data_format
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revisionLast revisionBoth sides next revision | ||
data_format [2008/06/16 15:47] – heidi | data_format [2009/02/18 17:35] – heidi | ||
---|---|---|---|
Line 3: | Line 3: | ||
\\ | \\ | ||
- | |||
- | |||
- | |||
- | |||
Line 26: | Line 22: | ||
* [[PAML]] | * [[PAML]] | ||
* [[Immanc]] (BayesAss) | * [[Immanc]] (BayesAss) | ||
- | * [[Batwing]] | + | * [[BATWING]] |
+ | * [[MSVar]] | ||
+ | * [[FDist2]] | ||
+ | * [[MSA]] | ||
+ | * [[GDA]] | ||
+ | * [[GENETIX]] | ||
Line 35: | Line 36: | ||
* **[[NEXUS]]** | * **[[NEXUS]]** | ||
* **[[FASTA]]** | * **[[FASTA]]** | ||
+ | * [[KML]] | ||
Line 67: | Line 69: | ||
===== new data format ===== | ===== new data format ===== | ||
- | * in [[XML_presentation|XML]] | + | * [[PGD]] |
- | * root element: < | + | |
- | + | ||
- | + | ||
- | + | ||
- | ==== 1. version: ==== | + | |
- | \\ | + | |
- | | ^^^^ data type ^^^^^^ | + | |
- | ^ block ^ subtags ^^^ standard ^ DNA ^ SNP ^ Microsattelite ^ RFLP (AFLP) ^ Allel frequency ^ | + | |
- | ^^^^^^^^^^^ | + | |
- | | header (attribute: title) | number_samples ||| x | x | x | x | x | x | | + | |
- | | | data_type ||| x | x | x | x | x | x | | + | |
- | | | number_loci | number || x | x | x | x | x | | | + | |
- | | || loci (attribute: name) | locations | o | o | o | o | o | | | + | |
- | | ||| length | o | o | o | o | o | | | + | |
- | | | missing ||| o | o | o | o | o | | | + | |
- | | | gap ||| o | o | o | o | o | | | + | |
- | | | gametic_phase ||| o | o | o | o | o | | | + | |
- | | | recessive_alleles ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | sample (attribute: name) | size ||| x | x | x | x | x | x | | + | |
- | | | id (attribute: name) | frequency || x | x | x | x | x | x | | + | |
- | | || loci (attribute: name) //(when unaligned)// | + | |
- | | ||| genotype/ | + | |
- | | || genotype/ | + | |
- | ^^^^^^^^^^^ | + | |
- | | structure (attribute: name) | number_groups ||| o | o | o | o | o | | | + | |
- | | | group (attribute: name) //(sample name, sample name)// ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | distance_matrix (attribute: name) | size ||| o | o | o | o | o | | | + | |
- | | | lables ||| o | o | o | o | o | | | + | |
- | | | matrix ||| o | o | o | o | o | | | + | |
- | + | ||
- | x: obligatory\\ | + | |
- | o: optional\\ | + | |
- | a: alternative\\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | \\ | + | |
- | ==== 2. version: ==== | + | |
- | \\ | + | |
- | | ^^^^ data type ^^^^^^ | + | |
- | ^ block ^ subtags ^^^ standard ^ DNA ^ SNP ^ Microsattelite ^ RFLP (AFLP) ^ Allel frequency ^ | + | |
- | ^^^^^^^^^^^ | + | |
- | | header (attribute: title) | number_population ||| x | x | x | x | x | x | | + | |
- | | | data_type ||| x | x | x | x | x | x | | + | |
- | | | number_loci* | number || x | x | x | x | x | | | + | |
- | | || loci (attribute: name) | locations | o | o | o | o | o | | | + | |
- | | ||| length | o | o | o | o | o | | | + | |
- | | | missing ||| o | o | o | o | o | | | + | |
- | | | gap ||| o | o | o | o | o | | | + | |
- | | | gametic_phase ||| o | o | o | o | o | | | + | |
- | | | recessive_alleles ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | population (attribute: name) | size ||| x | x | x | x | x | x | | + | |
- | | | geographic_coord ||| o | o | o | o | o | o | | + | |
- | | | id (attribute: name) (a3) | frequency || x | x | x | x | x | x | | + | |
- | | || loci (attribute: name) //(when unaligned)// | + | |
- | | ||| begin | | + | |
- | | ||| length | | + | |
- | | ||| genotype/ | + | |
- | | || genotype/ | + | |
- | | | ind (attribute: name) (a3) | geographic_coord || o | o | o | o | o | o | | + | |
- | | || loci (attribute: name) //(when unaligned)// | + | |
- | | ||| begin | | + | |
- | | ||| length | | + | |
- | | ||| genotype/ | + | |
- | | || genotype/ | + | |
- | ^^^^^^^^^^^ | + | |
- | | structure (attribute: name) | number_groups ||| o | o | o | o | o | | | + | |
- | | | group (attribute: name) //(sample name, sample name)// ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | distance_matrix (attribute: name) | size ||| o | o | o | o | o | | | + | |
- | | | lables ||| o | o | o | o | o | | | + | |
- | | | matrix ||| o | o | o | o | o | | | + | |
- | + | ||
- | * when for all populations the same\\ | + | |
- | x: obligatory\\ | + | |
- | o: optional\\ | + | |
- | a: alternative to\\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | \\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | ==== 3. version: ==== | + | |
- | \\ | + | |
- | | ^^^^ data type ^^^^^^ | + | |
- | ^ block ^ subtags ^^^ standard ^ DNA ^ SNP ^ Microsattelite ^ RFLP (AFLP) ^ Allel frequency ^ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **header** (attribute: title) | number_populations ||| x | x | x | x | x | x | | + | |
- | | | data_type ||| x | x | x | x | x | x | | + | |
- | | | number_loci * | number || x | x | x | x | x | | | + | |
- | | || loci (attribute: name) | location | o | o | o | o | o | | | + | |
- | | ||| length | o | o | o | o | o | | | + | |
- | | | gene_copies * ||| x | x (a1) | x (a1) | x | x (a1) | | | + | |
- | | | aligned ||| x | x | x | x | x | | | + | |
- | | | genotypic_data ||| x | x | x | x | x | | | + | |
- | | | missing ||| x | x | x | x | x | | | + | |
- | | | gap ||| x | x | x | x | x | | | + | |
- | | | gametic_phase ||| o | o | o | o | o | | | + | |
- | | | recessive_alleles ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) | size ||| x | x | x | x | x | x | | + | |
- | | | geographic_coord ||| o | o | o | o | o | o | | + | |
- | | | linguistic_group ||| o | o | o | o | o | o | | + | |
- | | | id (attribute: name) (a3) | frequency || x | x | x | x | x | x | | + | |
- | | || genotype/ | + | |
- | | | ind (attribute: name) (a3) | geographic_coord || o | o | o | o | o | | | + | |
- | | || linguistic_group || o | o | o | o | o | | | + | |
- | | || loci (attribute: name) //(when unaligned)// | + | |
- | | ||| begin | | + | |
- | | ||| length | | + | |
- | | ||| gene_copies | | + | |
- | | ||| genotype/ | + | |
- | | || genotype/ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **structure** (attribute: name) | number_groups ||| o | o | o | o | o | o | | + | |
- | | | group (attribute: name) //(sample name, sample name, ...)// ||| o | o | o | o | o | o | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **distance_matrix** (attribute: name) | size ||| o | o | o | o | o | o | | + | |
- | | | labels ||| o | o | o | o | o | o | | + | |
- | | | matrix //(number (line break) | + | |
- | + | ||
- | * when for all populations the same\\ | + | |
- | x: obligatory\\ | + | |
- | o: optional\\ | + | |
- | a: alternative to\\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | \\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | ==== 4. version: ==== | + | |
- | \\ | + | |
- | | ^^^^ data type ^^^^^^ | + | |
- | ^ block ^ subtags ^^^ standard ^ DNA ^ SNP ^ Microsattelite ^ RFLP (AFLP) ^ Allel frequency ^ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **header** (attribute: title) | number_populations ||| x | x | x | x | x | x | | + | |
