Dev

hdr_schemata/definitions/HDRUK/AgeEnum.py

@@ -0,0 +1,28 @@
+from pydantic import BaseModel
+from enum import Enum
+
+class AgeEnum(Enum):
+    DAYS_0_6 = '0-6 days'
+    DAYS_7_27 = '7-27 days'
+    MONTHS_1_11 = '1-11 months'
+    YEARS_1_4 = '1-4 years'
+    YEARS_5_9 = '5-9 years'
+    YEARS_10_14 = '10-14 years'
+    YEARS_15_19 = '15-19 years'
+    YEARS_20_14 = '20-14 years'
+    YEARS_25_29 = '25-29 years'
+    YEARS_30_34 = '30-34 years'
+    YEARS_35_39 = '35-39 years'
+    YEARS_40_44 = '40-44 years'
+    YEARS_45_49 = '45-49 years'
+    YEARS_50_54 = '50-54 years'
+    YEARS_55_59 = '55-59 years'
+    YEARS_60_64 = '60-64 years'
+    YEARS_65_69 = '65-69 years'
+    YEARS_70_74 = '70-74 years'
+    YEARS_75_79 = '75-79 years'
+    YEARS_80_84 = '80-84 years'
+    YEARS_85_89 = '85-89 years'
+    YEARS_90_94 = '90-94 years'
+    YEARS_65_99 = '65-99 years'
+    YEARS_100_PLUS = '100+ years'

hdr_schemata/definitions/HDRUK/Assay.py

@@ -0,0 +1,21 @@
+from enum import Enum
+
+class Assay(Enum):
+    NMR_SPECTROSCOPY = 'NMR spectroscopy'
+    MASS_SPECTROMETRY = 'mass-spectrometry'
+    WHOLE_GENOME_SEQUENCING = 'whole genome sequencing'
+    EXOME_SEQUENCING = 'exome sequencing'
+    GENOTYPING_BY_ARRAY = 'genotyping by array'
+    TRANSCRIPTOME_PROFILING_BY_HIGH_THROUGHPUT_SEQUENCING = 'transcriptome profiling by high-throughput sequencing'
+    TRANSCRIPTOME_PROFILING_BY_ARRAY = 'transcriptome profiling by array'
+    AMPLICON_SEQUENCING = 'amplicon sequencing'
+    METHYLATION_BINDING_DOMAIN_SEQUENCING = 'methylation binding domain sequencing'
+    METHYLATION_PROFILING_BY_HIGH_THROUGHPUT_SEQUENCING = 'methylation profiling by high-throughput sequencing'
+    GENOMIC_VARIANT_CALLING = 'genomic variant calling'
+    CHROMATIN_ACCESSIBILITY_PROFILING_BY_HIGH_THROUGHPUT_SEQUENCING = 'chromatin accessibility profiling by high-throughput sequencing'
+    HISTONE_MODIFICATION_PROFILING_BY_HIGH_THROUGHPUT_SEQUENCING = 'histone modification profiling by high-throughput sequencing'
+    CHROMATIN_IMMUNOPRECIPITATION_SEQUENCING = 'chromatin immunoprecipitation sequencing'
+    WHOLE_GENOME_SHOTGUN_SEQUENCING = 'whole genome shotgun sequencing'
+    WHOLE_TRANSCRIPTOME_SEQUENCING = 'whole transcriptome sequencing'
+    TARGETED_MUTATION_ANALYSIS = 'targeted mutation analysis'
+

