diff --git a/.gitattributes b/.gitattributes index 9992776affeb3d3878119e09bd8176a7fd14fcb0..7c3cf7781734b30a8e0cfccc6bdf9857f38f05a5 100644 --- a/.gitattributes +++ b/.gitattributes @@ -5,4 +5,4 @@ /assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text /assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text /assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text -/runs/kallisto_index/kallisto_index filter=lfs diff=lfs merge=lfs -text +/runs/kallisto_index/out/kallisto_index filter=lfs diff=lfs merge=lfs -text diff --git a/runs/kallisto_collect/README.md b/runs/kallisto_collect/README.md deleted file mode 100644 index 574080e009fc120d02514c5dfa15b6b6c602f00b..0000000000000000000000000000000000000000 --- a/runs/kallisto_collect/README.md +++ /dev/null @@ -1,21 +0,0 @@ - -# cwltool README - -## First cd into the (runs) folder, with the .yml file - -cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_collect - -## Let it flow - -```bash -### store arc root (two levels up from here) as variable -arc_root=$(echo ${PWD%/*/*}) - -### replace arc root line in yml (specific to the machine from where this is run) -### not sure, if this works on linux... -sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" kallisto_collect.yml - -### run with cwltool -cwltool ../../workflows/kallisto_collect.cwl kallisto_collect.yml - -``` diff --git a/runs/kallisto_collect/kallisto_collect.yml b/runs/kallisto_collect/kallisto_collect.yml deleted file mode 100644 index 1b300513c1481db8c9c0188d7dbd09f3acae4ad3..0000000000000000000000000000000000000000 --- a/runs/kallisto_collect/kallisto_collect.yml +++ /dev/null @@ -1,10 +0,0 @@ -cores: 1 -r_script: - class: File - path: ../../workflows/kallisto_collect.R -in_kallisto_results: "runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results" -in_metadata_file: "runs/merged_isa_metadata/merged_isa.tsv" -in_metadata_sample: "Sample.Name.2" -in_metadata_factor: "Factor..Photosynthesis.mode." -out_folder: runs/kallisto_collect -arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq \ No newline at end of file diff --git a/runs/kallisto_collect/isa.dataset.xlsx b/runs/kallisto_collect/out/isa.dataset.xlsx similarity index 100% rename from runs/kallisto_collect/isa.dataset.xlsx rename to runs/kallisto_collect/out/isa.dataset.xlsx diff --git a/runs/kallisto_collect/kallisto_mappingStats.csv b/runs/kallisto_collect/out/kallisto_mappingStats.csv similarity index 100% rename from runs/kallisto_collect/kallisto_mappingStats.csv rename to runs/kallisto_collect/out/kallisto_mappingStats.csv diff --git a/runs/kallisto_collect/kallisto_tpmMatrix.csv b/runs/kallisto_collect/out/kallisto_tpmMatrix.csv similarity index 100% rename from runs/kallisto_collect/kallisto_tpmMatrix.csv rename to runs/kallisto_collect/out/kallisto_tpmMatrix.csv diff --git a/workflows/kallisto_collect.cwl b/runs/kallisto_collect/run.cwl similarity index 85% rename from workflows/kallisto_collect.cwl rename to runs/kallisto_collect/run.cwl index 8e3064c8dae6adb671d4daa9bded1894915f32e4..eaee053d15b5358ec2e125861995edda2004e684 100644 --- a/workflows/kallisto_collect.cwl +++ b/runs/kallisto_collect/run.cwl @@ -8,30 +8,26 @@ inputs: type: File inputBinding: position: 0 -- id: arc_root - type: string - inputBinding: - position: 1 - id: in_kallisto_results - type: string + type: Directory inputBinding: - position: 2 + position: 1 - id: in_metadata_file - type: string + type: File inputBinding: - position: 3 + position: 2 - id: in_metadata_sample type: string inputBinding: - position: 4 + position: 3 - id: in_metadata_factor type: string inputBinding: - position: 5 + position: 4 - id: out_folder type: string inputBinding: - position: 6 + position: 5 outputs: - id: outdir @@ -42,4 +38,4 @@ outputs: glob: $(runtime.outdir)/$(inputs.out_folder) baseCommand: -- Rscript \ No newline at end of file +- Rscript diff --git a/runs/kallisto_collect/run.yml b/runs/kallisto_collect/run.yml new file mode 100644 index 0000000000000000000000000000000000000000..2a4197c55b150b9c73030aac479a6ecbc2ec0edf --- /dev/null +++ b/runs/kallisto_collect/run.yml @@ -0,0 +1,13 @@ +cores: 1 +r_script: + class: File + path: ../../workflows/kallisto_collect/kallisto_collect.R +in_kallisto_results: + class: Directory + path: ../kallisto_sleuth/out +in_metadata_file: + class: File + path: ../merged_isa_metadata/out/merged_isa.tsv +in_metadata_sample: "Sample.Name.2" +in_metadata_factor: "Factor..Photosynthesis.mode." +out_folder: out diff --git a/runs/kallisto_index/README.md b/runs/kallisto_index/README.md deleted file mode 100644 index 16475f8b77405c2dbb0e3b86c84bda9db3d4ccdd..0000000000000000000000000000000000000000 --- a/runs/kallisto_index/README.md +++ /dev/null @@ -1,21 +0,0 @@ - -# cwltool README - -## First cd into the (runs) folder, with the .yml file - -cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_index - -## Let it flow - -```bash -### store arc root (two levels up from here) as variable -arc_root=$(echo ${PWD%/*/*}) - -### replace arc root line in yml (specific to the machine from where this is run) -### not sure, if this works on linux... -sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" kallisto_index.yml - -### run with cwltool -cwltool ../../workflows/kallisto_index.cwl kallisto_index.yml - -``` diff --git a/runs/kallisto_index/kallisto_index.yml b/runs/kallisto_index/kallisto_index.yml deleted file mode 100644 index 60f3a27f69a426983d158a83029b18693cf30c0c..0000000000000000000000000000000000000000 --- a/runs/kallisto_index/kallisto_index.yml +++ /dev/null @@ -1,7 +0,0 @@ -cores: 1 -sh_script: - class: File - path: ../../workflows/kallisto_index.sh -in_genome_ref: studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa -out_folder: runs/kallisto_index -arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq diff --git a/runs/kallisto_index/kallisto_index b/runs/kallisto_index/out/kallisto_index similarity index 100% rename from runs/kallisto_index/kallisto_index rename to runs/kallisto_index/out/kallisto_index diff --git a/workflows/kallisto_index.cwl b/runs/kallisto_index/run.cwl similarity index 82% rename from workflows/kallisto_index.cwl rename to runs/kallisto_index/run.cwl index a6389de36bedc4d46d297b71c7dabd50ed07e200..a8665ac38a52da961f0dc10751bedaef0451c8bd 100644 --- a/workflows/kallisto_index.cwl +++ b/runs/kallisto_index/run.cwl @@ -8,12 +8,8 @@ inputs: type: File inputBinding: position: 0 -- id: arc_root - type: string - inputBinding: - position: 1 - id: in_genome_ref - type: string + type: File inputBinding: position: 2 - id: out_folder @@ -30,4 +26,4 @@ outputs: glob: $(runtime.outdir)/$(inputs.out_folder) baseCommand: -- bash \ No newline at end of file +- bash diff --git a/runs/kallisto_index/run.yml b/runs/kallisto_index/run.yml new file mode 100644 index 0000000000000000000000000000000000000000..df0c0706df4bcbda3746868761ef252449eb736c --- /dev/null +++ b/runs/kallisto_index/run.yml @@ -0,0 +1,8 @@ +cores: 1 +sh_script: + class: File + path: ../../workflows/kallisto_index/kallisto_index.sh +in_genome_ref: + class: File + path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa +out_folder: ./out diff --git a/runs/kallisto_quant/README.md b/runs/kallisto_quant/README.md deleted file mode 100644 index 7e0399169b09ac01f90709bcec1dd8d6e2e9694a..0000000000000000000000000000000000000000 --- a/runs/kallisto_quant/README.md +++ /dev/null @@ -1,21 +0,0 @@ - -# cwltool README - -## First cd into the (runs) folder, with the .yml file - -cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_quant - -## Let it flow - -```bash -### store arc root (two levels up from here) as variable -arc_root=$(echo ${PWD%/*/*}) - -### replace arc root line in yml (specific to the machine from where this is run) -### not sure, if this works on linux... -sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" kallisto_quant.yml - -### run with cwltool -cwltool ../../workflows/kallisto_quant.cwl kallisto_quant.yml - -``` diff --git a/runs/kallisto_quant/kallisto_quant.yml b/runs/kallisto_quant/kallisto_quant.yml deleted file mode 100644 index 3a700dde637416106f587147d1a6104ecdd6326d..0000000000000000000000000000000000000000 --- a/runs/kallisto_quant/kallisto_quant.yml +++ /dev/null @@ -1,12 +0,0 @@ -cores: 4 -sh_script: - class: File - path: ../../workflows/kallisto_quant.sh -arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq -out_folder: runs/kallisto_quant/kallisto_results -in_kallisto_index: runs/kallisto_index/kallisto_index -in_fastq_folder: assays/Talinum_RNASeq_minimal/dataset -kallisto_bootstrap: 100 -kallisto_threads: 4 -kallisto_fragmentLength: 200 -kallisto_stdDev: 20 \ No newline at end of file diff --git a/workflows/kallisto_quant.cwl b/runs/kallisto_quant/run.cwl similarity index 86% rename from workflows/kallisto_quant.cwl rename to runs/kallisto_quant/run.cwl index 9259357a2df7043a94a49eba13d0d1b1f534db28..980dc14143bab29a391bfbffc7040a6323df4b4a 100644 --- a/workflows/kallisto_quant.cwl +++ b/runs/kallisto_quant/run.cwl @@ -8,38 +8,34 @@ inputs: type: File inputBinding: position: 0 -- id: arc_root +- id: out_folder type: string inputBinding: position: 1 -- id: out_folder - type: string +- id: in_kallisto_index + type: File inputBinding: position: 2 -- id: in_kallisto_index - type: string +- id: in_fastq_dir + type: Directory inputBinding: position: 3 -- id: in_fastq_folder - type: string - inputBinding: - position: 4 - id: kallisto_bootstrap type: int inputBinding: - position: 5 + position: 4 - id: kallisto_threads type: int inputBinding: - position: 6 + position: 5 - id: kallisto_fragmentLength type: int inputBinding: - position: 7 + position: 6 - id: kallisto_stdDev type: int inputBinding: - position: 8 + position: 7 outputs: - id: outdir diff --git a/runs/kallisto_quant/run.yml b/runs/kallisto_quant/run.yml new file mode 100644 index 0000000000000000000000000000000000000000..09afef48ab9d86fcdc40a041f12c78635c47bd18 --- /dev/null +++ b/runs/kallisto_quant/run.yml @@ -0,0 +1,15 @@ +cores: 4 +sh_script: + class: File + path: ../../workflows/kallisto_quant/kallisto_quant.sh +out_folder: ./kallisto_results +in_kallisto_index: + class: File + path: ../kallisto_index/out/kallisto_index +in_fastq_dir: + class: Directory + path: ../../assays/Talinum_RNASeq_minimal/dataset +kallisto_bootstrap: 100 +kallisto_threads: 4 +kallisto_fragmentLength: 200 +kallisto_stdDev: 20 diff --git a/runs/kallisto_sleuth/README.md b/runs/kallisto_sleuth/README.md deleted file mode 100644 index 05639e7e53b53e81a9f51f01627e43af130fec9c..0000000000000000000000000000000000000000 --- a/runs/kallisto_sleuth/README.md +++ /dev/null @@ -1,21 +0,0 @@ - -# cwltool README - -## First cd into the (runs) folder, with the .yml file - -cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_sleuth - -## Let it flow - -```bash -### store arc root (two levels up from here) as variable -arc_root=$(echo ${PWD%/*/*}) - -### replace arc root line in yml (specific to the machine from where this is run) -### not sure, if this works on linux... -sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" kallisto_sleuth.yml - -### run with cwltool -cwltool ../../workflows/kallisto_sleuth.cwl kallisto_sleuth.yml - -``` diff --git a/runs/kallisto_sleuth/kallisto_sleuth.yml b/runs/kallisto_sleuth/kallisto_sleuth.yml deleted file mode 100644 index 34364fd1b8f453cf2ec511b2549f890fd06442ba..0000000000000000000000000000000000000000 --- a/runs/kallisto_sleuth/kallisto_sleuth.yml +++ /dev/null @@ -1,7 +0,0 @@ -cores: 1 -r_script: - class: File - path: ../../workflows/kallisto_sleuth.R -in_sleuth: runs/kallisto_collect/kallisto_sleuthObject.RData -out_folder: runs/kallisto_sleuth -arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq \ No newline at end of file diff --git a/runs/kallisto_sleuth/sleuth_dge.csv b/runs/kallisto_sleuth/out/sleuth_dge.csv similarity index 100% rename from