Commit 502d88dd authored by mmassaviol's avatar mmassaviol
Browse files

Update tool yamls to include dependencies and remove dependencies files

parent 7af5d1c3
......@@ -63,7 +63,7 @@ def generate_container_recipe(config, template_file, out_file):
params = read_yaml(config)
for step in params["sag"]["steps"]:
for tool in params["sag"]["steps"][step]["tools"]:
dependencies = read_yaml("tools/" + tool + "/" + tool + ".dependencies.yaml")
dependencies = read_yaml("tools/" + tool + "/" + tool + ".yaml")
tools.update(dependencies["install"])
for key, value in tools.items():
......@@ -101,7 +101,7 @@ def scripts_list(config):
params = read_yaml(config)
for step in params["sag"]["steps"]:
for tool in params["sag"]["steps"][step]["tools"]:
dependencies = read_yaml("tools/" + tool + "/" + tool + ".dependencies.yaml")
dependencies = read_yaml("tools/" + tool + "/" + tool + ".yaml")
if ("script" in dependencies.keys()):
res.append(tool)
return(res)
......
name: "deseq2"
version: "3.8"
description: "Differential gene expression analysis based on the negative binomial distribution"
documentation: "https://bioconductor.org/packages/release/bioc/manuals/DESeq2/man/DESeq2.pdf"
install:
DESeq2: "Rscript -e 'BiocManager::install(\"DESeq2\", version = \"3.8\",Ncpus=8)'"
apeglm: "Rscript -e 'BiocManager::install(\"apeglm\", version = \"3.8\",Ncpus=8)'"
BiocParallel: "Rscript -e 'BiocManager::install(\"BiocParallel\", version = \"3.8\",Ncpus=8)'"
tximport: "Rscript -e 'BiocManager::install(\"tximport\", version = \"3.8\",Ncpus=8)'"
rhdf5: "Rscript -e 'BiocManager::install(\"rhdf5\", version = \"3.8\",Ncpus=8)'"
GenomicFeatures: "Rscript -e 'BiocManager::install(\"GenomicFeatures\", version = \"3.8\",Ncpus=8)'"
script: deseq2.script.R
\ No newline at end of file
......@@ -12,8 +12,38 @@
command: ~,
output_dir: deseq2,
inputs: [{ name: counts }],
outputs: [{ name: de_table, file: de_table.csv }, { name: RData, file: data.RData }],
options: [],
outputs:
[
{ name: de_table, file: de_table.csv },
{ name: RData, file: data.RData },
],
options:
[
{
name: "deseq2_tx2gene",
type: "checkbox",
value: FALSE,
label: "Aggregate transcripts counts to gene counts : ",
},
{
name: "deseq2_annotations",
type: "text",
value: "",
label: "Annotation file (gtf or gff) : ",
},
],
},
],
version: "3.8",
documentation: "https://bioconductor.org/packages/release/bioc/manuals/DESeq2/man/DESeq2.pdf",
install:
{
DESeq2: 'Rscript -e ''BiocManager::install("DESeq2", version = "3.8",Ncpus=8)''',
apeglm: 'Rscript -e ''BiocManager::install("apeglm", version = "3.8",Ncpus=8)''',
BiocParallel: 'Rscript -e ''BiocManager::install("BiocParallel", version = "3.8",Ncpus=8)''',
tximport: 'Rscript -e ''BiocManager::install("tximport", version = "3.8",Ncpus=8)''',
rhdf5: 'Rscript -e ''BiocManager::install("rhdf5", version = "3.8",Ncpus=8)''',
GenomicFeatures: 'Rscript -e ''BiocManager::install("GenomicFeatures", version = "3.8",Ncpus=8)''',
},
script: deseq2.script.R,
}
name: "edger"
version: "3.14.0"
description: "Empirical Analysis of Digital Gene Expression Data in R"
documentation: "http://bioconductor.org/packages/release/bioc/manuals/edgeR/man/edgeR.pdf"
install:
limma: "Rscript -e 'BiocManager::install(\"limma\", version = \"3.8\")'"
edger: "Rscript -e 'BiocManager::install(\"edgeR\", version = \"3.8\")'"
tximport: "Rscript -e 'BiocManager::install(\"tximport\", version = \"3.8\",Ncpus=8)'"
rhdf5: "Rscript -e 'BiocManager::install(\"rhdf5\", version = \"3.8\",Ncpus=8)'"
GenomicFeatures: "Rscript -e 'BiocManager::install(\"GenomicFeatures\", version = \"3.8\",Ncpus=8)'"
script: edger.script.R
\ No newline at end of file
......@@ -13,7 +13,32 @@
output_dir: edger,
inputs: [{ name: counts }],
outputs: [{ name: de_table }, { name: RData }],
options: [],
options:
[
{
name: "edger_tx2gene",
type: "checkbox",
value: FALSE,
label: "Aggregate transcripts counts to gene counts : ",
},
{
name: "edger_annotations",
type: "text",
value: "",
label: "Annotation file (gtf or gff) : ",
},
],
},
],
version: "3.14.0",
documentation: "http://bioconductor.org/packages/release/bioc/manuals/edgeR/man/edgeR.pdf",
install:
{
limma: 'Rscript -e ''BiocManager::install("limma", version = "3.8")''',
edger: 'Rscript -e ''BiocManager::install("edgeR", version = "3.8")''',
tximport: 'Rscript -e ''BiocManager::install("tximport", version = "3.8",Ncpus=8)''',
rhdf5: 'Rscript -e ''BiocManager::install("rhdf5", version = "3.8",Ncpus=8)''',
GenomicFeatures: 'Rscript -e ''BiocManager::install("GenomicFeatures", version = "3.8",Ncpus=8)''',
},
script: edger.script.R,
}
name: "fastqc"
version: "0.11.5"
description: "A quality control tool for high throughput sequence data."
documentation: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/"
install:
fastqc: "conda install -c bioconda fastqc=0.11.5"
......@@ -19,7 +19,7 @@
name: fastqc_threads,
prefix: -t,
type: numeric,
default: 1,
value: 1,
min: 1,
max: NA,
step: 1,
......@@ -28,4 +28,7 @@
],
},
],
version: "0.11.5",
documentation: "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/",
install: { fastqc: "conda install -c bioconda fastqc=0.11.5" },
}
name: "kallisto"
version: "0.44.0"
description: "kallisto is a program for quantifying abundances of transcripts from RNA-Seq data, or more generally of target sequences using high-throughput sequencing reads"
documentation: "https://pachterlab.github.io/kallisto/manual"
install:
kallisto: "conda install -c bioconda -c conda-forge kallisto=0.44.0"
......@@ -16,7 +16,7 @@
{
id: kallisto_index_input,
type: text,
default: "",
value: "",
label: "Address to reference fasta file",
},
],
......@@ -30,9 +30,9 @@
inputs: [{ name: index }, { name: reads }],
outputs:
[
{ name: h5, file: abundance.h5 },
{ name: counts, file: abundance.tsv },
{ name: run_info, file: run_info.json },
{ name: h5, file: "{sample}/abundance.h5" },
{ name: counts, file: "{sample}/abundance.tsv" },
{ name: run_info, file: "{sample}/run_info.json" },
],
options:
[
......@@ -40,7 +40,7 @@
name: kallisto_quant_threads,
prefix: -t,
type: numeric,
default: 1,
value: 1,
min: 1,
max: NA,
step: 1,
......@@ -49,11 +49,20 @@
{
name: kallisto_quant_pe_stranded,
type: radio,
choices: [Not stranded: "", Forward Reverse: --fr-stranded, Reverse Forward: --rf-stranded],
default: "",
choices:
[
Not stranded: "",
Forward Reverse: --fr-stranded,
Reverse Forward: --rf-stranded,
],
value: "",
label: For strand specific mode choose --fr-stranded if the first read is forward and choose --rf-stranded if the first read is reverse,
},
],
},
],
version: "0.44.0",
documentation: "https://pachterlab.github.io/kallisto/manual",
install:
{ kallisto: "conda install -c bioconda -c conda-forge kallisto=0.44.0" },
}
name: "salmon"
version: "0.11.3"
description: "Salmon is a tool for quantifying the expression of transcripts using RNA-seq data"
documentation: "https://salmon.readthedocs.io/en/latest/"
install:
salmon: "conda install -c bioconda -c conda-forge salmon=0.11.3"
......@@ -17,18 +17,18 @@
name: salmon_index_input,
prefix: -t,
type: text,
default: "",
value: "",
label: "Address to reference fasta file",
},
],
outputs: [{name: index}],
outputs: [{ name: index }],
options:
[
{
name: salmon_index_threads,
prefix: -p,
type: numeric,
default: 1,
value: 1,
min: 1,
max: NA,
step: 1,
......@@ -43,9 +43,9 @@
inputs: [{ name: index }, { name: reads }],
outputs:
[
{ name: lib_counts, file: lib_format_counts.json },
{ name: counts, file: quant.sf },
{ name: run_info, file: cmd_info.json },
{ name: lib_counts, file: "{sample}/lib_format_counts.json" },
{ name: counts, file: "{sample}/quant.sf" },
{ name: run_info, file: "{sample}/cmd_info.json" },
],
options:
[
......@@ -53,7 +53,7 @@
name: salmon_quant_threads,
prefix: -t,
type: numeric,
default: 1,
value: 1,
min: 1,
max: NA,
step: 1,
......@@ -62,4 +62,7 @@
],
},
],
version: "0.11.3",
documentation: "https://salmon.readthedocs.io/en/latest/",
install: { salmon: "conda install -c bioconda -c conda-forge salmon=0.11.3" },
}
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment