****** TODO Vérifier les flags de chaque étape
post_cleanSam = _cleaned.bam
post_markDuplicate = _marked_dup.bam
post_BaseRecalibrator = _recal.table
post_ApplyBQSR = _recalibrated_hg38.bam
post_haplotypecaller = .vcf
post_depth_filter = _DP_over_30.vcf
post_exclude_SNP = _DP_over_30_not_SNP
post_consensual = _DP_over_30_not_SNP_consensual_sequence.vcf
post_technical = _DP_over_30_not_SNP_consensual_sequence_not_technical.vcf.gz
******* DONE Clean sam
CLOSED: [2023-01-20 Fri 23:44]
ref
$ samtools view -H 63003856_S135_cleaned.bam | grep PN
@PG ID:samtools PN:samtools PP:bwa VN:1.10 CL:/mnt/h/tools/samtools sort -@ 4 -O BAM -o /mnt/j/working_directory_pipeline_analyse_exome/tmp_63003856_S135/63003856_S135.bam
@PG ID:samtools PN:samtools PP:bwa VN:1.13 CL:samtools sort -@ 4 -O BAM -o files/tmp_63003856_S135/63003856_S135.bam
******* DONE Markduplicates
CLOSED: [2023-01-20 Fri 23:44]
ref
| @PG ID:MarkDuplicates VN:Version:4.2.4.1 CL:MarkDuplicates | @PG ID:MarkDuplicates VN:Version:4.2.4.1 CL:MarkDuplicates | |
| --INPUT /mnt/j/working_directory_pipeline_analyse_exome/tmp_63003856_S135/63003856_S135_cleaned.bam | --INPUT files/tmp_63003856_S135/63003856_S135_cleaned.bam | |
| --OUTPUT /mnt/j/working_directory_pipeline_analyse_exome/tmp_63003856_S135/63003856_S135_marked_dup.bam | --OUTPUT files/tmp_63003856_S135/63003856_S135_marked_dup.bam | |
| --METRICS_FILE /mnt/j/working_directory_pipeline_analyse_exome/tmp_63003856_S135/63003856_S135_marked_dup.metrix | --METRICS_FILE files/tmp_63003856_S135/63003856_S135_marked_dup.metrix | |
| --VERBOSITY WARNING | --VERBOSITY WARNING | |
| --CREATE_INDEX true | --CREATE_INDEX true | |
| --MAX_SEQUENCES_FOR_DISK_READ_ENDS_MAP 50000 | --MAX_SEQUENCES_FOR_DISK_READ_ENDS_MAP 50000 | |
| --MAX_FILE_HANDLES_FOR_READ_ENDS_MAP 8000 | --MAX_FILE_HANDLES_FOR_READ_ENDS_MAP 8000 | |
| --SORTING_COLLECTION_SIZE_RATIO 0.25 | --SORTING_COLLECTION_SIZE_RATIO 0.25 | |
| --TAG_DUPLICATE_SET_MEMBERS false | --TAG_DUPLICATE_SET_MEMBERS false | |
| --REMOVE_SEQUENCING_DUPLICATES false | --REMOVE_SEQUENCING_DUPLICATES false | |
| --TAGGING_POLICY DontTag | --TAGGING_POLICY DontTag | |
| --CLEAR_DT true | --CLEAR_DT true | |
| --DUPLEX_UMI false | --DUPLEX_UMI false | |
| --ADD_PG_TAG_TO_READS true | --ADD_PG_TAG_TO_READS true | |
| --REMOVE_DUPLICATES false | --REMOVE_DUPLICATES false | |
| --ASSUME_SORTED false | --ASSUME_SORTED false | |
| --DUPLICATE_SCORING_STRATEGY SUM_OF_BASE_QUALITIES | --DUPLICATE_SCORING_STRATEGY SUM_OF_BASE_QUALITIES | |
| --PROGRAM_RECORD_ID MarkDuplicates | --PROGRAM_RECORD_ID MarkDuplicates | |
| --PROGRAM_GROUP_NAME MarkDuplicates | --PROGRAM_GROUP_NAME MarkDuplicates | |
| --READ_NAME_REGEX <optimized capture of last three ':' separated fields as numeric values> | --READ_NAME_REGEX <optimized capture of last three ':' separated fields as numeric values> | |
| --OPTICAL_DUPLICATE_PIXEL_DISTANCE 100 | --OPTICAL_DUPLICATE_PIXEL_DISTANCE 100 | |
| --MAX_OPTICAL_DUPLICATE_SET_SIZE 300000 | --MAX_OPTICAL_DUPLICATE_SET_SIZE 300000 | |
| --QUIET false | --QUIET false | |
| --VALIDATION_STRINGENCY STRICT | --VALIDATION_STRINGENCY STRICT | |
| --COMPRESSION_LEVEL 2 | --COMPRESSION_LEVEL 2 | |
| --MAX_RECORDS_IN_RAM 500000 | --MAX_RECORDS_IN_RAM 500000 | |
| --CREATE_MD5_FILE false | --CREATE_MD5_FILE false | |
| --GA4GH_CLIENT_SECRETS client_secrets.json | --GA4GH_CLIENT_SECRETS client_secrets.json | |
