diff options
Diffstat (limited to 'scripts')
| -rw-r--r-- | scripts/create_sra_metadata/SraExperimentPackage.2020.07.05.xml.gz | bin | 0 -> 6502056 bytes | |||
| -rw-r--r-- | scripts/create_sra_metadata/create_sra_metadata.py (renamed from scripts/download_sra_data/download_sra_data.py) | 52 | ||||
| -rw-r--r-- | scripts/dict_ontology_standardization/ncbi_countries.csv | 37 | ||||
| -rw-r--r-- | scripts/dict_ontology_standardization/ncbi_host_species.csv | 1 | ||||
| -rw-r--r-- | scripts/dict_ontology_standardization/ncbi_sequencing_technology.csv | 23 | ||||
| -rw-r--r-- | scripts/docker/Dockerfile | 4 | ||||
| -rwxr-xr-x | scripts/download_genbank_data/from_genbank_to_fasta_and_yaml.py | 125 | ||||
| -rw-r--r-- | scripts/download_sra_data/SraExperimentPackage.2020.06.08.xml.gz | bin | 3227724 -> 0 bytes | |||
| -rw-r--r-- | scripts/fetch_from_genbank.cwl | 49 | ||||
| -rw-r--r-- | scripts/import.cwl | 2 | ||||
| -rw-r--r-- | scripts/import_from_genbank.cwl | 27 | ||||
| -rw-r--r-- | scripts/import_to_arvados.py | 2 | ||||
| -rw-r--r-- | scripts/split_into_arrays.cwl | 30 | ||||
| -rw-r--r-- | scripts/upload.cwl | 13 |
14 files changed, 284 insertions, 81 deletions
diff --git a/scripts/create_sra_metadata/SraExperimentPackage.2020.07.05.xml.gz b/scripts/create_sra_metadata/SraExperimentPackage.2020.07.05.xml.gz Binary files differnew file mode 100644 index 0000000..88acb18 --- /dev/null +++ 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 9145a43..ef0d119 100644 --- a/scripts/download_sra_data/download_sra_data.py +++ b/scripts/create_sra_metadata/create_sra_metadata.py @@ -8,9 +8,11 @@ import gzip dir_yaml = 'yaml' -date = '2020.06.08' +date = '2020.07.05' -# Query on SRA: 'txid2697049[Organism]' (https://www.ncbi.nlm.nih.gov/sra/?term=txid2697049%5BOrganism%5D) -> Send to -> File -> Full XML -> Create File +# Query on SRA: 'txid2697049[Organism]' (https://www.ncbi.nlm.nih.gov/sra/?term=txid2697049%5BOrganism%5D) +# Query on SRA: 'txid2697049[Organism:noexp] NOT 0[Mbases ' (https://www.ncbi.nlm.nih.gov/sra/?term=txid2697049%5BOrganism:noexp%5D%20NOT%200[Mbases) +# -> Send to -> File -> Full XML -> Create File path_sra_metadata_xml = 'SraExperimentPackage.{}.xml.gz'.format(date) dir_dict_ontology_standardization = '../dict_ontology_standardization/' @@ -70,14 +72,14 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): accession = RUN.attrib['accession'] run_accession_set.add(accession) #print(accession) - + info_for_yaml_dict['sample']['sample_id'] = accession - SRAFiles = RUN.find('SRAFiles') - if SRAFiles is not None: - url = SRAFiles.find('SRAFile').attrib['url'] - if 'sra-download.ncbi.nlm.nih.gov' in url: - run_accession_to_downloadble_file_url_dict[accession] = url + #SRAFiles = RUN.find('SRAFiles') + #if SRAFiles is not None: + # url = SRAFiles.find('SRAFile').attrib['url'] + # if 'sra-download.ncbi.nlm.nih.gov' in url: + # run_accession_to_downloadble_file_url_dict[accession] = url SAMPLE = EXPERIMENT_PACKAGE.find('SAMPLE') @@ -90,6 +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: @@ -100,11 +105,19 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): elif VALUE_text.strip("'") not in ['missing', 'not collected', 'not provided']: missing_value_list.append('\t'.join([accession, 'host_health_status', VALUE_text])) elif TAG_text in ['strain', 'isolate']: - if VALUE_text.lower() not in ['not applicable', 'missing', 'na', 'unknown']: - if 'virus_strain' not in info_for_yaml_dict: - info_for_yaml_dict['virus']['virus_strain'] = VALUE_text + 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', 'homosapiens']: + value_to_insert = 'Homo sapiens' + + if value_to_insert in term_to_uri_dict: + value_to_insert = term_to_uri_dict[value_to_insert] + + if 'virus_strain' not in info_for_yaml_dict: + info_for_yaml_dict['virus']['virus_strain'] = value_to_insert else: - info_for_yaml_dict['virus']['virus_strain'] += '; ' + VALUE_text + info_for_yaml_dict['virus']['virus_strain'] += '; ' + value_to_insert elif TAG_text in ['isolation_source', 'isolation source host-associated']: if VALUE_text in term_to_uri_dict: info_for_yaml_dict['sample']['specimen_source'] = [term_to_uri_dict[VALUE_text]] @@ -179,17 +192,18 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): EXPERIMENT = EXPERIMENT_PACKAGE.find('EXPERIMENT') INSTRUMENT_MODEL = [x.text for x in EXPERIMENT.find('PLATFORM').iter('INSTRUMENT_MODEL')][0] + if INSTRUMENT_MODEL.lower() != 'unspecified': if INSTRUMENT_MODEL in term_to_uri_dict: info_for_yaml_dict['technology']['sample_sequencing_technology'] = [term_to_uri_dict[INSTRUMENT_MODEL]] else: missing_value_list.append('\t'.join([accession, 'sample_sequencing_technology', INSTRUMENT_MODEL])) - + #else: + # print(accession, 'Missing INSTRUMENT_MODEL', info_for_yaml_dict) LIBRARY_DESCRIPTOR = EXPERIMENT.find('DESIGN').find('LIBRARY_DESCRIPTOR') if LIBRARY_DESCRIPTOR.text not in ['OTHER']: info_for_yaml_dict['technology']['additional_technology_information'] = 'LIBRARY_STRATEGY: {};'.format(LIBRARY_DESCRIPTOR.find('LIBRARY_STRATEGY').text) - - + SUBMISSION = EXPERIMENT_PACKAGE.find('SUBMISSION') info_for_yaml_dict['submitter']['submitter_sample_id'] = SUBMISSION.attrib['accession'] @@ -197,7 +211,7 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): info_for_yaml_dict['submitter']['originating_lab'] = SUBMISSION.attrib['lab_name'] STUDY = EXPERIMENT_PACKAGE.find('STUDY') - info_for_yaml_dict['submitter']['publication'] = SUBMISSION.attrib['lab_name'] + info_for_yaml_dict['submitter']['publication'] = STUDY.attrib['alias'] Organization = EXPERIMENT_PACKAGE.find('Organization') @@ -222,6 +236,10 @@ for i, EXPERIMENT_PACKAGE in enumerate(EXPERIMENT_PACKAGE_SET): info_for_yaml_dict['sample']['collection_date'] = '1970-01-01' info_for_yaml_dict['sample']['additional_collection_information'] = "The real 'collection_date' is missing" + if 'sample_sequencing_technology' not in info_for_yaml_dict['technology']: + print(accession, ' - technology not found') + continue + with open(os.path.join(dir_yaml, '{}.yaml'.format(accession)), 'w') as fw: json.dump(info_for_yaml_dict, fw, indent=2) @@ -229,4 +247,4 @@ if len(missing_value_list) > 0: path_missing_terms_tsv = 'missing_terms.tsv' print('Written missing terms in {}'.format(path_missing_terms_tsv)) with open(path_missing_terms_tsv, 'w') as fw: - fw.write('\n'.join(missing_value_list))
\ No newline at end of file + fw.write('\n'.join(missing_value_list)) diff --git a/scripts/dict_ontology_standardization/ncbi_countries.csv b/scripts/dict_ontology_standardization/ncbi_countries.csv index 204f7f2..4bea3ec 100644 --- a/scripts/dict_ontology_standardization/ncbi_countries.csv +++ b/scripts/dict_ontology_standardization/ncbi_countries.csv @@ -284,6 +284,7 @@ USA:CA,http://www.wikidata.org/entity/Q99 USA: California,http://www.wikidata.org/entity/Q99 USA:California,http://www.wikidata.org/entity/Q99 "USA: CA, San Diego County",http://www.wikidata.org/entity/Q108143 +"USA: California, Monterey County",http://www.wikidata.org/entity/Q108072 USA: CO,http://www.wikidata.org/entity/Q1261 USA: CT,http://www.wikidata.org/entity/Q779 USA: Connecticut,http://www.wikidata.org/entity/Q779 @@ -301,8 +302,9 @@ USA: IN,http://www.wikidata.org/entity/Q1415 USA: KS,http://www.wikidata.org/entity/Q1558 USA: KY,http://www.wikidata.org/entity/Q1603 USA: LA,http://www.wikidata.org/entity/Q1588 -USA:Los Angeles,http://www.wikidata.org/entity/Q65 -"USA: New Orleans, LA",http://www.wikidata.org/entity/Q34404 +"USA: SLIDELL, LA, LA",https://www.wikidata.org/wiki/Q988156 +"USA: Slidell, LA, LA",https://www.wikidata.org/wiki/Q988156 +"USA: New Orleans, LA",https://www.wikidata.org/wiki/Q34404 USA: MA,http://www.wikidata.org/entity/Q771 USA: Massachusetts,http://www.wikidata.org/entity/Q771 USA: MD,http://www.wikidata.org/entity/Q1391 @@ -336,6 +338,33 @@ USA: SC,http://www.wikidata.org/entity/Q1456 USA: South Carolina,http://www.wikidata.org/entity/Q1456 USA: SD,http://www.wikidata.org/entity/Q1211 "USA: Snohomish County, WA",http://www.wikidata.org/entity/Q110403 +"USA: Washington,Snohomish County",http://www.wikidata.org/entity/Q110403 +"USA: Washington, Snohomish County",http://www.wikidata.org/entity/Q110403 +"USA: Washington,Skagit County",http://www.wikidata.org/entity/Q113892 +"USA: Washington, Skagit County",http://www.wikidata.org/entity/Q113892 +"USA: Washington,Pierce County",http://www.wikidata.org/entity/Q156459 +"USA: Washington, Pierce County",http://www.wikidata.org/entity/Q156459 +"USA: Washington,Mason County",http://www.wikidata.org/entity/Q111904 +"USA: Washington, Mason County",http://www.wikidata.org/entity/Q111904 +"USA: Washington,Kittitas County",http://www.wikidata.org/entity/Q111540 +"USA: Washington,King County",http://www.wikidata.org/entity/Q108861 +"USA: Washington, King County",http://www.wikidata.org/entity/Q108861 +"USA: King County,WA",http://www.wikidata.org/entity/Q108861 +"USA: Washington,Jefferson County",http://www.wikidata.org/entity/Q384737 +"USA: Washington,Grant County",http://www.wikidata.org/entity/Q281681 +"USA: Washington, Grant County",http://www.wikidata.org/entity/Q281681 +"USA: Washington,Franklin County",http://www.wikidata.org/entity/Q118716 +"USA: Washington, Franklin County",http://www.wikidata.org/entity/Q118716 +"USA: Washington,Clark County",http://www.wikidata.org/entity/Q156287 +"USA: Washington,Benton County",http://www.wikidata.org/entity/Q156216 +"USA: Washington, Benton County",http://www.wikidata.org/entity/Q156216 +"USA: Washington,Asotin County",http://www.wikidata.org/entity/Q156295 +"USA: Washington, Asotin County",http://www.wikidata.org/entity/Q156295 +"USA: Washington,Adams County",http://www.wikidata.org/entity/Q156273 +"USA: Washington, Adams County",http://www.wikidata.org/entity/Q156273 +"USA: Washington, Spokane County",http://www.wikidata.org/entity/Q485276 +"USA: Washington, Douglas County",http://www.wikidata.org/entity/Q156220 +"USA: Washington, Cowlitz County",http://www.wikidata.org/entity/Q156276 USA: TN,http://www.wikidata.org/entity/Q1509 USA: TX,http://www.wikidata.org/entity/Q1439 USA: UT,http://www.wikidata.org/entity/Q829 @@ -347,6 +376,10 @@ USA: WA,http://www.wikidata.org/entity/Q1223 USA: Washington,http://www.wikidata.org/entity/Q1223 USA: WI,http://www.wikidata.org/entity/Q1537 USA: Wisconsin,http://www.wikidata.org/entity/Q1537 +"USA: Washington,Yakima County",http://www.wikidata.org/entity/Q156629 +"USA: Washington, Yakima County",http://www.wikidata.org/entity/Q156629 +"USA: Washington,Whatcom County",http://www.wikidata.org/entity/Q156623 +"USA: Dane County, Wisconsin",http://www.wikidata.org/entity/Q502200 USA: WV,http://www.wikidata.org/entity/Q1371 USA: WY,http://www.wikidata.org/entity/Q1214 Uzbekistan,http://www.wikidata.org/entity/Q265 diff --git a/scripts/dict_ontology_standardization/ncbi_host_species.csv b/scripts/dict_ontology_standardization/ncbi_host_species.csv index bc6ac04..40572a3 100644 --- a/scripts/dict_ontology_standardization/ncbi_host_species.csv +++ b/scripts/dict_ontology_standardization/ncbi_host_species.csv @@ -5,5 +5,6 @@ sapiens,http://purl.obolibrary.org/obo/NCBITaxon_9606 Mustela lutreola,http://purl.obolibrary.org/obo/NCBITaxon_9666 Manis javanica,http://purl.obolibrary.org/obo/NCBITaxon_9974 Felis catus,http://purl.obolibrary.org/obo/NCBITaxon_9685 +Felis catus; Domestic Shorthair,http://purl.obolibrary.org/obo/NCBITaxon_9685 Panthera tigris jacksoni,http://purl.obolibrary.org/obo/NCBITaxon_419130 Canis lupus familiaris,http://purl.obolibrary.org/obo/NCBITaxon_9615 diff --git a/scripts/dict_ontology_standardization/ncbi_sequencing_technology.csv b/scripts/dict_ontology_standardization/ncbi_sequencing_technology.csv index 964cbf3..59c4800 100644 --- a/scripts/dict_ontology_standardization/ncbi_sequencing_technology.csv +++ b/scripts/dict_ontology_standardization/ncbi_sequencing_technology.csv @@ -13,12 +13,14 @@ Illumina NextSeq 550,http://www.ebi.ac.uk/efo/EFO_0008566 NextSeq550,http://www.ebi.ac.uk/efo/EFO_0008566 NextSeq 550,http://www.ebi.ac.uk/efo/EFO_0008566 Illumina MiniSeq,http://www.ebi.ac.uk/efo/EFO_0008636 +Illumina NovaSeq,http://www.ebi.ac.uk/efo/EFO_0008637 Illumina NovaSeq 6000,http://www.ebi.ac.uk/efo/EFO_0008637 Nanopore MinION,http://www.ebi.ac.uk/efo/EFO_0008632 Oxford Nanopore MinION,http://www.ebi.ac.uk/efo/EFO_0008632 ONT (Oxford Nanopore Technologies),http://purl.obolibrary.org/obo/NCIT_C146818 Oxford Nanopore Technology,http://purl.obolibrary.org/obo/NCIT_C146818 Oxford Nanopore technologies MinION,http://www.ebi.ac.uk/efo/EFO_0008632 +Oxford Nanopore Sequencing,http://purl.obolibrary.org/obo/NCIT_C146818 MinION Oxford Nanopore,http://www.ebi.ac.uk/efo/EFO_0008632 MinION,http://www.ebi.ac.uk/efo/EFO_0008632 Nanopore,http://purl.obolibrary.org/obo/NCIT_C146818 @@ -33,3 +35,24 @@ ThermoFisher S5Plus,http://purl.obolibrary.org/obo/NCIT_C125894 Sanger dideoxy sequencing,http://purl.obolibrary.org/obo/NCIT_C19641 MGISEQ 2000,http://virtual-bh/MGISEQ2000 MGISEQ2000,http://virtual-bh/MGISEQ2000 +Illumina HiSeq X,http://www.ebi.ac.uk/efo/EFO_0008567 +ONT GridION X5,http://www.ebi.ac.uk/efo/EFO_0008633 +ONT PremethION,http://www.ebi.ac.uk/efo/EFO_0008634 +PacBio RS II,http://www.ebi.ac.uk/efo/EFO_0008631 +PacBio Sequel System,http://www.ebi.ac.uk/efo/EFO_0008630 +Illumina Genome Analyzer,http://www.ebi.ac.uk/efo/EFO_0004200 +Illumina Genome Analyzer II,http://www.ebi.ac.uk/efo/EFO_0004201 +Illumina Genome Analyzer IIx,http://www.ebi.ac.uk/efo/EFO_0004202 +454 GS 20 sequencer,http://www.ebi.ac.uk/efo/EFO_0004206 +454 GS FLX Titanium sequencer,http://www.ebi.ac.uk/efo/EFO_0004433 +454 GS FLX sequencer,http://www.ebi.ac.uk/efo/EFO_0004432 +454 GS Junior sequencer,http://www.ebi.ac.uk/efo/EFO_0004434 +454 GS sequencer,http://www.ebi.ac.uk/efo/EFO_0004431 +AB SOLiD 4 System,http://www.ebi.ac.uk/efo/EFO_0004438 +AB SOLiD 4hq System,http://www.ebi.ac.uk/efo/EFO_0004441 +AB SOLiD 5500,http://www.ebi.ac.uk/efo/EFO_0004440 +AB SOLiD 5500xl,http://www.ebi.ac.uk/efo/EFO_0004436 +AB SOLiD PI System,http://www.ebi.ac.uk/efo/EFO_0004437 +AB SOLiD System,http://www.ebi.ac.uk/efo/EFO_0004435 +AB SOLiD System 2.0,http://www.ebi.ac.uk/efo/EFO_0004442 +AB SOLiD System 3.0,http://www.ebi.ac.uk/efo/EFO_0004439 diff --git a/scripts/docker/Dockerfile b/scripts/docker/Dockerfile index 9fb33d5..02829d4 100644 --- a/scripts/docker/Dockerfile +++ b/scripts/docker/Dockerfile @@ -3,8 +3,8 @@ FROM debian:10 RUN apt-get update && \ apt-get -yq --no-install-recommends -o Acquire::Retries=6 install \ python3 python3-pip python3-setuptools python3-dev