Merge pull request #73 from PMCC-BioinformaticsCore/release-v0.13.0

Release v0.13.0

.github/workflows/publish.yml

@@ -13,7 +13,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: '3.8.17'
+        python-version: '3.10.5'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

.github/workflows/unit_tests.yml

@@ -7,7 +7,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.8.17]
+        python-version: [3.10.5, 3.11]
 
     steps:
     - uses: actions/checkout@v3

.gitignore

@@ -1,14 +1,38 @@
-cromwell-executions/
-cromwell-workflow-logs/
+
+# built files
 __pycache__/
+build/
 .idea/
 .pyc
-.env
 .DS_Store
 *.egg-info/
 pip-wheel-metadata/
-.coverage
-.mypy_cache/
 dist/
-venv/
+
+# env & IDE
+.env
 .python-version
+.mypy_cache/
+.vscode/
+venv/
+
+# tests
+.coverage
+.nextflow/
+cromwell-executions/
+cromwell-workflow-logs/
+sample_data/
+local_data/
+
+# translation files
+.janis/
+output/
+translated*/
+testout/
+*.log
+involucro
+
+# misc files
+test.py
+ubu*
+temp.txt

configs/nextflow.config.BwaAlignment

@@ -0,0 +1,97 @@
+docker.enabled = true
+
+params {
+
+    // OUTPUT DIRECTORY
+    outdir  = './outputs'
+
+    // INPUTS
+    fastqs                          = [
+        [
+            '/home/grace/work/pp/translation/janis-assistant/local_data/data/NA12878-BRCA1_R1.fastq.gz',
+            '/home/grace/work/pp/translation/janis-assistant/local_data/data/NA12878-BRCA1_R2.fastq.gz'
+        ],
+    ]
+
+    // FastaWithIndexes
+    reference                       = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.amb',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.ann',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.bwt',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.dict',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.fai',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.pac',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.sa',
+    ]
+
+    // CompressedIndexedVCF
+    snps_dbsnp                      = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz.tbi'
+    ]
+
+    // CompressedIndexedVCF
+    snps_1000gp                     = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz.tbi'
+    ]
+
+    // CompressedIndexedVCF
+    known_indels                    = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz.tbi'
+    ]
+
+    // CompressedIndexedVCF
+    mills_indels                    = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz.tbi'
+    ]
+
+    adapter_file                    = '/home/grace/work/pp/translation/janis-assistant/local_data/data/adapter_list.txt'
+    contaminant_file                = '/home/grace/work/pp/translation/janis-assistant/local_data/data/contaminant_list.txt'
+    sample_name                     = 'NA12878-BRCA1'
+    allele_freq_threshold           = 0.05
+    min_mapping_qual                = null
+    filter                          = null
+    align_and_sort_sortsam_tmp_dir  = './tmp'
+
+    // PROCESSES
+    getfastqc_adapters.code_file                       = '/home/grace/work/pp/translation/janis-assistant/translated_BwaAlignmentAndQC/templates/ParseFastqcAdapters.py'
+    calculate_performancesummary_genomefile.code_file  = '/home/grace/work/pp/translation/janis-assistant/translated_BwaAlignmentAndQC/templates/GenerateGenomeFileForBedtoolsCoverage.py'
+    fastqc.cpus    = 1
+    fastqc.memory  = 8
+
+    // SUBWORKFLOW: ALIGN_AND_SORT
+    align_and_sort.five_prime_adapter_read1       = [
+        // list values here
+    ]
+    align_and_sort.five_prime_adapter_read2       = [
+        // list values here
+    ]
+    align_and_sort.cutadapt_quality_cutoff        = 15
+    align_and_sort.cutadapt_minimum_length        = 50
+    align_and_sort.bwamem_mark_shorter_splits     = true
+    align_and_sort.sortsam_sort_order             = 'coordinate'
+    align_and_sort.sortsam_create_index           = true
+    align_and_sort.sortsam_validation_stringency  = 'SILENT'
+    align_and_sort.sortsam_max_records_in_ram     = 5000000
+    align_and_sort.cutadapt.cpus                  = 5
+    align_and_sort.cutadapt.memory                = 4
+    align_and_sort.bwamem.cpus                    = 16
+    align_and_sort.bwamem.memory                  = 16
+    align_and_sort.sortsam.cpus                   = 1
+    align_and_sort.sortsam.memory                 = 8
+
+    // SUBWORKFLOW: MERGE_AND_MARKDUPS
+    merge_and_markdups.create_index                           = true
+    merge_and_markdups.max_records_in_ram                     = 5000000
+    merge_and_markdups.merge_sam_files_use_threading          = true
+    merge_and_markdups.merge_sam_files_validation_stringency  = 'SILENT'
+    merge_and_markdups.merge_sam_files.cpus                   = 4
+    merge_and_markdups.merge_sam_files.memory                 = 8
+    merge_and_markdups.mark_duplicates.cpus                   = 4
+    merge_and_markdups.mark_duplicates.memory                 = 8
+
+}

