From 32547fc9df65b1b4ddfed4571281ab3ee6dfefdc Mon Sep 17 00:00:00 2001 From: sellth Date: Tue, 5 Mar 2024 17:43:24 +0100 Subject: [PATCH] Fix cubit location (#116) --- .../docs/best-practice/project-structure.md | 4 ++-- bih-cluster/docs/cubit/index.md | 2 +- bih-cluster/docs/first-steps/episode-0.md | 2 +- bih-cluster/docs/first-steps/episode-1.md | 22 +++++++++---------- bih-cluster/docs/first-steps/episode-2.md | 12 +++++----- bih-cluster/docs/first-steps/episode-3.md | 22 +++++++++---------- bih-cluster/docs/first-steps/episode-4.md | 14 ++++++------ .../docs/how-to/software/cell-ranger.md | 4 ++-- 8 files changed, 41 insertions(+), 41 deletions(-) diff --git a/bih-cluster/docs/best-practice/project-structure.md b/bih-cluster/docs/best-practice/project-structure.md index 125e20eed..d4b729cb2 100644 --- a/bih-cluster/docs/best-practice/project-structure.md +++ b/bih-cluster/docs/best-practice/project-structure.md @@ -71,7 +71,7 @@ Creating the work directory and copy the input files into `work/input`. ```bash $ mkdir -p project/work/input -$ cp /fast/projects/cubit/tutorial/input/* project/work/input +$ cp /data/cephfs-1/work/projects/cubit/tutorial/input/* project/work/input ``` Creating the home space. @@ -159,7 +159,7 @@ EOF $ chmod +x scripts/run-mapping.sh $ mkdir -p config $ cat <<"EOF" >config/default-config.sh -BWA_INDEX=/fast/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa +BWA_INDEX=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/hs37d5/hs37d5.fa SAMPLES= EOF $ cat <<"EOF" >config/project-config.sh diff --git a/bih-cluster/docs/cubit/index.md b/bih-cluster/docs/cubit/index.md index 73547c6ce..50afe0131 100644 --- a/bih-cluster/docs/cubit/index.md +++ b/bih-cluster/docs/cubit/index.md @@ -1,6 +1,6 @@ # Overview -The static data installation can be found at `/fast/projects/cubit/18.12/static_data`. +The static data installation can be found at `/data/cephfs-1/work/projects/cubit/18.12/static_data`. The static data directory contains a sub-directory for the genomes, the precomputed index files for several different popular mapping tools and associated annotation (GFF and GTF files) from Ensembl and GENCODE for each of the available genomes. The top-level directory structure is as follows: diff --git a/bih-cluster/docs/first-steps/episode-0.md b/bih-cluster/docs/first-steps/episode-0.md index 04b633668..b02541066 100644 --- a/bih-cluster/docs/first-steps/episode-0.md +++ b/bih-cluster/docs/first-steps/episode-0.md @@ -23,7 +23,7 @@ introduce the following convention that we use throughout the series: $ Commands are prefixed with a little dollar sign ``` -While file paths are highlighted like this: `/fast/projects/cubit/current`. +While file paths are highlighted like this: `/data/cephfs-1/work/projects/cubit/current`. ## Instant Gratification diff --git a/bih-cluster/docs/first-steps/episode-1.md b/bih-cluster/docs/first-steps/episode-1.md index d936e6ec8..476eb1352 100644 --- a/bih-cluster/docs/first-steps/episode-1.md +++ b/bih-cluster/docs/first-steps/episode-1.md @@ -22,8 +22,8 @@ $ srun --time 7-00 --mem=8G --ntasks=8 --pty bash -i We will provide you with some example FASTQ files, but you can use your own if you like. You can find the data here: -- `/fast/projects/cubit/work/tutorial/input/test_R1.fq.gz` -- `/fast/projects/cubit/work/tutorial/input/test_R2.fq.gz` +- `/data/cephfs-1/work/projects/cubit/tutorial/input/test_R1.fq.gz` +- `/data/cephfs-1/work/projects/cubit/tutorial/input/test_R2.fq.gz` ## Creating a Project Directory @@ -57,11 +57,11 @@ You can create one in your `~/scratch` folder and make it available to the syste ## Using the Cubit Static Data -The static data is located in `/fast/projects/cubit/current/static_data`. +The static data is located in `/data/cephfs-1/work/projects/cubit/current/static_data`. For our small example, the required reference genome and index can be found at: -- `/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta` -- `/fast/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta` +- `/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta` +- `/data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta` ## Aligning the Reads @@ -70,9 +70,9 @@ Let's align our data: ```terminal (first-steps) $ bwa mem -t 8 \ -R "@RG\tID:FLOWCELL.LANE\tPL:ILLUMINA\tLB:test\tSM:PA01" \ - /fast/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta \ - /fast/projects/cubit/work/tutorial/input/test_R1.fq.gz \ - /fast/projects/cubit/work/tutorial/input/test_R2.fq.gz \ + /data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta \ + /data/cephfs-1/work/projects/cubit/tutorial/input/test_R1.fq.gz \ + /data/cephfs-1/work/projects/cubit/tutorial/input/test_R2.fq.gz \ | samtools view -b \ | samtools sort -O BAM -T $TMPDIR -o aln.bam @@ -85,7 +85,7 @@ And do the structural variant calling: ```terminal (first-steps) $ delly call \ - -g /fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta \ + -g /data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta \ aln.bam ``` @@ -97,7 +97,7 @@ And now for the SNP calling (this step will take ~ 20 minutes): ```terminal (first-steps) $ gatk HaplotypeCaller \ - -R /fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta \ + -R /data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta \ -I aln.bam \ -ploidy 2 \ -O test.GATK.vcf @@ -111,5 +111,5 @@ You can access a list of all static data through this wiki, follow this link to You can also have a peek via: ```terminal -(first-steps) $ tree -L 3 /fast/projects/cubit/current/static_data | less +(first-steps) $ tree -L 3 /data/cephfs-1/work/projects/cubit/current/static_data | less ``` diff --git a/bih-cluster/docs/first-steps/episode-2.md b/bih-cluster/docs/first-steps/episode-2.md index 0c9558dc5..5a9261bc9 100644 --- a/bih-cluster/docs/first-steps/episode-2.md +++ b/bih-cluster/docs/first-steps/episode-2.md @@ -33,7 +33,7 @@ You may have noticed that you run `sbatch` with a script, not with regular comma The reason is that `sbatch` only accepts bash scripts. If you give `sbatch` a normal shell command or binary, it won't work. This means that we have to put the command(s) we want to use in a bash script. -A skeleton script can be found at `/fast/projects/cubit/work/tutorial/skeletons/submit_job.sh` +A skeleton script can be found at `/data/cephfs-1/work/projects/cubit/tutorial/skeletons/submit_job.sh` The content of the file: @@ -79,7 +79,7 @@ and copy the wrapper script to this directory: ```terminal (first-steps) $ pushd /fast/users/$USER/work/tutorial/episode2 -(first-steps) $ cp /fast/projects/cubit/work/tutorial/skeletons/submit_job.sh . +(first-steps) $ cp /data/cephfs-1/work/projects/cubit/tutorial/skeletons/submit_job.sh . (first-steps) $ chmod u+w submit_job.sh ``` @@ -119,14 +119,14 @@ Your file should look something like this: export TMPDIR=/fast/users/${USER}/scratch/tmp mkdir -p ${TMPDIR} -BWAREF=/fast/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta -REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta +BWAREF=/data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta +REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta bwa mem -t 8 \ -R "@RG\tID:FLOWCELL.LANE\tPL:ILLUMINA\tLB:test\tSM:PA01" \ $BWAREF \ - /fast/projects/cubit/work/tutorial/input/test_R1.fq.gz \ - /fast/projects/cubit/work/tutorial/input/test_R2.fq.gz \ + /data/cephfs-1/work/projects/cubit/tutorial/input/test_R1.fq.gz \ + /data/cephfs-1/work/projects/cubit/tutorial/input/test_R2.fq.gz \ | samtools view -b \ | samtools sort -O BAM -T $TMPDIR -o aln.bam diff --git a/bih-cluster/docs/first-steps/episode-3.md b/bih-cluster/docs/first-steps/episode-3.md index 89a0b5477..a087bd184 100644 --- a/bih-cluster/docs/first-steps/episode-3.md +++ b/bih-cluster/docs/first-steps/episode-3.md @@ -32,7 +32,7 @@ copy the skeleton: ```terminal (first-steps) $ mkdir -p /fast/users/${USER}/work/tutorial/episode3 (first-steps) $ pushd /fast/users/${USER}/work/tutorial/episode3 -(first-steps) $ cp /fast/projects/cubit/work/tutorial/skeletons/Snakefile . +(first-steps) $ cp /data/cephfs-1/work/projects/cubit/tutorial/skeletons/Snakefile . (first-steps) $ chmod u+w Snakefile ``` @@ -46,8 +46,8 @@ rule all: rule alignment: input: - '/fast/projects/cubit/work/tutorial/input/test_R1.fq.gz', - '/fast/projects/cubit/work/tutorial/input/test_R2.fq.gz', + '/data/cephfs-1/work/projects/cubit/tutorial/input/test_R1.fq.gz', + '/data/cephfs-1/work/projects/cubit/tutorial/input/test_R2.fq.gz', output: bam='alignment/test.bam', bai='alignment/test.bam.bai', @@ -56,7 +56,7 @@ rule alignment: export TMPDIR=/fast/users/${{USER}}/scratch/tmp mkdir -p ${{TMPDIR}} - BWAREF=/fast/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta + BWAREF=/data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta bwa mem -t 8 \ -R "@RG\tID:FLOWCELL.LANE\tPL:ILLUMINA\tLB:test\tSM:PA01" \ @@ -75,7 +75,7 @@ rule structural_variants: 'structural_variants/test.vcf' shell: r""" - REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta + REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta delly call -o {output} -g ${{REF}} {input} """ @@ -87,7 +87,7 @@ rule snps: 'snps/test.vcf' shell: r""" - REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta + REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta gatk HaplotypeCaller \ -R ${{REF}} \ @@ -147,8 +147,8 @@ rule all: rule alignment: input: - '/fast/projects/cubit/work/tutorial/input/{id}_R1.fq.gz', - '/fast/projects/cubit/work/tutorial/input/{id}_R2.fq.gz', + '/data/cephfs-1/work/projects/cubit/tutorial/input/{id}_R1.fq.gz', + '/data/cephfs-1/work/projects/cubit/tutorial/input/{id}_R2.fq.gz', output: bam='alignment/{id}.bam', bai='alignment/{id}.bam.bai', @@ -157,7 +157,7 @@ rule alignment: export TMPDIR=/fast/users/${{USER}}/scratch/tmp mkdir -p ${{TMPDIR}} - BWAREF=/fast/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta + BWAREF=/data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta bwa mem -t 8 \ -R "@RG\tID:FLOWCELL.LANE\tPL:ILLUMINA\tLB:test\tSM:PA01" \ @@ -176,7 +176,7 @@ rule structural_variants: 'structural_variants/{id}.vcf' shell: r""" - REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta + REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta delly call -o {output} -g ${{REF}} {input} """ @@ -188,7 +188,7 @@ rule snps: 'snps/{id}.vcf' shell: r""" - REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta + REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta gatk HaplotypeCaller \ -R ${{REF}} \ diff --git a/bih-cluster/docs/first-steps/episode-4.md b/bih-cluster/docs/first-steps/episode-4.md index fd12e83d7..13012e39c 100644 --- a/bih-cluster/docs/first-steps/episode-4.md +++ b/bih-cluster/docs/first-steps/episode-4.md @@ -27,8 +27,8 @@ First, create a new folder for this episode: And copy the wrapper script to this folder as well as the Snakefile (you can also reuse the one with the adjustments from the previous [episode](episode-3.md)): ```terminal -(first-steps) $ cp /fast/projects/cubit/work/tutorial/skeletons/submit_snakejob.sh . -(first-steps) $ cp /fast/projects/cubit/work/tutorial/skeletons/Snakefile . +(first-steps) $ cp /data/cephfs-1/work/projects/cubit/tutorial/skeletons/submit_snakejob.sh . +(first-steps) $ cp /data/cephfs-1/work/projects/cubit/tutorial/skeletons/Snakefile . (first-steps) $ chmod u+w submit_snakejob.sh Snakefile ``` @@ -109,8 +109,8 @@ rule all: rule alignment: input: - '/fast/projects/cubit/work/tutorial/input/{id}_R1.fq.gz', - '/fast/projects/cubit/work/tutorial/input/{id}_R2.fq.gz', + '/data/cephfs-1/work/projects/cubit/tutorial/input/{id}_R1.fq.gz', + '/data/cephfs-1/work/projects/cubit/tutorial/input/{id}_R2.fq.gz', output: bam='alignment/{id}.bam', bai='alignment/{id}.bam.bai', @@ -123,7 +123,7 @@ rule alignment: export TMPDIR=/fast/users/${{USER}}/scratch/tmp mkdir -p ${{TMPDIR}} - BWAREF=/fast/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta + BWAREF=/data/cephfs-1/work/projects/cubit/current/static_data/precomputed/BWA/0.7.17/GRCh37/g1k_phase1/human_g1k_v37.fasta bwa mem -t 8 \ -R "@RG\tID:FLOWCELL.LANE\tPL:ILLUMINA\tLB:test\tSM:PA01" \ @@ -146,7 +146,7 @@ rule structural_variants: time='2-00:00:00', shell: r""" - REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta + REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta delly call -o {output} -g ${{REF}} {input} """ @@ -166,7 +166,7 @@ rule snps: time='04:00:00', shell: r""" - REF=/fast/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta + REF=/data/cephfs-1/work/projects/cubit/current/static_data/reference/GRCh37/g1k_phase1/human_g1k_v37.fasta gatk HaplotypeCaller \ -R ${{REF}} \ diff --git a/bih-cluster/docs/how-to/software/cell-ranger.md b/bih-cluster/docs/how-to/software/cell-ranger.md index 65bd766ca..8d1525237 100644 --- a/bih-cluster/docs/how-to/software/cell-ranger.md +++ b/bih-cluster/docs/how-to/software/cell-ranger.md @@ -18,7 +18,7 @@ tar -xzvf cellranger-3.0.2.tar.gz # reference data -will be provided in `/fast/projects/cubit/current/static_data/app_support/cellranger` +will be provided in `/data/cephfs-1/work/projects/cubit/current/static_data/app_support/cellranger` # cluster support SLURM @@ -76,7 +76,7 @@ create a script `run_cellranger.sh` with these contents (consult the [documentat /fast/users/$USER/work/cellranger-3.0.2/cellranger count \ --id=sample_id \ - --transcriptome=/fast/projects/cubit/current/static_data/app_support/cellranger/refdata-cellranger-${species}-3.0.0\ + --transcriptome=/data/cephfs-1/work/projects/cubit/current/static_data/app_support/cellranger/refdata-cellranger-${species}-3.0.0\ --fastqs=/path/to/fastqs \ --sample=sample_name \ --expect-cells=n_cells \