- | | | data_type ||| x | x | x | x | x | x | | + | |
- | | | number_loci * | number || x | x | x | x | x | | | + | |
- | | || loci (attribute: name) | location | o | o | o | o | o | | | + | |
- | | ||| length | o | o | o | o | o | | | + | |
- | | | number_strains * ||| x | x (a1) | x (a1) | x | x (a1) | | | + | |
- | | | aligned ||| x | x | x | x | x | | | + | |
- | | | genotypic_data ||| x | x | x | x | x | | | + | |
- | | | missing ||| x | x | x | x | x | | | + | |
- | | | gap ||| x | x | x | x | x | | | + | |
- | | | gametic_phase ||| o | o | o | o | o | | | + | |
- | | | recessive_alleles ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) //aligned// (a2) | size ||| x | x | x | x | x | x | | + | |
- | | | geographic_coord * ||| o (a4) | o (a4) | o (a4) | o (a4) | o (a4) | o | | + | |
- | | | linguistic_group * ||| o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | o | | + | |
- | | | number_strains * ||| o (a1) | o (a1) | o (a1) | o (a1) | o (a1) | | | + | |
- | | | id (attribute: name) (a3) | frequency || x | x | x | x | x | x | | + | |
- | | || genotype/ | + | |
- | | | ind (attribute: name) (a3) | geographic_coord || o (a4) | o (a4) | o (a4) | o (a4) | o | | | + | |
- | | || linguistic_group || o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | | | + | |
- | | || number_strains || x (a1) | x (a1) | x (a1) | x (a1) | x (a1) | | | + | |
- | | || genotype/ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) // | + | |
- | | | geographic_coord * ||| | o (a6) | o (a6) | | o (a6) | | | + | |
- | | | linguistic_group * ||| | o (a7) | o (a7) | | o (a7) | | | + | |
- | | | loci_location (attribute: name) * ||| | o (a8) | o (a8) | | o (a8) | | | + | |
- | | | number_strains * ||| | o (a9) | o (a9) | | o (a9) | | | + | |
- | | | ind (attribute: name) | geographic_coord || | o (a6)*< | + | |
- | | || linguistic_group || | o (a7)*< | + | |
- | | || loci_location (attribute: name)*< | + | |
- | | || number_strains || | x (a9) | x (a9) | | x (a9) | | | + | |
- | | || strain (attribute: name) | begin | | x | x | | x | | | + | |
- | | ||| length | | x | x | | x | | | + | |
- | | ||| genotype/ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **structure** (attribute: name) (o) | number_groups ||| x | x | x | x | x | x | | + | |
- | | | group (attribute: name) //(sample name, sample name, ...)// ||| x | x | x | x | x | x | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **distance_matrix** (attribute: name) (o) | size ||| x | x | x | x | x | x | | + | |
- | | | labels ||| x | x | x | x | x | x | | + | |
- | | | matrix //(number (line break) | + | |
- | + | ||
- | * when for all populations/ | + | |
- | *< | + | |
- | *< | + | |
- | x: obligatory\\ | + | |
- | o: optional\\ | + | |
- | a: alternative to\\ | + | |
- | + | ||
- | \\ | + | |
- | * **stylesheet: | + | |
- | + | ||
- | \\ | + | |
- | + | ||
- | + | ||
- | ==== 5. version: ==== | + | |
- | \\ | + | |
- | | ^^^^ data type ^^^^^^ | + | |
- | ^ block ^ subtags ^^^ standard ^ DNA ^ SNP ^ Microsattelite ^ RFLP (AFLP) ^ Allel frequency ^ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **header** (attribute: title) | nb_pop ||| x | x | x | x | x | x | | + | |
- | | | data_type ||| x | x | x | x | x | x | | + | |
- | | | loci (o) * | nb || x | x | x | x | x | | | + | |
- | | || locus (attribute: id) | location | x | x | x | x | x | | | + | |
- | | ||| length | o | o | o | o | o | | | + | |
- | | ||| links | o | o | o | o | o | | | + | |
- | | | nb_reads * ||| x (a1) | x (a1) | x (a1) | x (a1) | x (a1) | | | + | |