python-pycurl \ - clustalw python3-biopython libcurl4-openssl-dev build-essential \ + minimap2 python3-biopython libcurl4-openssl-dev build-essential \ libssl-dev libmagic-dev python3-magic && \ apt-get clean -RUN pip3 install bh20-seq-uploader +RUN pip3 install bh20-seq-uploader py-dateutil 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 d76f56b..cb94787 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 @@ -4,6 +4,8 @@ import argparse parser = argparse.ArgumentParser() parser.add_argument('--skip-request', action='store_true', help='skip metadata and sequence request', required=False) parser.add_argument('--only-missing-id', action='store_true', help='download only missing id', required=False) +parser.add_argument('--dict-ontology', type=str, help='where is the ontology', + default='../dict_ontology_standardization/',required=False) args = parser.parse_args() from Bio import Entrez @@ -22,7 +24,7 @@ num_ids_for_request = 100 dir_metadata = 'metadata_from_nuccore' dir_fasta_and_yaml = 'fasta_and_yaml' -dir_dict_ontology_standardization = '../dict_ontology_standardization/' +dir_dict_ontology_standardization = args.dict_ontology today_date = date.today().strftime("%Y.%m.%d") path_ncbi_virus_accession = 'sequences.{}.acc'.format(today_date) @@ -126,7 +128,7 @@ for path_dict_xxx_csv in [os.path.join(dir_dict_ontology_standardization, name_x if term in term_to_uri_dict: print('Warning: in the dictionaries there are more entries for the same term ({}).'.format(term)) continue - + term_to_uri_dict[term] = uri if not os.path.exists(dir_fasta_and_yaml): @@ -171,7 +173,9 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml) # submitter info GBSeq_references = GBSeq.find('GBSeq_references') if GBSeq_references is not None: - info_for_yaml_dict['submitter']['authors'] = ["{}".format(x.text) for x in GBSeq_references.iter('GBAuthor')] + author_list = ["{}".format(x.text) for x in GBSeq_references.iter('GBAuthor')] + if len(author_list) > 0: + info_for_yaml_dict['submitter']['authors'] = author_list GBReference = GBSeq_references.find('GBReference') if GBReference is not None: @@ -220,7 +224,8 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml) new_seq_tec_list.append(seq_tec) - info_for_yaml_dict['technology']['sample_sequencing_technology'] = [x for x in new_seq_tec_list] + if len(new_seq_tec_list) > 0: + info_for_yaml_dict['technology']['sample_sequencing_technology'] = [x for x in new_seq_tec_list] else: info_for_yaml_dict['technology'][field_in_yaml] = tech_info_to_parse @@ -238,58 +243,62 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml) GBQualifier_name_text = GBQualifier.find('GBQualifier_name').text if GBQualifier_name_text == 'host': - GBQualifier_value_text_list = GBQualifier_value_text.split('; ') - - if GBQualifier_value_text_list[0] in term_to_uri_dict: - info_for_yaml_dict['host']['host_species'] = term_to_uri_dict[GBQualifier_value_text_list[0]] - elif GBQualifier_value_text_list[0] and ('MT215193' in accession_version or 'MT270814' in accession_version): - # Information checked manually from NCBI Virus - info_for_yaml_dict['host']['host_species'] = term_to_uri_dict['Canis lupus familiaris'] + if GBQualifier_value_text in term_to_uri_dict: + # Cases like 'Felis catus; Domestic Shorthair' + info_for_yaml_dict['host']['host_species'] = term_to_uri_dict[GBQualifier_value_text] else: - missing_value_list.append('\t'.join([accession_version, 'host_species', GBQualifier_value_text_list[0]])) - - # Possible cases: - # - Homo sapiens --> ['Homo sapiens'] - # - Homo sapiens; female --> ['Homo sapiens', 'female'] - # - Homo sapiens; female 63 --> ['Homo sapiens', 