Update README.md

WES/README.md

@@ -43,26 +43,35 @@ Below the workflow and commands used:
 We implemented several layers of annotation using different datasets including [SNPeff](http://pcingola.github.io/SnpEff/) (v.86), [dbSNP](https://www.ncbi.nlm.nih.gov/snp/) (v.152), [dbNSFP4](http://database.liulab.science/dbNSFP) (4.0a for academic). 
 
 ```
-snpEff -v -csvStats ${sampleid}\_rawstats_canon.csv -s ${sampleid}\_rawstats_canon.html -canon GRCh38.86 Mutect2_raw_call_${sampleid}\_exome_refseq_light_filtered.vcf.gz > $sampleid\_raw_annot_refseq_light_filtered.vcf
+snpEff -v -csvStats SampleID_rawstats_canon.csv -s SampleID_rawstats_canon.html -canon GRCh38.86 Mutect2_raw_call_SampleID_exome_refseq_light_filtered.vcf.gz > SampleID_raw_annot_refseq_light_filtered.vcf
 
 # dbSNP annotation
 
-SnpSift annotate $dbsnp ${sampleid}\_raw_annot_refseq_light_filtered.vcf > ${sampleid}\_dbsnp_refseq_light_filtered.vcf
-gatk IndexFeatureFile -I ${sampleid}\_dbsnp_refseq_light_filtered.vcf
+SnpSift annotate $dbsnp SampleID_raw_annot_refseq_light_filtered.vcf > SampleID_dbsnp_refseq_light_filtered.vcf
+gatk IndexFeatureFile -I SampleID_dbsnp_refseq_light_filtered.vcf
 
 # Cosmic annotation (coding)
 
-SnpSift annotate $cosmic ${sampleid}\_dbsnp_refseq_light_filtered.vcf > ${sampleid}\_dbsnp_cc_refseq_light_filtered.vcf
-gatk IndexFeatureFile -I ${sampleid}\_dbsnp_cc_refseq_light_filtered.vcf
+SnpSift annotate $cosmic SampleID_dbsnp_refseq_light_filtered.vcf > SampleID_dbsnp_cc_refseq_light_filtered.vcf
+gatk IndexFeatureFile -I SampleID_dbsnp_cc_refseq_light_filtered.vcf
 
 # Cosmic annotation (non coding)
 
-SnpSift annotate $cosmicnc ${sampleid}\_dbsnp_cc_refseq_light_filtered.vcf > ${sampleid}\_dbsnp_cc_cnc_refseq_light_filtered.vcf
-gatk IndexFeatureFile -I ${sampleid}\_dbsnp_cc_cnc_refseq_light_filtered.vcf
+SnpSift annotate $cosmicnc SampleID_dbsnp_cc_refseq_light_filtered.vcf > SampleID_dbsnp_cc_cnc_refseq_light_filtered.vcf
+gatk IndexFeatureFile -I SampleID_dbsnp_cc_cnc_refseq_light_filtered.vcf
 
 # dbNSFP4 annotation 
 
-SnpSift dbnsfp -db dbNSFP4.0a/dbNSFP4.0a.txt.gz -v ${sampleid}\_dbsnp_cc_cnc_refseq_light_filtered.vcf  > ${sampleid}\_dbsnp_cc_cnc_dbnsfp_refseq_light_filtered.vcf
+SnpSift dbnsfp -db dbNSFP4.0a/dbNSFP4.0a.txt.gz -v SampleID_dbsnp_cc_cnc_refseq_light_filtered.vcf  > SampleID_dbsnp_cc_cnc_dbnsfp_refseq_light_filtered.vcf
+
+# NOTE: a pass-only version is also produced by picking-up only PASS variants:  
+
+bcftools_viewCommand=view -f PASS -O z Mutect2_raw_call_SampleID_exome_refseq_light_filtered_DP10.vcf.gz
+- SnpEff  -csvStats SampleID_rawstats_canon.csv -s SampleID_rawstats_canon.html GRCh38.86 Mutect2_raw_call_SampleID_exome_refseq_light_filtered_DP10_PASS.vcf.gz
+- SnpSift Annotate dbSNP.v152.vcf.gz SampleID_raw_annot_refseq_light.vcf
+- SnpSift Annotate CosmicCodingMuts.vcf.gz SampleID_dbsnp_refseq_light.vcf
+- SnpSift Annotate CosmicNonCodingVariants.vcf.gz SampleID_dbsnp_cc_refseq_light.vcf
+- SnpSift DbNsfp SampleID_dbsnp_cc_cnc_refseq_light.vcf
 
