From 537f6c09e16dcddd8ae193f1a70c600c6bd274c6 Mon Sep 17 00:00:00 2001 From: ameyner2 <alison.meynert@ed.ac.uk> Date: Fri, 13 Aug 2021 10:43:50 +0100 Subject: [PATCH] Initial documentation of software installation on ultra2 (sdf-cs1) at EIDF/EPCC. Got as far as executing bcbio base installation. --- docs/Software_installation_ultra2.md | 176 +++++++++++++++++++++++++++ 1 file changed, 176 insertions(+) create mode 100644 docs/Software_installation_ultra2.md diff --git a/docs/Software_installation_ultra2.md b/docs/Software_installation_ultra2.md new file mode 100644 index 0000000..19fe100 --- /dev/null +++ b/docs/Software_installation_ultra2.md @@ -0,0 +1,176 @@ +# Installation of software for trio whole exome project + +## Aspera + +Downloaded Aspera Connect version 3.9.6.1467 installer script from https://downloads.asperasoft.com to /home/u035/project/software/install and run it. This installs the software in ~/.aspera, so it needs to be moved to the shared folder. + +``` +bash ibm-aspera-cli-3.9.6.1467.159c5b1-linux-64-release.sh +mv ~/.aspera ../aspera +``` + +## bcbio + +Version 1.2.8 (14 April 2021). + +Start with installing the base software, and add datatargets. + +This will take a long time, and may require multiple runs if it fails on a step. It will resume if needed. Run on a screen session and log each attempt. It's important to set the limit on the number of concurrently open files to as high as possible (4096). + +``` +cd /home/u035/u035/shared/software/install +mkdir bcbio_install_logs + +wget https://raw.github.com/bcbio/bcbio-nextgen/master/scripts/bcbio_nextgen_install.py + +ulimit -n 4096 + +DATE=`date +%Y%m%d%H%M` +python3 bcbio_nextgen_install.py /home/u035/u035/shared/software/bcbio \ + --tooldir /home/u035/u035/shared/software/bcbio/tools \ + --genomes hg38 --aligners bwa \ + --cores 128 &> bcbio_install_logs/bcbio_install_base_${DATE}.log +``` + +Note: this could be fixed in version 1.2.8. Check htslib version after base install. + +Fix an issue with bcbio & vt/samtools/htslib. See https://github.com/bcbio/bcbio-nextgen/issues/3327 and https://github.com/bcbio/bcbio-nextgen/issues/3328. + +``` +DATE=`date +%Y%m%d%H%M` +/home/u035/project/software/bcbio/tools/bin/bcbio_nextgen.py upgrade -u development --tools &> bcbio_install_logs/bcbio_install_upgrade_tools_${DATE}.log +``` + +Install datatarget vep + +``` +DATE=`date +%Y%m%d%H%M` +/home/u035/project/software/bcbio/tools/bin/bcbio_nextgen.py upgrade -u skip --datatarget vep &> bcbio_install_logs/bcbio_install_datatarget_vep_${DATE}.log +``` + +gnomAD 3.1.1 installation will take about 6 days (old ultra). Might be faster on ultra2. + +``` +DATE=`date +%Y%m%d%H%M` +/home/u035/project/software/bcbio/tools/bin/bcbio_nextgen.py upgrade -u skip --datatarget gnomad &> bcbio_install_logs/bcbio_install_datatarget_gnomad_${DATE}.log +``` + +Increase JVM memory for GATK in galaxy/bcbio_system.yaml + +``` + gatk: + jvm_opts: ["-Xms500m", "-Xmx5g"] +``` + +### Patch Ensembl VEP 100.4 + +See https://github.com/Ensembl/ensembl-variation/pull/621/files + +Edit /home/u035/project/software/bcbio/anaconda/share/ensembl-vep-100.4-0/Bio/EnsEMBL/Variation/BaseAnnotation.pm accordingly. + +### Verifybamid custom panel for exomes + +``` +source /home/u035/project/scripts/trio_whole_exome_config.sh + +mkdir /home/u035/project/software/install/1000G_phase3_hg38 +cd /home/u035/project/software/install/1000G_phase3_hg38 + +# download the 1000 Genomes autosomes + X site VCFs +for ((i = 1; i <= 22; i = i + 1)) +do + wget ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000_genomes_project/release/20190312_biallelic_SNV_and_INDEL/ALL.chr${i}.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.vcf.gz; + wget ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000_genomes_project/release/20190312_biallelic_SNV_and_INDEL/ALL.chr${i}.