'female 63'] - # - Homo sapiens; female; age 40 --> ['Homo sapiens', 'female', 'age 40'] - # - Homo sapiens; gender: F; age: 61 --> ['Homo sapiens', 'gender: F', 'age: 61'] - # - Homo sapiens; gender: M; age: 68 --> ['Homo sapiens', 'gender: M', 'age: 68'] - # - Homo sapiens; hospitalized patient --> ['Homo sapiens', 'hospitalized patient'] - # - Homo sapiens; male --> ['Homo sapiens', 'male'] - # - Homo sapiens; male; 63 --> ['Homo sapiens', 'male', '63'] - # - Homo sapiens; male; age 29 --> ['Homo sapiens', 'male', 'age 29'] - # - Homo sapiens; symptomatic --> ['Homo sapiens', 'symptomatic'] - if len(GBQualifier_value_text_list) > 1: - host_sex = '' - if 'female' in GBQualifier_value_text_list[1]: - host_sex = 'female' - elif 'male' in GBQualifier_value_text_list[1]: - host_sex = 'male' - elif 'gender' in GBQualifier_value_text_list[1]: - host_sex_one_lecter = GBQualifier_value_text_list[1].split(':')[-1].strip() - if host_sex_one_lecter in ['F', 'M']: - host_sex = 'female' if host_sex_one_lecter == 'F' else 'male' - - if host_sex in ['male', 'female']: - info_for_yaml_dict['host']['host_sex'] = "http://purl.obolibrary.org/obo/PATO_0000384" if host_sex == 'male' else "http://purl.obolibrary.org/obo/PATO_0000383" - elif GBQualifier_value_text_list[1] in term_to_uri_dict: - info_for_yaml_dict['host']['host_health_status'] = term_to_uri_dict[GBQualifier_value_text_list[1]] + GBQualifier_value_text_list = GBQualifier_value_text.split('; ') + + if GBQualifier_value_text_list[0] in term_to_uri_dict: + info_for_yaml_dict['host']['host_species'] = term_to_uri_dict[GBQualifier_value_text_list[0]] + elif GBQualifier_value_text_list[0] and ('MT215193' in accession_version or 'MT270814' in accession_version): + # Information checked manually from NCBI Virus + info_for_yaml_dict['host']['host_species'] = term_to_uri_dict['Canis lupus familiaris'] else: - missing_value_list.append('\t'.join([accession_version, 'host_sex or host_health_status', GBQualifier_value_text_list[1]])) - - # Host age - host_age = -1 - if len(GBQualifier_value_text_list[1].split(' ')) > 1 and is_integer(GBQualifier_value_text_list[1].split(' ')[-1]): - host_age = int(GBQualifier_value_text_list[1].split(' ')[-1]) - elif len(GBQualifier_value_text_list) > 2 and is_integer(GBQualifier_value_text_list[2].split(' ')[-1]): - host_age = int(GBQualifier_value_text_list[2].split(' ')[-1]) - - if host_age > -1: - info_for_yaml_dict['host']['host_age'] = host_age - info_for_yaml_dict['host']['host_age_unit'] = 'http://purl.obolibrary.org/obo/UO_0000036' - elif len(GBQualifier_value_text_list) > 2: - missing_value_list.append('\t'.join([accession_version, 'host_age', GBQualifier_value_text_list[2]])) + missing_value_list.append('\t'.join([accession_version, 'host_species', GBQualifier_value_text_list[0]])) + + # Possible cases: + # - Homo sapiens --> ['Homo sapiens'] + # - Homo sapiens; female --> ['Homo sapiens', 'female'] + # - Homo sapiens; female 63 --> ['Homo sapiens', 'female 63'] + # - Homo sapiens; female; age 40 --> ['Homo sapiens', 'female', 'age 40'] + # - Homo sapiens; gender: F; age: 61 --> ['Homo sapiens', 'gender: F', 'age: 61'] + # - Homo sapiens; gender: M; age: 68 --> ['Homo sapiens', 'gender: M', 'age: 68'] + # - Homo sapiens; hospitalized patient --> ['Homo sapiens', 'hospitalized patient'] + # - Homo sapiens; male --> ['Homo sapiens', 'male'] + # - Homo sapiens; male; 63 --> ['Homo sapiens', 'male', '63'] + # - Homo sapiens; male; age 29 --> ['Homo sapiens', 'male', 'age 29'] + # - Homo sapiens; symptomatic --> ['Homo sapiens', 'symptomatic'] + if len(GBQualifier_value_text_list) > 1: + host_sex = '' + if 