hdr_schemata/definitions/HDRUK/CountryCodeEnum.py

@@ -0,0 +1,252 @@
+from enum import Enum
+
+class CountryCodeEnum(Enum):
+    AF = 'AF'
+    AL = 'AL'
+    DZ = 'DZ'
+    AS = 'AS'
+    AD = 'AD'
+    AO = 'AO'
+    AI = 'AI'
+    AQ = 'AQ'
+    AG = 'AG'
+    AR = 'AR'
+    AM = 'AM'
+    AW = 'AW'
+    AU = 'AU'
+    AT = 'AT'
+    AZ = 'AZ'
+    BS = 'BS'
+    BH = 'BH'
+    BD = 'BD'
+    BB = 'BB'
+    BY = 'BY'
+    BE = 'BE'
+    BZ = 'BZ'
+    BJ = 'BJ'
+    BM = 'BM'
+    BT = 'BT'
+    BO = 'BO'
+    BQ = 'BQ'
+    BA = 'BA'
+    BW = 'BW'
+    BV = 'BV'
+    BR = 'BR'
+    IO = 'IO'
+    BN = 'BN'
+    BG = 'BG'
+    BF = 'BF'
+    BI = 'BI'
+    CV = 'CV'
+    KH = 'KH'
+    CM = 'CM'
+    CA = 'CA'
+    KY = 'KY'
+    CF = 'CF'
+    TD = 'TD'
+    CL = 'CL'
+    CN = 'CN'
+    CX = 'CX'
+    CC = 'CC'
+    CO = 'CO'
+    KM = 'KM'
+    CD = 'CD'
+    CG = 'CG'
+    CK = 'CK'
+    CR = 'CR'
+    HR = 'HR'
+    CU = 'CU'
+    CW = 'CW'
+    CY = 'CY'
+    CZ = 'CZ'
+    CI = 'CI'
+    DK = 'DK'
+    DJ = 'DJ'
+    DM = 'DM'
+    DO = 'DO'
+    EC = 'EC'
+    EG = 'EG'
+    SV = 'SV'
+    GQ = 'GQ'
+    ER = 'ER'
+    EE = 'EE'
+    SZ = 'SZ'
+    ET = 'ET'
+    FK = 'FK'
+    FO = 'FO'
+    FJ = 'FJ'
+    FI = 'FI'
+    FR = 'FR'
+    GF = 'GF'
+    PF = 'PF'
+    TF = 'TF'
+    GA = 'GA'
+    GM = 'GM'
+    GE = 'GE'
+    DE = 'DE'
+    GH = 'GH'
+    GI = 'GI'
+    GR = 'GR'
+    GL = 'GL'
+    GD = 'GD'
+    GP = 'GP'
+    GU = 'GU'
+    GT = 'GT'
+    GG = 'GG'
+    GN = 'GN'
+    GW = 'GW'
+    GY = 'GY'
+    HT = 'HT'
+    HM = 'HM'
+    VA = 'VA'
+    HN = 'HN'
+    HK = 'HK'
+    HU = 'HU'
+    IS = 'IS'
+    IN = 'IN'
+    ID = 'ID'
+    IR = 'IR'
+    IQ = 'IQ'
+    IE = 'IE'
+    IM = 'IM'
+    IL = 'IL'
+    IT = 'IT'
+    JM = 'JM'
+    JP = 'JP'
+    JE = 'JE'
+    JO = 'JO'
+    KZ = 'KZ'
+    KE = 'KE'
+    KI = 'KI'
+    KP = 'KP'
+    KR = 'KR'
+    KW = 'KW'
+    KG = 'KG'
+    LA = 'LA'
+    LV = 'LV'
+    LB = 'LB'
+    LS = 'LS'
+    LR = 'LR'
+    LY = 'LY'
+    LI = 'LI'
+    LT = 'LT'
+    LU = 'LU'
+    MO = 'MO'
+    MG = 'MG'
+    MW = 'MW'
+    MY = 'MY'
+    MV = 'MV'
+    ML = 'ML'
+    MT = 'MT'
+    MH = 'MH'
+    MQ = 'MQ'
+    MR = 'MR'
+    MU = 'MU'
+    YT = 'YT'
+    MX = 'MX'
+    FM = 'FM'
+    MD = 'MD'
+    MC = 'MC'
+    MN = 'MN'
+    ME = 'ME'
+    MS = 'MS'
+    MA = 'MA'
+    MZ = 'MZ'
+    MM = 'MM'
+    NA = 'NA'
+    NR = 'NR'
+    NP = 'NP'
+    NL = 'NL'
+    NC = 'NC'
+    NZ = 'NZ'
+    NI = 'NI'
+    NE = 'NE'
+    NG = 'NG'
+    NU = 'NU'
+    NF = 'NF'
+    MK = 'MK'
+    MP = 'MP'
+    NO = 'NO'
+    OM = 'OM'
+    PK = 'PK'
+    PW = 'PW'
+    PS = 'PS'
+    PA = 'PA'
+    PG = 'PG'
+    PY = 'PY'
+    PE = 'PE'
+    PH = 'PH'
+    PN = 'PN'
+    PL = 'PL'
+    PT = 'PT'
+    PR = 'PR'
+    QA = 'QA'
+    RO = 'RO'
+    RU = 'RU'
+    RW = 'RW'
+    RE = 'RE'
+    BL = 'BL'
+    SH = 'SH'
+    KN = 'KN'
+    LC = 'LC'
+    MF = 'MF'
+    PM = 'PM'
+    VC = 'VC'
+    WS = 'WS'
+    SM = 'SM'
+    ST = 'ST'
+    SA = 'SA'
+    SN = 'SN'
+    RS = 'RS'
+    SC = 'SC'
+    SL = 'SL'
+    SG = 'SG'
+    SX = 'SX'
+    SK = 'SK'
+    SI = 'SI'
+    SB = 'SB'
+    SO = 'SO'
+    ZA = 'ZA'
+    GS = 'GS'
+    SS = 'SS'
+    ES = 'ES'
+    LK = 'LK'
+    SD = 'SD'
+    SR = 'SR'
+    SJ = 'SJ'
+    SE = 'SE'
+    CH = 'CH'
+    SY = 'SY'
+    TW = 'TW'
+    TJ = 'TJ'
+    TZ = 'TZ'
+    TH = 'TH'
+    TL = 'TL'
+    TG = 'TG'
+    TK = 'TK'
+    TO = 'TO'
+    TT = 'TT'
+    TN = 'TN'
+    TM = 'TM'
+    TC = 'TC'
+    TV = 'TV'
+    TR = 'TR'
+    UG = 'UG'
+    UA = 'UA'
+    AE = 'AE'
+    GB = 'GB'
+    UM = 'UM'
+    US = 'US'
+    UY = 'UY'
+    UZ = 'UZ'
+    VU = 'VU'
+    VE = 'VE'
+    VN = 'VN'
+    VG = 'VG'
+    VI = 'VI'
+    WF = 'WF'
+    EH = 'EH'
+    YE = 'YE'
+    ZM = 'ZM'
+    ZW = 'ZW'
+    AX = 'AX'

