aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndreaGuarracino2020-11-21 23:06:05 +0100
committerAndreaGuarracino2020-11-21 23:06:05 +0100
commit1e9a735e84a8e89099b1de2ec66c56669caf6cc8 (patch)
tree0beefb8e9f7a6321a5c8382b1be7b5b809c87d5e
parent862ae0235e3d1b105fa342cedf4aa59ae73d90c4 (diff)
downloadbh20-seq-resource-1e9a735e84a8e89099b1de2ec66c56669caf6cc8.tar.gz
bh20-seq-resource-1e9a735e84a8e89099b1de2ec66c56669caf6cc8.tar.lz
bh20-seq-resource-1e9a735e84a8e89099b1de2ec66c56669caf6cc8.zip
added abPOA workflow; typos
-rw-r--r--scripts/create_sra_metadata/create_sra_metadata.py2
-rw-r--r--workflows/pangenome-generate/abpoa.cwl26
-rw-r--r--workflows/pangenome-generate/odgi-build-from-xpoa-gfa.cwl (renamed from workflows/pangenome-generate/odgi-build-from-spoa-gfa.cwl)0
-rw-r--r--workflows/pangenome-generate/pangenome-generate_abpoa.cwl120
-rw-r--r--workflows/pangenome-generate/pangenome-generate_spoa.cwl2
5 files changed, 148 insertions, 2 deletions
diff --git a/scripts/create_sra_metadata/create_sra_metadata.py b/scripts/create_sra_metadata/create_sra_metadata.py
index eebd9aa..35f61a5 100644
--- a/scripts/create_sra_metadata/create_sra_metadata.py
+++ b/scripts/create_sra_metadata/create_sra_metadata.py
@@ -232,7 +232,7 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET):
taxon_id = SAMPLE.find('SAMPLE_NAME').find('TAXON_ID').text
info_for_yaml_dict['virus']['virus_species'] = "http://purl.obolibrary.org/obo/NCBITaxon_" + taxon_id
- # This script download and prepare data and metadata for samples that will be mapepd againg a referenceT
+ # This script download and prepare data and metadata for samples that will be mapped against a referenceT
info_for_yaml_dict['technology']['assembly_method'] = 'http://purl.obolibrary.org/obo/GENEPIO_0002028'
EXPERIMENT = EXPERIMENT_PACKAGE.find('EXPERIMENT')
diff --git a/workflows/pangenome-generate/abpoa.cwl b/workflows/pangenome-generate/abpoa.cwl
new file mode 100644
index 0000000..fa9f157
--- /dev/null
+++ b/workflows/pangenome-generate/abpoa.cwl
@@ -0,0 +1,26 @@
+cwlVersion: v1.1
+class: CommandLineTool
+inputs:
+ readsFA: File
+ script:
+ type: File
+ default: {class: File, location: relabel-seqs.py}
+outputs:
+ abpoaGFA:
+ type: stdout
+requirements:
+ InlineJavascriptRequirement: {}
+hints:
+ DockerRequirement:
+ dockerPull: "quay.io/biocontainers/abpoa:1.0.5--hed695b0_0"
+ ResourceRequirement:
+ coresMin: 1
+ ramMin: $(15 * 1024)
+ outdirMin: $(Math.ceil(inputs.readsFA.size/(1024*1024*1024) + 20))
+baseCommand: abpoa
+stdout: $(inputs.readsFA.nameroot).O0.gfa
+arguments: [
+ $(inputs.readsFA),
+ -r 3,
+ -O, '0'
+]
diff --git a/workflows/pangenome-generate/odgi-build-from-spoa-gfa.cwl b/workflows/pangenome-generate/odgi-build-from-xpoa-gfa.cwl
index eee4031..eee4031 100644
--- a/workflows/pangenome-generate/odgi-build-from-spoa-gfa.cwl
+++ b/workflows/pangenome-generate/odgi-build-from-xpoa-gfa.cwl
diff --git a/workflows/pangenome-generate/pangenome-generate_abpoa.cwl b/workflows/pangenome-generate/pangenome-generate_abpoa.cwl
new file mode 100644
index 0000000..8f98dc6
--- /dev/null
+++ b/workflows/pangenome-generate/pangenome-generate_abpoa.cwl
@@ -0,0 +1,120 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.1
+class: Workflow
+requirements:
+ ScatterFeatureRequirement: {}
+ StepInputExpressionRequirement: {}
+inputs:
+ seqs: File
+ metadata: File
+ bin_widths:
+ type: int[]
