Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions README.md

This file was deleted.

27 changes: 27 additions & 0 deletions bash_script_Anna.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
#!/bin/sh
fastqc -outdir ../fastqc/ -t 8 ../../../Data/AI-69_S60_R1_001.fastq.gz ../../../Data/AI-69_S60_R2_001.fastq.gz
trimmomatic PE -phred33 -threads 8 data/raw_reads/AI-69_S60_R1_001.fastq.gz data/raw_reads/AI-69_S60_R2_001.fastq.gz -baseout trim1 LEADING:15 TRAILING:15 SLIDINGWINDOW:10:20 MINLEN:20
trimmomatic PE -phred33 -threads 8 data/rawreads/AI-69_S60_R1_001.fastq.gz data/rawreads/AI-69_S60_R2_001.fastq.gz -baseout trim1 LEADING:15 TRAILING:15 SLIDINGWINDOW:10:20 MINLEN:20
bwa index data/references/T5_sequence.fasta
fastqc --outdir=../fastqc/ trim1_1P trim1_2P
bwa mem -t 8 data/references/T5_sequence.fasta data/trims/trim1_1P data/trims/trim1_2P | samtools view -Sb > T5_AI_69_S60_aligned.bam
mkdir mapped
mkdir mapped_sorted
mkdir calling
mv T5_AI_69_S60_aligned.bam mapped
samtools sort -@ 8 mapped/T5_AI_69_S60_aligned.bam -o mapped_sorted/T5_AI_69_S60_aligned_sorted.bam
cd mapped_sorted/
ls
cd ../mapped
samtools view -h T5_AI_69_S60_aligned.bam | head 50
samtools view -h T5_AI_69_S60_aligned.bam | head -50
cd ../
samtools index mapped_sorted/T5_AI_69_S60_aligned_sorted.bam
bcftools mpileup -Ou -f data/references/T5_sequence.fasta mapped_sorted/T5_AI_69_S60_aligned_sorted.bam | bcftools call -Ou -mv --ploidy 1 | bcftools filter -s LowQual -e '%QUAL<20 || DP>100' > calling/T5_AI_69_S60_variants.vcf
cd calling/
rm *
cd ../
bcftools mpileup -Ou -f data/reference/T5_sequence.fasta mapped_sorted/T5_AI_69_S60_aligned_sorted.bam | bcftools call -Ou -mv --ploidy 1 | bcftools filter -s LowQual -e '%QUAL<20 || DP>100' > calling/T5_AI_69_S60_variants.vcf
bcftools mpileup -Ou -f data/references/T5_sequence.fasta mapped_sorted/T5_AI_69_S60_aligned_sorted.bam | bcftools call -Ou -mv --ploidy 1 | bcftools filter -s LowQual -e '%QUAL<20 || DP>100' > calling/T5_AI_69_S60_variants.vcf
less T5_AI_69_S60_variants.vcf
exit
34 changes: 34 additions & 0 deletions vcf results.vcf
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
##fileformat=VCFv4.2
##FILTER=<ID=PASS,Description="All filters passed">
##bcftoolsVersion=1.10+htslib-1.10
##bcftoolsCommand=mpileup -Ou -f data/references/T5_sequence.fasta mapped_sorted/T5_AI_69_S60_aligned_sorted.bam
##reference=file://data/references/T5_sequence.fasta
##contig=<ID=T5,length=113951>
##ALT=<ID=*,Description="Represents allele(s) other than observed.">
##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL.">
##INFO=<ID=IDV,Number=1,Type=Integer,Description="Maximum number of raw reads supporting an indel">
##INFO=<ID=IMF,Number=1,Type=Float,Description="Maximum fraction of raw reads supporting an indel">
##INFO=<ID=DP,Number=1,Type=Integer,Description="Raw read depth">
##INFO=<ID=VDB,Number=1,Type=Float,Description="Variant Distance Bias for filtering splice-site artefacts in RNA-seq data (bigger is better)",Version="3">
##INFO=<ID=RPB,Number=1,Type=Float,Description="Mann-Whitney U test of Read Position Bias (bigger is better)">
##INFO=<ID=MQB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality Bias (bigger is better)">
##INFO=<ID=BQB,Number=1,Type=Float,Description="Mann-Whitney U test of Base Quality Bias (bigger is better)">
##INFO=<ID=MQSB,Number=1,Type=Float,Description="Mann-Whitney U test of Mapping Quality vs Strand Bias (bigger is better)">
##INFO=<ID=SGB,Number=1,Type=Float,Description="Segregation based metric.">
##INFO=<ID=MQ0F,Number=1,Type=Float,Description="Fraction of MQ0 reads (smaller is better)">
##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods">
##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
##INFO=<ID=ICB,Number=1,Type=Float,Description="Inbreeding Coefficient Binomial test (bigger is better)">
##INFO=<ID=HOB,Number=1,Type=Float,Description="Bias in the number of HOMs number (smaller is better)">
##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes for each ALT allele, in the same order as listed">
##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
##INFO=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward , ref-reverse, alt-forward and alt-reverse bases">
##INFO=<ID=MQ,Number=1,Type=Integer,Description="Average mapping quality">
##bcftools_callVersion=1.10+htslib-1.10
##bcftools_callCommand=call -Ou -mv --ploidy 1; Date=Wed Jan 18 19:05:00 2023
##FILTER=<ID=LowQual,Description="Set if true: %QUAL<20 || DP>100">
##bcftools_filterVersion=1.10+htslib-1.10
##bcftools_filterCommand=filter -s LowQual -e '%QUAL<20 || DP>100'; Date=Wed Jan 18 19:05:19 2023
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT mapped_sorted/T5_AI_69_S60_aligned_sorted.bam
T5 57822 . G A 225 LowQual DP=243;VDB=0.000940976;SGB=-0.693147;MQSB=1;MQ0F=0;AC=1;AN=1;DP4=0,0,177,39;MQ=60 GT:PL 1:255,0
T5 65803 . GTT GT 199 LowQual INDEL;IDV=207;IMF=0.848361;DP=244;VDB=0.959859;SGB=-0.693147;MQSB=1;MQ0F=0;AC=1;AN=1;DP4=33,2,167,42;MQ=60 GT:PL 1:226,0