metrics

codescripts/extract_multiqc.py

@@ -1,66 +0,0 @@
-import json
-import pandas as pd
-import sys, argparse, os
-
-parser = argparse.ArgumentParser(description="This script is to get information from multiqc")
-
-parser.add_argument('-fastqc_qualimap', '--fastqc_qualimap', type=str, help='multiqc_general_stats.txt',  required=True)
-parser.add_argument('-fastqc', '--fastqc', type=str, help='multiqc_fastqc.txt',  required=True)
-parser.add_argument('-fastqscreen', '--fastqscreen', type=str, help='multiqc_fastq_screen.txt',  required=True)
-parser.add_argument('-hap', '--happy', type=str, help='multiqc_happy_data.json',  required=True)
-
-args = parser.parse_args()
-
-# Rename input:
-fastqc_qualimap_file = args.fastqc_qualimap
-fastqc_file = args.fastqc
-fastqscreen_file = args.fastqscreen
-hap_file = args.happy
-
-
-# fastqc and qualimap
-dat = pd.read_table(fastqc_qualimap_file)
-
-fastqc = dat.loc[:, dat.columns.str.startswith('FastQC')]
-fastqc.insert(loc=0, column='Sample', value=dat['Sample'])
-fastqc_stat = fastqc.dropna()
-
-# qulimap
-qualimap = dat.loc[:, dat.columns.str.startswith('QualiMap')]
-qualimap.insert(loc=0, column='Sample', value=dat['Sample'])
-qualimap_stat = qualimap.dropna()
-
-# fastqc
-dat = pd.read_table(fastqc_file)
-
-fastqc_module = dat.loc[:, "per_base_sequence_quality":"kmer_content"]
-fastqc_module.insert(loc=0, column='Sample', value=dat['Sample'])
-fastqc_all = pd.merge(fastqc_stat,fastqc_module,  how='outer', left_on=['Sample'], right_on = ['Sample'])
-
-# fastqscreen
-dat = pd.read_table(fastqscreen_file)
-fastqscreen = dat.loc[:, dat.columns.str.endswith('percentage')]
-dat['Sample'] = [i.replace('_screen','') for i in dat['Sample']]
-fastqscreen.insert(loc=0, column='Sample', value=dat['Sample'])
-
-# benchmark
-with open(hap_file) as hap_json:
-	happy = json.load(hap_json)
-dat =pd.DataFrame.from_records(happy)
-dat = dat.loc[:, dat.columns.str.endswith('ALL')]
-dat_transposed = dat.T
-benchmark = dat_transposed.loc[:,['sample_id','METRIC.Precision','METRIC.Recall']]
-benchmark['sample_id'] = benchmark.index
-benchmark.columns = ['Sample','Precision','Recall']
-
-#output
-fastqc_all.to_csv('fastqc.final.result.txt',sep="\t",index=0)
-fastqscreen.to_csv('fastqscreen.final.result.txt',sep="\t",index=0)
-qualimap_stat.to_csv('qualimap.final.result.txt',sep="\t",index=0)
-benchmark.to_csv('benchmark.final.result.txt',sep="\t",index=0)
-
-
-
-
-
-

