| Next changeset 1:64e681a1cad5 (2017-12-06) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/structure commit b4d0a8f3dfee920840c77befdf626c52a5d617cb |
|
added:
structure.xml test-data/testdata1 test-data/testdata1_f |
| b |
| diff -r 000000000000 -r a1574aada200 structure.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/structure.xml Wed Nov 15 16:31:24 2017 -0500 |
| [ |
| b'@@ -0,0 +1,536 @@\n+<tool id="structure" name="Structure" version="2.3.4">\n+ <description>using multi-locus genotype data to investigate population structure</description>\n+ <requirements>\n+ <requirement type="package" version="2.3.4">structure</requirement>\n+ </requirements>\n+ <version_command><![CDATA[\n+ structure | grep -E -o \'Version.+\'\n+ ]]></version_command>\n+ <command detect_errors="exit_code"><![CDATA[\n+ mv \'$mainparams\' \'$out_mainparams\' &&\n+ mv \'$extraparams\' \'$out_extraparams\' &&\n+\n+ mkdir out log\n+\n+ #for $run in range(1, int($nb_run) + 1):\n+ && structure -i \'$infile\' -o outfile -m \'$out_mainparams\' -e \'$out_extraparams\' > \'log/run${run}_K_${main.MAXPOPS}.log\'\n+ && mv \'outfile_f\' \'out/run${run}_K_${main.MAXPOPS}.out\'\n+ #end for\n+\n+ ]]></command>\n+ <configfiles>\n+ <configfile name="mainparams"><![CDATA[\n+KEY PARAMETERS FOR THE PROGRAM structure. YOU WILL NEED TO SET THESE\n+IN ORDER TO RUN THE PROGRAM. VARIOUS OPTIONS CAN BE ADJUSTED IN THE\n+FILE extraparams.\n+\n+\n+"(int)" means that this takes an integer value.\n+"(B)" means that this variable is Boolean\n+ (ie insert 1 for True, and 0 for False)\n+"(str)" means that this is a string (but not enclosed in quotes!)\n+\n+\n+Basic Program Parameters\n+\n+#define MAXPOPS $main.MAXPOPS // default:2 // (int) number of populations assumed\n+#define BURNIN $main.BURNIN // default:10000 // (int) length of burnin period\n+#define NUMREPS $main.NUMREPS // default:20000 // (int) number of MCMC reps after burnin\n+\n+Input/Output files\n+\n+#define INFILE $infile // (str) name of input data file\n+#define OUTFILE outfile //(str) name of output data file\n+\n+Data file format\n+\n+#define NUMINDS $main.NUMINDS // default:100 // (int) number of diploid individuals in data file\n+#define NUMLOCI $main.NUMLOCI // default:100 // (int) number of loci in data file\n+#define PLOIDY $main.PLOIDY // default:2 // (int) ploidy of data\n+#define MISSING $main.MISSING // default:-9 // (int) value given to missing genotype data\n+#define ONEROWPERIND $main.ONEROWPERIND // default:0 // (B) store data for individuals in a single line\n+\n+\n+#define LABEL $main.LABEL // default:1 // (B) Input file contains individual labels\n+#define POPDATA $main.POPDATA // default:1 // (B) Input file contains a population identifier\n+#define POPFLAG ${extra.usepopinfo_cond.POPFLAG} // default:0 // (B) Input file contains a flag which says\n+ whether to use popinfo when USEPOPINFO==1\n+#define LOCDATA $main.LOCDATA // default:0 // (B) Input file contains a location identifier\n+\n+#define PHENOTYPE $main.PHENOTYPE // default:0 // (B) Input file contains phenotype information\n+#define EXTRACOLS $main.EXTRACOLS // default:0 // (int) Number of additional columns of data\n+ before the genotype data start.