replace sentieon

README.md

 # Quality control of germline variants calling results using a Chinese Quartet family
 
-> Author： Run Luyao
+> Author： Ren Luyao, Chen Haonan
 >
-> E-mail：18110700050@fudan.edu.cn
+> E-mail：18110700050@fudan.edu.cn, haonanchen0815@163.com
 >
-> Git: http://47.103.223.233/renluyao/quartet_dna_quality_control_wgs_big_pipeline
+> Git: http://choppy.3steps.cn/chenhaonan/quartet_dna_quality_control_wes_big_pipeline.git
 >
-> Last Updates: 2022/10/31
+> Last Updates: 2023/7/31
 
 ## Install
 
 ```
 open-choppy-env
-choppy install renluyao/quartet_dna_quality_control_big_pipeline
+choppy install chenhaonan/quartet_dna_quality_control_big_pipeline
 ```
 
 ## Introduction 
 
 ### 2. Genome alignment
 
-####[sentieon-genomics](https://support.sentieon.com/manual/):v2019.11.28
+Reads were mapped to the human reference genome GRCh38 using BWA-MEM.SAMTools is a tool used for SAM/BAM file conversion and BAM file sorting.
+
+####[BWA-MEM](https://github.com/lh3/bwa):v0.7.17
+
 
-Reads were mapped to the human reference genome GRCh38 using Sentieon BWA.
 
 ```bash
-${SENTIEON_INSTALL_DIR}/bin/bwa mem -M -R "@RG\tID:${group}\tSM:${sample}\tPL:${pl}" -t $nt -K 10000000 ${ref_dir}/${fasta} ${fastq_1} ${fastq_2} | ${SENTIEON_INSTALL_DIR}/bin/sentieon util sort -o ${sample}.sorted.bam -t $nt --sam2bam -i -
+# Mapping to reference genome, converting sam to bam, sorting bam file 
+bwa mem -M -R "@RG\tID:${group}\tSM:${sample}\tPL:${pl}" -t $(nproc) -K 10000000 ${ref_dir}/${fasta} ${fastq_1} ${fastq_2} | samtools view -bS -@ $(nproc) - 
+| samtools sort -@ $(nproc) -o ${user_define_name}_${project}_${sample}.sorted.bam -
+```
 
+####[SAMTools](https://github.com/samtools/samtools):v1.17
+
+```bash
+# Building an index for sorted bam file
+samtools index -@ $(nproc) -o ${user_define_name}_${project}_${sample}.sorted.bam.bai ${user_define_name}_${project}_${sample}.sorted.bam
 ```
 
 ### 3. Post-alignment QC
 
-Qualimap and Paicard Tools (implemented by Sentieon) are used to check the quality of BAM files. Deduplicated BAM files are used in this step.
+Qualimap and Picard Tools  are used to check the quality of BAM files. Deduplicated BAM files are used in this step.
 
 #### [Qualimap](<http://qualimap.bioinfo.cipf.es/>) 2.0.0
 
 ```bash
+# BAM QC by qualimap
 qualimap bamqc -bam <bam_file> -outformat PDF:HTML -nt <threads> -outdir <output_directory> --java-mem-size=32G 
 ```
 
-####[Sentieon-genomics](https://support.sentieon.com/manual/):v2019.11.28
+####[Picard](https://github.com/broadinstitute/picard/):v3.0.0
 