codescripts/post-alignment.py

@@ -0,0 +1,101 @@
+import json
+import pandas as pd
+import sys, argparse, os
+import statistics 
+
+parser = argparse.ArgumentParser(description="This script is to summary information for pre-alignment QC")
+
+parser.add_argument('-general', '--general_stat', type=str, help='multiqc_general_stats.txt',  required=True)
+parser.add_argument('-is', '--is_metrics', type=str, help='_is_metrics.txt',  required=True)
+parser.add_argument('-wgsmetrics', '--WgsMetricsAlgo', type=str, help='deduped_WgsMetricsAlgo',  required=True)
+parser.add_argument('-qualityyield', '--QualityYield', type=str, help='deduped_QualityYield',  required=True)
+parser.add_argument('-aln', '--aln_metrics', type=str, help='aln_metrics.txt',  required=True)
+
+args = parser.parse_args()
+
+general_file = args.general_stat
+is_file = args.is_metrics
+wgsmetrics_file = args.wgsmetrics
+qualityyield_file = args.qualityyield
+aln_file = args.aln_metrics
+
+##### Table
+## general stat: % GC
+dat = pd.read_table(general_file)
+qualimap = dat.loc[:, dat.columns.str.startswith('QualiMap')]
+qualimap.insert(loc=0, column='Sample', value=dat['Sample'])
+qualimap_stat = qualimap.dropna()
+part1 = fastqc_stat.loc[:,['Sample', 'FastQC_mqc-generalstats-fastqc-percent_duplicates','FastQC_mqc-generalstats-fastqc-total_sequences']]
+
+## is_metrics: median insert size
+## deduped_WgsMetricsAlgo: 1x, 5x, 10x, 30x, median coverage
+with open(html_file) as file:
+	origDict = json.load(file)
+newdict = {(k1, k2):v2 for k1,v1 in origDict.items() \
+                       for k2,v2 in origDict[k1].items()}
+df = pd.DataFrame([newdict[i] for i in sorted(newdict)],
+                  index=pd.MultiIndex.from_tuples([i for i in sorted(newdict.keys())]))
+gc = []
+at = []
+for i in part1['Sample']:
+	sub_df = df.loc[i,:]
+	gc.append(statistics.mean(sub_df['g']/sub_df['c']))
+	at.append(statistics.mean(sub_df['a']/sub_df['t']))
+
+## fastq_screen
+dat = pd.read_table(fastqscreen_file)
+fastqscreen = dat.loc[:, dat.columns.str.endswith('percentage')]
+del fastqscreen['ERCC percentage']
+del fastqscreen['Phix percentage']
+
+### merge all information
+part1.insert(loc=3, column='G/C ratio', value=gc)
+part1.insert(loc=4, column='A/T ratio', value=at)
+part1.reset_index(drop=True, inplace=True)
+fastqscreen.reset_index(drop=True, inplace=True)
+df = pd.concat([part1, fastqscreen], axis=1)
+df = df.append(df.mean(axis=0),ignore_index=True)
+df = df.fillna('Batch average value')
+df.columns = ['Sample','Total sequences (million)','% Dup','G/C ratio','A/T ratio','% Human','% EColi','% Adapter' , '% Vector','% rRNA' , '% Virus','% Yeast' ,'% Mitoch' ,'% No hits']
+df.to_csv('per-alignment_table_summary.txt',sep='\t',index=False)
+
+##### Picture
+## cumulative genome coverage
+with open(json_file) as file:
+	all_dat = json.load(file)
+genome_coverage_json = all_dat['report_plot_data']['qualimap_genome_fraction']['datasets'][0]
+dat =pd.DataFrame.from_records(genome_coverage_json)
+genome_coverage = pd.DataFrame(index=pd.DataFrame(dat.loc[0,'data'])[0])
+for i in range(dat.shape[0]):
+	one_sample = pd.DataFrame(dat.loc[i,'data'])
+	one_sample.index = one_sample[0]
+	genome_coverage[dat.loc[i,'name']] = one_sample[1]
+genome_coverage = genome_coverage.transpose() 
+genome_coverage['Sample'] = genome_coverage.index
+genome_coverage.to_csv('post-alignment_genome_coverage.txt',sep='\t',index=False)
+
+## insert size histogram
+insert_size_json = all_dat['report_plot_data']['qualimap_insert_size']['datasets'][0]
+dat =pd.DataFrame.from_records(insert_size_json)
+insert_size = pd.DataFrame(index=pd.DataFrame(dat.loc[0,'data'])[0])
+for i in range(dat.shape[0]):
+	one_sample = pd.DataFrame(dat.loc[i,'data'])
+	one_sample.index = one_sample[0]
+	insert_size[dat.loc[i,'name']] = one_sample[1]
+insert_size = insert_size.transpose() 
+insert_size['Sample'] = insert_size.index
+insert_size.to_csv('post-alignment_insert_size.txt',sep='\t',index=False)
+
+## GC content distribution
+gc_content_json = all_dat['report_plot_data']['qualimap_gc_content']['datasets'][0]
+dat =pd.DataFrame.from_records(gc_content_json)
+gc_content = pd.DataFrame(index=pd.DataFrame(dat.loc[0,'data'])[0])
+for i in range(dat.shape[0]):
+	one_sample = pd.DataFrame(dat.loc[i,'data'])
+	one_sample.index = one_sample[0]
+	gc_content[dat.loc[i,'name']] = one_sample[1]
+gc_content = gc_content.transpose() 
+gc_content['Sample'] = gc_content.index
+gc_content.to_csv('post-alignment_gc_content.txt',sep='\t',index=False)
+
+