\n+\n+#define MARKERNAMES $main.MARKERNAMES // default:1 // (B) data file contains row of marker names\n+#define RECESSIVEALLELES $main.recessivealleles_cond.RECESSIVEALLELES // default:0 // (B) data file contains dominant markers (eg AFLPs)\n+ // and a row to indicate which alleles are recessive\n+#define MAPDISTANCES $main.MAPDISTANCES // default:0 // (B) data file contains row of map distances\n+ // between loci\n+\n+\n+Advanced data file options\n+\n+#define PHASED $main.PHASED // default:0 // (B) Data are in correct phase (relevant for linkage model only)\n+#define PHASEINFO $main.PHASEINFO // default:0 // (B) the data for each individual contains a line\n+ indicating phase (linkage model)\n+#define MARKOVPHASE $main.MARKOVPHASE // default:0 // (B) the phase info follows a Markov model.\n+#define NOTAMBIGUOUS $main.recessivealleles_cond.NOTAMBIGUOUS // default:-999'..b'+ </tests>\n+ <help><![CDATA[\n+**Introduction**\n+\n+The program structure_ implements a model-based clustering method for inferring population structure\n+using genotype data consisting of unlinked markers. The method was introduced in a paper\n+by Pritchard, Stephens and Donnelly (2000a) and extended in sequels by Falush, Stephens and\n+Pritchard (2003a, 2007). Applications of our method include demonstrating the presence of population\n+structure, identifying distinct genetic populations, assigning individuals to populations, and\n+identifying migrants and admixed individuals.\n+\n+Briefly, we assume a model in which there are K populations (where K may be unknown),\n+each of which is characterized by a set of allele frequencies at each locus. Individuals in the\n+sample are assigned (probabilistically) to populations, or jointly to two or more populations if their\n+genotypes indicate that they are admixed. It is assumed that within populations, the loci are at\n+Hardy-Weinberg equilibrium, and linkage equilibrium. Loosely speaking, individuals are assigned\n+to populations in such a way as to achieve this.\n+\n+Our model does not assume a particular mutation process, and it can be applied to most of the\n+commonly used genetic markers including microsatellites, SNPs and RFLPs. The model assumes\n+that markers are not in linkage disequilibrium (LD) within subpopulations, so we can\xe2\x80\x99t handle\n+markers that are extremely close together. Starting with version 2.0, we can now deal with weakly\n+linked markers.