Jody Phelan jodyphelan
jodyphelan
/ setGT_bug.sh
Created
October 16, 2019 20:18
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR040/ERR040131/ERR040131_1.fastq.gz | |
| wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR040/ERR040131/ERR040131_2.fastq.gz | |
| wget ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/195/955/GCF_000195955.2_ASM19595v2/GCF_000195955.2_ASM19595v2_genomic.fna.gz | |
| gunzip GCF_000195955.2_ASM19595v2_genomic.fna.gz | |
| mv GCF_000195955.2_ASM19595v2_genomic.fna H37Rv.fa | |
| # Get software | |
| wget https://github.com/samtools/samtools/releases/download/1.9/samtools-1.9.tar.bz2 && tar -xvf samtools-1.9.tar.bz2 && cd samtools-1.9/ && make && cd .. | |
| wget https://github.com/samtools/bcftools/releases/download/1.9/bcftools-1.9.tar.bz2 && tar -xvf bcftools-1.9.tar.bz2 && cd bcftools-1.9/ && make && cd .. | |
| git clone https://github.com/lh3/bwa.git && cd bwa && make && cd ../ |
jodyphelan
/ vcf2fasta.py
Created
October 4, 2019 07:24
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #! /usr/bin/env python | |
| import sys | |
| import subprocess | |
| import argparse | |
| import random | |
| import os | |
| rand_generator = random.SystemRandom() | |
| def get_random_file(prefix = None,extension=None): | |
| randint = rand_generator.randint(1,999999) |
jodyphelan
/ course_data_update.sh
Created
September 18, 2019 08:53
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| cd ~/data/ | |
| rm -r gwas/* | |
| wget http://pathogenseq.lshtm.ac.uk/downloads/new_gwas.tgz | |
| tar -xvf new_gwas.tgz | |
| rm new_gwas.tgz |
jodyphelan
/ err_download.py
Created
September 4, 2019 10:39
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #! /usr/bin/env python | |
| import sys | |
| for l in sys.stdin: | |
| accessions = l.rstrip().split("_") | |
| for accession in accessions: | |
| if len(accession)==9: | |
| dir1 = accession[:6] | |
| sys.stdout.write("ftp://ftp.sra.ebi.ac.uk/vol1/fastq/%s/%s/%s_1.fastq.gz\n" % (dir1,accession,accession)) | |
| sys.stdout.write("ftp://ftp.sra.ebi.ac.uk/vol1/fastq/%s/%s/%s_2.fastq.gz\n" % (dir1,accession,accession)) | |
| elif len(accession)==10: |
jodyphelan
/ rsync.txt
Created
August 23, 2019 13:51
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| rsync -am --include='*.gatk.vcf.gz' --include='*/' --exclude='*' /mnt/storage/jody/ena/vcf/ . |
jodyphelan
/ vcf to binary matrix
Created
August 6, 2019 11:35
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # VCF file = test.filt.vcf.gz | |
| # replace where necessary | |
| (printf "chr\npos\nref\n"; bcftools query -l test.filt.vcf.gz) | datamash transpose > test.filt.mat.bin | |
| bcftools query -f '%CHROM\t%POS\t%REF[\t%GT]\n' test.filt.vcf.gz | tr '|' '/' | sed 's/\.\/\./N/g' | sed 's/0\/0/0/g' | sed 's/.\/./1/g' >> test.filt.mat.bin |
jodyphelan
/ gist:5005626a2faf771050951395ee325615
Created
July 30, 2019 11:01
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| rm -r genomics_db | |
| gatk GenomicsDBImport --genomicsdb-workspace-path genomics_db -L Chromosome --sample-name-map test.map --reader-threads 10 --max-num-intervals-to-import-in-parallel 10 | |
| gatk --java-options "-Xmx40g" GenotypeGVCFs -R ~/refgenome/MTB-h37rv_asm19595v2-eg18.fa -V gendb://genomics_db -O test.raw.vcf.gz | |
| bcftools view -V indels test.raw.vcf.gz | bcftools filter -e 'GT="het"' -S . | awk 'length($4)==1 || $0~/^#/' | tr '|' '/' | tr '*' '.' | bcftools view -a | bcftools view -c 1 -Oz -o test.filt.vcf.gz | |
| bcf2fasta.py test.filt.vcf.gz ~/refgenome/MTB-h37rv_asm19595v2-eg18.fa test.snps.fa |
jodyphelan
/ gist:9545e04fd44aea6d39c5b0faf039b3eb
Last active
June 27, 2019 16:40
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| cd /tmp/ | |
| git clone https://github.com/jodyphelan/pathogen-profiler.git | |
| cd pathogen-profiler | |
| python setup.py install | |
| cd ../ | |
| rm -fr pathogen-profiler |
jodyphelan
/ bcftools query
Created
June 25, 2019 20:35
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR209/009/SRR2099969/SRR2099969_1.fastq.gz | |
| wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR209/009/SRR2099969/SRR2099969_2.fastq.gz | |
| wget ftp://ftp.ensemblgenomes.org/pub/release-32/bacteria//fasta/bacteria_0_collection/mycobacterium_tuberculosis_h37rv/dna/Mycobacterium_tuberculosis_h37rv.ASM19595v2.dna.toplevel.fa.gz | |
| gunzip Mycobacterium_tuberculosis_h37rv.ASM19595v2.dna.toplevel.fa.gz | |
| mv Mycobacterium_tuberculosis_h37rv.ASM19595v2.dna.toplevel.fa H37Rv.fa | |
| # Get software | |
| wget https://github.com/samtools/samtools/releases/download/1.9/samtools-1.9.tar.bz2 && tar -xvf samtools-1.9.tar.bz2 && cd samtools-1.9/ && make && cd .. | |
| wget https://github.com/samtools/bcftools/releases/download/1.9/bcftools-1.9.tar.bz2 && tar -xvf bcftools-1.9.tar.bz2 && cd bcftools-1.9/ && make && cd .. | |
| git clone https://github.com/lh3/bwa.git && cd bwa && make && cd ../ |
jodyphelan
/ run_sample.sh
Created
June 17, 2019 12:06
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| echo $1 > $1.sample_name.txt \ | |
| && ebiDownload.pl $1.sample_name.txt | parallel wget \ | |
| && tb-profiler profile -1 ${1}_1.fastq.gz -2 ${1}_2.fastq.gz -t 5 -p $1 \ | |
| && bcftools mpileup -f /home/ubuntu/refgenome/MTB-h37rv_asm19595v2-eg18.fa bam/$1.bam -a DP,AD -g 10 -B -Q 0 -q 0 -I | bcftools call -mg 10 -V indels -Oz -o vcf/$1.bcftools.g.vcf.gz \ | |
| && gatk HaplotypeCaller -I bam/$1.bam -R /home/ubuntu/refgenome/MTB-h37rv_asm19595v2-eg18.fa -O vcf/$1.gatk.vcf.gz -ERC GVCF \ | |
| && delly call -g /home/ubuntu/refgenome/MTB-h37rv_asm19595v2-eg18.fa -o vcf/$1.delly.bcf bam/$1.bam \ | |
| && rm ${1}_1.fastq.gz ${1}_2.fastq.gz bam/${1}.* |