codescripts/pre_alignment.py

@@ -0,0 +1,132 @@
+import json
+import pandas as pd
+import sys, argparse, os
+import statistics 
+
+parser = argparse.ArgumentParser(description="This script is to summary information for pre-alignment QC")
+
+parser.add_argument('-general', '--general_stat', type=str, help='multiqc_general_stats.txt',  required=True)
+parser.add_argument('-html', '--html', type=str, help='multiqc_report.html',  required=True)
+parser.add_argument('-fastqscreen', '--fastqscreen', type=str, help='multiqc_fastq_screen.txt',  required=True)
+parser.add_argument('-json', '--json', type=str, help='multiqc_happy_data.json',  required=True)
+
+args = parser.parse_args()
+
+general_file = args.general_stat
+html_file = args.html
+fastqscreen_file = args.fastqscreen
+json_file = args.json
+
+##### Table
+## general stat: 1. Total sequences; 2. %Dup
+dat = pd.read_table(general_file)
+
+fastqc = dat.loc[:, dat.columns.str.startswith('FastQC')]
+fastqc.insert(loc=0, column='Sample', value=dat['Sample'])
+fastqc_stat = fastqc.dropna()
+part1 = fastqc_stat.loc[:,['Sample', 'FastQC_mqc-generalstats-fastqc-percent_duplicates','FastQC_mqc-generalstats-fastqc-total_sequences']]
+
+## report html: 1. G/C ratio; 2. A/T ratio
+## cat multiqc_report.html | grep 'fastqc_seq_content_data = ' | sed s'/fastqc_seq_content_data\ =\ //g' | sed 's/^[ \t]*//g' | sed s'/;//g' > fastqc_sequence_content.json
+with open(html_file) as file:
+	origDict = json.load(file)
+newdict = {(k1, k2):v2 for k1,v1 in origDict.items() \
+                       for k2,v2 in origDict[k1].items()}
+df = pd.DataFrame([newdict[i] for i in sorted(newdict)],
+                  index=pd.MultiIndex.from_tuples([i for i in sorted(newdict.keys())]))
+gc = []
+at = []
+for i in part1['Sample']:
+	sub_df = df.loc[i,:]
+	gc.append(statistics.mean(sub_df['g']/sub_df['c']))
+	at.append(statistics.mean(sub_df['a']/sub_df['t']))
+
+## fastq_screen
+dat = pd.read_table(fastqscreen_file)
+fastqscreen = dat.loc[:, dat.columns.str.endswith('percentage')]
+del fastqscreen['ERCC percentage']
+del fastqscreen['Phix percentage']
+
+### merge all information
+part1.insert(loc=3, column='G/C ratio', value=gc)
+part1.insert(loc=4, column='A/T ratio', value=at)
+part1.reset_index(drop=True, inplace=True)
+fastqscreen.reset_index(drop=True, inplace=True)
+df = pd.concat([part1, fastqscreen], axis=1)
+df = df.append(df.mean(axis=0),ignore_index=True)
+df = df.fillna('Batch average value')
+df.columns = ['Sample','Total sequences (million)','% Dup','G/C ratio','A/T ratio','% Human','% EColi','% Adapter' , '% Vector','% rRNA' , '% Virus','% Yeast' ,'% Mitoch' ,'% No hits']
+df.to_csv('per-alignment_table_summary.txt',sep='\t',index=False)
+
+##### Picture
+## mean quality scores
+with open(json_file) as file:
+	all_dat = json.load(file)
+mean_quality_json = all_dat['report_plot_data']['fastqc_per_base_sequence_quality_plot']['datasets'][0]
+dat =pd.DataFrame.from_records(mean_quality_json)
+mean_quality = pd.DataFrame(index=pd.DataFrame(dat.loc[0,'data'])[0])
+for i in range(dat.shape[0]):
+	one_sample = pd.DataFrame(dat.loc[i,'data'])
+	one_sample.index = one_sample[0]
+	mean_quality[dat.loc[i,'name']] = one_sample[1]
+mean_quality = mean_quality.transpose() 
+mean_quality['Sample'] = mean_quality.index
+mean_quality.to_csv('pre-alignment_mean_quality.txt',sep='\t',index=False)
+
+## per sequence GC content
+
+gc_content_json = all_dat['report_plot_data']['fastqc_per_sequence_gc_content_plot']['datasets'][0]
+dat =pd.DataFrame.from_records(gc_content_json)
+gc_content = pd.DataFrame(index=pd.DataFrame(dat.loc[0,'data'])[0])
+for i in range(dat.shape[0]):
+	one_sample = pd.DataFrame(dat.loc[i,'data'])
+	one_sample.index = one_sample[0]
+	gc_content[dat.loc[i,'name']] = one_sample[1]
+gc_content = gc_content.transpose() 
+gc_content['Sample'] = gc_content.index
+gc_content.to_csv('pre-alignment_gc_content.txt',sep='\t',index=False)
+
+# fastqc and qualimap
+dat = pd.read_table(fastqc_qualimap_file)
+
+fastqc = dat.loc[:, dat.columns.str.startswith('FastQC')]
+fastqc.insert(loc=0, column='Sample', value=dat['Sample'])
+fastqc_stat = fastqc.dropna()
+
+# qulimap
+qualimap = dat.loc[:, dat.columns.str.startswith('QualiMap')]
+qualimap.insert(loc=0, column='Sample', value=dat['Sample'])
+qualimap_stat = qualimap.dropna()
+
+# fastqc
+dat = pd.read_table(fastqc_file)
+
+fastqc_module = dat.loc[:, "per_base_sequence_quality":"kmer_content"]
+fastqc_module.insert(loc=0, column='Sample', value=dat['Sample'])
+fastqc_all = pd.merge(fastqc_stat,fastqc_module,  how='outer', left_on=['Sample'], right_on = ['Sample'])
+
+# fastqscreen
+dat = pd.read_table(fastqscreen_file)
+fastqscreen = dat.loc[:, dat.columns.str.endswith('percentage')]
+dat['Sample'] = [i.replace('_screen','') for i in dat['Sample']]
+fastqscreen.insert(loc=0, column='Sample', value=dat['Sample'])
+
+# benchmark
+with open(hap_file) as hap_json:
+	happy = json.load(hap_json)
+dat =pd.DataFrame.from_records(happy)
+dat = dat.loc[:, dat.columns.str.endswith('ALL')]
+dat_transposed = dat.T
+benchmark = dat_transposed.loc[:,['sample_id','METRIC.Precision','METRIC.Recall']]
+benchmark['sample_id'] = benchmark.index
+benchmark.columns = ['Sample','Precision','Recall']
+
+#output
+fastqc_all.to_csv('fastqc.final.result.txt',sep="\t",index=0)
+fastqscreen.to_csv('fastqscreen.final.result.txt',sep="\t",index=0)
+qualimap_stat.to_csv('qualimap.final.result.txt',sep="\t",index=0)
+benchmark.to_csv('benchmark.final.result.txt',sep="\t",index=0)
+
+
+
+