-```
-${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${Dedup_bam} --algo CoverageMetrics --omit_base_output ${sample}_deduped_coverage_metrics --algo MeanQualityByCycle ${sample}_deduped_mq_metrics.txt --algo QualDistribution ${sample}_deduped_qd_metrics.txt --algo GCBias --summary ${sample}_deduped_gc_summary.txt ${sample}_deduped_gc_metrics.txt --algo AlignmentStat ${sample}_deduped_aln_metrics.txt --algo InsertSizeMetricAlgo ${sample}_deduped_is_metrics.txt --algo QualityYield ${sample}_deduped_QualityYield.txt --algo WgsMetricsAlgo ${sample}_deduped_WgsMetricsAlgo.txt
+```bash
+# Remove duplicates
+java -jar /usr/local/picard.jar  MarkDuplicates -I ${sorted_bam} -O ${sample}.sorted.deduped.bam -M ${sample}_dedup_metrics.txt --REMOVE_DUPLICATES
+# Building an index for the sorted and deduplicated bam file			
+samtools index -@ $(nproc) -o  ${sample}.sorted.deduped.bam.bai  ${sample}.sorted.deduped.bam
 ```
 
 ### 4. Germline variant calling
 
-HaplotyperCaller implemented by Sentieon is used to identify germline variants.
+HaplotyperCaller implemented by Google DeepVariant is used to identify germline variants.
+
+#### [DeepVariant](<https://github.com/google/deepvariant>) 1.5.0
 
 ```bash
-${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${recaled_bam} --algo Haplotyper ${sample}_hc.vcf
+# Calling variant
+deepvariant/bin/run_deepvariant --model_type=WES --ref=${ref_dir}/${fasta} --reads=${recaled_bam} --output_vcf=${sample}_hc.vcf --num_shards=$(nproc)
+# Building an index for the vcf file
+gatk IndexFeatureFile -I ${sample}_hc.vcf -O ${sample}_hc.vcf.idx
 ```
 
 ### 5. Variants Calling QC
 | PCT_1X                | Fraction of genome with at least 1x coverage  |
 | PCT_5X                | Fraction of genome with at least 5x coverage  |
 | PCT_10X               | Fraction of genome with at least 10x coverage |
-| PCT_20X               | Fraction of genome with at least 20x coverage |
 | PCT_30X               | Fraction of genome with at least 30x coverage |
-| Fold-80               | Fold-80 penalty								|
-| On target bases rate  | On target bases rate 							|
-
 
 ####3. variants.calling.qc.txt
 

defaults

 {
   "benchmarking_dir": "oss://pgx-result/renluyao/manuscript_v3.0/reference_datasets_v202103/",
-  "SENTIEON_INSTALL_DIR": "/opt/sentieon-genomics",
   "fasta": "GRCh38.d1.vd1.fa",
   "BENCHMARKdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-hap:latest",
   "dbsnp_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/",
   "BIGcluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
   "fastq_screen_conf": "oss://pgx-reference-data/fastq_screen_reference/fastq_screen.conf",
   "FASTQSCREENdocker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/fastqscreen:0.12.0",
-  "SENTIEON_LICENSE": "192.168.0.55:8990",
-  "SENTIEONdocker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/sentieon-genomics:v2019.11.28",
+  "REPLACE_SENTIEON_DOCKER": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/sentieon-replaced:2.0",
+  "DEEPVARIANT_DOCKER": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/deepvariant:v1.5.0_20230721",
   "QUALIMAPdocker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/qualimap:2.0.0",
   "vcf_D5": "",
   "benchmark_region": "oss://pgx-result/renluyao/manuscript_v3.0/reference_datasets_v202103/Quartet.high.confidence.region.v202103.bed",
   "MENDELIANdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
   "DIYdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:1.5",
   "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
-}
+}

tasks/BQSR.wdl

     File ref_dir
     File dbsnp_dir
     File dbmills_dir
-	String SENTIEON_INSTALL_DIR
 	String fasta
 	String dbsnp
 	String db_mills
 	
 	command <<<
 		set -o pipefail
-		set -e
-		export SENTIEON_LICENSE=192.168.0.55:8990
-		nt=$(nproc)
+        set -e
+        /usr/local/gatk-4.4.0.0/gatk BaseRecalibrator \
+            -R ${ref_dir}/${fasta} \
+            -I ${realigned_bam} \
+            --known-sites ${dbsnp_dir}/${dbsnp} \
+            --known-sites ${dbmills_dir}/${db_mills} \
+            -O ${sample}_recal_data.table
 
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${realigned_bam} --algo QualCal -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} ${sample}_recal_data.table
-
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${realigned_bam} -q ${sample}_recal_data.table --algo QualCal -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} ${sample}_recal_data.table.post --algo ReadWriter ${sample}.sorted.deduped.realigned.recaled.bam
-
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt --algo QualCal --plot --before ${sample}_recal_data.table --after ${sample}_recal_data.table.post ${sample}_recal_data.csv
-
-		${SENTIEON_INSTALL_DIR}/bin/sentieon plot QualCal -o ${sample}_bqsrreport.pdf ${sample}_recal_data.csv
+        /usr/local/gatk-4.4.0.0/gatk ApplyBQSR \
+            -R ${ref_dir}/${fasta} \
+            -I ${realigned_bam} \
+            -bqsr ${sample}_recal_data.table \
+            -O ${sample}.sorted.deduped.realigned.recaled.bam
 
+        /usr/local/samtools-1.17/bin/samtools index -@ $(nproc) -o ${sample}.sorted.deduped.realigned.recaled.bam.bai ${sample}.sorted.deduped.realigned.recaled.bam