runs/kallisto_sleuth/sleuth_dge.csv rename to runs/kallisto_sleuth/out/sleuth_dge.csv diff --git a/workflows/merge_isa_metadata.cwl b/runs/kallisto_sleuth/run.cwl similarity index 70% rename from workflows/merge_isa_metadata.cwl rename to runs/kallisto_sleuth/run.cwl index d812914728833fca5140a2b9347c5e6994aa52ce..60a4475f53945dbe96e9499d6bf46859d3273b4d 100644 --- a/workflows/merge_isa_metadata.cwl +++ b/runs/kallisto_sleuth/run.cwl @@ -8,22 +8,14 @@ inputs: type: File inputBinding: position: 0 -- id: arc_root - type: string +- id: in_sleuth + type: File inputBinding: position: 1 -- id: in_isa_study - type: string - inputBinding: - position: 2 -- id: in_isa_assay - type: string - inputBinding: - position: 3 - id: out_folder type: string inputBinding: - position: 4 + position: 2 outputs: - id: outdir diff --git a/runs/kallisto_sleuth/run.yml b/runs/kallisto_sleuth/run.yml new file mode 100644 index 0000000000000000000000000000000000000000..7307a3537891c059bbbb4bea668f34678140f032 --- /dev/null +++ b/runs/kallisto_sleuth/run.yml @@ -0,0 +1,8 @@ +cores: 1 +r_script: + class: File + path: ../../workflows/kallisto_sleuth/kallisto_sleuth.R +in_sleuth: + class: File + path: ../kallisto_collect/out/kallisto_sleuthObject.RData +out_folder: out diff --git a/runs/merged_isa_metadata/README.md b/runs/merged_isa_metadata/README.md deleted file mode 100644 index 59c24ded29d2efa45432c30c827d84606161102c..0000000000000000000000000000000000000000 --- a/runs/merged_isa_metadata/README.md +++ /dev/null @@ -1,23 +0,0 @@ - -# cwltool README - -## First cd into the (runs) folder, with the .yml file - -cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/merged_isa_metadata - - -## Let it flow - -```bash - -### store arc root (two levels up from here) as variable -arc_root=$(echo ${PWD%/*/*}) - -### replace arc root line in yml (specific to the machine from where this is run) -### not sure, if this works on linux... -sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" merge_isa_metadata.yml - -### run with cwltool -cwltool ../../workflows/merge_isa_metadata.cwl merge_isa_metadata.yml - -``` diff --git a/runs/merged_isa_metadata/merge_isa_metadata.yml b/runs/merged_isa_metadata/merge_isa_metadata.yml deleted file mode 100644 index 0a52d038aaf9436fa63bd102e14eeb7066a4efb5..0000000000000000000000000000000000000000 --- a/runs/merged_isa_metadata/merge_isa_metadata.yml +++ /dev/null @@ -1,8 +0,0 @@ -cores: 1 -r_script: - class: File - path: ../../workflows/merge_isa_metadata.R -in_isa_study: studies/TalinumFacultativeCAM/isa.study.xlsx:plant_growth -in_isa_assay: assays/Talinum_RNASeq_minimal/isa.assay.xlsx:2EXT01_RNA:3ASY01_RNASeq -out_folder: runs/merged_isa_metadata -arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq \ No newline at end of file diff --git a/runs/merged_isa_metadata/merged_isa.tsv b/runs/merged_isa_metadata/out/merged_isa.tsv similarity index 100% rename from runs/merged_isa_metadata/merged_isa.tsv rename to runs/merged_isa_metadata/out/merged_isa.tsv diff --git a/workflows/kallisto_sleuth.cwl b/runs/merged_isa_metadata/run.cwl similarity index 86% rename from workflows/kallisto_sleuth.cwl rename to runs/merged_isa_metadata/run.cwl index 6f427261e5ec6da3dce2b916d2fcfc25659eff7a..859ac0b1c11de8981a582ea4bc1b12526c12c909 100644 --- a/workflows/kallisto_sleuth.cwl +++ b/runs/merged_isa_metadata/run.cwl @@ -1,26 +1,23 @@ #!/usr/bin/env cwl-runner - cwlVersion: v1.2 class: CommandLineTool - inputs: - id: r_script type: File inputBinding: position: 0 -- id: arc_root - type: string +- id: in_isa_study + type: File inputBinding: position: 1 -- id: in_sleuth - type: string +- id: in_isa_assay + type: File inputBinding: position: 2 - id: out_folder type: string inputBinding: position: 3 - outputs: - id: outdir type: diff --git a/runs/merged_isa_metadata/run.yml b/runs/merged_isa_metadata/run.yml new file mode 100644 index 0000000000000000000000000000000000000000..154dc89bd42c3a389aecb4a80ad8d3d868d167d4 --- /dev/null +++ b/runs/merged_isa_metadata/run.yml @@ -0,0 +1,11 @@ +cores: 1 +r_script: + class: File + path: ../../workflows/merge_isa_metadata/merge_isa_metadata.R +in_isa_study: + class: File + path: ../../studies/TalinumFacultativeCAM/isa.study.xlsx +in_isa_assay: + class: File + path: ../../assays/Talinum_RNASeq_minimal/isa.assay.xlsx +out_folder: out diff --git a/workflows/shiny_plots.Rmd b/runs/shiny_plots.Rmd similarity index 96% rename from workflows/shiny_plots.Rmd rename to runs/shiny_plots.Rmd index 8809a420c9cc539ff3b53988f40e09dc314f8715..3a1e99cf680cdd3c67d2d5d55397db7e39147d13 100644 --- a/workflows/shiny_plots.Rmd +++ b/runs/shiny_plots.Rmd @@ -11,9 +11,8 @@ knitr::opts_chunk$set(echo = TRUE) ```{r load_data, include=FALSE} -# Load data +load(file = "../runs/shiny_prep/out/shiny_prep.RData") -load(file = "../runs/shiny_prep/shiny_prep.RData") ``` diff --git a/runs/shiny_prep/README.md b/runs/shiny_prep/README.md deleted file mode 100644 index 05639e7e53b53e81a9f51f01627e43af130fec9c..0000000000000000000000000000000000000000 --- a/runs/shiny_prep/README.md +++ /dev/null @@ -1,21 +0,0 @@ - -# cwltool README - -## First cd into the (runs) folder, with the .yml file - -cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_sleuth - -## Let it flow - -```bash -### store arc root (two levels up from here) as variable -arc_root=$(echo ${PWD%/*/*}) - -### replace arc root line in yml (specific to the machine from where this is run) -### not sure, if this works on linux... -sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" kallisto_sleuth.yml - -### run with cwltool -cwltool ../../workflows/kallisto_sleuth.cwl kallisto_sleuth.yml - -``` diff --git a/runs/shiny_prep/out/shiny_prep.RData b/runs/shiny_prep/out/shiny_prep.RData new file mode 100644 index 0000000000000000000000000000000000000000..ae56a9cb309ac5e6b27e0c2a7c916035cbcc9dae Binary files /dev/null and b/runs/shiny_prep/out/shiny_prep.RData differ diff --git a/workflows/shiny_prep.cwl