 ```
 
@@ -71,7 +80,10 @@ SnpSift dbnsfp -db dbNSFP4.0a/dbNSFP4.0a.txt.gz -v ${sampleid}\_dbsnp_cc_cnc_ref
 We leverage SnpSift extractfield function for selecting fields of interest and performing Allele Fraction analysis.
 
 ```
-- SnpSift extractFields ${sampleid}_dbsnp_cc_cnc_dbnsfp_refseq_light_filtered.vcf CHROM POS REF ALT GEN[0].AF GEN[0].DP GEN[0].AD[0] GEN[0].AD[1] GEN[0].GT ID FILTER ANN[0].HGVS_P ANN[0].GENE ANN[0].BIOTYPE ANN[0].RANK ANN[0].EFFECT ANN[0].IMPACT COMMON G5 dbNSFP_ExAC_Adj_AF dbNSFP_1000Gp3_AF dbNSFP_ExAC_AF dbNSFP_phastCons100way_vertebrate dbNSFP_FATHMM_pred dbNSFP_GERP___RS dbNSFP_GERP___NR dbNSFP_CADD_phred dbNSFP_MetaSVM_pred dbNSFP_LRT_pred dbNSFP_PROVEAN_pred dbNSFP_MutationTaster_pred dbNSFP_MutationAssessor_pred dbNSFP_SIFT_pred dbNSFP_Polyphen2_HVAR_pred dbNSFP_Polyphen2_HDIV_pred > ${sampleid}_dbsnp_cc_cnc_dbnsfp_refseq_light_raw_filtered.fields.txt
+- SnpSift extractFields SampleID_dbsnp_cc_cnc_dbnsfp_refseq_light_filtered.vcf CHROM POS REF ALT GEN[0].AF GEN[0].DP GEN[0].AD[0] GEN[0].AD[1] GEN[0].GT ID FILTER ANN[0].HGVS_P ANN[0].GENE ANN[0].BIOTYPE ANN[0].RANK ANN[0].EFFECT ANN[0].IMPACT COMMON G5 dbNSFP_ExAC_Adj_AF dbNSFP_1000Gp3_AF dbNSFP_ExAC_AF dbNSFP_phastCons100way_vertebrate dbNSFP_FATHMM_pred dbNSFP_GERP___RS dbNSFP_GERP___NR dbNSFP_CADD_phred dbNSFP_MetaSVM_pred dbNSFP_LRT_pred dbNSFP_PROVEAN_pred dbNSFP_MutationTaster_pred dbNSFP_MutationAssessor_pred dbNSFP_SIFT_pred dbNSFP_Polyphen2_HVAR_pred dbNSFP_Polyphen2_HDIV_pred > SampleID_dbsnp_cc_cnc_dbnsfp_refseq_light_raw_filtered.fields.txt
+
+SnpSift extractFields SampleID_dbsnp_cc_cnc_dbnsfp_refseq_light.vcf CHROM POS REF ALT GEN[0].AF GEN[0].DP GEN[0].AD[0] GEN[0].AD[1] GEN[0].GT ID FILTER ANN[0].HGVS_P ANN[0].GENE ANN[0].BIOTYPE ANN[0].RANK ANN[0].EFFECT ANN[0].IMPACT COMMON G5 dbNSFP_ExAC_Adj_AF dbNSFP_1000Gp3_AF dbNSFP_ExAC_AF dbNSFP_phastCons100way_vertebrate dbNSFP_FATHMM_pred dbNSFP_GERP___RS dbNSFP_GERP___NR dbNSFP_CADD_phred dbNSFP_MetaSVM_pred dbNSFP_LRT_pred dbNSFP_PROVEAN_pred dbNSFP_MutationTaster_pred dbNSFP_MutationAssessor_pred dbNSFP_SIFT_pred dbNSFP_Polyphen2_HVAR_pred dbNSFP_Polyphen2_HDIV_pred > SampleID_dbsnp_cc_cnc_dbnsfp_refseq_light.fields.txt
+
 ```