 	>>>
 	runtime {
 		docker:docker
 	}
 
 	output {
-		File recal_table = "${sample}_recal_data.table"
-		File recal_post = "${sample}_recal_data.table.post"
 		File recaled_bam = "${sample}.sorted.deduped.realigned.recaled.bam"
 		File recaled_bam_index = "${sample}.sorted.deduped.realigned.recaled.bam.bai"
-		File recal_csv = "${sample}_recal_data.csv"
-		File bqsrreport_pdf = "${sample}_bqsrreport.pdf"
 	}
 }

tasks/Dedup.wdl

 task Dedup {
-
-	String SENTIEON_INSTALL_DIR
 	File sorted_bam
 	File sorted_bam_index
 	String sample = basename(sorted_bam,".sorted.bam")
 	command <<<
 		set -o pipefail
 		set -e
-		export SENTIEON_LICENSE=192.168.0.55:8990
-		nt=$(nproc)
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt -i ${sorted_bam} --algo LocusCollector --fun score_info ${sample}_score.txt
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt -i ${sorted_bam} --algo Dedup --rmdup --score_info ${sample}_score.txt --metrics ${sample}_dedup_metrics.txt ${sample}.sorted.deduped.bam	
+
+		/usr/local/jdk-20.0.1/bin/java -jar /usr/local/picard.jar  MarkDuplicates \
+					-I ${sorted_bam}  \
+					-O ${sample}.sorted.deduped.bam \
+					-M ${sample}_dedup_metrics.txt \
+					--REMOVE_DUPLICATES
+					
+		/usr/local/samtools-1.17/bin/samtools index -@ $(nproc) -o  ${sample}.sorted.deduped.bam.bai  ${sample}.sorted.deduped.bam
 	>>>
 	runtime {
 		docker:docker
 	}
 
 	output {
-		File score = "${sample}_score.txt"
-		File dedup_metrics = "${sample}_dedup_metrics.txt"
 		File Dedup_bam = "${sample}.sorted.deduped.bam"
 		File Dedup_bam_index = "${sample}.sorted.deduped.bam.bai"
 	}

tasks/Haplotyper.wdl

 task Haplotyper {
-	
     File ref_dir
-	String SENTIEON_INSTALL_DIR
 	String fasta
 	File recaled_bam
 	File recaled_bam_index
 command <<<
 		set -o pipefail
 		set -e
-		export SENTIEON_LICENSE=192.168.0.55:8990
-		nt=$(nproc)	
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${recaled_bam} --algo Haplotyper ${sample}_hc.vcf
+		/opt/deepvariant/bin/run_deepvariant \
+			--model_type=WES \
+			--ref=${ref_dir}/${fasta} \
+			--reads=${recaled_bam} \
+			--output_vcf=${sample}_hc.vcf \
+			--num_shards=$(nproc) 
 	>>>
 	
 	runtime {
 
 	output {
 		File vcf = "${sample}_hc.vcf"
-		File vcf_idx = "${sample}_hc.vcf.idx"
 	}
 }
 

tasks/Realigner.wdl

     File ref_dir
     File dbmills_dir
 
-	String SENTIEON_INSTALL_DIR
 	String fasta
 
 	File Dedup_bam
 	command <<<
 	set -o pipefail
 	set -e
-	export SENTIEON_LICENSE=192.168.0.55:8990
 	nt=$(nproc)
-	${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${Dedup_bam} --algo Realigner -k ${dbmills_dir}/${db_mills} ${sample}.sorted.deduped.realigned.bam
-	
+	/usr/local/jdk-1.8.0/bin/java -jar /usr/local/GenomeAnalysisTK.jar -T RealignerTargetCreator -R ${ref_dir}/${fasta} -nt $nt -I ${Dedup_bam} -known ${dbmills_dir}/${db_mills} -o ${sample}.IndelRealigner.intervals
+	/usr/local/jdk-1.8.0/bin/java -jar /usr/local/GenomeAnalysisTK.jar -T IndelRealigner -R ${ref_dir}/${fasta} -I ${Dedup_bam} --targetIntervals ${sample}.IndelRealigner.intervals -o ${sample}.sorted.deduped.realigned.bam
+	/usr/local/samtools-1.17/bin/samtools index -@ $(nproc) -o  ${sample}.sorted.deduped.realigned.bam.bai  ${sample}.sorted.deduped.realigned.bam
 	>>>
 
 	runtime {

tasks/deduped_Metrics.wdl

 
     File ref_dir
     File bed
-	String SENTIEON_INSTALL_DIR
 	String fasta
 	File Dedup_bam
 	File Dedup_bam_index
 		set -e
 		export SENTIEON_LICENSE=192.168.0.55:8990
 		nt=$(nproc)
-		${SENTIEON_INSTALL_DIR}/bin/sentieon driver -r ${ref_dir}/${fasta} -t $nt -i ${Dedup_bam} --interval ${bed} --algo CoverageMetrics --omit_base_output ${sample}_deduped_coverage_metrics --algo MeanQualityByCycle ${sample}_deduped_mq_metrics.txt --algo QualDistribution ${sample}_deduped_qd_metrics.txt --algo GCBias --summary ${sample}_deduped_gc_summary.txt ${sample}_deduped_gc_metrics.txt --algo AlignmentStat ${sample}_deduped_aln_metrics.txt --algo InsertSizeMetricAlgo ${sample}_deduped_is_metrics.txt --algo QualityYield ${sample}_deduped_QualityYield.txt --algo WgsMetricsAlgo ${sample}_deduped_WgsMetricsAlgo.txt --algo HsMetricAlgo --targets_list ${interval_list} --baits_list ${interval_list} ${sample}_deduped_HsMetricAlgo.txt
