How to use the biothings.utils.dataload.dict_sweep function in biothings

To help you get started, we’ve selected a few biothings examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github biothings / myvariant.info / src / hub / dataload / sources / clinvar / clinvar_xml_parser.py View on Github external
}})
            yield _obj
    else:
        variant_id = cp.ReferenceClinVarAssertion.MeasureSet.ID
        for _measure in cp.ReferenceClinVarAssertion.MeasureSet.Measure:
            json_obj = parse_measure(_measure, hg19=hg19)
            if json_obj:
                json_obj['clinvar']['rcv'].update({'accession': rcv_accession,
                        'clinical_significance': clinical_significance,
                        'number_submitters': number_submitters,
                        'review_status': review_status,
                        'last_evaluated': str(last_evaluated),
                        'origin': origin,
                        'conditions': conditions})
                json_obj['clinvar'].update({'variant_id': variant_id})
                json_obj = (dict_sweep(unlist(value_convert_to_number(json_obj,
                                               ['chrom', 'omim', 'id', 'orphanet', 'gene',
                                                'rettbase_(cdkl5)', 'cosmic', 'dbrbc'])), [None, '', 'None']))
                yield json_obj
github biothings / mychem.info / src / hub / dataload / sources / chembl / chembl_parser.py View on Github external
if _flag == 0:
        restr_dict['chembl'] = dictionary
    if 'cross_references' in restr_dict['chembl'] and restr_dict['chembl']['cross_references']:
        restr_dict['chembl']['xrefs'] = restructure_xref(restr_dict['chembl']['cross_references'])

    del restr_dict['chembl']['molecule_structures']
    del restr_dict['chembl']['cross_references']
    restr_dict = unlist(restr_dict)
    # Add "CHEBI:" prefix, standardize the way representing CHEBI IDs
    if 'chebi_par_id' in restr_dict['chembl'] and restr_dict['chembl']['chebi_par_id']:
        restr_dict['chembl']['chebi_par_id'] = 'CHEBI:' + str(restr_dict['chembl']['chebi_par_id'])
    else:
        # clean, could be a None
        restr_dict['chembl'].pop("chebi_par_id",None)

    restr_dict = dict_sweep(restr_dict, vals=[None,".", "-", "", "NA", "None","none", " ", "Not Available", "unknown","null"])
    restr_dict = value_convert_to_number(restr_dict, skipped_keys=["chebi_par_id","first_approval"])
    restr_dict = boolean_convert(restr_dict, ["topical","oral","parenteral","dosed_ingredient","polymer_flag",
        "therapeutic_flag","med_chem_friendly","molecule_properties.ro3_pass"])
    return restr_dict
github biothings / mychem.info / src / hub / dataload / sources / chebi / chebi_parser.py View on Github external
def restructure_dict(dictionary):
    restr_dict = dict()
    restr_dict['_id'] = dictionary['ChEBI ID']
    restr_dict['chebi']= dictionary
    restr_dict['chebi'] = clean_up(restr_dict['chebi'])
    restr_dict = dict_sweep(restr_dict,vals=[None,".", "-", "", "NA", "none", " ", "Not Available",
        "unknown","null","None","NaN"])
    restr_dict = value_convert_to_number(unlist(restr_dict),skipped_keys=[
        "beilstein","pubmed","sabio_rk","gmelin","molbase", "synonyms", "wikipedia","url_stub"])
    return restr_dict
github biothings / mychem.info / src / dataload / contrib / chembl / chembl_parser.py View on Github external
restr_dict['chembl'] = dictionary
            _flag=1
            for x,y in iter(dictionary['molecule_structures'].items()):
                if x == 'standard_inchi_key':
                    restr_dict['chembl'].update(dictionary)
                    restr_dict['chembl'].update({'inchi_key':y})
                if x == 'canonical_smiles':
                    restr_dict['chembl']['smiles'] = y
                if x == 'standard_inchi':
                    restr_dict['chembl']['inchi'] = y
            
    if _flag == 0:
        restr_dict['chembl'] = dictionary
    del restr_dict['chembl']['molecule_structures']           
    restr_dict = unlist(restr_dict)
    restr_dict = dict_sweep(restr_dict, vals=[None,".", "-", "", "NA", "None","none", " ", "Not Available", "unknown","null"])        
    restr_dict = value_convert(restr_dict, skipped_keys=["chebi_par_id","first_approval"])
    restr_dict = boolean_convert(restr_dict, added_keys=["topical","oral","parenteral",
                              "dosed_ingredient","polymer_flag","therapeutic_flag","med_chem_friendly","ro3_pass"])     
    return restr_dict
github biothings / mychem.info / src / hub / dataload / sources / drugbank / drugbank_parser.py View on Github external
"drugbank.weight.average",
                                   "drugbank.predicted_properties.molecular_weight",
                                   "drugbank.predicted_properties.monoisotopic_weight"])
    # Mixed types coerced to floats
    restr_dict = float_convert(restr_dict,
                               include_keys=[
                                   "drugbank.experimental_properties.logp",
                                   "drugbank.experimental_properties.logs",
                                   "drugbank.predicted_properties.logp",
                                   "drugbank.predicted_properties.logs",
                                   "drugbank.predicted_properties.pka_(strongest_basic)",
                                   "drugbank.predicted_properties.pka_(strongest_acidic)",
                                   "drugbank.predicted_properties.refractivity",
                                   "drugbank.predicted_properties.polarizability",
                                   "drugbank.predicted_properties.polar_surface_area_(psa)"])
    restr_dict = dict_sweep(restr_dict,vals=[None,math.inf,"INF",".", "-", "", "NA", "none", " ",
        "Not Available", "unknown","null","None"])
    return restr_dict