+ default: [ 1, 4, 16, 64, 256, 1000, 4000, 16000]
+ doc: width of each bin in basepairs along the graph vector
+ cells_per_file:
+ type: int
+ default: 100
+ doc: Cells per file on component_segmentation
+ reversed_sort:
+ type: string
+ default: "true"
+outputs:
+ odgiGraph:
+ type: File
+ outputSource: buildGraph/odgiGraph
+ odgiPNG:
+ type: File
+ outputSource: vizGraph/graph_image
+ abpoaGFA:
+ type: File
+ outputSource: induceGraph/abpoaGFA
+# odgiRDF:
+# type: File
+# outputSource: odgi2rdf/rdf
+ readsMergeDedupSortedByQualAndLen:
+ type: File
+ outputSource: dedup_and_sort_by_quality_and_len/sortedReadsFA
+ mergedMetadata:
+ type: File
+ outputSource: dups2metadata/merged
+# indexed_paths:
+# type: File
+# outputSource: index_paths/indexed_paths
+# colinear_components:
+# type: Directory
+# outputSource: segment_components/colinear_components
+steps:
+ dedup_and_sort_by_quality_and_len:
+ in: {readsFA: seqs, reversed_sorting: reversed_sort}
+ out: [sortedReadsFA, dups]
+ run: sort_fasta_by_quality_and_len.cwl
+ induceGraph:
+ in:
+ readsFA: dedup_and_sort_by_quality_and_len/sortedReadsFA
+ out: [abpoaGFA]
+ run: abpoa.cwl
+ buildGraph:
+ in: {inputGFA: induceGraph/abpoaGFA}
+ out: [odgiGraph]
+ run: odgi-build-from-xpoa-gfa.cwl
+ vizGraph:
+ in:
+ sparse_graph_index: buildGraph/odgiGraph
+ width:
+ default: 50000
+ height:
+ default: 500
+ path_per_row:
+ default: true
+ path_height:
+ default: 4
+ out: [graph_image]
+ requirements:
+ ResourceRequirement:
+ ramMin: $(15 * 1024)
+ outdirMin: 10
+ run: ../tools/odgi/odgi_viz.cwl
+ # odgi2rdf:
+ # in: {odgi: buildGraph/odgiGraph}
+ # out: [rdf]
+ # run: odgi_to_rdf.cwl
+ dups2metadata:
+ in:
+ metadata: metadata
+ dups: dedup_and_sort_by_quality_and_len/dups
+ out: [merged]
+ run: dups2metadata.cwl
+ # bin_paths:
+ # requirements:
+ # ResourceRequirement:
+ # ramMin: 3000
+ # outdirMin: 10
+ # run: ../tools/odgi/odgi_bin.cwl
+ # in:
+ # sparse_graph_index: buildGraph/odgiGraph
+ # bin_width: bin_widths
+ # scatter: bin_width
+ # out: [ bins, pangenome_sequence ]
+ # index_paths:
+ # label: Create path index
+ # requirements:
+ # ResourceRequirement:
+ # ramMin: 3000
+ # outdirMin: 10
+ # run: ../tools/odgi/odgi_pathindex.cwl
+ # in:
+ # sparse_graph_index: buildGraph/odgiGraph
+ # out: [ indexed_paths ]
+ # segment_components:
+ # label: Run component segmentation
+ # run: ../tools/graph-genome-segmentation/component_segmentation.cwl
+ # in:
+ # bins: bin_paths/bins
+ # cells_per_file: cells_per_file
+ # pangenome_sequence:
+ # source: bin_paths/pangenome_sequence
+ # valueFrom: $(self[0])
+ # # the bin_paths step is scattered over the bin_width array, but always using the same sparse_graph_index
+ # # the pangenome_sequence that is extracted is exactly the same for the same sparse_graph_index
+ # # regardless of bin_width, so we take the first pangenome_sequence as input for this step
+ # out: [ colinear_components ]
diff --git a/workflows/pangenome-generate/pangenome-generate_spoa.cwl b/workflows/pangenome-generate/pangenome-generate_spoa.cwl
index 4e7302d..fa16809 100644
--- a/workflows/pangenome-generate/pangenome-generate_spoa.cwl
+++ b/workflows/pangenome-generate/pangenome-generate_spoa.cwl
@@ -56,7 +56,7 @@ steps:
buildGraph:
in: {inputGFA: induceGraph/spoaGFA}
out: [odgiGraph]
- run: odgi-build-from-spoa-gfa.cwl
+ run: odgi-build-from-xpoa-gfa.cwl
vizGraph:
in:
sparse_graph_index: buildGraph/odgiGraph