tasks/Metrics.wdl

@@ -1,5 +1,6 @@
 task Metrics {
 
+
     File ref_dir
 	String SENTIEON_INSTALL_DIR
 	String sample
@@ -10,6 +11,8 @@ task Metrics {
 	File sorted_bam
 	File sorted_bam_index
 	String disk_size
+	
+
 
 	command <<<
 		set -o pipefail

tasks/benchmark.wdl

@@ -34,13 +34,13 @@ task benchmark {
 		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.rtg.vcf.gz
 
 		if [[ ${sample} =~ "LCL5" ]];then
-			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL5.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL5.high.confidence.bed --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL5.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL5.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
 	    elif [[ ${sample} =~ "LCL6" ]]; then
-	    	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL6.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL6.high.confidence.bed --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+	    	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL6.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL6.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
         elif [[ ${sample} =~ "LCL7" ]]; then
-        	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL7.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL7.high.confidence.bed --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+        	/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL7.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL7.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
 	    elif [[ ${sample} =~ "LCL8" ]]; then
-			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL8.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL8.high.confidence.bed --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+			/opt/hap.py/bin/hap.py ${benchmarking_dir}/LCL8.afterfilterdiffbed.vcf.gz ${sample}.rtg.vcf.gz -f ${benchmarking_dir}/LCL8.high.confidence.bed.gz --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
         else
         	echo "only for quartet samples"
         fi		