hdr_schemata/definitions/HDRUK/DataUseLimitation.py

@@ -17,9 +17,15 @@ class DataUseLimitation(Enum):
 
 class DataUseLimitationV2(Enum):
     GENERAL_RESEARCH_USE = 'General research use'
+    COMMERCIAL_RESEARCH_USE = 'Commercial research use'
     GENETIC_STUDIES_ONLY = 'Genetic studies only'
     NO_GENERAL_METHODS_RESEARCH = 'No general methods research'
     NO_RESTRICTION = 'No restriction'
+    GEOGRAPHICAL_RESTRICTIONS = 'Geographical restrictions'
+    INSTITUTION_SPECIFIC_RESTRICTIONS = 'Institution-specific restrictions'
+    NOT_FOR_PROFIT_USE = 'Not for profit use'
+    PROJECT_SPECIFIC_RESTRICTIONS = 'Project-specific restrictions'
     RESEARCH_SPECIFIC_RESTRICTIONS = 'Research-specific restrictions'
+    USER_SPECIFIC_RESTRICTIONS = 'User-specific restrictions'
     RESEARCH_USE_ONLY = 'Research use only'
     NO_LINKAGE = 'No linkage'

hdr_schemata/definitions/HDRUK/DataUseRequirements.py

@@ -17,13 +17,14 @@ class DataUseRequirements(Enum):
 