| --help false | --help false | |
| --version false | --version false | |
| --showHidden false | --showHidden false | |
| --USE_JDK_DEFLATER false | --USE_JDK_DEFLATER false | |
| --USE_JDK_INFLATER false | --USE_JDK_INFLATER false | |
| @PG ID:samtools.1 PN:samtools PP:samtools VN:1.13 CL:samtools view -H 63003856_S135_marked_dup.bam |
******* DONE ApplyBQSR
CLOSED: [2023-01-20 Fri 23:48]
Ref
@PG ID:GATK ApplyBQSR VN:4.2.4.1 CL:ApplyBQSR
| --output /mnt/j/working_directory_pipeline_analyse_exome/bam/63003856_S135_recalibrated_hg38.bam | --output files/bam/63003856_S135_recalibrated_hg38.bam |
| --bqsr-recal-file /mnt/j/working_directory_pipeline_analyse_exome/tmp_63003856_S135/63003856_S135_recal.table | --bqsr-recal-file files/tmp_63003856_S135/63003856_S135_recal.table |
| --input /mnt/j/working_directory_pipeline_analyse_exome/tmp_63003856_S135/63003856_S135_marked_dup.bam | --input files/tmp_63003856_S135/63003856_S135_marked_dup.bam |
| --reference /mnt/j/bases_de_donnees/genome/GRCh38_latest_genomic.fna | --reference /Work/Groups/bisonex/data-alexis-reference/genome/GRCh38_latest_genomic.fna |
| --verbosity WARNING | --verbosity WARNING |
| --preserve-qscores-less-than 6 | --preserve-qscores-less-than 6 |
| --use-original-qualities false | --use-original-qualities false |
| --quantize-quals 0 | --quantize-quals 0 |
| --round-down-quantized false | --round-down-quantized false |
| --emit-original-quals false | --emit-original-quals false |
| --global-qscore-prior -1.0 | --global-qscore-prior -1.0 |
| --interval-set-rule UNION | --interval-set-rule UNION |
| --interval-padding 0 | --interval-padding 0 |
| --interval-exclusion-padding 0 | --interval-exclusion-padding 0 |
| --interval-merging-rule ALL | --interval-merging-rule ALL |
| --read-validation-stringency SILENT | --read-validation-stringency SILENT |
| --seconds-between-progress-updates 10.0 | --seconds-between-progress-updates 10.0 |
| --disable-sequence-dictionary-validation false | --disable-sequence-dictionary-validation false |
| --create-output-bam-index true | --create-output-bam-index true |
| --create-output-bam-md5 false | --create-output-bam-md5 false |
| --create-output-variant-index true | --create-output-variant-index true |
| --create-output-variant-md5 false | --create-output-variant-md5 false |
| --max-variants-per-shard 0 | --max-variants-per-shard 0 |
| --lenient false | --lenient false |
| --add-output-sam-program-record true | --add-output-sam-program-record true |
| --add-output-vcf-command-line true | --add-output-vcf-command-line true |
| --cloud-prefetch-buffer 40 | --cloud-prefetch-buffer 40 |
| --cloud-index-prefetch-buffer -1 | --cloud-index-prefetch-buffer -1 |
| --disable-bam-index-caching false | --disable-bam-index-caching false |
| --sites-only-vcf-output false | --sites-only-vcf-output false |
| --help false | --help false |
| --version false | --version false |
| --showHidden false | --showHidden false |
| --QUIET false | --QUIET false |
| --use-jdk-deflater false | --use-jdk-deflater false |
| --use-jdk-inflater false | --use-jdk-inflater false |
| --gcs-max-retries 20 | --gcs-max-retries 20 |
| --gcs-project-for-requester-pays | --gcs-project-for-requester-pays |
| --disable-tool-default-read-filters false PN:GATK ApplyBQSR | --disable-tool-default-read-filters false PN:GATK ApplyBQSR |
***** TODO Relancer avec la même version de samtools ?