+		/usr/local/jdk-20.0.1/bin/java -jar /usr/local/picard.jar CollectAlignmentSummaryMetrics \
+			-I ${Dedup_bam} \
+			-O ${sample}_deduped_aln_metrics.txt \
+			-R ${ref_dir}/${fasta} \
+			--VALIDATION_STRINGENCY LENIENT
+		/usr/local/jdk-20.0.1/bin/java -jar /usr/local/picard.jar CollectInsertSizeMetrics \
+			-I ${Dedup_bam} \
+			-O ${sample}_deduped_is_metrics.txt \
+			-H ${sample}_deduped_is_metrics.pdf
+		/usr/local/jdk-20.0.1/bin/java -jar /usr/local/picard.jar CollectQualityYieldMetrics \
+			-I ${Dedup_bam} \
+			-O ${sample}_deduped_QualityYield.txt
+		/usr/local/jdk-20.0.1/bin/java -jar /usr/local/picard.jar CollectWgsMetrics \
+			-I ${Dedup_bam} \
+			-O ${sample}_deduped_WgsMetricsAlgo.txt \
+			-R ${ref_dir}/${fasta} \
+			--VALIDATION_STRINGENCY LENIENT
+		/usr/local/jdk-20.0.1/bin/java -jar /usr/local/picard.jar CollectHsMetrics \
+			-I ${Dedup_bam} \
+			-O ${sample}_deduped_HsMetricAlgo.txt \
+			--TARGET_INTERVALS ${interval_list} \
+			--BAIT_INTERVALS ${interval_list}
 	>>>
 
 	runtime {
 	}
 
 	output {
-		File deduped_coverage_metrics_sample_summary = "${sample}_deduped_coverage_metrics.sample_summary"
-		File deduped_coverage_metrics_sample_statistics = "${sample}_deduped_coverage_metrics.sample_statistics"
-		File deduped_coverage_metrics_sample_interval_statistics = "${sample}_deduped_coverage_metrics.sample_interval_statistics"
-		File deduped_coverage_metrics_sample_cumulative_coverage_proportions = "${sample}_deduped_coverage_metrics.sample_cumulative_coverage_proportions"
-		File deduped_coverage_metrics_sample_cumulative_coverage_counts = "${sample}_deduped_coverage_metrics.sample_cumulative_coverage_counts"
-		File deduped_mean_quality = "${sample}_deduped_mq_metrics.txt"
-		File deduped_qd_metrics = "${sample}_deduped_qd_metrics.txt"
-		File deduped_gc_summary = "${sample}_deduped_gc_summary.txt"
-		File deduped_gc_metrics = "${sample}_deduped_gc_metrics.txt"
 		File dedeuped_aln_metrics = "${sample}_deduped_aln_metrics.txt"
 		File deduped_is_metrics = "${sample}_deduped_is_metrics.txt"
 		File deduped_QualityYield = "${sample}_deduped_QualityYield.txt"

tasks/mapping.wdl

 	File fastq_1
 	File fastq_2
 
-	String SENTIEON_INSTALL_DIR
-	String SENTIEON_LICENSE
 	String group
 	String sample
 	String project
 	command <<<
 		set -o pipefail
 		set -e	
-		export SENTIEON_LICENSE=${SENTIEON_LICENSE}
-		nt=$(nproc)
-		${SENTIEON_INSTALL_DIR}/bin/bwa mem -M -R "@RG\tID:${group}\tSM:${sample}\tPL:${pl}" -t $nt -K 10000000 ${ref_dir}/${fasta} ${fastq_1} ${fastq_2} | ${SENTIEON_INSTALL_DIR}/bin/sentieon util sort -o ${user_define_name}_${project}_${sample}.sorted.bam -t $nt --sam2bam -i -
+		bwa mem -M -R "@RG\tID:${group}\tSM:${sample}\tPL:${pl}" -t $(nproc) -K 10000000 ${ref_dir}/${fasta} ${fastq_1} ${fastq_2} \
+			| samtools view -bS -@ $(nproc) - \
+			| samtools sort -@ $(nproc) -o ${user_define_name}_${project}_${sample}.sorted.bam -
+		
+		samtools index -@ $(nproc) \
+						-o ${user_define_name}_${project}_${sample}.sorted.bam.bai  \
+						${user_define_name}_${project}_${sample}.sorted.bam
 	>>>
 
 	runtime {

tasks/sentieon.wdl

 	String disk_size
 
 	command <<<
-		set -o pipefail
+		set -o pipefail	
 		set -e
-
-		cat ${quality_yield} | sed -n '2,2p' > quality_yield.header
-		cat ${quality_yield} | sed -n '3,3p' > ${sample}.quality_yield
-
-		cat ${wgs_metrics_algo} | sed -n '2,2p' > wgs_metrics_algo.header
-		cat ${wgs_metrics_algo} | sed -n '3,3p' > ${sample}.wgs_metrics_algo
-
-		cat ${aln_metrics} | sed -n '2,2p'  > aln_metrics.header
-		cat ${aln_metrics} | sed -n '5,5p'  > ${sample}.aln_metrics
-
-		cat ${is_metrics} | sed -n '2,2p' > is_metrics.header
-		cat ${is_metrics} | sed -n '3,3p' > ${sample}.is_metrics
-