\n+\n+While the computational approaches implemented here are fairly powerful, some care is needed\n+in running the program in order to ensure sensible answers. For example, it is not possible to\n+determine suitable run-lengths theoretically, and this requires some experimentation on the part of\n+the user. This document describes the use and interpretation of the software and supplements the\n+published papers, which provide more formal descriptions and evaluations of the methods.\n+\n+.. _structure: https://web.stanford.edu/group/pritchardlab/structure.html\n+\n+**Documentation**\n+\n+Please see the full Sructure documentation_\n+\n+.. _documentation: https://web.stanford.edu/group/pritchardlab/structure_software/release_versions/v2.3.4/structure_doc.pdf\n+\n+**Upstream**\n+\n+Inputs can be produced from:\n+\n+- Microsatellite analysis\n+- RADSeq analysis (eg: using populations_ from Stacks suite)\n+\n+.. _populations: http://catchenlab.life.illinois.edu/stacks/manual/#export\n+\n+**Input**\n+\n+======= === ===== ===== ===== ===== =====\n+ loc_a loc_b loc_c loc_d loc_e\n+======= === ===== ===== ===== ===== =====\n+George 1 -9 145 66 0 92\n+George 1 -9 -9 64 0 94\n+Paula 1 106 142 68 1 92\n+Paula 1 106 148 64 0 94\n+Matthew 2 110 145 -9 0 92\n+Matthew 2 110 148 66 1 -9\n+Bob 2 108 142 64 1 94\n+Bob 2 -9 142 -9 0 94\n+Anja 1 112 142 -9 1 -9\n+Anja 1 114 142 66 1 94\n+Peter 1 -9 145 66 0 -9\n+Peter 1 110 145 -9 1 -9\n+Carsten 2 108 145 62 0 -9\n+Carsten 2 110 145 64 1 92\n+======= === ===== ===== ===== ===== =====\n+\n+You will find other sample data sets: here_\n+\n+.. _here: https://web.stanford.edu/group/pritchardlab/structure_software/release_versions/v2.3.4/html/structure-data.html\n+\n+**Downstream**\n+\n+- Clumpp_\n+- Distruct_\n+- Structure-harvester_\n+\n+.. _Clumpp: https://rosenberglab.stanford.edu/clumpp.html\n+.. _Distruct: https://rosenberglab.stanford.edu/distruct.html\n+.. _Structure-harvester: http://taylor0.biology.ucla.edu/structureHarvester/\n+\n+ ]]></help>\n+ <citations>\n+ <citation type="doi">10.1111/j.1471-8286.2007.01758.x</citation>\n+ <citation type="doi">10.1111/j.1755-0998.2009.02591.x</citation>\n+ </citations>\n+</tool>\n' |
| b |
| diff -r 000000000000 -r a1574aada200 test-data/testdata1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/testdata1 Wed Nov 15 16:31:24 2017 -0500 |
| b |
| b'@@ -0,0 +1,400 @@\n+1 1 0 0 1 3 8 9\n+1 1 0 1 -1 -1 7 -3\n+2 1 0 -1 2 2 6 7\n+2 1 0 0 5 0 9 7\n+3 1 0 -1 2 0 2 8\n+3 1 0 0 2 4 10 9\n+4 1 0 -1 2 -1 8 6\n+4 1 0 -1 -2 0 9 9\n+5 1 0 0 1 3 7 8\n+5 1 0 -1 2 1 5 7\n+6 1 0 3 3 -1 7 6\n+6 1 0 -1 6 0 5 8\n+7 1 0 -1 3 -1 5 9\n+7 1 0 1 3 -1 8 -3\n+8 1 0 -2 6 -1 7 7\n+8 1 0 -1 -1 3 8 8\n+9 1 0 0 3 0 14 7\n+9 1 0 -1 2 3 6 6\n+10 1 0 -1 3 2 5 8\n+10 1 0 1 2 2 8 8\n+11 1 0 2 0 3 9 7\n+11 1 0 0 2 0 5 6\n+12 1 0 1 3 2 7 3\n+12 1 0 -1 1 -1 7 7\n+13 1 0 -1 5 -1 4 5\n+13 1 0 1 -1 2 7 9\n+14 1 0 1 3 2 10 7\n+14 1 0 1 2 2 8 7\n+15 1 0 -3 5 3 10 6\n+15 1 0 -1 7 -1 8 7\n+16 1 0 0 3 3 4 7\n+16 1 0 1 5 -1 8 7\n+17 1 0 1 2 2 9 3\n+17 1 0 -1 3 -1 2 -3\n+18 1 0 0 5 2 10 -2\n+18 1 0 0 -1 2 7 7\n+19 1 0 1 6 -1 5 8\n+19 1 0 2 6 -1 2 5\n+20 1 0 1 -1 3 14 -1\n+20 1 0 -1 2 0 2 6\n+21 1 0 -1 2 -1 8 8\n+21 1 0 1 6 0 2 7\n+22 1 0 -1 3 3 14 -3\n+22 1 0 1 2 0 8 3\n+23 1 0 2 5 2 7 5\n+23 1 0 0 2 0 8 7\n+24 1 0 -1 2 0 2 8\n+24 1 0 1 1 0 2 8\n+25 1 0 -1 2 0 6 -3\n+25 1 0 -1 0 5 10 7\n+26 1 0 2 3 0 10 8\n+26 1 0 2 7 0 7 8\n+27 1 0 1 2 -1 10 7\n+27 1 0 1 3 -1 10 8\n+28 1 0 -1 2 2 8 5\n+28 1 0 -1 -1 3 6 -1\n+29 1 0 2 2 5 10 -3\n+29 1 0 -1 2 1 7 9\n+30 1 0 1 7 0 10 7\n+30 1 0 0 3 3 10 7\n+31 1 0 0 3 0 10 8\n+31 1 0 -1 3 1 8 7\n+32 1 0 1 2 3 7 8\n+32 1 0 -1 2 3 10 -1\n+33 1 0 -1 0 -1 7 6\n+33 1 0 1 2 0 7 9\n+34 1 0 -3 3 0 5 7\n+34 1 0 -1 2 -1 4 8\n+35 1 0 -1 6 2 7 9\n+35 1 0 -1 2 2 10 7\n+36 1 0 0 5 0 14 6\n+36 1 0 1 2 2 6 5\n+37 1 0 1 7 4 8 9\n+37 1 0 0 5 3 10 8\n+38 1 0 -1 -2 2 8 -3\n+38 1 0 2 6 2 6 7\n+39 1 0 1 0 1 14 9\n+39 1 0 1 2 3 8 7\n+40 1 0 2 2 2 5 -2\n+40 1 0 0 -1 3 4 7\n+41 1 0 -1 7 0 2 8\n+41 1 0 -1 5 0 13 8\n+42 1 0 -1 2 -1 9 -2\n+42 1 0 0 2 3 14 9\n+43 1 0 1 6 1 4 8\n+43 1 0 0 1 0 5 6\n+44 1 0 -1 2 0 10 8\n+44 1 0 2 4 0 4 5\n+45 1 0 -1 3 2 5 7\n+45 1 0 -3 3 0 9 7\n+46 1 0 -1 3 2 10 7\n+46 1 0 -1 2 2 8 8\n+47 1 0 0 2 4 10 8\n+47 1 0 1 2 -1 5 5\n+48 1 0 3 1 2 10 7\n+48 1 0 1 2 0 6 8\n+49 1 0 0 -1 0 7 7\n+49 1 0 2 0 -1 14 6\n+50 1 0 1 6 3 5 6\n+50 1 0 2 3 3 5 7\n+51 1 1 -1 3 3 9 8\n+51 1 1 -1 2 2 10 8\n+52 1 1 -1 5 0 8 7\n+52 1 1 -1 1 2 7 7\n+53 1 1 0 3 2 9 7\n+53 1 1 -3 -1 5 6 8\n+54 1 1 -1 3 4 7 -3\n+54 1 1 2 -2 0 10 -3\n+55 1 1 0 2 0 13 7\n+55 1 1 1 -1 1 10 5\n+56 1 1 0 3 3 14 8\n+56 1 1 -1 -2 -1 10 7\n+57 1 1 2 4 2 7 9\n+57 1 1 2 2 -1 7 7\n+58 1 1 0 2 0 5 9\n+58 1 1 -1 3 -3 13 4\n+59 1 1 3 5 0 9 -3\n+59 1 1 2 4 2 7 -3\n+60 1 1 -2 2 3 8 9\n+60 1 1 0 1 1 10 -1\n+61 1 1 -1 -1 2 14 7\n+61 1 1 -2 5 4 10 -3\n+62 1 1 2 5 4 10 -3\n+62 1 1 2 2 0 6 8\n+63 1 1 2 3 -2 10 8\n+63 1 1 0 5 -1 10 -1\n+64 1 1 -1 2 0 5 8\n+64 1 1 0 3 -2 6 -4\n+65 1 1 0 2 3 10 7\n+65 1 1 1 2 0 8 -1\n+66 1 1 -1 4 1 7 -1\n+66 1 1 -1 2 -1 9 5\n+67 1 1 0 2 1 14 8\n+67 1 1 -1 2 -1 5 8\n+68 1 1 -1 3 -1 10 7\n+68 1 1 0 3 -1 10 7\n+69 1 1 1 2 3 5 3\n+69 1 1 1 4 4 9 7\n+70 1 1 -1 -1 0 14 -3\n+70 1 1 -1 -2 0 10 -3\n+71 1 1 1 1 1 10 5\n+71 1 1 -3 2 2 13 5\n+72 1 1 0 -1 3 4 7\n+72 1 1 1 -1 -1 8 5\n+73 1 1 2 6 3 8 7\n+73 1 1 2 6 3 6 6\n+74 1 1 -3 1 2 7 5\n+74 1 1 2 -1 0 5 8\n+75 1 1 -1 4 3 10 6\n+75 1 1 -3 3 -1 7 9\n+76 1 1 -1 2 3 9 7\n+76 1 1 2 2 0 8 6\n+77 1 1 0 -1 1 10 7\n+77 1 1 -1 3 0 10 9\n+78 1 1 2 3 3 7 7\n+78 1 1 2 3 2 7 8\n+79 1 1 -1 -1 -2 8 5\n+79 1 1 -1 2 3 10 8\n+80 1 1 2 -3 1 10 8\n+80 1 1 -1 6 4 7 -3\n+81 1 1 1 3 0 2 7\n+81 1 1 -1 2 3 4 -3\n+82 1 1 2 -1 1 14 8\n+82 1 1 -1 2 3 10 -1\n+83 1 1 0 5 -1 8 -3\n+83 1 1 -1 6 2 4 7\n+84 1 1 0 -3 2 8 -2\n+84 1 1 1 3 4 14 9\n+85 