#Preposed changes for GRCh38
Reference/
GRCh37/
GRCh38/
GATK_Bundle
GRCh37/
GRCh38/
##fileformat=VCFv4.2 | |
##ALT=<ID=NON_REF,Description="Represents any possible alternative allele at this location"> | |
##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed"> | |
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read depth"> | |
##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype quality"> | |
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> | |
##FORMAT=<ID=MIN_DP,Number=1,Type=Integer,Description="Minimum DP observed within the GVCF block"> | |
##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another"> | |
##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group"> | |
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="The phred-scaled genotype likelihoods rounded to the closest integer"> |
#Preposed changes for GRCh38
Reference/
GRCh37/
GRCh38/
GATK_Bundle
GRCh37/
GRCh38/
package main | |
import ( | |
"crypto/sha1" | |
"encoding/base64" | |
"fmt" | |
"log" | |
"runtime" | |
"sync" |
package main | |
import ( | |
"crypto/sha1" | |
"encoding/base64" | |
"fmt" | |
"log" | |
"runtime" | |
"sync" |
#!/usr/bin/env perl | |
use strict; | |
use warnings; | |
use feature 'say'; | |
use autodie; | |
open( my $FILE, '<', $ARGV[0] ) or die; | |
( my $individual = $ARGV[0] ) =~ s/\.data.prep.txt//g; | |
open(my $OUT, '>>', "$individual.align.txt") or die; |
$> ls NA06985/ | |
NA06985/ERR050082_1.filt.fastq.gz NA06985/ERR068361_1.filt.fastq.gz NA06985/SRR400038_1.filt.fastq.gz NA06985/SRR400039_1.filt.fastq.gz NA06985/SRR709972_1.filt.fastq.gz | |
NA06985/ERR050082_2.filt.fastq.gz NA06985/ERR068361_2.filt.fastq.gz NA06985/SRR400038_2.filt.fastq.gz NA06985/SRR400039_2.filt.fastq.gz NA06985/SRR709972_2.filt.fastq.gz | |
NA06985/ERR050082.filt.fastq.gz NA06985/ERR068361.filt.fastq.gz NA06985/SRR400038.filt.fastq.gz NA06985/SRR400039.filt.fastq.gz NA06985/SRR709972.filt.fastq.g | |
$> data_prep.pl NA06985/*fastq.gz > NA06985.data.prep.txt | |
$> perl alignMaker.pl NA06985.data.prep.txt | |
$> ls |
##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed"> | |
##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read depth"> | |
##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype quality"> | |
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype"> | |
##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another"> | |
##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group"> | |
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="The phred-scaled genotype likelihoods rounded to the closest integer"> | |
##FORMAT=<ID=SAC,Number=.,Type=Integer,Description="Number of reads on the forward and reverse strand supporting each allele (including reference)"> | |
##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for |
cmdline: /sentieon-genomics-201808.03/libexec/driver --thread_count 30 -r /scratch/ucgd/lustre/common/data/Reference/GRCh38/human_g1k_v38_decoy_phix.fasta --interval /scratch/ucgd/lustre/common/data/Regions/GRCh38/UCGD.CDS.Region.bed --algo VarCal --vcf 17-10-27_Test-Yandell-Disease_merged.vcf.gz --var_type SNP --tranches_file 17-10-27_Test-Yandell-Disease_recal.tranches.snp --resource /scratch/ucgd/lustre/common/data/GATK_Bundle/GRCh38/hapmap_3.3.hg38.vcf.gz --resource_param hapmap,known=false,training=true,truth=true,prior=15.0 --resource /scratch/ucgd/lustre/common/data/GATK_Bundle/GRCh38/1000G_omni2.5.hg38.vcf.gz --resource_param omni,known=false,training=true,truth=true,prior=12.0 --resource /scratch/ucgd/lustre/common/data/GATK_Bundle/GRCh38/1000G_phase1.snps.high_confidence.hg38.vcf.gz --resource_param 1000G,known=false,training=true,truth=false,prior=10.0 --resource /scratch/ucgd/lustre/common/data/GATK_Bundle/GRCh38/dbsnp_138.hg38.vcf.gz --resource_param dbsnp,known=true,training=false,truth=false,pr |
REMOVE RAW_MQ: | |
... | |
progress 100% @chrX:154320758, elapsed 5.6s, est remaining 0.0s, peak mem 281MB, user 156.8s, sys 3.6s, output queue size 887 | |
data size = 175996 | |
There is no training data for annotation SAC for var_type SNP. Please remove SAC from annotations | |
REMOVE SAC: | |
... | |
progress 100% @chrX:154320758, elapsed 9.5s, est remaining 0.0s, peak mem 321MB, user 154.3s, sys 3.8s, output queue size 887 | |
data size = 175996 |
Error: Package: kmod-lustre-client-2.10.6-1.el7.x86_64 (/kmod-lustre-client-2.10.6-1.el7.x86_64) | |
Requires: kernel(clear_page_dirty_for_io) = 0x2e1a09e1 | |
Installed: kernel-4.14.88-88.73.amzn2.x86_64 (installed) | |
kernel(clear_page_dirty_for_io) = 0xba614b0b | |
Installed: kernel-4.14.101-91.76.amzn2.x86_64 (@amzn2-core) | |
kernel(clear_page_dirty_for_io) = 0x49960ae2 | |
Available: kernel-4.9.62-10.57.amzn2.x86_64 (amzn2-core) | |
kernel(clear_page_dirty_for_io) = 0xd3ad0089 | |
Available: kernel-4.9.70-2.243.amzn2.x86_64 (amzn2-core) | |
kernel(clear_page_dirty_for_io) = 0x69b783ca |