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.vcf.gz.tbi +done +wget ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000_genomes_project/release/20190312_biallelic_SNV_and_INDEL/ALL.chrX.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.vcf.gz +wget ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/data_collections/1000_genomes_project/release/20190312_biallelic_SNV_and_INDEL/ALL.chrX.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.vcf.gz.tbi +cd .. + +# create bare to prefixed chromosome map +for ((i = 1; i <= 22; i = i + 1)) +do + echo $i "chr"$i >> chr_prefix_map.txt +done +echo chrX >> chr_prefix_map.txt + +# use the TWIST kit to subset the variants and add the chr prefix at the same time +for file in 1000G_phase3_hg38/*vcf.gz +do + bname=`basename $file` + bcftools view -R /home/u035/project/resources/Twist_Exome_Target_hg38.bed -m2 -M2 -v snps -i 'AF >= 0.01' $file | bcftools annotate --rename-chrs chr_prefix_map.txt | bgzip -c > ${bname%.vcf.gz}.biallelic.snps.m\ +inAF0.01.vcf.gz + tabix ${bname%.vcf.gz}.biallelic.snps.minAF0.01.vcf.gz +done + +# concatenate all the files in the correct order +bcftools concat -o ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz -O z \ + ALL.chr[1-9].shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz \ + ALL.chr[12][0-9].shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz \ + ALL.chrX.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz +tabix ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz + +# use VerifyBamID to create the new panel +/home/u035/project/software/bcbio/anaconda/share/verifybamid2-1.0.6-0/VerifyBamID \ + --RefVCF ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz + --Reference bcbio-1.1.5/genomes/Hsapiens/hg38/seq/hg38.fa + +# rename the files to the correct format +mv ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz.bed 1000g.phase3.100k.b38.vcf.gz.dat.bed +mv ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz.mu 1000g.phase3.100k.b38.vcf.gz.dat.mu +mv ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz.PC 1000g.phase3.100k.b38.vcf.gz.dat.V +mv ALL.shapeit2_integrated_snvindels_v2a_27022019.GRCh38.phased.chr.biallelic.snps.minAF0.01.vcf.gz.UD 1000g.phase3.100k.b38.vcf.gz.dat.UD + +# move them into the correct location, backing up the original resource folder +cd /home/u035/project/software/bcbio/anaconda/share/verifybamid2-1.0.6-0 +mv resource resource.bak +mkdir resource +mv /home/u035/project/software/install/1000G_phase3_hg38/1000g.phase3.100k.b38* resource/ +``` + +## Python modules + +### VASE + +VASE v0.4 was installed 28 August 2020. + +``` +cd /home/u035/project/software +./bcbio/anaconda/bin/pip3 install git+git://github.com/david-a-parry/vase.git#egg=project[BGZIP,REPORTER,MYGENE] +``` + +### XlsxWriter + +XlsxWriter 1.3.3 was installed 28 August 2020. + +``` +cd /home/u035/project/software +./bcbio/anaconda/bin/pip3 install XlsxWriter +``` + +## GATK 3.8 + +``` +cd /home/u035/project/software/install +wget https://storage.googleapis.com/gatk-software/package-archive/gatk/GenomeAnalysisTK-3.8-0-ge9d806836.tar.bz2 +bzip2 -d GenomeAnalysisTK-3.8-0-ge9d806836.tar.bz2 +tar -xf GenomeAnalysisTK-3.8-0-ge9d806836.tar +mv GenomeAnalysisTK-3.8-0-ge9d806836 ../GenomeAnalysisTK-3.8 +``` + +## RTG tools + +``` +cd /home/u035/project/software +wget https://github.com/RealTimeGenomics/rtg-tools/releases/download/3.11/rtg-tools-3.11-linux-x64.zip +unzip rtg-tools-3.11-linux-x64.zip +rm rtg-tools-3.11-linux-x64.zip +``` + +## IGV + +``` +cd /home/u035/project/software +wget https://data.broadinstitute.org/igv/projects/downloads/2.8/IGV_Linux_2.8.9.zip +unzip IGV_Linux_2.8.9.zip +rm IGV_Linux_2.8.9.zip +``` -- GitLab