diff options
| author | AndreaGuarracino | 2020-07-06 15:24:06 +0200 |
|---|---|---|
| committer | AndreaGuarracino | 2020-07-06 15:24:06 +0200 |
| commit | 4e2ac9bdef97175f5d762c6e7f065a83512a3c40 (patch) | |
| tree | e8b609c0e089bc9d871a5d78211bccb539a21e91 /scripts | |
| parent | c8b12b4e2b7e2e51315fe738f8bb4e37cb78ae55 (diff) | |
| download | bh20-seq-resource-4e2ac9bdef97175f5d762c6e7f065a83512a3c40.tar.gz bh20-seq-resource-4e2ac9bdef97175f5d762c6e7f065a83512a3c40.tar.lz bh20-seq-resource-4e2ac9bdef97175f5d762c6e7f065a83512a3c40.zip | |
renamed sra script; added seq technology in its additional information field if the term …
Diffstat (limited to 'scripts')
| -rw-r--r-- | scripts/create_sra_metadata/SraExperimentPackage.2020.07.05.xml.gz (renamed from scripts/download_sra_data/SraExperimentPackage.2020.07.05.xml.gz) | bin | 6502056 -> 6502056 bytes | |||
| -rw-r--r-- | scripts/create_sra_metadata/create_sra_metadata.py (renamed from scripts/download_sra_data/download_sra_data.py) | 6 |
2 files changed, 5 insertions, 1 deletions
diff --git a/scripts/download_sra_data/SraExperimentPackage.2020.07.05.xml.gz b/scripts/create_sra_metadata/SraExperimentPackage.2020.07.05.xml.gz Binary files differindex 88acb18..88acb18 100644 --- a/scripts/download_sra_data/SraExperimentPackage.2020.07.05.xml.gz +++ b/scripts/create_sra_metadata/SraExperimentPackage.2020.07.05.xml.gz diff --git a/scripts/download_sra_data/download_sra_data.py b/scripts/create_sra_metadata/create_sra_metadata.py index e36afb6..470980e 100644 --- a/scripts/download_sra_data/download_sra_data.py +++ b/scripts/create_sra_metadata/create_sra_metadata.py @@ -92,6 +92,9 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): VALUE_text = VALUE.text if TAG_text in ['host', 'host scientific name']: + if VALUE_text.lower() in ['homo sapien', 'homosapiens']: + VALUE_text = 'Homo sapiens' + if VALUE_text in term_to_uri_dict: info_for_yaml_dict['host']['host_species'] = term_to_uri_dict[VALUE_text] else: @@ -105,7 +108,7 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): if VALUE_text.lower() not in ['not applicable', 'missing', 'na', 'unknown', 'not provided']: value_to_insert = VALUE_text - if value_to_insert.lower() in ['homo sapien']: + if value_to_insert.lower() in ['homo sapien', 'homosapiens']: value_to_insert = 'Homo sapiens' if value_to_insert in term_to_uri_dict: @@ -194,6 +197,7 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): if INSTRUMENT_MODEL in term_to_uri_dict: info_for_yaml_dict['technology']['sample_sequencing_technology'] = [term_to_uri_dict[INSTRUMENT_MODEL]] else: + info_for_yaml_dict['technology']['additional_technology_information'] = INSTRUMENT_MODEL missing_value_list.append('\t'.join([accession, 'sample_sequencing_technology', INSTRUMENT_MODEL])) #else: # print(accession, 'Missing INSTRUMENT_MODEL', info_for_yaml_dict) |