aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndreaGuarracino2020-11-12 18:50:13 +0100
committerAndreaGuarracino2020-11-12 18:50:13 +0100
commitdbd32a3042099d52d30028364ffdadcd0f60ede2 (patch)
tree3d482ffb952c14e34afc063298ab5dcde066b32f
parent87440554e57d5c5ed846e98a3b3ec428330e15e8 (diff)
downloadbh20-seq-resource-dbd32a3042099d52d30028364ffdadcd0f60ede2.tar.gz
bh20-seq-resource-dbd32a3042099d52d30028364ffdadcd0f60ede2.tar.lz
bh20-seq-resource-dbd32a3042099d52d30028364ffdadcd0f60ede2.zip
managed the assembly_method in the scripts, doc, and the example templates
-rw-r--r--doc/blog/using-covid-19-pubseq-part3.org1
-rw-r--r--example/esr_example.yaml1
-rw-r--r--example/uthsc_example.yaml1
-rw-r--r--scripts/create_sra_metadata/create_sra_metadata.py2
-rwxr-xr-xscripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py2
-rw-r--r--scripts/esr_samples/template.yaml1
-rw-r--r--scripts/uthsc_samples/template.yaml1
-rw-r--r--test/data/input/TN_UT2.yaml1
8 files changed, 10 insertions, 0 deletions
diff --git a/doc/blog/using-covid-19-pubseq-part3.org b/doc/blog/using-covid-19-pubseq-part3.org
index c98bf27..7336cf6 100644
--- a/doc/blog/using-covid-19-pubseq-part3.org
+++ b/doc/blog/using-covid-19-pubseq-part3.org
@@ -236,6 +236,7 @@ a more elaborate example (note most fields are optional) may look like
sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0009173,http://www.ebi.ac.uk/efo/EFO_0009173]
alignment_protocol: Protocol used for assembly
sequencing_coverage: [70.0, 100.0]
+ assembly_method: "http://purl.obolibrary.org/obo/GENEPIO_0001628"
additional_technology_information: Optional free text field for additional information
submitter:
diff --git a/example/esr_example.yaml b/example/esr_example.yaml
index b3e97d5..693aff3 100644
--- a/example/esr_example.yaml
+++ b/example/esr_example.yaml
@@ -25,6 +25,7 @@ virus:
technology:
sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0008632] // Nanopore MinION
alignment_protocol: https://github.com/ESR-NZ/NZ_SARS-CoV-2_genomics
+ assembly_method: "http://purl.obolibrary.org/obo/GENEPIO_0001628"
additional_technology_information: "Artic V3 workflow"
submitter:
diff --git a/example/uthsc_example.yaml b/example/uthsc_example.yaml
index 3bdbf6f..2384114 100644
--- a/example/uthsc_example.yaml
+++ b/example/uthsc_example.yaml
@@ -25,6 +25,7 @@ virus:
technology:
sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0008632] // Nanopore MinION
alignment_protocol: guppy
+ assembly_method: "http://purl.obolibrary.org/obo/GENEPIO_0001628"
additional_technology_information: Optional free text field for additional information
submitter:
diff --git a/scripts/create_sra_metadata/create_sra_metadata.py b/scripts/create_sra_metadata/create_sra_metadata.py
index 2aac0e5..554aea3 100644
--- a/scripts/create_sra_metadata/create_sra_metadata.py
+++ b/scripts/create_sra_metadata/create_sra_metadata.py
@@ -227,6 +227,8 @@ 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
+ info_for_yaml_dict['technology']['assembly_method'] = 'http://purl.obolibrary.org/obo/GENEPIO_0002028'
EXPERIMENT = EXPERIMENT_PACKAGE.find('EXPERIMENT')
INSTRUMENT_MODEL = [x.text for x in EXPERIMENT.find('PLATFORM').iter('INSTRUMENT_MODEL')][0]
diff --git a/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py b/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
index 87b348b..9a46474 100755
--- a/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
+++ b/scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py
@@ -179,6 +179,8 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml)
else:
info_for_yaml_dict['submitter']['additional_submitter_information'] = GBReference_journal.text
+ # This script download and prepare data and metadata for assemblies samples
+ info_for_yaml_dict['technology']['assembly_method'] = 'http://purl.obolibrary.org/obo/GENEPIO_0001628'
GBSeq_comment = GBSeq.find('GBSeq_comment')
if GBSeq_comment is not None and 'Assembly-Data' in GBSeq_comment.text:
diff --git a/scripts/esr_samples/template.yaml b/scripts/esr_samples/template.yaml
index 3ca1de3..3846122 100644
--- a/scripts/esr_samples/template.yaml
+++ b/scripts/esr_samples/template.yaml
@@ -15,6 +15,7 @@ virus:
technology:
sample_sequencing_technology: ["http://www.ebi.ac.uk/efo/EFO_0008632"]
alignment_protocol: "https://github.com/ESR-NZ/NZ_SARS-CoV-2_genomics"
+ assembly_method: "http://purl.obolibrary.org/obo/GENEPIO_0001628"
additional_technology_information: "Artic V3 workflow"
submitter:
diff --git a/scripts/uthsc_samples/template.yaml b/scripts/uthsc_samples/template.yaml
index c81bd28..dab8634 100644
--- a/scripts/uthsc_samples/template.yaml
+++ b/scripts/uthsc_samples/template.yaml
@@ -23,6 +23,7 @@ virus:
technology:
sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0008632]
alignment_protocol: https://bio.tools/BWA#!
+ assembly_method: "http://purl.obolibrary.org/obo/GENEPIO_0001628"
additional_technology_information: "Oxford Nanopore MiniIon RNA long reads"
submitter:
diff --git a/test/data/input/TN_UT2.yaml b/test/data/input/TN_UT2.yaml
index 236110d..f2f190b 100644
--- a/test/data/input/TN_UT2.yaml
+++ b/test/data/input/TN_UT2.yaml
@@ -23,6 +23,7 @@ virus:
technology:
sample_sequencing_technology: [http://www.ebi.ac.uk/efo/EFO_0008632]
alignment_protocol: https://bio.tools/BWA#!
+ assembly_method: "http://purl.obolibrary.org/obo/GENEPIO_0001628"
additional_technology_information: Oxford Nanopore MiniIon RNA long reads
submitter: