OpenCGA
Page tree

Versions Compared

Old Version 8

changes.mady.by.user Jacobo Coll

Saved on

compared with

New Version 9

changes.mady.by.user Jacobo Coll

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.


Index


Annotate


Custom annotation

Calculate Statistics

Define cohorts

Remove



Export / Query


Export frequencies (statistics)

Export frequencies (statistics) is an special case of export. Instead of export full variants, only the variant cohort statistics are exported.

To export variant frequencies, use the command variant export-frequencies in the command line.

As for variants export, there are multiple possible output formats:

  • VCF : Standard VCF format without samples information, with the stats as values in the INFO column.

    Code Block
    languagebash
    titleVCF
    ##fileformat=VCFv4.2
##FILTER=<ID=.,Description="No FILTER info">
##FILTER=<ID=PASS,Description="Valid variant">
##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes, for each ALT allele, in the same order as listed">
##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, calculated from AC and AN, in the range (0,1), in the same order as listed">
##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
##INFO=<ID=AFK_AF,Number=A,Type=Float,Description="Allele frequency in the C1 cohort calculated from AC and AN, in the range (0,1), in the same order as listed">
#CHROM    POS    ID    REF    ALT    QUAL    FILTER    INFO
22    16050115    .    G    A    .    PASS    AC=1;AF=0.001;AN=1000;AFK_AF=0.002008
22    16050213    .    C    T    .    PASS    AC=1;AF=0.001;AN=1000;AFK_AF=0
22    16050319    .    C    T    .    PASS    AC=1;AF=0.001;AN=1000;AFK_AF=0
22    16050607    .    G    A    .    PASS    AC=2;AF=0.002;AN=1000;AFK_AF=0.004016


  • TSV (Tab Separated Values). Simple format with each cohort in one column.

    Code Block
    languagebash
    titleTSV
    #CHR    POS    REF    ALT    ALL_AN    ALL_AC    ALL_AF    ALL_HET    ALL_HOM
22    16050213    C    T    1000    1    0.001    0.002    0.0
22    16050607    G    A    1000    2    0.002    0.004    0.0
22    16050740    A    -    1000    1    0.001    0.002    0.0
22    16050840    C    G    1000    13    0.013    0.026    0.0
22    16051075    G    A    1000    2    0.002    0.004    0.0
22    16051249    T    C    1000    91    0.091    0.162    0.01
22    16051453    A    C    998    74    0.074    0.144    0.004
22    16051453    A    G    926    2    0.002    0.144    0.004
22    16051723    A    -    1000    12    0.012    0.024    0.0
22    16051816    T    G    1000    2    0.002    0.004    0.0


  • JSON. Variant model just with minimal information and statistics.