b/runs/shiny_prep/run.cwl similarity index 82% rename from workflows/shiny_prep.cwl rename to runs/shiny_prep/run.cwl index 918aaa0aefa401caed518703a64ac7fd6c333e3b..aa7ea15dbeb66f345b610edc8c2ba3b0043d7851 100644 --- a/workflows/shiny_prep.cwl +++ b/runs/shiny_prep/run.cwl @@ -8,18 +8,14 @@ inputs: type: File inputBinding: position: 0 -- id: arc_root - type: string - inputBinding: - position: 1 - id: out_folder type: string inputBinding: - position: 2 + position: 1 - id: in_kallisto_df - type: string + type: File inputBinding: - position: 3 + position: 2 outputs: - id: outdir @@ -30,4 +26,4 @@ outputs: glob: $(runtime.outdir)/$(inputs.out_folder) baseCommand: -- Rscript \ No newline at end of file +- Rscript diff --git a/runs/shiny_prep/run.yml b/runs/shiny_prep/run.yml new file mode 100644 index 0000000000000000000000000000000000000000..7124f42d4bf3c475754e9f72ef0bddfd7c4d9dc7 --- /dev/null +++ b/runs/shiny_prep/run.yml @@ -0,0 +1,8 @@ +cores: 1 +r_script: + class: File + path: ../../workflows/shiny_prep/shiny_prep.R +in_kallisto_df: + class: File + path: ../kallisto_collect/out/kallisto_df.csv +out_folder: out \ No newline at end of file diff --git a/runs/shiny_prep/shiny_prep.RData b/runs/shiny_prep/shiny_prep.RData deleted file mode 100644 index 258a091981fee5ee5389d9e76ca25e2a237768b8..0000000000000000000000000000000000000000 Binary files a/runs/shiny_prep/shiny_prep.RData and /dev/null differ diff --git a/runs/shiny_prep/shiny_prep.yml b/runs/shiny_prep/shiny_prep.yml deleted file mode 100644 index a8fec1d28132c8b86ab7e4264eae03acf7d79e2d..0000000000000000000000000000000000000000 --- a/runs/shiny_prep/shiny_prep.yml +++ /dev/null @@ -1,7 +0,0 @@ -cores: 1 -r_script: - class: File - path: ../../workflows/shiny_prep.R -in_kallisto_df: runs/kallisto_collect/kallisto_df.csv -out_folder: runs/shiny_prep -arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq diff --git a/workflows/install_dependencies/install_cwl.md b/workflows/install_dependencies/install_cwl.md deleted file mode 100644 index d812962a3932a710221301d08205e47345bc95a2..0000000000000000000000000000000000000000 --- a/workflows/install_dependencies/install_cwl.md +++ /dev/null @@ -1,13 +0,0 @@ - -# CWL Installation (MacOS) - -Docs: https://www.commonwl.org/ -GitHub: https://github.com/common-workflow-language/cwltool - -## Install CWL via conda - -> requires conda installation, which is a whole different story. Good luck. - -```bash -conda install -c conda-forge cwltool -``` diff --git a/workflows/install_dependencies/install_kallisto.md b/workflows/install_dependencies/install_kallisto.md deleted file mode 100644 index 121b9f229d207352c3529e572286b3bd34b3f2f9..0000000000000000000000000000000000000000 --- a/workflows/install_dependencies/install_kallisto.md +++ /dev/null @@ -1,13 +0,0 @@ - -# Kallisto Installation - -- Docs: http://pachterlab.github.io/kallisto/manual.html -- GitHub: https://github.com/pachterlab/kallisto - -## MacOS Installation via conda - -see: https://anaconda.org/bioconda/kallisto - -```bash -conda install -c bioconda kallisto -``` diff --git a/workflows/install_dependencies/install_r_packages.R b/workflows/install_dependencies/install_r_packages.R deleted file mode 100644 index fdb1eb1afb2ded3fb31d9f59a4487ce6a028163b..0000000000000000000000000000000000000000 --- a/workflows/install_dependencies/install_r_packages.R +++ /dev/null @@ -1,31 +0,0 @@ -#!/usr/bin/env Rscript - -################################################ -### Installation of R dependencies ############# -################################################ - -### Default (CRAN) - -if(!"tidyverse" %in% row.names(installed.packages())){install.packages("tidyverse")} -if(!"jsonlite" %in% row.names(installed.packages())){install.packages("jsonlite")} -if(!"openxlsx" %in% row.names(installed.packages())){install.packages("openxlsx")} -if(!"kableExtra" %in% row.names(installed.packages())){install.packages("kableExtra")} -if(!"shiny" %in% row.names(installed.packages())){install.packages("shiny")} -if(!"RColorBrewer" %in% row.names(installed.packages())){install.packages("RColorBrewer")} - -### From BiocManager - -if (!requireNamespace("BiocManager", quietly = TRUE)){install.packages("BiocManager")} -if(!"BiocManager" %in% row.names(installed.packages())){BiocManager::install()} -if(!"devtools" %in% row.names(installed.packages())){BiocManager::install("devtools")} -if(!"sleuth" %in% row.names(installed.packages())){BiocManager::install("pachterlab/sleuth")} - -### Test load packages - -library(tidyverse) -library(jsonlite) -library(openxlsx) -library(sleuth) -library(kableExtra) -library(shiny) -library(RColorBrewer) diff --git a/workflows/kallisto_collect.R b/workflows/kallisto_collect/kallisto_collect.R similarity index 63% rename from workflows/kallisto_collect.R rename to workflows/kallisto_collect/kallisto_collect.R index b52176342b317b3c38a0f1359c2d7ad171cd9fe1..6a24e7ee2b4cd5711ec8603ec9f19828a15565cb 100644 --- a/workflows/kallisto_collect.R +++ b/workflows/kallisto_collect/kallisto_collect.R @@ -1,16 +1,5 @@ #!