'female' in GBQualifier_value_text_list[1]: + host_sex = 'female' + elif 'male' in GBQualifier_value_text_list[1]: + host_sex = 'male' + elif 'gender' in GBQualifier_value_text_list[1]: + host_sex_one_lecter = GBQualifier_value_text_list[1].split(':')[-1].strip() + if host_sex_one_lecter in ['F', 'M']: + host_sex = 'female' if host_sex_one_lecter == 'F' else 'male' + + if host_sex in ['male', 'female']: + info_for_yaml_dict['host']['host_sex'] = "http://purl.obolibrary.org/obo/PATO_0000384" if host_sex == 'male' else "http://purl.obolibrary.org/obo/PATO_0000383" + elif GBQualifier_value_text_list[1] in term_to_uri_dict: + info_for_yaml_dict['host']['host_health_status'] = term_to_uri_dict[GBQualifier_value_text_list[1]] + else: + missing_value_list.append('\t'.join([accession_version, 'host_sex or host_health_status', GBQualifier_value_text_list[1]])) + + # Host age + host_age = -1 + if len(GBQualifier_value_text_list[1].split(' ')) > 1 and is_integer(GBQualifier_value_text_list[1].split(' ')[-1]): + host_age = int(GBQualifier_value_text_list[1].split(' ')[-1]) + elif len(GBQualifier_value_text_list) > 2 and is_integer(GBQualifier_value_text_list[2].split(' ')[-1]): + host_age = int(GBQualifier_value_text_list[2].split(' ')[-1]) + + if host_age > -1: + info_for_yaml_dict['host']['host_age'] = host_age + info_for_yaml_dict['host']['host_age_unit'] = 'http://purl.obolibrary.org/obo/UO_0000036' + elif len(GBQualifier_value_text_list) > 2: + missing_value_list.append('\t'.join([accession_version, 'host_age', GBQualifier_value_text_list[2]])) elif GBQualifier_name_text == 'collected_by': if any([x in GBQualifier_value_text.lower() for x in ['institute', 'hospital', 'city', 'center']]): info_for_yaml_dict['sample']['collecting_institution'] = GBQualifier_value_text @@ -362,9 +371,9 @@ for path_metadata_xxx_xml in [os.path.join(dir_metadata, name_metadata_xxx_xml) info_for_yaml_dict['virus']['virus_species'] = "http://purl.obolibrary.org/obo/NCBITaxon_"+GBQualifier_value_text.split('taxon:')[1] - # Remove technology key if empty! - if (info_for_yaml_dict['technology']=={}): - del info_for_yaml_dict['technology'] + if 'sample_sequencing_technology' not in info_for_yaml_dict['technology']: + print(accession_version, ' - technology not found') + continue with open(os.path.join(dir_fasta_and_yaml, '{}.fasta'.format(accession_version)), 'w') as fw: fw.write('>{}\n{}'.format(accession_version, GBSeq_sequence.text.upper())) @@ -391,5 +400,5 @@ if len(accession_with_errors_list) > 0: print('Written the accession with errors in {}'.format(path_accession_with_errors_tsv)) with open(path_accession_with_errors_tsv, 'w') as fw: fw.write('\n'.join(accession_with_errors_list)) - + print('Num. new sequences with length >= {} bp: {}'.format(min_len_to_count, num_seq_with_len_ge_X_bp)) diff --git a/scripts/download_sra_data/SraExperimentPackage.2020.06.08.xml.gz b/scripts/download_sra_data/SraExperimentPackage.2020.06.08.xml.gz Binary files differdeleted file mode 100644 index f9cd995..0000000 --- a/scripts/download_sra_data/SraExperimentPackage.2020.06.08.xml.gz +++ /dev/null diff --git a/scripts/fetch_from_genbank.cwl b/scripts/fetch_from_genbank.cwl new file mode 100644 index 0000000..45c8eec --- /dev/null +++ b/scripts/fetch_from_genbank.cwl @@ -0,0 +1,49 @@ +cwlVersion: v1.1 +class: CommandLineTool +inputs: + importScript: + type: File + default: + class: File + location: download_genbank_data/from_genbank_to_fasta_and_yaml.py + inputBinding: {position: 1} + dict: + type: Directory + inputBinding: + prefix: --dict-ontology + position: 2 + default: + class: Directory + location: dict_ontology_standardization + existing_metadata_from_nuccore: + type: Directory? + inputBinding: + valueFrom: "--skip-request" + position: 3 +outputs: + fasta_and_yaml: + type: Directory + outputBinding: + glob: fasta_and_yaml + metadata_from_nuccore: + type: Directory + outputBinding: + glob: metadata_from_nuccore + accessions: + type: File? + outputBinding: + glob: "*.acc" + missing_terms: + type: File + outputBinding: + glob: missing_terms.tsv +requirements: + InitialWorkDirRequirement: + listing: + - entry: $(inputs.existing_metadata_from_nuccore) + entryname: metadata_from_nuccore + DockerRequirement: + dockerPull: bh20-seq-uploader/import + NetworkAccess: + networkAccess: true +baseCommand: python3 diff --git a/scripts/import.cwl b/scripts/import.cwl index d84516b..4b4b8ca 100644 --- a/scripts/import.cwl +++ b/scripts/import.cwl @@ -12,7 +12,7 @@ inputs: type: File default: class: File - location: from_genbank_to_fasta_and_yaml.py + location: download_genbank_data/from_genbank_to_fasta_and_yaml.py inputBinding: {position: 2} dict: type: Directory diff --git a/scripts/import_from_genbank.cwl b/scripts/import_from_genbank.cwl new file mode 100644 index 0000000..dcf9acb --- /dev/null +++ b/scripts/import_from_genbank.cwl @@ -0,0 +1,27 @@ +cwlVersion: v1.1 +class: Workflow +inputs: + existing_metadata_from_nuccore: + type: Directory? +outputs: [] +requirements: + ScatterFeatureRequirement: {} +steps: + fetch_from_genbank: + in: + existing_metadata_from_nuccore: existing_metadata_from_nuccore + out: [fasta_and_yaml, metadata_from_nuccore, accessions] + run: fetch_from_genbank.cwl + split_into_arrays: + in: + dir: fetch_from_genbank/fasta_and_yaml + out: [fasta, metadata] + run: split_into_arrays.cwl + upload: + in: + fasta: split_into_arrays/fasta + metadata: split_into_arrays/metadata + out: [] + scatter: [fasta, metadata] + scatterMethod: dotproduct + run: upload.cwl diff --git a/scripts/import_to_arvados.py b/scripts/import_to_arvados.py index 78cd13d..aca72d6 100644 --- a/scripts/import_to_arvados.py +++ b/scripts/import_to_arvados.py @@ -11,4 +11,4 @@ os.chdir("fasta_and_yaml") fasta_files = glob.glob("*.fasta") for f in fasta_files: - subprocess.run(["bh20-seq-uploader", f, "%s.yaml" %f[:-6]]) + subprocess.run(["bh20-seq-uploader", "%s.yaml" %f[:-6], f]) diff --git a/scripts/split_into_arrays.cwl b/scripts/split_into_arrays.cwl new file mode 100644 index 0000000..102fe7d --- /dev/null +++ b/scripts/split_into_arrays.cwl @@ -0,0 +1,30 @@ +cwlVersion: v1.1 +class: ExpressionTool +requirements: + InlineJavascriptRequirement: {} +inputs: + dir: + type: Directory + loadListing: shallow_listing +outputs: + fasta: File[] + metadata: File[] +expression: | + ${ + var dir = inputs.dir; + var fasta = []; + var metadata = []; + dir.listing.sort(function(a, b) { return a.basename < b.basename; }); + for (var i = 0; i < dir.listing.length; i++) { + if (dir.listing[i].basename.substr(-6) == ".fasta") { + fasta.push(dir.listing[i]); + } + if (dir.listing[i].basename.substr(-5) == ".yaml") { + metadata.push(dir.listing[i]); + } + } + if (fasta.length != metadata.length) { + throw "They dont match"; + } + return {"fasta": fasta, "metadata": metadata}; + } diff --git a/scripts/upload.cwl b/scripts/upload.cwl new file mode 100644 index 0000000..0fed09a --- /dev/null +++ b/scripts/upload.cwl @@ -0,0 +1,13 @@ +cwlVersion: v1.1 +class: CommandLineTool +inputs: + fasta: File + metadata: File +outputs: [] +requirements: + DockerRequirement: + dockerPull: bh20-seq-uploader/import + NetworkAccess: + networkAccess: true +baseCommand: bh20-seq-uploader +arguments: [--skip-qc, $(inputs.metadata), $(inputs.fasta)] |