    Code Block
    languagejs
    titleJSON
    {"reference":"G","names":[],"chromosome":"22","alternate":"A","start":16050115,"annotation":null,"id":"22:16050115:G:A","type":"SNV","studies":[{"format":[],"samplesData":[],"studyId":"user@p1:s1","stats":{"C3":{"refAllele":"G","altAllele":"A","refAlleleCount":2,"altAlleleCount":0,"genotypesCount":{"0/0":1},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"ALL":{"refAllele":"G","altAllele":"A","refAlleleCount":999,"altAlleleCount":1,"genotypesCount":{"0/0":499,"0|1":1},"genotypesFreq":{"0/0":0.998,"0|1":0.002},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.999,"altAlleleFreq":0.001,"maf":0.001,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C4":{"refAllele":"G","altAllele":"A","refAlleleCount":-1,"altAlleleCount":-1,"genotypesCount":{},"genotypesFreq":{},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":2.0,"altAlleleFreq":-1.0,"maf":-1.0,"mgf":-1.0,"mafAllele":null,"mgfGenotype":null,"passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C1":{"refAllele":"G","altAllele":"A","refAlleleCount":500,"altAlleleCount":0,"genotypesCount":{"0/0":250},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C2":{"refAllele":"G","altAllele":"A","refAlleleCount":497,"altAlleleCount":1,"genotypesCount":{"0/0":248,"0|1":1},"genotypesFreq":{"0/0":0.99598396,"0|1":0.004016064},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.997992,"altAlleleFreq":0.002008032,"maf":0.002008032,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"}},"files":[],"secondaryAlternates":[]}],"end":16050115,"strand":"+","sv":null,"hgvs":{},"length":1}
{"reference":"C","names":[],"chromosome":"22","alternate":"T","start":16050213,"annotation":null,"id":"22:16050213:C:T","type":"SNV","studies":[{"format":[],"samplesData":[],"studyId":"user@p1:s1","stats":{"C3":{"refAllele":"C","altAllele":"T","refAlleleCount":2,"altAlleleCount":0,"genotypesCount":{"0/0":1},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"ALL":{"refAllele":"C","altAllele":"T","refAlleleCount":999,"altAlleleCount":1,"genotypesCount":{"0|1":1,"0/0":499},"genotypesFreq":{"0|1":0.002,"0/0":0.998},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.999,"altAlleleFreq":0.001,"maf":0.001,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C4":{"refAllele":"C","altAllele":"T","refAlleleCount":-1,"altAlleleCount":-1,"genotypesCount":{},"genotypesFreq":{},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":2.0,"altAlleleFreq":-1.0,"maf":-1.0,"mgf":-1.0,"mafAllele":null,"mgfGenotype":null,"passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C1":{"refAllele":"C","altAllele":"T","refAlleleCount":500,"altAlleleCount":0,"genotypesCount":{"0/0":250},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C2":{"refAllele":"C","altAllele":"T","refAlleleCount":497,"altAlleleCount":1,"genotypesCount":{"0|1":1,"0/0":248},"genotypesFreq":{"0|1":0.004016064,"0/0":0.99598396},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.997992,"altAlleleFreq":0.002008032,"maf":0.002008032,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"}},"files":[],"secondaryAlternates":[]}],"end":16050213,"strand":"+","sv":null,"hgvs":{},"length":1}
{"reference":"C","names":[],"chromosome":"22","alternate":"T","start":16050319,"annotation":null,"id":"22:16050319:C:T","type":"SNV","studies":[{"format":[],"samplesData":[],"studyId":"user@p1:s1","stats":{"C3":{"refAllele":"C","altAllele":"T","refAlleleCount":2,"altAlleleCount":0,"genotypesCount":{"0/0":1},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"ALL":{"refAllele":"C","altAllele":"T","refAlleleCount":999,"altAlleleCount":1,"genotypesCount":{"0/0":499,"1|0":1},"genotypesFreq":{"0/0":0.998,"1|0":0.002},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.999,"altAlleleFreq":0.001,"maf":0.001,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C4":{"refAllele":"C","altAllele":"T","refAlleleCount":-1,"altAlleleCount":-1,"genotypesCount":{},"genotypesFreq":{},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":2.0,"altAlleleFreq":-1.0,"maf":-1.0,"mgf":-1.0,"mafAllele":null,"mgfGenotype":null,"passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C1":{"refAllele":"C","altAllele":"T","refAlleleCount":500,"altAlleleCount":0,"genotypesCount":{"0/0":250},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C2":{"refAllele":"C","altAllele":"T","refAlleleCount":497,"altAlleleCount":1,"genotypesCount":{"0/0":248,"1|0":1},"genotypesFreq":{"0/0":0.99598396,"1|0":0.004016064},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.997992,"altAlleleFreq":0.002008032,"maf":0.002008032,"mgf":0.0,"mafAllele":"T","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"}},"files":[],"secondaryAlternates":[]}],"end":16050319,"strand":"+","sv":null,"hgvs":{},"length":1}
{"reference":"G","names":[],"chromosome":"22","alternate":"A","start":16050607,"annotation":null,"id":"22:16050607:G:A","type":"SNV","studies":[{"format":[],"samplesData":[],"studyId":"user@p1:s1","stats":{"C3":{"refAllele":"G","altAllele":"A","refAlleleCount":2,"altAlleleCount":0,"genotypesCount":{"0/0":1},"genotypesFreq":{"0/0":1.0},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":1.0,"altAlleleFreq":0.0,"maf":0.0,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"ALL":{"refAllele":"G","altAllele":"A","refAlleleCount":998,"altAlleleCount":2,"genotypesCount":{"0/0":498,"0|1":1,"1|0":1},"genotypesFreq":{"0/0":0.996,"0|1":0.002,"1|0":0.002},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.998,"altAlleleFreq":0.002,"maf":0.002,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C4":{"refAllele":"G","altAllele":"A","refAlleleCount":-1,"altAlleleCount":-1,"genotypesCount":{},"genotypesFreq":{},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":2.0,"altAlleleFreq":-1.0,"maf":-1.0,"mgf":-1.0,"mafAllele":null,"mgfGenotype":null,"passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C1":{"refAllele":"G","altAllele":"A","refAlleleCount":499,"altAlleleCount":1,"genotypesCount":{"0/0":249,"0|1":1},"genotypesFreq":{"0/0":0.996,"0|1":0.004},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.998,"altAlleleFreq":0.002,"maf":0.002,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"},"C2":{"refAllele":"G","altAllele":"A","refAlleleCount":497,"altAlleleCount":1,"genotypesCount":{"0/0":248,"1|0":1},"genotypesFreq":{"0/0":0.99598396,"1|0":0.004016064},"missingAlleles":0,"missingGenotypes":0,"refAlleleFreq":0.997992,"altAlleleFreq":0.002008032,"maf":0.002008032,"mgf":0.0,"mafAllele":"A","mgfGenotype":"1/1","passedFilters":false,"mendelianErrors":-1,"casesPercentDominant":-1.0,"controlsPercentDominant":-1.0,"casesPercentRecessive":-1.0,"controlsPercentRecessive":-1.0,"quality":-1.0,"numSamples":-1,"variantType":"SNV"}},"files":[],"secondaryAlternates":[]}],"end":16050607,"strand":"+","sv":null,"hgvs":{},"length":1}


  • Population Frequencies (Cellbase mode). Specific JSON format for import into Cellbase variation. It is a Variant model with VariantAnnotation with PupulationFrequencies.