/usr/bin/env Rscript -################################################ -#### CWL-independent tests -################################################ - -# arc_root <- "~/gitlab_dataplant/samplearc_rnaseq/" -# in_kallisto_results <- "runs/kallisto_quant/kallisto_results" -# in_metadata_file <- "runs/merged_isa_metadata/merged_isa.tsv" -# in_metadata_sample <- "Sample.Name.2" -# in_metadata_factor <- "Factor..Photosynthesis.mode." -# out_folder <- "runs/kallisto_collect" - ################################################ #### Load required library ################################################ @@ -25,31 +14,30 @@ library(jsonlite) args <- commandArgs(trailingOnly = T) -arc_root <- args[1] -in_kallisto_results <- args[2] -in_metadata_file <- args[3] -in_metadata_sample <- args[4] -in_metadata_factor <- args[5] -out_folder <- args[6] +in_kallisto_results <- args[1] +in_metadata_file <- args[2] +in_metadata_sample <- args[3] +in_metadata_factor <- args[4] +out_folder <- args[5] ################################################ #### If it does not exist, create out dir ################################################ -dir.create(paste(arc_root, out_folder, sep = "/"), recursive = T, showWarnings = F) +dir.create(out_folder, recursive = T, showWarnings = F) ################################################ #### Read ISA sample metadata ################################################ -samples <- read.table(file = paste(arc_root, in_metadata_file, sep = "/"), sep = "\t") +samples <- read.table(file = in_metadata_file, sep = "\t") ################################################ #### Read Kallisto results ################################################ -base_dir <- paste(arc_root, in_kallisto_results, sep = "/") +base_dir <- in_kallisto_results # A list of paths to the kallisto results indexed by the sample IDs is collated with kal_dirs <- dir(base_dir, full.names = T) ## Sleuth requires full paths @@ -67,7 +55,7 @@ s2c <- merge(s2c, path_df, by = "out_name") so <- sleuth_prep(s2c, full_model = ~condition, num_cores = 1) -save(so, file = paste(arc_root, out_folder, "kallisto_sleuthObject.RData", sep = "/")) +save(so, file = paste(out_folder, "kallisto_sleuthObject.RData", sep = "/")) ################################################ @@ -78,13 +66,13 @@ save(so, file = paste(arc_root, out_folder, "kallisto_sleuthObject.RData", sep = expression_data <- kallisto_table(so) ## write to file -write.csv(expression_data, paste(arc_root, out_folder, "/kallisto_df.csv", sep = "/"), row.names = F) +write.csv(expression_data, paste(out_folder, "/kallisto_df.csv", sep = "/"), row.names = F) ## as tpm matrix (gene x sample) tpm_table <- pivot_wider(expression_data, id_cols = target_id, names_from = sample, values_from = tpm) ## write to file -write.csv(tpm_table, paste(arc_root, out_folder, "/kallisto_tpmMatrix.csv", sep = "/"), row.names = F) +write.csv(tpm_table, paste(out_folder, "/kallisto_tpmMatrix.csv", sep = "/"), row.names = F) ################################################ #### Summarize mapping stats @@ -99,4 +87,4 @@ for (i in dir(kal_dirs, pattern = ".json", full.names = T)) mapping_stats <- rbind(mapping_stats, z) } -write.csv(mapping_stats, paste(arc_root, out_folder, "/kallisto_mappingStats.csv", sep = "/"), row.names = F) +write.csv(mapping_stats, paste(out_folder, "/kallisto_mappingStats.csv", sep = "/"), row.names = F) diff --git a/workflows/kallisto_index.sh b/workflows/kallisto_index/kallisto_index.sh old mode 100755 new mode 100644 similarity index 57% rename from workflows/kallisto_index.sh rename to workflows/kallisto_index/kallisto_index.sh index 6cd3e178fa47e59af1e430a16e3def895dcefb37..c346206eca3c0d7ec2294deb2387573e8d7926f8 --- a/workflows/kallisto_index.sh +++ b/workflows/kallisto_index/kallisto_index.sh @@ -2,23 +2,12 @@ ### Build kallisto index - -################################################ -#### CWL-independent tests -################################################ - -# in_genome_ref=studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa -# out_folder=runs/kallisto_index -# arc_root=/Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq - - ################################################ #### Read arguments from CLI ################################################ -arc_root=$1 -in_genome_ref=$2 -out_folder=$3 +in_genome_ref=$1 +out_folder=$2 ################################################ #### Print version and citation to test kallisto @@ -31,11 +20,10 @@ kallisto cite #### If it does not exist, create out dir ################################################ -mkdir -p "$arc_root/$out_folder/" - +mkdir -p $out_folder ################################################ #### Build kallisto index ################################################ -kallisto index -i "$arc_root/$out_folder/kallisto_index" "$arc_root/$in_genome_ref" +kallisto index -i $out_folder/kallisto_index $in_genome_ref diff --git a/workflows/kallisto_quant.sh b/workflows/kallisto_quant.sh deleted file mode 100755 index c1217416f77460b75944ccf50bb7cf9632a93ba8..0000000000000000000000000000000000000000 --- a/workflows/kallisto_quant.sh +++ /dev/null @@ -1,59 +0,0 @@ -#!/usr/bin/env bash - -### Map RNASeq reads via kallisto -### Note, this is written for single-end mode only - -################################################ -#### CWL-independent tests -################################################ - -# arc_root=/Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq -# out_folder=runs/kallisto_quant/kallisto_results_v48_anaconda -# in_kallisto_index=runs/kallisto_index/kallisto_index -# in_fastq_folder=assays/Talinum_RNASeq_minimal/dataset -# kallisto_bootstrap=100 -# kallisto_threads=4 -# kallisto_fragmentLength=200 -# kallisto_stdDev=20 - -################################################ -#### Read arguments from CLI -################################################ - -arc_root=$1 -out_folder=$2 -in_kallisto_index=$3 -in_fastq_folder=$4 -kallisto_bootstrap=$5 -kallisto_threads=$6 -kallisto_fragmentLength=$7 -kallisto_stdDev=$8 - -################################################ -#### If it does not exist, create out dir -################################################ - -mkdir -p "$arc_root/$out_folder/" - -################################################ -#### Store fastq files in variable -################################################ - -fastq_files=$(ls "${arc_root}"/"${in_fastq_folder}"/*fastq*) - -################################################ -#### Loop over fastq files and quantify reads -################################################ - -for j in $fastq_files; do - - # cut away path. retain only first six chars of file name - sampleName=$(echo $j | sed -e 's|.*/||' | sed -e 's|.fastq.