Skip to content

Commit 8d53787

Browse files
author
Madalina Giurgiu
committed
add complete conda installation and scripts for ecDNA processing
1 parent 68b857c commit 8d53787

4 files changed

Lines changed: 50 additions & 22 deletions

File tree

genomics/circle-seq/README.md

Lines changed: 2 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -18,12 +18,8 @@ Run the analysis for the PDX primary and relapse:
1818
```
1919
# setup variables
2020
REF=../genome/hs37d5_mm10.fa
21-
PRIMARY_SAMPLE=PDXprimary
22-
RELAPSE_SAMPLE=PDXrelapse
23-
PRIMARY_1_FASTQ=ecDNA/lane1PrimaryPDX_1_sequence.fq.gz
24-
PRIMARY_2_FASTQ=ecDNA/lane1PrimaryPDX_2_sequence.fq.gz
25-
RELAPSE_1_FASTQ=ecDNA/lane1RelapsePDX_1_sequence.fq.gz
26-
RELAPSE_2_FASTQ=ecDNA/lane1RelapsePDX_2_sequence.fq.gz
21+
PRIMARY_SAMPLE=PrimaryPDX
22+
RELAPSE_SAMPLE=RelapsePDX
2723
2824
# run analysis
2925
bash run.sh

genomics/circle-seq/bwa_mem_align.sh

Lines changed: 27 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -4,22 +4,41 @@ date
44
hostname
55

66
sample=$1
7-
read1=$2
8-
read2=$3
9-
genome=$4
7+
genome=$2
108

119
##get quality of fastqs
12-
mkdir -p ${sample}/qc/
13-
fastqc -o ${sample}/qc/ ${read1} ${read2}
10+
mkdir -p ecDNA/${sample}/qc/
11+
fastqc -o ecDNA/${sample}/qc/ ecDNA/${sample}/lane1${sample}_1_sequence.fq.gz ecDNA/${sample}/lane1${sample}_2_sequence.fq.gz
12+
13+
##trim reads
14+
trim_galore -q 20 --phred33 --illumina --paired -j 4 ecDNA/${sample}/lane1${sample}_1_sequence.fq.gz ecDNA/${sample}/lane1${sample}_2_sequence.fq.gz
15+
mv lane1${sample}_1_sequence.fq.gz_trimming_report.txt ecDNA/${sample}/
16+
mv lane1${sample}_1_sequence_val_1.fq.gz ecDNA/${sample}/
17+
mv lane1${sample}_2_sequence.fq.gz_trimming_report.txt ecDNA/${sample}/
18+
mv lane1${sample}_2_sequence_val_2.fq.gz ecDNA/${sample}/
1419

1520
##align with bwa mem
16-
bwa mem -q -t 4 ${genome} ${read1} ${read2} | samtools sort -@4 -o sorted_${sample}.bam -
21+
bwa mem -q -t 4 ${genome} ecDNA/${sample}/lane1${sample}_1_sequence_val_1.fq.gz ecDNA/${sample}/lane1${sample}_2_sequence_val_2.fq.gz | samtools sort -@4 -o ecDNA/${sample}/sorted_${sample}.bam -
22+
23+
##index bam file
24+
samtools index ecDNA/${sample}/sorted_${sample}.bam
25+
26+
##mark duplicates
27+
picard MarkDuplicates \
28+
I=ecDNA/${sample}/sorted_${sample}.bam \
29+
O=ecDNA/${sample}/sorted_${sample}.dedup.bam \
30+
M=ecDNA/${sample}/sorted_${sample}.dedup.metrix
1731

1832
##index bam file
19-
samtools index sorted_${sample}.bam
33+
samtools index ecDNA/${sample}/sorted_${sample}.dedup.bam
2034

2135
##create coverage overview in bigwig format
22-
bamCoverage --bam sorted_${sample}.bam -o ${sample}.bw
36+
bamCoverage --bam ecDNA/${sample}/sorted_${sample}.dedup.bam -o ecDNA/${sample}/sorted_${sample}.dedup.bw
37+
38+
## remove files
39+
rm ecDNA/${sample}/sorted_${sample}.bam*
40+
41+
chmod +x ecDNA/${sample}/*
2342

2443
echo "=========================================================="
2544
echo "Finished on : $(date)"

genomics/circle-seq/circleseq.yaml

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,4 +10,7 @@ dependencies:
1010
- openjdk==11.0.1
1111
- picard==2.25.0
1212
- python==2.7.15
13-
- bwamem==0.7.17
13+
- bwa==0.7.17
14+
- fastqc==0.11.9
15+
- pysam==0.14.1
16+
- trim-galore==0.6.7

genomics/circle-seq/run.sh

Lines changed: 17 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,28 @@
11
#!/bin/bash
2+
#SBATCH --job-name=circleseq
3+
#SBATCH --ntasks=16
4+
#SBATCH --nodes=1
5+
#SBATCH --time=1-00:00:00
6+
#SBATCH --mem=30G
27

38
date
49
hostname
510

6-
conda activate circleseq
11+
#conda activate circleseq
12+
13+
PRIMARY_SAMPLE=PrimaryPDX
14+
RELAPSE_SAMPLE=RelapsePDX
715

816
# mapping
9-
bash bwa_mem_align.sh $PRIMARY_SAMPLE $PRIMARY_1_FASTQ $PRIMARY_2_FASTQ $REF
10-
bash bwa_mem_align.sh $PRIMARY_SAMPLE $RELAPSE_1_FASTQ $RELAPSE_2_FASTQ $REF
17+
#bash bwa_mem_align.sh $PRIMARY_SAMPLE $REF
18+
#bash bwa_mem_align.sh $RELAPSE_SAMPLE $REF
1119

1220
# circle-enrich-finder
13-
git clone git clone https://github.com/henssen-lab/circle-enrich-filter.git
21+
#git clone https://github.com/henssen-lab/circle-enrich-filter.git
22+
# checkout version 1.0.0
1423
cd circle-enrich-filter
15-
bash run_CircleEnrichFilter.sh $PRIMARY_SAMPLE/sorted_PDXprimary.dedup.bam $PRIMARY_SAMPLE/circleEnrich0 $REF
16-
bash run_CircleEnrichFilter.sh $RELAPSE_SAMPLE/sorted_PDXprimary.dedup.bam $RELAPSE_SAMPLE/circleEnrich0 $REF
24+
git checkout f0fc687c974c9e4308e423f9cbe883344c6b359a
25+
bash run_CircleEnrichFilter.sh -i ${PWD}/../ecDNA/$PRIMARY_SAMPLE/sorted_${PRIMARY_SAMPLE}.dedup.bam -o ${PWD}/../ecDNA/$PRIMARY_SAMPLE/circleEnrich0 -s 0
26+
bash run_CircleEnrichFilter.sh -i ${PWD}/../ecDNA/$RELAPSE_SAMPLE/sorted_${RELAPSE_SAMPLE}.dedup.bam -o ${PWD}/../ecDNA/$RELAPSE_SAMPLE/circleEnrich0 -s 0
1727

18-
conda deactivate
28+
#conda deactivate

0 commit comments

Comments
 (0)