tasks/deduped_Metrics.wdl

@@ -17,7 +17,7 @@ task deduped_Metrics {
 		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 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
+		${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
 	>>>
 
 	runtime {
@@ -33,5 +33,13 @@ task deduped_Metrics {
 		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"
+		File deduped_wgsmetrics = "${sample}_deduped_WgsMetricsAlgo.txt"
 	}
 }

tasks/extract_multiqc.wdl → tasks/extract_tables.wdl

@@ -1,6 +1,5 @@
-task extract_multiqc {
+task extract_tables {
 
-	File fastqc_qualimap
 	File fastqc
 	File fastqscreen
 	File hap

tasks/mergeSentieon.wdl

@@ -2,14 +2,14 @@ task mergeSentieon {
 	Array[File] aln_metrics_header
 	Array[File] aln_metrics_data
 
-	Array[File] dedup_metrics_header
-	Array[File] dedup_metrics_data
-
 	Array[File] is_metrics_header
 	Array[File] is_metrics_data
 
-	Array[File] deduped_coverage_header
-	Array[File] deduped_coverage_data
+	Array[File] quality_yield_header
+	Array[File] quality_yield_data
+
+	Array[File] wgs_metrics_header
+	Array[File] wgs_metrics_data
 
 	String docker
 	String cluster_config
@@ -18,10 +18,13 @@ task mergeSentieon {
 	command <<<
 		set -o pipefail
 		set -e
-		cat ${sep=" " aln_metrics_header} | sed -n '1,1p' | cat - ${sep=" " aln_metrics_data} > aln_metrics.txt
-		cat ${sep=" " dedup_metrics_header} | sed -n '1,1p' | cat - ${sep=" " dedup_metrics_data} > dedup_metrics.txt
+		echo '''Sample''' > sample_column
+		cat ${sep=" " aln_metrics_header} | sed -n '1,1p' | cat - ${sep=" " aln_metrics_data} > aln_metrics
+		ls ${sep=" " aln_metrics_data} | cut -d '.' -f1 | cat sample_column - | paste - aln_metrics > aln_metrics.txt
 		cat ${sep=" " is_metrics_header} | sed -n '1,1p' | cat - ${sep=" " is_metrics_data} > is_metrics.txt
-		cat ${sep=" " deduped_coverage_header} | sed -n '1,1p' | cat - ${sep=" " deduped_coverage_data} > deduped_coverage.txt
+		
+		cat ${sep=" " quality_yield_header} | sed -n '1,1p' | cat - ${sep=" " quality_yield_data} > quality_yield_data.txt
+		cat ${sep=" " wgs_metrics_header} | sed -n '1,1p' | cat - ${sep=" " wgs_metrics_data} > wgs_metrics_data.txt		
 	>>>
 
 	runtime {
@@ -33,8 +36,8 @@ task mergeSentieon {
 
 	output {
 		File aln_metrics_merge = "aln_metrics.txt"
-		File dedup_metrics_merge = "dedup_metrics.txt"
 		File is_metrics_merge = "is_metrics.txt"
-		File deduped_coverage_merge = "deduped_coverage.txt"
+		File quality_yield_merge = "quality_yield_data.txt"
+		File wgs_metrics_merge = "wgs_metrics_data.txt"
 	}
 }

tasks/multiqc.wdl

@@ -32,7 +32,6 @@ task multiqc {
 		multiqc /cromwell_root/tmp/
 
 		cat multiqc_data/multiqc_general_stats.txt > multiqc_general_stats.txt
-		cat multiqc_data/multiqc_fastqc.txt > multiqc_fastqc.txt
 		cat multiqc_data/multiqc_fastq_screen.txt > multiqc_fastq_screen.txt
 		cat multiqc_data/multiqc_happy_data.json > multiqc_happy_data.json
 	
