      "platform_unit": "sim01",
+      "is_paired_end": true,
+      "file_r1": "sample_01_L1_1.fastq.gz",
+      "file_r2": "sample_01_L1_2.fastq.gz",
+      "read_length_r1": 100,
+      "read_length_r2": 100,
+      "insert_size": 250,
+      "sample_barcode": null,
+      "library_name": "sim01"
+    }
+  ]
+}

payload-gen-rna-alignment/tests/test-job-6.json

@@ -0,0 +1,16 @@
+{
+  "seq_experiment_analysis": "input/s3.881fe6cf-8c80-4c7b-9f4d-b8dac9601d01.sequencing_experiment.payload.json",
+  "files_to_upload": [
+    "input/SA001_Aligned.toTranscriptome.out.bam"
+  ],
+  "expected_output": "expected/expected.test-job-6.out.json",
+  "aligner": "star",
+  "analysis_type": "sequencing_alignment",
+  "genome_annotation": "GENCODE v40",
+  "genome_build": "GRCh38_Verily_v1",
+  "wf_name": "rna-seq-alignment",
+  "wf_version": "0.2.0",
+  "publish_dir": "outdir",
+  "cpus": 1,
+  "mem": 0.5
+}