New JSON format

[robinandeer]

Hej, det kommer att bli ganska stor skillnad i den information som du får från mongo-databasen Robin.

Om man ser på den data som detta anrop ger idag http://clinical-db:8084/variants/77787685 så får du data enligt nedan:

{
    "rating": "",
    "location_reliability": "",
    "functional_annotation": "nonsynonymous SNV",
    "stop_bp": 6645448,
    "dbsnp129": null,
    "lrt_whole_exome": 0.0121,
    "omim_morbid_desc": "",
    "rank_score": 21,
    "hgnc_synonyms": "GCSP, NKH;",
    "unscaled_cscore_snv": 3.2367,
    "phast_const_elements": "Score=389;Name=lod=51",
    "snorna_mirna_annotation": "-",
    "chr": "chr9",
    "hgnc_transcript_id": "GLDC:NM_000170:exon1:c.52G>T:p.G18C,",
    "esp6500": null,
    "hgnc_symbol": "GLDC",
    "GT_call_filter": "PASS",
    "reduced_penetrance": "",
    "pseudogene": "processed_pseudogene;",
    "clinical_db_gene_annotation": "IEM:EP",
    "main_location": "",
    "dbsnp132": null,
    "disease_group": "Nonketotic hyperglycinemia",
    "ref_nt": "C",
    "mutation_taster": 0.009623,
    "hgmd_accession": null,
    "hgmd": "",
    "gene_annotation": "exonic",
    "omim_gene_desc": "",
    "start_bp": 6645448,
    "hgmd_variant_type": null,
    "otherVariants": [
        {
            "pk": 75559832,
            "family": "183"
        },
        {
            "pk": 62008206,
            "family": "43"
        },
        {
            "pk": 65943750,
            "family": "92"
        },
        {
            "pk": 66075846,
            "family": "93"
        },
        {
            "pk": 77048406,
            "family": "trio22X"
        }
    ],
    "dbsnp": "-",
    "sift_whole_exome": 0.1,
    "id": 77787685,
    "gerp_element": 598.0,
    "dbsnp_id": "-",
    "scaled_cscore_snv": 16.85,
    "compounds": [
        {
            "alt_nt": "T",
            "ref_nt": "C",
            "variant": 93754058,
            "combined_score": 38,
            "chr": "chr9",
            "start_bp": 6588403
        },
        {
            "alt_nt": "T",
            "ref_nt": "C",
            "variant": 93754059,
            "combined_score": 20,
            "chr": "chr9",
            "start_bp": 6610326
        },
        {
            "alt_nt": "C",
            "ref_nt": "T",
            "variant": 93754056,
            "combined_score": 16,
            "chr": "chr9",
            "start_bp": 6591972
        },
        {
            "alt_nt": "T",
            "ref_nt": "C",
            "variant": 93754057,
            "combined_score": 16,
            "chr": "chr9",
            "start_bp": 6602374
        },
        {
            "alt_nt": "C",
            "ref_nt": "T",
            "variant": 93754060,
            "combined_score": 16,
            "chr": "chr9",
            "start_bp": 6606746
        },
        {
            "alt_nt": "-",
            "ref_nt": "T",
            "variant": 93754061,
            "combined_score": 16,
            "chr": "chr9",
            "start_bp": 6602378
        }
    ],
    "hgmd_variant_pmid": null,
    "polyphen_var_human": 0.671,
    "unscaled_cscore_thousand_g": null,
    "other_location": "",
    "scaled_cscore_thousand_g": null,
    "disease_gene_model": "AR",
    "hbvdb": 0.0127,
    "alt_nt": "A",
    "phylop_whole_exome": 1.27,
    "expression_type": "",
    "gene_model": "AR_compound:AD:AD_denovo",
    "variant_count": null,
    "individual_rank_score": 21,
    "thousand_g": null,
    "ensembl_geneid": "ENSG00000178445;",
    "hgnc_approved_name": "glycine dehydrogenase (decarboxylating);",
    "genomic_super_dups": "-",
    "polyphen_div_human": 0.975,
    "gerp_whole_exome": 3.62
}

Med den data som jag komer att ha i mongo-databasen så kommer informationen för en variant typiskt att se ut som nedan:

{
    "CHROM":1,
    "POS":2332391,
    "REF":C,
    "ALT":[T]
   "KGPhase1": true,
    "RSPOS": 2332391,
    "OTHERKG": true,
    "set": "Intersection",
    "SLO": true,
    "HGVS_PROTEIN_VAR": [
        null
    ],
    "POSITIVE_TRAIN_SITE": true,
    "Comp": [
        "-"
    ],
    "VC": "SNV",
    "EA_GTC": [
        "845",
        "2007",
        "1257"
    ],
    "Dbsnp129MAF": 0.3503,
    "GTC": [
        "1009",
        "2709",
        "2273"
    ],
    "CADD": 0.35,
    "dbSNPBuildID": 120,
    "FG": [
        "NM_007033.4:intron"
    ],
    "AA_AC": [
        "1030",
        "2734"
    ],
    "EA_AC": [
        "3697",
        "4521"
    ],
    "CAF": [
        "[0.6497",
        "0.3503]"
    ],
    "DP": 5362,
    "CDS_SIZES": [
        "NM_007033.4:591"
    ],
    "GL": [
        "RER1"
    ],
    "SAO": 0,
    "culprit": "FS",
    "RS": 12037485,
    "HGVScp": [
        "PEX10:NM_002617.3:downstream_gene_variant:s.-",
        "PEX10:NM_153818.1:downstream_gene_variant:s.-"
    ],
    "HGVS_CDNA_VAR": [
        "NM_007033.4:c.365+17C>T"
    ],
    "VLD": true,
    "GNO": true,
    "Dels": 0.0,
    "COMMON": 1,
    "pop": "ALL",
    "TAC": [
        "4727",
        "7255"
    ],
    "HaplotypeScore": 0.2072,
    "DBSNP": [
        "dbSNP_120"
    ],
    "GWAS_PUBMED": [
        null
    ],
    "DbsnpMAF": 0.3503,
    "SB": -20674.8,
    "AA": "C",
    "AC": [
        3
    ],
    "G5A": true,
    "GS": [
        null
    ],
    "ESPMAF": 0.394508,
    "AF": [
        0.5
    ],
    "AA_AGE": [
        null
    ],
    "CA": [
        null
    ],
    "CG": -6.4,
    "G5": true,
    "AN": 6,
    "VP": "0x05010008000117011e000100",
    "MQ0": 0,
    "GTS": [
        "TT",
        "TC",
        "CC"
    ],
    "EA_AGE": [
        null
    ],
    "AA_GTC": [
        "164",
        "702",
        "1016"
    ],
    "BVDMAF": 0.4522,
    "GQ_MEAN": 514.92,
    "GM": [
        "NA"
    ],
    "CP": 0.0,
    "CSQ": [
        "T|5192|NM_002617.3|Transcript|downstream_gene_variant|||||||||3850|-1|PEX10|||||",
        "T|5192|NM_153818.1|Transcript|downstream_gene_variant|||||||||3850|-1|PEX10|||||"
    ],
    "PH": [
        null
    ],
    "KGPROD": true,
    "WGT": 1,
    "INT": true,
    "1000GMAF": 0.34547,
    "HRun": 0,
    "GeneticRegionAnnotation": [
        "PEX10:downstream"
    ],
    "GQ_STDDEV": 561.47,
    "SSR": 0,
    "EXOME_CHIP": [
        "no"
    ],
    "MS": null,
    "MAF": [
        "44.9866",
        "27.3645",
        "39.4508"
    ],
    "KGPilot123": true,
    "MostSevereConsequence": [
        "PEX10:downstream_gene_variant"
    ],
    "NCC": 0,
    "ANN": [
        "PEX10"
    ]
}

Så det blir ganska stor skillnad. /Mats

[robinandeer]

Japp, det blir mer oklart vad som är vad (för din del). Men jag tror att det är det som är meningen, all tolkning av data och namn på taggar flyttas nu från mitt program som parsar data och insertar det i mysql till den som söker i databasen. Tror att det är det som är meningen med att använda en schema-lös databas.

Mitt dataladdningsprogram kommer nu bara att ta rad för rad i VCF-filen och lagra det i mongo-databasen.

Ska försöka hitta exempel på Compounds.

/Mats

[robinandeer]

Hej igen, jag hittade en variant där Comp inte var tom. Den ser ut som nedan. Vet inte om det räcker eller om du kommer behöva ytterligare info?