@@ -48,8 +47,7 @@ task multiqc {
 	output {
 		File multiqc_html = "multiqc_report.html"
 		Array[File] multiqc_txt = glob("multiqc_data/*")
-		File fastqc_qualimap = "multiqc_general_stats.txt"
-		File fastqc = "multiqc_fastqc.txt"
+		File fastqc = "multiqc_general_stats.txt"
 		File fastqscreen = "multiqc_fastq_screen.txt"
 		File hap = "multiqc_happy_data.json"
 	}

tasks/sentieon.wdl

@@ -1,9 +1,8 @@
 task sentieon {
 	File aln_metrics
-	File dedup_metrics
 	File is_metrics
-	File deduped_coverage
-	String sample_name
+	File wgsmetrics
+	File quality_yield
 	String docker
 	String cluster_config
 	String disk_size

workflow.wdl

@@ -1,5 +1,4 @@
 import "./tasks/mapping.wdl" as mapping
-import "./tasks/Metrics.wdl" as Metrics
 import "./tasks/Dedup.wdl" as Dedup
 import "./tasks/deduped_Metrics.wdl" as deduped_Metrics
 import "./tasks/Realigner.wdl" as Realigner
@@ -14,8 +13,7 @@ import "./tasks/merge_mendelian.wdl" as merge_mendelian
 import "./tasks/quartet_mendelian.wdl" as quartet_mendelian
 import "./tasks/fastqc.wdl" as fastqc
 import "./tasks/fastqscreen.wdl" as fastqscreen
-import "./tasks/qualimap.wdl" as qualimap
-import "./tasks/extract_multiqc.wdl" as extract_multiqc
+import "./tasks/extract_tables.wdl" as extract_tables
 import "./tasks/D5_D6.wdl" as D5_D6
 import "./tasks/merge_family.wdl" as merge_family
 
@@ -89,19 +87,6 @@ workflow {{ project_name }} {
 			disk_size=disk_size
 		}
 
-		call Metrics.Metrics as Metrics {
-			input:
-			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
-			fasta=fasta,
-			ref_dir=ref_dir,
-			sorted_bam=mapping.sorted_bam,
-			sorted_bam_index=mapping.sorted_bam_index,		
-			sample=quartet[2],
-			docker=SENTIEONdocker,
-			disk_size=disk_size,
-			cluster_config=BIGcluster_config
-		}
-
 		call Dedup.Dedup as Dedup {
 			input:
 			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
@@ -113,15 +98,6 @@ workflow {{ project_name }} {
 			cluster_config=BIGcluster_config
 		}
 
-		call qualimap.qualimap as qualimap {
-			input:
-			bam=Dedup.Dedup_bam,
-			bai=Dedup.Dedup_bam_index,
-			docker=QUALIMAPdocker,
-			cluster_config=BIGcluster_config,
-			disk_size=disk_size
-		}
-
 		call deduped_Metrics.deduped_Metrics as deduped_Metrics {
 			input:
 			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
@@ -165,6 +141,7 @@ workflow {{ project_name }} {
 			disk_size=disk_size,
 			cluster_config=BIGcluster_config
 		}
+
 		call Haplotyper_gVCF.Haplotyper_gVCF as Haplotyper_gVCF {
 			input:
 			SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
@@ -224,19 +201,20 @@ workflow {{ project_name }} {
 		read2_zip=fastqc.read2_zip,
 		txt1=fastqscreen.txt1,
 		txt2=fastqscreen.txt2,
-		zip=qualimap.zip,
 		summary=benchmark.summary,
 		docker=MULTIQCdocker,
 		cluster_config=SMALLcluster_config,
 		disk_size=disk_size
 	}
 
-	call extract_multiqc.extract_multiqc as extract_multiqc {
+	call extract_tables.extract_tables as extract_tables {
 		input:
-		fastqc_qualimap=multiqc.fastqc_qualimap,
 		fastqc=multiqc.fastqc,
 		fastqscreen=multiqc.fastqscreen,
 		hap=multiqc.hap,
+		aln=deduped_Metrics.dedeuped_aln_metrics,
+		quality_yield=deduped_Metrics.deduped_QualityYield,
+		wgs_metrics=deduped_Metrics.deduped_wgsmetrics,
 		docker=DIYdocker,
 		cluster_config=SMALLcluster_config,
 		disk_size=disk_size