1 1 -1 3 2 8 -3\n+85 1 1 -1 3 2 4 7\n+86 1 1 -1 -1 0 13 8\n+86 1 1 -1 -1 3 10 7\n+87 1 1 -1 5 -1 9 8\n+87 1 1 1 3 -1 6 -3\n+88 1 1 1 2 2 5 5\n+88 1 1 -1 6 4 10 -2\n+89 1 1 0 2 3 14 7\n+89 1 1 0 -1 0 7 8\n+90 1 1 0 3 3 8 7\n+90 1 1 3 3 -1 9 7\n+91 1 1 1 -1 2 10 7\n+91 1 1 1 1 0 5 5\n+92 1 1 2 5 1 5 5\n+92 1 1 1 5 -1 10 -3\n+93 1 1 -1 3 4 9 -2\n+93 1 1 3 4 3 10 8\n+94 1 1 3 1 -1 8 7\n+94 1 1 0 -1 2 10 8\n+95 1 1 3 2 3 5 7\n+95 1 1 1 2 1 8 7\n+96 1 1 1 -1 3 8 8\n+96 1 1 0 2 2 10 -2\n+97 1 1 2 3 2 10 7\n+97 1 1 0 2 0 9 7\n+98 1 1 -1 2 3 8 7\n+98 1 1 -1 -1 0 8 -2\n+99 1 1 3 0 -1 8 8\n+99 1 1 -1 3 -1 14 7\n+100 1 1 -1 6 0 6 7\n+100 1 1 -1 2 2 2 -3\n+101 2 0 -2 1 1 5 -2\n+101 2 0 -4 2 4 3 7\n+102 2 0 -3 -2 2 8 -3\n+102 2 0 2 2 4 5 -3\n+103 2 0 2 3 2 5 -2\n+103 2 0 -2 2 4 15 -2\n+104 2 0 '..b'1 1 17 7\n+106 2 0 -3 5 4 15 -2\n+106 2 0 -3 2 3 6 -1\n+107 2 0 1 -3 3 17 7\n+107 2 0 1 2 3 7 -3\n+108 2 0 -4 -3 1 5 6\n+108 2 0 -2 -1 3 6 -3\n+109 2 0 -3 3 5 7 -1\n+109 2 0 -3 1 2 17 4\n+110 2 0 1 2 7 6 -3\n+110 2 0 -4 -4 1 4 -3\n+111 2 0 -2 0 1 5 -4\n+111 2 0 1 -4 3 7 5\n+112 2 0 0 5 5 4 -5\n+112 2 0 1 -4 3 7 -2\n+113 2 0 2 1 5 7 7\n+113 2 0 -2 1 0 15 7\n+114 2 0 1 -4 1 9 4\n+114 2 0 -1 0 4 16 4\n+115 2 0 2 -3 1 6 5\n+115 2 0 2 2 1 5 -3\n+116 2 0 1 2 4 6 6\n+116 2 0 -2 -2 3 17 -4\n+117 2 0 -2 2 0 3 -2\n+117 2 0 -3 1 4 5 -3\n+118 2 0 -3 2 0 17 6\n+118 2 0 -4 -3 1 17 -1\n+119 2 0 2 5 0 5 5\n+119 2 0 -3 2 4 5 4\n+120 2 0 1 2 1 6 -2\n+120 2 0 -1 -3 1 14 -4\n+121 2 0 1 0 3 3 -3\n+121 2 0 0 1 1 15 -2\n+122 2 0 -2 2 7 6 -1\n+122 2 0 -3 -4 4 5 6\n+123 2 0 1 -3 7 15 5\n+123 2 0 -5 -1 1 6 -3\n+124 2 0 -1 -3 0 7 -2\n+124 2 0 -3 2 4 5 4\n+125 2 0 -4 3 4 15 4\n+125 2 0 -3 2 1 14 -3\n+126 2 0 1 -4 0 5 -1\n+126 2 0 -3 -4 7 14 -2\n+127 2 0 1 -4 4 6 -3\n+127 2 0 1 2 1 15 -2\n+128 2 0 1 2 1 15 -1\n+128 2 0 -1 1 3 6 -4\n+129 2 0 -5 -4 1 15 -3\n+129 2 0 3 -4 3 17 4\n+130 2 0 1 1 4 6 -1\n+130 2 0 -2 2 2 14 6\n+131 2 0 -3 3 0 14 -3\n+131 2 0 -4 1 0 5 1\n+132 2 0 -4 2 6 17 7\n+132 2 0 -2 3 4 15 5\n+133 2 0 -2 3 4 14 7\n+133 2 0 -2 2 -1 15 -2\n+134 2 0 -2 -3 2 16 6\n+134 2 0 0 3 3 9 4\n+135 2 0 -3 2 0 5 7\n+135 2 0 -3 -4 1 6 4\n+136 2 0 2 -4 1 15 -2\n+136 2 0 -2 2 1 14 -2\n+137 2 0 1 -4 0 14 7\n+137 2 0 -1 1 1 6 -1\n+138 2 0 -3 5 0 17 1\n+138 2 0 -3 1 4 15 4\n+139 2 0 2 2 1 17 2\n+139 2 0 1 1 3 6 -4\n+140 2 0 -2 2 4 5 -1\n+140 2 0 -2 -4 1 3 4\n+141 2 0 3 -3 1 3 4\n+141 2 0 0 0 0 6 4\n+142 2 0 -4 2 4 5 -2\n+142 2 0 1 3 0 16 3\n+143 2 0 -5 -3 6 15 -3\n+143 2 0 1 -4 7 15 5\n+144 2 0 2 1 5 7 -2\n+144 2 0 1 -3 1 5 5\n+145 2 0 -3 2 3 15 5\n+145 2 0 1 -4 1 17 7\n+146 2 0 -4 2 1 15 -2\n+146 2 0 -3 -4 0 15 -1\n+147 2 0 1 5 3 6 5\n+147 2 0 1 2 4 3 5\n+148 2 0 -2 -3 0 17 -3\n+148 2 0 -3 -4 5 6 6\n+149 2 0 -3 2 0 17 -2\n+149 2 0 -4 2 4 6 -3\n+150 2 0 -2 -1 5 5 -3\n+150 2 0 1 1 1 14 6\n+151 2 1 2 -3 1 5 -2\n+151 2 1 -3 -4 1 14 3\n+152 2 1 1 2 2 15 -1\n+152 