- | | | aligned ||| x | x | x | x | x | | | + | |
- | | | geno_data ||| x | x | x | x | x | | | + | |
- | | | missing ||| x | x | x | x | x | | | + | |
- | | | gap ||| x | x | x | x | x | | | + | |
- | | | gametic_phase ||| o | o | o | o | o | | | + | |
- | | | recessive_alleles ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **loci** (o) | nb ||| x | x | x | x | x | | | + | |
- | | | locus (attribute: id) | location || x | x | x | x | x | | | + | |
- | | || length || o | o | o | o | o | | | + | |
- | | || links || o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) //aligned, same data type// (a2) | size ||| x | x | x | x | x | x | | + | |
- | | | geo_coord * ||| o (a4) | o (a4) | o (a4) | o (a4) | o (a4) | o | | + | |
- | | | linguistic_group * ||| o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | o | | + | |
- | | | nb_reads * ||| x (a1) | x (a1) | x (a1) | x (a1) | x (a1) | | | + | |
- | | | loci //(locus, locus, | + | |
- | | | id (attribute: name) (a3) | freq || x | x | x | x | x | x | | + | |
- | | || geno/hap (attribute: name) //(locus, locus, | + | |
- | | | ind (attribute: name) (a3) | geo_coord || o (a4) | o (a4) | o (a4) | o (a4) | o | | | + | |
- | | || linguistic_group || o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | | | + | |
- | | || nb_reads || x (a1) | x (a1) | x (a1) | x (a1) | x (a1) | | | + | |
- | | || geno/hap (attribute: name) //(locus, locus, | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) // | + | |
- | | | geo_coord * ||| | o (a6) | o (a6) | | o (a6) | | | + | |
- | | | linguistic_group * ||| | o (a7) | o (a7) | | o (a7) | | | + | |
- | | | locus (attribute: id)* ||| | o (a8) | o (a8) | | o (a8) | | | + | |
- | | | nb_reads * ||| | o (a9) | o (a9) | | o (a9) | | | + | |
- | | | ind (attribute: name) | geo_coord || | o (a6)*< | + | |
- | | || linguistic_group || | o (a7)*< | + | |
- | | || locus (attribute: id)*< | + | |
- | | || nb_reads || | x (a9) | x (a9) | | x (a9) | | | + | |
- | | || read (attribute: name) | start | | x | x | | x | | | + | |
- | | ||| length | | x | x | | x | | | + | |
- | | ||| geno/hap | | x | x | | x | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **structure** (attribute: name) (o) | number_groups ||| x | x | x | x | x | x | | + | |
- | | | group (attribute: name) //(sample name, sample name, ...)// ||| x | x | x | x | x | x | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **distance_matrix** (attribute: name) (o) | size ||| x | x | x | x | x | x | | + | |
- | | | labels ||| x | x | x | x | x | x | | + | |
- | | | matrix //(number (line break) | + | |
- | + | ||
- | * when for all populations/ | + | |
- | *< | + | |
- | *< | + | |
- | + | ||
- | x: obligatory\\ | + | |
- | o: optional\\ | + | |
- | a: alternative to\\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | \\ | + | |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | ==== 6 version: ==== | + | |
- | \\ | + | |
- | | ^^^^ data type ^^^^^^ | + | |
- | ^ block ^ subtags ^^^ standard ^ DNA ^ SNP ^ Microsattelite ^ RFLP (AFLP) ^ Allel frequency ^ | + | |
- | ^^^^^^^^^^^ | + | |
- | | **header** (attribute: title) | organism ||| x | x | x | x | x | x | | + | |
- | | | numPop ||| x | x | x | x | x | x | | + | |
- | | | numReads * ||| x | x | x | x | x | | | + | |
- | | | aligned ||| x | x | x | x | x | | | + | |
- | | | missing ||| x | x | x | x | x | | | + | |
- | | | gap ||| x | x | x | x | x | | | + | |
- | | | gameticPhase ||| o | o | o | o | o | | | + | |
- | | | recessiveData ||| o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **loci** (o) | lociNum ||| x | x | x | x | x | | | + | |