-		cat ${hs_metrics} | sed -n '2,2p' > hs_metrics.header
-		cat ${hs_metrics} | sed -n '3,3p' > ${sample}.hs_mtrics
+		cat ${quality_yield} | sed -n '7,7p' > quality_yield.header
+		cat ${quality_yield} | sed -n '8,8p' > ${sample}.quality_yield
+		cat ${wgs_metrics_algo} | sed -n '7,7p' > wgs_metrics_algo.header
+		cat ${wgs_metrics_algo} | sed -n '8,8p' > ${sample}.wgs_metrics_algo
+		cat ${aln_metrics} | sed -n '7,7p'  > aln_metrics.header
+		cat ${aln_metrics} | sed -n '10,10p'  > ${sample}.aln_metrics
+		cat ${is_metrics} | sed -n '7,7p' > is_metrics.header
+		cat ${is_metrics} | sed -n '8,8p' > ${sample}.is_metrics
+
+		cat ${hs_metrics} | sed -n '7,7p' > hs_metrics.header
+		cat ${hs_metrics} | sed -n '8,8p' > ${sample}.hs_mtrics
 
 
 	>>>

workflow.wdl

 
 	File bed
 
-	String SENTIEON_INSTALL_DIR
-	String SENTIEON_LICENSE
-	String SENTIEONdocker
+	String REPLACE_SENTIEON_DOCKER
+	String DEEPVARIANT_DOCKER
+
 	String FASTQCdocker
 	String FASTQSCREENdocker
 	String QUALIMAPdocker
 
 		call mapping.mapping as mapping_D5 {
 			input: 
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
-			SENTIEON_LICENSE=SENTIEON_LICENSE,
 			pl=pl,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			group=project,
 			sample='LCL5',
 			project=project,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Dedup.Dedup as Dedup_D5 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			sorted_bam=mapping_D5.sorted_bam,
 			sorted_bam_index=mapping_D5.sorted_bam_index,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call deduped_Metrics.deduped_Metrics as deduped_Metrics_D5 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			bed=bed,
 			Dedup_bam=Dedup_D5.Dedup_bam,
 			Dedup_bam_index=Dedup_D5.Dedup_bam_index,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			interval_list=bed_to_interval_list.interval_list,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 			disk_size=disk_size		
 		}
 
+		## Bam realignment doesn't support in GATK 4
 		call Realigner.Realigner as Realigner_D5 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			Dedup_bam=Dedup_D5.Dedup_bam,
 			Dedup_bam_index=Dedup_D5.Dedup_bam_index,
 			db_mills=db_mills,
 			dbmills_dir=dbmills_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
-		call BQSR.BQSR as BQSR_D5 {
+		call BQSR.BQSR as BQSR_D5{
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
-			realigned_bam=Realigner_D5.realigner_bam,
-			realigned_bam_index=Realigner_D5.realigner_bam_index,
+			realigned_bam=Realigner_M8.realigner_bam,
+			realigned_bam_index=Realigner_M8.realigner_bam_index,
 			db_mills=db_mills,
 			dbmills_dir=dbmills_dir,
 			dbsnp=dbsnp,
 			dbsnp_dir=dbsnp_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Haplotyper.Haplotyper as Haplotyper_D5 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			recaled_bam=BQSR_D5.recaled_bam,
 			recaled_bam_index=BQSR_D5.recaled_bam_index,
-			docker=SENTIEONdocker,
+			docker=DEEPVARIANT_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call mapping.mapping as mapping_D6 {
 			input: 
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
-			SENTIEON_LICENSE=SENTIEON_LICENSE,
 			pl=pl,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			group=project,
 			sample='LCL6',
 			project=project,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Dedup.Dedup as Dedup_D6 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			sorted_bam=mapping_D6.sorted_bam,
 			sorted_bam_index=mapping_D6.sorted_bam_index,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call deduped_Metrics.deduped_Metrics as deduped_Metrics_D6 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			bed=bed,
 			Dedup_bam=Dedup_D6.Dedup_bam,
 			Dedup_bam_index=Dedup_D6.Dedup_bam_index,
 			interval_list=bed_to_interval_list.interval_list,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Realigner.Realigner as Realigner_D6 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			Dedup_bam=Dedup_D6.Dedup_bam,
 			Dedup_bam_index=Dedup_D6.Dedup_bam_index,
 			db_mills=db_mills,