{
    "CHROM":1,
    "POS":11856378,
    "REF": G
    "ALT":[A],
    "RSPOS": 11856378,
    "BVDMAF": 0.2994,
    "CLNDSDB": [
        "MedGen"
    ],
    "CLNACC": [
        "RCV000003697.3"
    ],
    "POSITIVE_TRAIN_SITE": true,
    "CLNDBN": [
        "MTHFR_deficiency\\x2c_thermolabile_type"
    ],
    "AA_AC": [
        "536",
        "3870"
    ],
    "G5": true,
    "GL": [
        "MTHFR"
    ],
    "SAO": 0,
    "RS": 1801133,
    "HGVScp": [
        "MTHFR:NM_005957.4:missense_variant:s.-:e.5/12:c.665C>T:p.Ala222Val"
    ],
    "CLNSIG": [
        "2"
    ],
    "Sift": [
        "MTHFR:0.06"
    ],
    "TAC": [
        "3519",
        "9487"
    ],
    "GS": [
        "64"
    ],
    "TPA": true,
    "dbNSFP_phyloP100way_vertebrate": [
        9.044,
        9.044
    ],
    "HGNC_id": [
        "MTHFR"
    ],
    "MQ0": 0,
    "EA_AGE": [
        "461.7+/-365.5"
    ],
    "AA_GTC": [
        "31",
        "474",
        "1698"
    ],
    "GQ_MEAN": 399.65,
    "GM": [
        "AR_comp"
    ],
    "OTHERKG": true,
    "PH": [
        "probably-damaging:0.999"
    ],
    "OM": true,
    "1000GMAF": 0.32667,
    "HRun": 0,
    "MAF": [
        "34.686",
        "12.1652",
        "27.0567"
    ],
    "dbNSFP_SIFT_score": [
        0.05,
        0.05
    ],
    "dbNSFP_MutationTaster_pred": [
        "P",
        "P"
    ],
    "dbNSFP_phastCons100way_vertebrate": [
        1.0,
        1.0
    ],
    "FG": [
        "NM_005957.4:missense"
    ],
    "PH3": true,
    "dbNSFP_Polyphen2_HVAR_pred": [
        "D",
        "D",
        "D",
        "D"
    ],
    "Disease_group_pathway": [
        "Cobalamin_and_folate_transport_and_metab"
    ],
    "HD": true,
    "LSD": true,
    "dbNSFP_FATHMM_pred": [
        "D",
        "D",
        "D",
        "D",
        "D",
        "D",
        "D",
        "D"
    ],
    "culprit": "ReadPosRankSum",
    "dbNSFP_phyloP46way_primate": [
        0.655,
        0.655
    ],
    "VLD": true,
    "COMMON": 1,
    "DBSNP": [
        "dbSNP_89"
    ],
    "KGPROD": true,
    "dbNSFP_RadialSVM_pred": [
        "T",
        "T"
    ],
    "PM": true,
    "dbNSFP_phastCons46way_primate": [
        0.116,
        0.116
    ],
    "ESPMAF": 0.270567,
    "AA_AGE": [
        "242.1+/-252.3"
    ],
    "KGPilot123": true,
    "RV": true,
    "WGT": 1,
    "CLNSRC": [
        "GTR|GTR|GTR|GTR|GTR|GTR|OMIM_Allelic_Variant"
    ],
    "CLNORIGIN": [
        "1"
    ],
    "SB": -20836.01,
    "dbNSFP_MutationTaster_score": [
        0.9999999135526,
        0.9999999135526
    ],
    "CSQ": [
        "A|4524|NM_005957.4|Transcript|missense_variant|894|665|222|A/V|gCc/gTc||5/12|||-1|MTHFR||0.06|1|NM_005957.4:c.665C>T|NP_005948.3:p.Ala222Val"
    ],
    "dbNSFP_GERP++_NR": [
        5.08,
        5.08
    ],
    "ANN": [
        "MTHFR"
    ],
    "GQ_STDDEV": 559.15,
    "SSR": 0,
    "MS": 60.0,
    "dbNSFP_MutationAssessor_score": [
        "2.425",
        "2.425"
    ],
    "dbNSFP_SiPhy_29way_logOdds": [
        17.4321,
        17.4321
    ],
    "HGVS_PROTEIN_VAR": [
        "NM_005957.4:p.(A222V)"
    ],
    "dbNSFP_GERP++_RS": [
        5.08,
        5.08
    ],
    "pop": "ALL",
    "EA_GTC": [
        "519",
        "1945",
        "1836"
    ],
    "Dbsnp129MAF": 0.3246,
    "set": "Intersection",
    "GENEINFO": "MTHFR:4524",
    "REF": true,
    "CDS_SIZES": [
        "NM_005957.4:1971"
    ],
    "ASP": true,
    "Comp": [
        "1_11851003_G_C:1_11848139_G_A:1_11854671_C_A:1_11844214_A_T:1_11854476_T_G:1_11860458_C_T:1_11852300_C_T"
    ],
    "PolyPhen": [
        "MTHFR:1"
    ],
    "PMC": true,
    "DbsnpMAF": 0.3246,
    "GTC": [
        "550",
        "2419",
        "3534"
    ],
    "G5A": true,
    "CG": 5.1,
    "GTS": [
        "AA",
        "AG",
        "GG"
    ],
    "CLNDSDBID": [
        "C1856059"
    ],
    "CP": 1.0,
    "dbNSFP_LR_score": [
        0.0,
        0.0
    ],
    "Clinical_db_gene_annotation": [
        "IEM"
    ],
    "GeneticRegionAnnotation": [
        "MTHFR:exonic"
    ],
    "dbNSFP_LR_pred": [
        "T",
        "T"
    ],
    "CLNHGVS": [
        "NC_000001.10:g.11856378G>A"
    ],
    "MostSevereConsequence": [
        "MTHFR:missense_variant"
    ],
    "CLNSRCID": [
        "GTR000017233|GTR000194242|GTR000254993|GTR000327733|GTR000500035|GTR000500311|607093.0003"
    ],
    "KGPhase1": true,
    "dbSNPBuildID": 89,
    "GWAS_PUBMED": [
        "http://www.ncbi.nlm.nih.gov/pubmed?term"
    ],
    "CADD": 21.9,
    "EA_AC": [
        "2983",
        "5617"
    ],
    "CAF": [
        "[0.6754",
        "0.3246]"
    ],
    "DP": 6452,
    "Disease_gene_model": [
        "AR"
    ],
    "NSM": true,
    "HGVS_CDNA_VAR": [
        "NM_005957.4:c.665C>T"
    ],
    "GNO": true,
    "dbNSFP_SIFT_pred": [
        "D",
        "D"
    ],
    "Dels": 0.0,
    "CLNALLE": [
        1
    ],
    "dbNSFP_LRT_score": [
        "0.000000",
        "0.000000"
    ],
    "dbNSFP_LRT_pred": [
        "D",
        "D"
    ],
    "HaplotypeScore": 0.3201,
    "CA": [
        "http://www.ncbi.nlm.nih.gov/pubmed?term"
    ],
    "dbNSFP_RadialSVM_score": [
        -1.4547,
        -1.4547
    ],
    "AA": "G",
    "AC": [
        2
    ],
    "VC": "SNV",
    "dbNSFP_Reliability_index": [
        9,
        9
    ],
    "AF": [
        0.333
    ],
    "MTP": true,
    "AN": 6,
    "SLO": true,
    "S3D": true,
    "OTH": true,
    "dbNSFP_FATHMM_score": [
        "-4.03",
        "-4.03",
        "-4.03",
        "-4.03",
        "-4.03",
        "-4.03",
        "-4.03",
        "-4.03"
    ],
    "dbNSFP_Polyphen2_HVAR_score": [
        "0.941",
        "0.987",
        "0.941",
        "0.987"
    ],
    "Clinical_db_genome_build": [
        "GRCh37.p8"
    ],
    "Ensembl_gene_id": [
        "ENSG00000177000"
    ],
    "EXOME_CHIP": [
        "yes"
    ],
    "NCC": 0
}

[robinandeer]

Vi kan nog be Måns att byta ut separatorn ':' mot ',' för det är standarden i VCF för att generera listor. Comp entryt skulle i så fall bli:

    "Comp": [
        "1_11851003_G_C",
        "1_11848139_G_A",
        "1_11854671_C_A",
        "1_11844214_A_T",
        "1_11854476_T_G",
        "1_11860458_C_T",
        "1_11852300_C_T"
    ]

Vilket är bättre tycker jag.