*||') - - echo $sampleName - - kallisto quant --single -b $kallisto_bootstrap -t $kallisto_threads -l $kallisto_fragmentLength -s $kallisto_stdDev -i "$arc_root/$in_kallisto_index" -o "$arc_root/$out_folder/$sampleName" $j - - echo 'Kallisto done' - -done diff --git a/workflows/kallisto_quant/kallisto_quant.sh b/workflows/kallisto_quant/kallisto_quant.sh new file mode 100644 index 0000000000000000000000000000000000000000..63d0cb1af98ba421d835ceb9c6787e20be95d2d1 --- /dev/null +++ b/workflows/kallisto_quant/kallisto_quant.sh @@ -0,0 +1,44 @@ +#!/usr/bin/env bash + +### Map RNASeq reads via kallisto +### Note, this is written for single-end mode only + +################################################ +#### Read arguments from CLI +################################################ + +out_folder=$1 +in_kallisto_index=$2 +in_fastq_folder=$3 +kallisto_bootstrap=$4 +kallisto_threads=$5 +kallisto_fragmentLength=$6 +kallisto_stdDev=$7 + +################################################ +#### If it does not exist, create out dir +################################################ + +mkdir -p "$out_folder" + +################################################ +#### Store fastq files in variable +################################################ + +fastq_files=$(ls "${in_fastq_folder}"/*fastq*) + +################################################ +#### Loop over fastq files and quantify reads +################################################ + +for j in $fastq_files; do + + sampleName=$(basename $j) + + echo $sampleName + + kallisto quant --single -b $kallisto_bootstrap -t $kallisto_threads -l $kallisto_fragmentLength -s $kallisto_stdDev -i "$in_kallisto_index" -o "$out_folder/$sampleName" $j + + echo 'Kallisto done' + +done diff --git a/workflows/kallisto_sleuth.R b/workflows/kallisto_sleuth/kallisto_sleuth.R similarity index 59% rename from workflows/kallisto_sleuth.R rename to workflows/kallisto_sleuth/kallisto_sleuth.R index ec3a84afe7aec0e9bab0b621c113e23e177a83bd..c4b599b5a0b99eae5b0026fd167ec6daaff93913 100644 --- a/workflows/kallisto_sleuth.R +++ b/workflows/kallisto_sleuth/kallisto_sleuth.R @@ -1,21 +1,10 @@ #!/usr/bin/env Rscript -################################################ -### Diff. gene expression with sleuth ########## -################################################ - -################################################ -#### CWL-independent tests -################################################ - -# arc_root <- "~/gitlab_dataplant/samplearc_rnaseq/" -# in_sleuth <- "runs/kallisto_collect/kallisto_sleuthObject.RData" -# out_folder <- "runs/kallisto_sleuth" +### Diff. gene expression with sleuth ################################################ #### Load required library ################################################ - library(sleuth) ################################################ @@ -24,21 +13,20 @@ library(sleuth) args <- commandArgs(trailingOnly = T) -arc_root <- args[1] -in_sleuth <- args[2] -out_folder <- args[3] +in_sleuth <- args[1] +out_folder <- args[2] ################################################ #### If it does not exist, create out dir ################################################ -dir.create(paste(arc_root, out_folder, sep = "/"), recursive = T, showWarnings = F) +dir.create(out_folder, recursive = T, showWarnings = F) ################################################ #### Load sleuth object ################################################ -load(file = paste(arc_root, in_sleuth, sep = "/")) +load(file = in_sleuth) ################################################ #### Run sleuth fit @@ -55,4 +43,4 @@ sleuth_table <- sleuth_results(so, "reduced:full", "lrt", show_all = FALSE) #### write to file ################################################ -write.csv(sleuth_table, paste(arc_root, out_folder, "sleuth_dge.csv", sep = "/"), row.names = F) +write.csv(sleuth_table, paste(out_folder, "sleuth_dge.csv", sep = "/"), row.names = F) diff --git a/workflows/merge_isa_metadata.R b/workflows/merge_isa_metadata/merge_isa_metadata.R similarity index 67% rename from workflows/merge_isa_metadata.R rename to workflows/merge_isa_metadata/merge_isa_metadata.R index 5af105c569fe6b23a20b25e53e82ef80eb76b787..b4daca150962998854d9a3aaaf7d3f695a98b524 100644 --- a/workflows/merge_isa_metadata.R +++ b/workflows/merge_isa_metadata/merge_isa_metadata.R @@ -1,14 +1,5 @@ #!/usr/bin/env Rscript -################################################ -#### CWL-independent tests -################################################ - -# arc_root <- "~/gitlab_dataplant/samplearc_rnaseq/" -# in_isa_study <- "studies/TalinumFacultativeCAM/isa.study.xlsx:plant_growth" -# in_isa_assay <- "assays/Talinum_RNASeq_minimal/isa.assay.xlsx:2EXT01_RNA:3ASY01_RNASeq" -# out_folder <- "runs/merged_isa_metadata" - ################################################ #### Load required library ################################################ @@ -21,17 +12,18 @@ library(openxlsx) args <- commandArgs(trailingOnly = T) -arc_root <- args[1] -in_isa_study <- args[2] -in_isa_assay <- args[3] -out_folder <- args[4] +in_isa_study <- paste(args[1], ":plant_growth", sep="") +print(in_isa_study) +in_isa_assay <- paste(args[2], ":2EXT01_RNA:3ASY01_RNASeq", sep="") +print(in_isa_assay) +out_folder <- args[3] ################################################ #### Read metadata from isa excel workbooks ################################################ -isa_study <- unlist(strsplit(paste(arc_root, in_isa_study, sep = "/"), split = ":")) -isa_assay <- unlist(strsplit(paste(arc_root, in_isa_assay, sep = "/"), split = ":")) +isa_study <- unlist(strsplit(in_isa_study, split = ":")) +isa_assay <- unlist(strsplit(in_isa_assay, split = ":")) isa_sheets <- list() for (i in 2:length(isa_study)) @@ -76,12 +68,10 @@ isa_merged <- isa_merged[, !apply(isa_merged, 2, function(x) { #### If it does not exist, create out dir ################################################ - -dir.create(paste(arc_root, out_folder, sep = "/"), recursive = T, showWarnings = F) - +dir.create(out_folder, recursive = T, showWarnings = F) ################################################ #### Write table to file ################################################ -write.table(isa_merged, file = paste(arc_root, out_folder, "merged_isa.tsv", sep = "/"), sep = "\t") +write.table(isa_merged, file = paste(out_folder, "merged_isa.tsv", sep = "/"), sep = "\t") diff --git a/workflows/rnaseq_pipeline.drawio.svg b/workflows/rnaseq_pipeline.drawio.svg deleted file mode 100644 index b9d487ccf97e05fda12d053e0324f68f6e7fd659..0000000000000000000000000000000000000000 --- a/workflows/rnaseq_pipeline.drawio.svg +++ /dev/null @@ -1,127 +0,0 @@ -<svg host="65bd71144e" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" width="602px" height="262px" viewBox="-0.5 -0.5 602 262" content="<mxfile><diagram id="xGNej_qxJKJTo4vCftfG" name="Page-1">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</diagram></mxfile>"> - <defs/> - <g> - <path d="M 380 60 L 380 93.63" fill="none" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="stroke"/> - <path d="M 380 98.88 L 376.5 91.88 L 380 93.63 L 383.5 91.88 Z" fill="rgb(0, 0, 0)" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="all"/> - <rect x="320" y="0" width="120" height="60" rx="9" ry="9" fill="rgb(255, 255, 255)" stroke="rgb(0, 0, 0)" pointer-events="all"/> - <g transform="translate(-0.5 -0.5)"> - <switch> - <foreignObject pointer-events="none" width="100%" height="100%" requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility" style="overflow: visible; text-align: left;"> - <div xmlns="http://www.w3.org/1999/xhtml" style="display: flex; align-items: unsafe center; justify-content: unsafe center; width: 118px; height: 1px; padding-top: 30px; margin-left: 321px;"> - <div data-drawio-colors="color: rgb(0, 0, 0); " style="box-sizing: border-box; font-size: 0px; text-align: center;"> - <div style="display: inline-block; font-size: 12px; font-family: Helvetica; color: rgb(0, 0, 0); line-height: 1.2; pointer-events: all; white-space: normal; overflow-wrap: normal;"> - merge_isa_metadata - </div> - </div> - </div> - </foreignObject> - <text x="380" y="34" fill="rgb(0, 0, 0)" font-family="Helvetica" font-size="12px" text-anchor="middle"> - merge_isa_metadata - </text> - </switch> - </g> - <path d="M 120 130 L 153.63 130" fill="none" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="stroke"/> - <path d="M 158.88 130 L 151.88 133.5 L 153.63 130 L 151.88 126.5 Z" fill="rgb(0, 0, 0)" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="all"/> - <rect x="0" y="100" width="120" height="60" rx="9" ry="9" fill="rgb(255, 255, 255)" stroke="rgb(0, 0, 0)" pointer-events="all"/> - <g transform="translate(-0.5 -0.5)"> - <switch> - <foreignObject pointer-events="none" width="100%" height="100%" requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility" style="overflow: visible; text-align: left;"> - <div xmlns="http://www.w3.org/1999/xhtml" style="display: flex; align-items: unsafe center; justify-content: unsafe center; width: 118px; height: 1px; padding-top: 130px; margin-left: 1px;"> - <div data-drawio-colors="color: rgb(0, 0, 0); " style="box-sizing: border-box; font-size: 0px; text-align: center;"> - <div style="display: inline-block; font-size: 12px; font-family: Helvetica; color: rgb(0, 0, 0); line-height: 1.2; pointer-events: all; white-space: normal; overflow-wrap: normal;"> - kallisto_index - </div> - </div> - </div> - </foreignObject> - <text x="60" y="134" fill="rgb(0, 0, 0)" font-family="Helvetica" font-size="12px" text-anchor="middle"> - kallisto_index - </text> - </switch> - </g> - <path d="M 280 130 L 313.63 130" fill="none" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="stroke"/> - <path d="M 318.88 130 L 311.88 133.5 L 313.63 130 L 311.88 126.5 Z" fill="rgb(0, 0, 0)" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="all"/> - <path d="M 280 130 L 313.63 130" fill="none" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="stroke"/> - <path d="M 318.88 130 L 311.88 133.5 L 313.63 130 L 311.88 126.5 Z" fill="rgb(0, 0, 0)" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="all"/> - <rect x="160" y="100" width="120" height="60" rx="9" ry="9" fill="rgb(255, 255, 255)" stroke="rgb(0, 0, 0)" pointer-events="all"/> - <g transform="translate(-0.5 -0.5)"> - <switch> - <foreignObject pointer-events="none" width="100%" height="100%" requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility" style="overflow: visible; text-align: left;"> - <div xmlns="http://www.w3.org/1999/xhtml" style="display: flex; align-items: unsafe center; justify-content: unsafe center; width: 118px; height: 1px; padding-top: 130px; margin-left: 161px;"> - <div data-drawio-colors="color: rgb(0, 0, 0); " style="box-sizing: border-box; font-size: 0px; text-align: center;"> - <div style="display: inline-block; font-size: 12px; font-family: Helvetica; color: rgb(0, 0, 0); line-height: 1.2; pointer-events: all; white-space: normal; overflow-wrap: normal;"> - kallisto_quant - </div> - </div> - </div> - </foreignObject> - <text x="220" y="134" fill="rgb(0, 0, 0)" font-family="Helvetica" font-size="12px" text-anchor="middle"> - kallisto_quant - </text> - </switch> - </g> - <path d="M 380 160 L 380 193.63" fill="none" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="stroke"/> - <path d="M 380 198.88 L 376.5 191.88 L 380 193.63 L 383.5 191.88 Z" fill="rgb(0, 0, 0)" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="all"/> - <path d="M 440 130 L 473.63 130" fill="none" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="stroke"/> - <path d="M 478.88 130 L 471.88 133.5 L 473.63 130 L 471.88 126.5 Z" fill="rgb(0, 0, 0)" stroke="rgb(0, 0, 0)" stroke-miterlimit="10" pointer-events="all"/> - <rect x="320" y="100" width="120" height="60" rx="9" ry="9" fill="rgb(255, 255, 255)" stroke="rgb(0, 0, 0)" pointer-events="all"/> - <g transform="translate(-0.5 -0.5)"> - <switch> - <foreignObject pointer-events="none" width="100%" height="100%" requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility" style="overflow: visible; text-align: left;"> - <div xmlns="http://www.w3.org/1999/xhtml" style="display: flex; align-items: unsafe center; justify-content: unsafe center; width: 118px; height: 1px; padding-top: 130px; margin-left: 321px;"> - <div data-drawio-colors="color: rgb(0, 0, 0); " style="box-sizing: border-box; font-size: 0px; text-align: center;"> - <div style="display: inline-block; font-size: 12px; font-family: Helvetica; color: rgb(0, 0, 0); line-height: 1.2; pointer-events: all; white-space: normal; overflow-wrap: normal;"> - kallisto_collect - </div> - </div> - </div> - </foreignObject> - <text x="380" y="134" fill="rgb(0, 0, 0)" font-family="Helvetica" font-size="12px" text-anchor="middle"> - kallisto_collect - </text> - </switch> - </g> - <rect x="320" y="200" width="120" height="60" rx="9" ry="9" fill="rgb(255, 255, 255)" stroke="rgb(0, 0, 0)" pointer-events="all"/> - <g transform="translate(-0.5 -0.5)"> - <switch> - <foreignObject pointer-events="none" width="100%" height="100%" requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility" style="overflow: visible; text-align: left;"> - <div xmlns="http://www.w3.org/1999/xhtml" style="display: flex; align-items: unsafe center; justify-content: unsafe center; width: 118px; height: 1px; padding-top: 230px; margin-left: 321px;"> - <div data-drawio-colors="color: rgb(0, 0, 0); " style="box-sizing: border-box; font-size: 0px; text-align: center;"> - <div style="display: inline-block; font-size: 12px; font-family: Helvetica; color: rgb(0, 0, 0); line-height: 1.2; pointer-events: all; white-space: normal; overflow-wrap: normal;"> - kallisto_sleuth - </div> - </div> - </div> - </foreignObject> - <text x="380" y="234" fill="rgb(0, 0, 0)" font-family="Helvetica" font-size="12px" text-anchor="middle"> - kallisto_sleuth - </text> - </switch> - </g> - <rect x="480" y="100" width="120" height="60" rx="9" ry="9" fill="rgb(255, 255, 255)" stroke="rgb(0, 0, 0)" pointer-events="all"/> - <g transform="translate(-0.5 -0.5)"> - <switch> - <foreignObject pointer-events="none" width="100%" height="100%" requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility" style="overflow: visible; text-align: left;"> - <div xmlns="http://www.w3.org/1999/xhtml" style="display: flex; align-items: unsafe center; justify-content: unsafe center; width: 118px; height: 1px; padding-top: 130px; margin-left: 481px;"> - <div data-drawio-colors="color: rgb(0, 0, 0); " style="box-sizing: border-box; font-size: 0px; text-align: center;"> - <div style="display: inline-block; font-size: 12px; font-family: Helvetica; color: rgb(0, 0, 0); line-height: 1.2; pointer-events: all; white-space: normal; overflow-wrap: normal;"> - shiny_prep - </div> - </div> - </div> - </foreignObject> - <text x="540" y="134" fill="rgb(0, 0, 0)" font-family="Helvetica" font-size="12px" text-anchor="middle"> - shiny_prep - </text> - </switch> - </g> - </g> - <switch> - <g requiredFeatures="http://www.w3.org/TR/SVG11/feature#Extensibility"/> - <a transform="translate(0,-5)" xlink:href="https://www.diagrams.net/doc/faq/svg-export-text-problems" target="_blank"> - <text text-anchor="middle" font-size="10px" x="50%" y="100%"> - Viewer does not support full SVG 1.1 - </text> - </a> - </switch> -</svg> \ No newline at end of file diff --git a/workflows/shiny_prep.R b/workflows/shiny_prep.R deleted file mode 100644 index a44796250a409d286eb330862a7cdb6c4b473036..0000000000000000000000000000000000000000 --- a/workflows/shiny_prep.R +++ /dev/null @@ -1,41 +0,0 @@ -#!/usr/bin/env Rscript - -################################################ -#### CWL-independent tests -################################################ - -# arc_root <- "~/gitlab_dataplant/samplearc_rnaseq/" -# out_folder <- "runs/shiny_prep" -# in_kallisto_df <- "runs/kallisto_collect/kallisto_df.csv" - -################################################ -#### Load required library -################################################ - - - -################################################ -#### Read arguments from CLI -################################################ - -args <- commandArgs(trailingOnly = T) - -arc_root <- args[1] -out_folder <- args[2] -in_kallisto_df <- args[3] - -################################################ -#### If it does not exist, create out dir -################################################ - -dir.create(paste(arc_root, out_folder, sep = "/"), recursive = T, showWarnings = F) - -################################################ -#### Prep data for shiny app -################################################ - -expression_data <- read.csv(file = paste(arc_root, in_kallisto_df, sep = "/")) - -available_genes <- unique(expression_data$target_id) - -save(expression_data, available_genes, file = paste(arc_root, out_folder, 'shiny_prep.RData', sep = "/")) diff --git a/workflows/shiny_prep/shiny_prep.R b/workflows/shiny_prep/shiny_prep.R new file mode 100644 index 0000000000000000000000000000000000000000..804ad85db72c912c214f19b868e6073316524bab --- /dev/null +++ b/workflows/shiny_prep/shiny_prep.R @@ -0,0 +1,26 @@ +#!/usr/bin/env Rscript + +################################################ +#### Read arguments from CLI +################################################ + +args <- commandArgs(trailingOnly = T) + +out_folder <- args[1] +in_kallisto_df <- args[2] + +################################################ +#### If it does not exist, create out dir +################################################ + +dir.create(out_folder, recursive = T, showWarnings = F) + +################################################ +#### Prep data for shiny app +################################################ + +expression_data <- read.csv(file = in_kallisto_df) + +available_genes <- unique(expression_data$target_id) + +save(expression_data, available_genes, file = paste(out_folder, 'shiny_prep.RData', sep = "/"))