configs/nextflow.config.BwaAlignmentAndQC

@@ -0,0 +1,104 @@
+docker.enabled = true
+
+params {
+
+    // OUTPUT DIRECTORY
+    outdir  = './outputs'
+
+    // INPUTS
+    fastqs                          = [
+        [
+            '/home/grace/work/pp/translation/janis-assistant/local_data/data/NA12878-BRCA1_R1.fastq.gz',
+            '/home/grace/work/pp/translation/janis-assistant/local_data/data/NA12878-BRCA1_R2.fastq.gz'
+        ],
+    ]
+
+    // FastaWithIndexes
+    reference                       = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.amb',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.ann',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.bwt',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.dict',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.fai',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.pac',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.chr17.fasta.sa',
+    ]
+
+    // CompressedIndexedVCF
+    snps_dbsnp                      = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz.tbi'
+    ]
+
+    // CompressedIndexedVCF
+    snps_1000gp                     = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz.tbi'
+    ]
+
+    // CompressedIndexedVCF
+    known_indels                    = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz.tbi'
+    ]
+
+    // CompressedIndexedVCF
+    mills_indels                    = [
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz',
+        '/home/grace/work/pp/translation/janis-assistant/local_data/data/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz.tbi'
+    ]
+
+    adapter_file                    = '/home/grace/work/pp/translation/janis-assistant/local_data/data/adapter_list.txt'
+    contaminant_file                = '/home/grace/work/pp/translation/janis-assistant/local_data/data/contaminant_list.txt'
+    sample_name                     = 'NA12878-BRCA1'
+    allele_freq_threshold           = 0.05
+    min_mapping_qual                = null
+    filter                          = null
+    align_and_sort_sortsam_tmp_dir  = './tmp'
+
+    // PROCESSES
+    getfastqc_adapters.code_file                       = '/home/grace/work/pp/translation/janis-assistant/translated_BwaAlignmentAndQC/templates/ParseFastqcAdapters.py'
+    calculate_performancesummary_genomefile.code_file  = '/home/grace/work/pp/translation/janis-assistant/translated_BwaAlignmentAndQC/templates/GenerateGenomeFileForBedtoolsCoverage.py'
+    fastqc.cpus    = 1
+    fastqc.memory  = 8
+
+    // SUBWORKFLOW: ALIGN_AND_SORT
+    align_and_sort.five_prime_adapter_read1       = [
+        // list values here
+    ]
+    align_and_sort.five_prime_adapter_read2       = [
+        // list values here
+    ]
+    align_and_sort.cutadapt_quality_cutoff        = 15
+    align_and_sort.cutadapt_minimum_length        = 50
+    align_and_sort.bwamem_mark_shorter_splits     = true
+    align_and_sort.sortsam_sort_order             = 'coordinate'
+    align_and_sort.sortsam_create_index           = true
+    align_and_sort.sortsam_validation_stringency  = 'SILENT'
+    align_and_sort.sortsam_max_records_in_ram     = 5000000
+    align_and_sort.cutadapt.cpus                  = 5
+    align_and_sort.cutadapt.memory                = 4
+    align_and_sort.bwamem.cpus                    = 16
+    align_and_sort.bwamem.memory                  = 16
+    align_and_sort.sortsam.cpus                   = 1
+    align_and_sort.sortsam.memory                 = 8
+
+    // SUBWORKFLOW: MERGE_AND_MARKDUPS
+    merge_and_markdups.create_index                           = true
+    merge_and_markdups.max_records_in_ram                     = 5000000
+    merge_and_markdups.merge_sam_files_use_threading          = true
+    merge_and_markdups.merge_sam_files_validation_stringency  = 'SILENT'
+    merge_and_markdups.merge_sam_files.cpus                   = 4
+    merge_and_markdups.merge_sam_files.memory                 = 8
+    merge_and_markdups.mark_duplicates.cpus                   = 4
+    merge_and_markdups.mark_duplicates.memory                 = 8
+
+    // SUBWORKFLOW: PERFORMANCE_SUMMARY
+    performance_summary.samtoolsview_do_not_output_alignments_with_bits_set  = '0x400'
+    performance_summary.performancesummary_genome                            = true
+    performance_summary.gatk4collectinsertsizemetrics.cpus                   = 1
+    performance_summary.gatk4collectinsertsizemetrics.memory                 = 8
+    performance_summary.bedtoolsgenomecoveragebed.memory                     = 8
+
+}