2 1 2 2 2 5 7\n+153 2 1 -4 2 3 14 -2\n+153 2 1 1 -4 1 16 4\n+154 2 1 -2 3 3 17 4\n+154 2 1 2 1 4 3 -4\n+155 2 1 1 3 5 14 -3\n+155 2 1 -1 3 2 6 1\n+156 2 1 2 3 1 17 -2\n+156 2 1 -3 1 2 14 -4\n+157 2 1 -4 2 0 14 -3\n+157 2 1 2 2 3 17 -4\n+158 2 1 -3 2 4 6 7\n+158 2 1 0 2 3 15 -2\n+159 2 1 1 1 1 14 7\n+159 2 1 -2 1 1 5 -2\n+160 2 1 -3 2 1 15 -4\n+160 2 1 -2 -3 3 14 5\n+161 2 1 -1 2 0 5 5\n+161 2 1 -2 -3 0 5 -4\n+162 2 1 1 -1 0 17 4\n+162 2 1 -4 -1 1 5 -2\n+163 2 1 1 2 0 5 -1\n+163 2 1 -4 1 0 5 -2\n+164 2 1 -3 1 0 16 -3\n+164 2 1 1 2 1 7 -3\n+165 2 1 -4 1 2 5 1\n+165 2 1 -2 -3 1 15 6\n+166 2 1 -2 1 3 5 -3\n+166 2 1 -1 -4 1 14 6\n+167 2 1 -4 1 1 15 -2\n+167 2 1 -1 2 2 15 -2\n+168 2 1 1 0 7 3 -2\n+168 2 1 1 2 1 5 -3\n+169 2 1 -3 -4 1 14 -3\n+169 2 1 -2 -4 1 15 -3\n+170 2 1 0 -4 0 5 7\n+170 2 1 1 -4 3 17 -2\n+171 2 1 -3 2 1 6 -2\n+171 2 1 -2 2 4 5 4\n+172 2 1 -2 2 3 14 1\n+172 2 1 -3 2 4 3 0\n+173 2 1 -3 2 4 17 1\n+173 2 1 -3 2 1 17 -3\n+174 2 1 1 -4 3 16 -3\n+174 2 1 -1 3 3 6 7\n+175 2 1 -4 2 3 17 7\n+175 2 1 -2 3 0 6 -3\n+176 2 1 1 -4 3 3 5\n+176 2 1 0 -4 1 5 -2\n+177 2 1 1 3 0 5 -3\n+177 2 1 -2 -4 4 14 -3\n+178 2 1 1 2 1 16 -1\n+178 2 1 1 -1 3 15 -2\n+179 2 1 1 -3 0 17 4\n+179 2 1 -4 2 4 3 -4\n+180 2 1 2 0 1 6 -2\n+180 2 1 -2 2 3 17 -2\n+181 2 1 -3 2 4 16 -2\n+181 2 1 -4 1 4 8 -3\n+182 2 1 0 2 1 3 -3\n+182 2 1 1 3 4 6 -1\n+183 2 1 -2 2 -1 17 -2\n+183 2 1 -3 -3 7 14 -3\n+184 2 1 1 1 1 3 5\n+184 2 1 2 1 1 6 4\n+185 2 1 -4 -4 3 7 -2\n+185 2 1 1 3 1 17 2\n+186 2 1 -1 3 4 14 -2\n+186 2 1 -3 -3 2 5 -2\n+187 2 1 0 2 4 15 -2\n+187 2 1 -2 2 1 16 -4\n+188 2 1 -2 2 3 17 -2\n+188 2 1 -4 1 4 7 -4\n+189 2 1 -1 -3 2 15 5\n+189 2 1 -3 -3 3 9 4\n+190 2 1 -3 2 1 17 -2\n+190 2 1 -2 -4 0 14 -4\n+191 2 1 1 3 2 15 6\n+191 2 1 2 1 1 5 -1\n+192 2 1 -3 5 1 7 -3\n+192 2 1 3 2 3 6 -2\n+193 2 1 -2 -3 4 9 -4\n+193 2 1 -4 3 0 5 -3\n+194 2 1 -4 2 7 5 4\n+194 2 1 1 2 1 8 5\n+195 2 1 1 2 3 3 -1\n+195 2 1 -2 2 1 17 5\n+196 2 1 -2 3 5 15 -2\n+196 2 1 1 2 1 7 -4\n+197 2 1 -2 1 0 5 -3\n+197 2 1 -1 2 5 14 5\n+198 2 1 2 1 3 6 6\n+198 2 1 -3 3 -1 5 -2\n+199 2 1 -3 1 3 6 5\n+199 2 1 -3 5 1 5 -2\n+200 2 1 -3 1 1 16 -3\n+200 2 1 1 5 4 15 5\n' |
| b |
| diff -r 000000000000 -r a1574aada200 test-data/testdata1_f --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/testdata1_f Wed Nov 15 16:31:24 2017 -0500 |
| [ |
| b'@@ -0,0 +1,347 @@\n+\n+\n+----------------------------------------------------\n+STRUCTURE by Pritchard, Stephens and Donnelly (2000)\n+ and Falush, Stephens and Pritchard (2003)\n+ Code by Pritchard, Falush and Hubisz\n+ Version 2.3.4 (Jul 2012)\n+----------------------------------------------------\n+\n+\n+\n+Command line arguments: structure -i /tmp/tmpd8muoH/files/000/dataset_1.dat -o outfile -m /tmp/tmpd8muoH/job_working_directory/000/2/tmpKOW8yP -e /tmp/tmpd8muoH/job_working_directory/000/2/tmpLDe27N \n+Input File: /tmp/tmpd8muoH/files/000/dataset_1.dat\n+\n+Run parameters:\n+ 200 individuals\n+ 5 loci\n+ 2 populations assumed\n+ 10000 Burn-in period\n+ 20000 Reps\n+RANDOMIZE turned off\n+\n+\n+--------------------------------------------\n+Proportion of membership of each pre-defined\n+ population in each of the 2 clusters\n+\n+Given Inferred Clusters Number of\n+ Pop 1 2 Individuals\n+\n+ 1: 0.033 0.967 100\n+ 2: 0.961 0.039 100\n+--------------------------------------------\n+\n+Allele-freq. divergence among pops (Net nucleotide distance),\n+computed using point estimates of P.\n+\n+ 1 2 \n+ 1 - 0.0691 \n+ 2 0.0691 - \n+\n+Average distances (expected heterozygosity) between individuals in same cluster:\n+cluster 1 : 0.8378 \n+cluster 2 : 0.8195 \n+\n+--------------------------------------------\n+Estimated Ln Prob of Data = -3966.7\n+Mean value of ln likelihood = -3924.5\n+Variance of ln likelihood = 84.4\n+Mean value of alpha = 0.0428\n+\n+Mean value of Fst_1 = 0.0712\n+Mean value of Fst_2 = 0.0966\n+\n+\n+Inferred ancestry of individuals:\n+ Label (%Miss) Pop: Inferred clusters\n+ 1 1 (0) 1 : 0.016 0.984 \n+ 2 2 (0) 1 : 0.011 0.989 \n+ 3 3 (0) 1 : 0.010 0.990 \n+ 4 4 (0) 1 : 0.008 0.992 \n+ 5 5 (0) 1 : 0.044 0.956 \n+ 6 6 (0) 1 : 0.009 0.991 \n+ 7 7 (0) 1 : 0.011 0.989 \n+ 8 8 (0) 1 : 0.021 0.979 \n+ 9 9 (0) 1 : 0.036 0.964 \n+ 10 10 (0) 1 : 0.009 0.991 \n+ 11 11 (0) 1 : 0.047 0.953 \n+ 12 12 (0) 1 : 0.016 0.984 \n+ 13 13 (0) 1 : 0.008 0.992 \n+ 14 14 (0) 1 : 0.009 0.991 \n+ 15 15 (0) 1 : 0.012 0.988 \n+ 16 16 (0) 1 : 0.008 0.992 \n+ 17 17 (0) 1 : 0.012 0.988 \n+ 18 18 (0) 1 : 0.012 0.988 \n+ 19 19 (0) 1 : 0.009 0.991 \n+ 20 20 (0) 1 : 0.040 0.960 \n+ 21 21 (0) 1 : 0.007 0.993 \n+ 22 22 (0) 1 : 0.048 0.952 \n+ 23 23 (0) 1 : 0.010 0.990 \n+ 24 24 (0) 1 : 0.012 0.988 \n+ 25 25 (0) 1 : 0.041 0.959 \n+ 26 26 (0) 1 : 0.006 0.994 \n+ 27 27 (0) 1 : 0.008 0.992 \n+ 28 28 (0) 1 : 0.024 0.976 \n+ 29 29 (0) 1 : 0.051 0.949 \n+ 30 30 (0) 1 : 0.007 0.993 \n+ 31 31 (0) 1 : 0.009 0.991 \n+ 32 32 (0) 1 : 0.019 0.981 \n+ 33 33 (0) 1 : 0.013 0.987 \n+ 34 34 (0) 1 : 0.022 0.978 \n+ 35 35 (0) 1 : 0.006 0.994 \n+ 36 36 (0) 1 : 0.173 0.827 \n+ 37 37 (0) 1 : 0.008 0.992 \n+ 38 38 (0) 1 : 0.010 0.990 \n+ 39 39 (0) 1 : 0.062 0.938 \n+ 40 40 (0) 1 : 0.044 0.956 \n+ 41 41 (0) 1 : 0.006 0.994 \n+ 42 42 (0) 1 : 0.030 0.970 \n+ 43 43 (0) 1 : 0.050 0.950 \n+ 44 44 (0) 1 : 0.008 0.992 \n+ 45 45 (0) 1 : 0.026 0.974 \n+ 46 46 (0) 1 : 0.006 0.994 \n+ 47 47 (0) 1 : 0.027 0.973 \n+ 48 48 (0) 1 : 0.018 0.982 \n+ 49 49 (0) 1 : 0.014 0.986 \n+ 50 50 (0) 1 : 0.046 0.954 \n+ 51 51 (0) 1 : 0.007 0.993 \n+ 52 52 (0) 1 : 0.010 0.990 \n+ 53 53 (0) 1 : 0.036 0.964 \n+ 54 54 (0) 1 : 0.024 '..b' : 0.973 0.027 \n+183 183 (0) 2 : 0.981 0.019 \n+184 184 (0) 2 : 0.991 0.009 \n+185 185 (0) 2 : 0.987 0.013 \n+186 186 (0) 2 : 0.969 0.031 \n+187 187 (0) 2 : 0.989 0.011 \n+188 