 			dbmills_dir=dbmills_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call BQSR.BQSR as BQSR_D6 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			realigned_bam=Realigner_D6.realigner_bam,
 			dbmills_dir=dbmills_dir,
 			dbsnp=dbsnp,
 			dbsnp_dir=dbsnp_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Haplotyper.Haplotyper as Haplotyper_D6 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			recaled_bam=BQSR_D6.recaled_bam,
 			recaled_bam_index=BQSR_D6.recaled_bam_index,
-			docker=SENTIEONdocker,
+			docker=DEEPVARIANT_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 	
 		call mapping.mapping as mapping_F7 {
 			input: 
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
-			SENTIEON_LICENSE=SENTIEON_LICENSE,
 			pl=pl,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			group=project,
 			sample='LCL7',
 			project=project,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Dedup.Dedup as Dedup_F7 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			sorted_bam=mapping_F7.sorted_bam,
 			sorted_bam_index=mapping_F7.sorted_bam_index,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call deduped_Metrics.deduped_Metrics as deduped_Metrics_F7 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			bed=bed,
 			Dedup_bam=Dedup_F7.Dedup_bam,
 			Dedup_bam_index=Dedup_F7.Dedup_bam_index,
 			interval_list=bed_to_interval_list.interval_list,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Realigner.Realigner as Realigner_F7 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			Dedup_bam=Dedup_F7.Dedup_bam,
 			Dedup_bam_index=Dedup_F7.Dedup_bam_index,
 			db_mills=db_mills,
 			dbmills_dir=dbmills_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call BQSR.BQSR as BQSR_F7 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			realigned_bam=Realigner_F7.realigner_bam,
 			dbmills_dir=dbmills_dir,
 			dbsnp=dbsnp,
 			dbsnp_dir=dbsnp_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Haplotyper.Haplotyper as Haplotyper_F7 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			recaled_bam=BQSR_F7.recaled_bam,
 			recaled_bam_index=BQSR_F7.recaled_bam_index,
-			docker=SENTIEONdocker,
+			docker=DEEPVARIANT_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 	
 		call mapping.mapping as mapping_M8 {
 			input: 
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
-			SENTIEON_LICENSE=SENTIEON_LICENSE,
 			pl=pl,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			group=project,
 			project=project,
 			sample='LCL8',
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Dedup.Dedup as Dedup_M8 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			sorted_bam=mapping_M8.sorted_bam,
 			sorted_bam_index=mapping_M8.sorted_bam_index,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call deduped_Metrics.deduped_Metrics as deduped_Metrics_M8 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			bed=bed,
 			Dedup_bam=Dedup_M8.Dedup_bam,
 			Dedup_bam_index=Dedup_M8.Dedup_bam_index,
 			interval_list=bed_to_interval_list.interval_list,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Realigner.Realigner as Realigner_M8 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			Dedup_bam=Dedup_M8.Dedup_bam,
 			Dedup_bam_index=Dedup_M8.Dedup_bam_index,
 			db_mills=db_mills,
 			dbmills_dir=dbmills_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call BQSR.BQSR as BQSR_M8 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			realigned_bam=Realigner_M8.realigner_bam,
 			dbmills_dir=dbmills_dir,
 			dbsnp=dbsnp,
 			dbsnp_dir=dbsnp_dir,
-			docker=SENTIEONdocker,
+			docker=REPLACE_SENTIEON_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
 
 		call Haplotyper.Haplotyper as Haplotyper_M8 {
 			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 			fasta=fasta,
 			ref_dir=ref_dir,
 			recaled_bam=BQSR_M8.recaled_bam,
 			recaled_bam_index=BQSR_M8.recaled_bam_index,
-			docker=SENTIEONdocker,
+			docker=DEEPVARIANT_DOCKER,
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}