- | | | lociDataType * ||| x (a10) | x (a10) | x (a10) | x (a10) | x (a10) | x | | + | |
- | | | locus (attribute: id) | locusDataType || a10 | a10 | a10 | a10 | a10 | | | + | |
- | | || locusChromosom || o | o | o | o | o | | | + | |
- | | || locusLocation || o | o | o | o | o | | | + | |
- | | || locusGenic || o | o | o | o | o | | | + | |
- | | || locusLength || o | o | o | o | o | | | + | |
- | | || locusLinks || o | o | o | o | o | | | + | |
- | | || locusComments || o | o | o | o | o | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) //aligned, same data type// (a2) | popSize ||| x | x | x | x | x | x | | + | |
- | | | popGeogCoord * ||| o (a4) | o (a4) | o (a4) | o (a4) | o (a4) | o | | + | |
- | | | popLingGroup * ||| o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | o | | + | |
- | | | popNumReads * ||| x (a1) | x (a1) | x (a1) | x (a1) | x (a1) | | | + | |
- | | | popLoci //(locus, locus, | + | |
- | | | ind (attribute: name) (a3) | indGeogCoord || o (a4) | o (a4) | o (a4) | o (a4) | o | | | + | |
- | | || indLingGroup || o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | | | + | |
- | | || indNumReads || a1 | a1 | a1 | a1 | a1 | | | + | |
- | | || indFreq //(absolute Freq)// || o | o | o | o | o | x | | + | |
- | | || data //(locus, locus, | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) //aligned, diff data type// (a2) | popSize ||| x | x | x | x | x | | | + | |
- | | | popGeogCoord * ||| o (a4) | o (a4) | o (a4) | o (a4) | o (a4) | | | + | |
- | | | popLingGroup * ||| o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | | | + | |
- | | | popNumReads * ||| x (a1) | x (a1) | x (a1) | x (a1) | x (a1) | | | + | |
- | | | ind (attribute: name) (a3) | indGeogCoord || o (a4) | o (a4) | o (a4) | o (a4) | o | | | + | |
- | | || indLingGroup || o (a5) | o (a5) | o (a5) | o (a5) | o (a5) | | | + | |
- | | || indLoci //(locus, locus, | + | |
- | | || indNumReads || a1 | a1 | a1 | a1 | a1 | | | + | |
- | | || indFreq //(absolute Freq)// || o | o | o | o | o | x | | + | |
- | | || data //(locus, locus, | + | |
- | ^^^^^^^^^^^ | + | |
- | | **population** (attribute: name) // | + | |
- | | | popGeogCoord * ||| | o (a6) | | | | | | + | |
- | | | popLingGroup * ||| | o (a7) | | | | | | + | |
- | | | popNumReads * ||| | x (a9) | | | | | | + | |
- | | | popLocus * ||| | o (a8) | | | | | | + | |
- | | | ind (attribute: name) | indGeogCoord || | o (a6)*< | + | |
- | | || indLingGroup || | o (a7)*< | + | |
- | | || indLocus *< | + | |
- | | || indFreq //(absolute Freq)// || | o | | | | | | + | |
- | | || indNumReads || | a9 | | | | | | + | |
- | | || read | start | | x (if unalig.) | + | |
- | | ||| length | | o | | | | | | + | |
- | | ||| data | | x | | | | | | + | |
- | ^^^^^^^^^^^ | + | |
- | | **structure** (attribute: name) (o) | numGroups ||| x | x | x | x | x | x | | + | |
- | | | group (attribute: name) //(sample name, sample name, ...)*< | + | |
- | ^^^^^^^^^^^ | + | |
- | | **distanceMatrix** (attribute: name) (o) | matrixSize ||| x | x | x | x | x | x | | + | |
- | | | matrixLabels //(name, name,...)// ||| x | x | x | x | x | x | | + | |
- | | | matrix //(number (line break) | + | |
- | + | ||
- | * when for all populations/ | + | |
- | *< | + | |
- | *< | + | |
- | *< | + | |
- | + | ||
- | x: obligatory\\ | + | |
- | o: optional\\ | + | |
- | a: alternative to\\ | + | |
- | + | ||
- | \\ | + | |
- | * stylesheet: {{stylesheet_data-format3.pdf|}} | + | |
data_format.txt · Last modified: 2009/03/02 14:05 by heidi