    Code Block
    languagejs
    titlePopulationFrequencies / Cellbase
    {"names":[],"reference":"T","chromosome":"22","alternate":"C","start":16174643,"annotation":{"populationFrequencies":[{"study":"s1","population":"ALL","refAllele":"T","altAllele":"C","refAlleleFreq":0.999,"altAlleleFreq":0.001,"refHomGenotypeFreq":0.998,"hetGenotypeFreq":0.002,"altHomGenotypeFreq":0.0},{"study":"s1","population":"C1","refAllele":"T","altAllele":"C","refAlleleFreq":0.998,"altAlleleFreq":0.002,"refHomGenotypeFreq":0.996,"hetGenotypeFreq":0.004,"altHomGenotypeFreq":0.0}]},"end":16174643,"type":"SNV","studies":[],"strand":"+","hgvs":{},"length":1}
{"names":[],"reference":"C","chromosome":"22","alternate":"T","start":16176715,"annotation":{"populationFrequencies":[{"study":"s1","population":"ALL","refAllele":"C","altAllele":"T","refAlleleFreq":0.998,"altAlleleFreq":0.002,"refHomGenotypeFreq":0.996,"hetGenotypeFreq":0.004,"altHomGenotypeFreq":0.0},{"study":"s1","population":"C2","refAllele":"C","altAllele":"T","refAlleleFreq":0.99598396,"altAlleleFreq":0.004016064,"refHomGenotypeFreq":0.99196786,"hetGenotypeFreq":0.008032128,"altHomGenotypeFreq":0.0}]},"end":16176715,"type":"SNV","studies":[],"strand":"+","hgvs":{},"length":1}
{"names":[],"reference":"C","chromosome":"22","alternate":"A","start":16176724,"annotation":{"populationFrequencies":[{"study":"s1","population":"ALL","refAllele":"C","altAllele":"A","refAlleleFreq":0.999,"altAlleleFreq":0.001,"refHomGenotypeFreq":0.998,"hetGenotypeFreq":0.002,"altHomGenotypeFreq":0.0},{"study":"s1","population":"C2","refAllele":"C","altAllele":"A","refAlleleFreq":0.997992,"altAlleleFreq":0.002008032,"refHomGenotypeFreq":0.99598396,"hetGenotypeFreq":0.004016064,"altHomGenotypeFreq":0.0}]},"end":16176724,"type":"SNV","studies":[],"strand":"+","hgvs":{},"length":1}
{"names":[],"reference":"T","chromosome":"22","alternate":"C","start":16176769,"annotation":{"populationFrequencies":[{"study":"s1","population":"ALL","refAllele":"T","altAllele":"C","refAlleleFreq":0.999,"altAlleleFreq":0.001,"refHomGenotypeFreq":0.998,"hetGenotypeFreq":0.002,"altHomGenotypeFreq":0.0},{"study":"s1","population":"C2","refAllele":"T","altAllele":"C","refAlleleFreq":0.997992,"altAlleleFreq":0.002008032,"refHomGenotypeFreq":0.99598396,"hetGenotypeFreq":0.004016064,"altHomGenotypeFreq":0.0}]},"end":16176769,"type":"SNV","studies":[],"strand":"+","hgvs":{},"length":1}
{"names":[],"reference":"T","chromosome":"22","alternate":"A","start":16176926,"annotation":{"populationFrequencies":[{"study":"s1","population":"C3","refAllele":"T","altAllele":"A","refAlleleFreq":0.5,"altAlleleFreq":0.5,"refHomGenotypeFreq":0.0,"hetGenotypeFreq":1.0,"altHomGenotypeFreq":0.0},{"study":"s1","population":"ALL","refAllele":"T","altAllele":"A","refAlleleFreq":0.473,"altAlleleFreq":0.527,"refHomGenotypeFreq":0.166,"hetGenotypeFreq":0.614,"altHomGenotypeFreq":0.22},{"study":"s1","population":"C1","refAllele":"T","altAllele":"A","refAlleleFreq":0.474,"altAlleleFreq":0.526,"refHomGenotypeFreq":0.164,"hetGenotypeFreq":0.62,"altHomGenotypeFreq":0.216},{"study":"s1","population":"C2","refAllele":"T","altAllele":"A","refAlleleFreq":0.4698795,"altAlleleFreq":0.5301205,"refHomGenotypeFreq":0.16465864,"hetGenotypeFreq":0.6104418,"altHomGenotypeFreq":0.2248996}]},"end":16176926,"type":"SNV","studies":[],"strand":"+","hgvs":{},"length":1}


Import



Table of Contents:

Table of Contents
indent20px