 class DataUseRequirementsV2(Enum):
     COLLABORATION_REQUIRED = 'Collaboration required'
+    PROJECT_SPECIFIC_RESTRICTIONS = 'Project-specific restrictions'
     ETHICS_APPROVAL_REQUIRED = 'Ethics approval required'
-    GEOGRAPHICAL_RESTRICTIONS = 'Geographical restrictions'
     INSTITUTION_SPECIFIC_RESTRICTIONS = 'Institution-specific restrictions'
-    NOT_FOR_PROFIT_USE = 'Not for profit use'
-    PROJECT_SPECIFIC_RESTRICTIONS = 'Project-specific restrictions'
+    GEOGRAPHICAL_RESTRICTIONS = 'Geographical restrictions'
     PUBLICATION_MORATORIUM = 'Publication moratorium'
     PUBLICATION_REQUIRED = 'Publication required'
     RETURN_TO_DATABASE_OR_RESOURCE = 'Return to database or resource'
     TIME_LIMIT_ON_USE = 'Time limit on use'
+    DISCLOSURE_CONTROL = 'Disclosure control'
+    NOT_FOR_PROFIT_USE = 'Not for profit use'
     USER_SPECIFIC_RESTRICTION = 'User-specific restriction'

hdr_schemata/definitions/HDRUK/DatasetType.py

@@ -26,7 +26,7 @@ class DatasetSubType(Enum):
     CARDIOVASCULAR = 'Cardiovascular'
     CANCER = 'Cancer'
     RARE_DISEASES = 'Rare diseases'
-    METABOLIC_AND_ENDOCRINE = 'Metabolic and Endocrine'
+    METABOLIC_AND_ENDOCRINE = 'Metabolic and endocrine'
     NEUROLOGICAL = 'Neurological'
     REPRODUCTIVE = 'Reproductive'
     MATERNITY_AND_NEONATOLOGY = 'Maternity and neonatology'
@@ -35,8 +35,8 @@ class DatasetSubType(Enum):
     MUSCULOSKELETAL = 'Musculoskeletal'
     VISION = 'Vision'
     RENAL_AND_UROGENITAL = 'Renal and urogenital'
-    ORAL_AND_GASTROINTESTINAL = 'Oral and Gastrointestinal'
-    COGNITIVE_FUNCTION = 'Cognitive Function'
+    ORAL_AND_GASTROINTESTINAL = 'Oral and gastrointestinal'
+    COGNITIVE_FUNCTION = 'Cognitive function'
     HEARING = 'Hearing'
     OTHERS = 'Others'
     VACCINES = 'Vaccines'
@@ -62,14 +62,14 @@ class DatasetSubType(Enum):
     TRANSCRIPTOMICS = 'Transcriptomics'
     EPIGENOMICS = 'Epigenomics'
     METABOLOMICS = 'Metabolomics'
-    MULTIOMICS = 'Multiomics'
     METAGENOMICS = 'Metagenomics'
     GENOMICS = 'Genomics'
+    LIPIDOMICS = 'Lipidomics'
     # OTHERS = 'Others'
     EDUCATION = 'Education'
-    CRIME_AND_JUSTICE = 'Crime and Justice'
+    CRIME_AND_JUSTICE = 'Crime and justice'
     ETHNICITY = 'Ethnicity'
-    HOUSING_ = 'Housing '
+    HOUSING_ = 'Housing'
     LABOUR = 'Labour'
     AGEING_ = 'Ageing '
     ECONOMICS = 'Economics'
@@ -82,12 +82,12 @@ class DatasetSubType(Enum):
     FAMILY_CIRCUMSTANCE = 'Family circumstance'
     # OTHERS = 'Others'
     SMOKING = 'Smoking'
-    PHYSICAL_ACTIVITY = 'Physical Activity'
+    PHYSICAL_ACTIVITY = 'Physical activity'
     DIETARY_HABITS = 'Dietary habits'
     ALCOHOL = 'Alcohol'
     # OTHERS = 'Others'
-    DISEASE_REGISTRY_RESEARCH = 'Disease Registry (research)'
-    NATIONAL_DISEASE_REGISTRIES_AND_AUDITS = 'National Disease Registries and Audits'
-    BIRTHS_AND_DEATHS = 'Births and Deaths'
+    DISEASE_REGISTRY_RESEARCH = 'Disease registry (research)'
+    NATIONAL_DISEASE_REGISTRIES_AND_AUDITS = 'National disease registries and audits'
+    BIRTHS_AND_DEATHS = 'Births and deaths'
     # OTHERS = 'Others'
-    NOT_APPLICABLE = 'Not applicable'
+    NOT_APPLICABLE = 'Not applicable'