188 (0) 2 : 0.991 0.009 \n+189 189 (0) 2 : 0.952 0.048 \n+190 190 (0) 2 : 0.993 0.007 \n+191 191 (0) 2 : 0.951 0.049 \n+192 192 (0) 2 : 0.920 0.080 \n+193 193 (0) 2 : 0.981 0.019 \n+194 194 (0) 2 : 0.963 0.037 \n+195 195 (0) 2 : 0.990 0.010 \n+196 196 (0) 2 : 0.987 0.013 \n+197 197 (0) 2 : 0.953 0.047 \n+198 198 (0) 2 : 0.821 0.179 \n+199 199 (0) 2 : 0.987 0.013 \n+200 200 (0) 2 : 0.989 0.011 \n+\n+\n+Estimated Allele Frequencies in each cluster\n+First column gives estimated ancestral frequencies\n+\n+\n+Locus 1 : \n+9 alleles\n+0.0% missing data\n+ 0 (0.115) 0.049 0.191 \n+ 1 (0.219) 0.245 0.208 \n+ -1 (0.160) 0.077 0.357 \n+ 3 (0.065) 0.018 0.041 \n+ -2 (0.099) 0.189 0.015 \n+ 2 (0.133) 0.088 0.144 \n+ -3 (0.125) 0.206 0.039 \n+ -4 (0.052) 0.112 0.002 \n+ -5 (0.032) 0.016 0.001 \n+\n+Locus 2 : \n+12 alleles\n+0.0% missing data\n+ 1 (0.117) 0.170 0.060 \n+ -1 (0.082) 0.033 0.123 \n+ 2 (0.241) 0.330 0.306 \n+ 5 (0.083) 0.042 0.091 \n+ -2 (0.046) 0.009 0.030 \n+ 3 (0.141) 0.112 0.216 \n+ 6 (0.038) 0.003 0.073 \n+ 0 (0.064) 0.033 0.031 \n+ 7 (0.031) 0.002 0.025 \n+ 4 (0.033) 0.002 0.035 \n+ -3 (0.068) 0.112 0.008 \n+ -4 (0.056) 0.153 0.003 \n+\n+Locus 3 : \n+11 alleles\n+0.0% missing data\n+ 3 (0.167) 0.173 0.200 \n+ -1 (0.081) 0.021 0.187 \n+ 2 (0.117) 0.065 0.208 \n+ 0 (0.174) 0.157 0.236 \n+ 4 (0.122) 0.175 0.056 \n+ 1 (0.155) 0.309 0.071 \n+ 5 (0.065) 0.045 0.019 \n+ -3 (0.025) 0.002 0.005 \n+ -2 (0.029) 0.002 0.015 \n+ 7 (0.036) 0.040 0.002 \n+ 6 (0.028) 0.011 0.001 \n+\n+Locus 4 : \n+14 alleles\n+0.0% missing data\n+ 8 (0.074) 0.015 0.168 \n+ 7 (0.108) 0.061 0.140 \n+ 6 (0.120) 0.145 0.067 \n+ 9 (0.075) 0.022 0.080 \n+ 2 (0.036) 0.002 0.049 \n+ 10 (0.046) 0.004 0.224 \n+ 5 (0.155) 0.208 0.112 \n+ 14 (0.109) 0.123 0.073 \n+ 4 (0.055) 0.011 0.052 \n+ 13 (0.033) 0.003 0.024 \n+ 3 (0.042) 0.069 0.002 \n+ 15 (0.057) 0.149 0.004 \n+ 17 (0.050) 0.140 0.002 \n+ 16 (0.039) 0.049 0.002 \n+\n+Locus 5 : \n+15 alleles\n+0.0% missing data\n+ 9 (0.037) 0.003 0.082 \n+ -3 (0.131) 0.181 0.116 \n+ 7 (0.131) 0.078 0.312 \n+ 8 (0.043) 0.003 0.215 \n+ 6 (0.085) 0.066 0.071 \n+ 3 (0.046) 0.013 0.021 \n+ 5 (0.106) 0.105 0.082 \n+ -2 (0.117) 0.226 0.041 \n+ -1 (0.083) 0.080 0.042 \n+ 4 (0.055) 0.108 0.006 \n+ -4 (0.050) 0.085 0.005 \n+ -5 (0.024) 0.005 0.002 \n+ 1 (0.037) 0.030 0.002 \n+ 2 (0.028) 0.011 0.001 \n+ 0 (0.025) 0.006 0.001 \n+\n+Values of parameters used in structure:\n+DATAFILE=/tmp/tmpd8muoH/files/000/dataset_1.dat,\tOUTFILE=outfile,\tNUMINDS=200,\tNUMLOCI=5,\tMISSING=-999,\tLABEL=1,\tPOPDATA=1,\tPOPFLAG=0,\tPHENOTYPE=0,\tEXTRACOLS=0,\tMAXPOPS=2,\tBURNIN=10000,\tNUMREPS=20000,\tUSEPOPINFO=0,\tINFERALPHA=1,\tINFERLAMBDA=0,\tPOPSPECIFICLAMBDA=0,\tPOPALPHAS=0,\tCOMPUTEPROB=1,\tNOADMIX=0,\tADMBURNIN=500,\tUPDATEFREQ=100,\tPRINTLIKES=0,\tINTERMEDSAVE=0,\tPRINTKLD=0,\tPRINTNET=1,\tPRINTLAMBDA=1,\tANCESTDIST=0,\tNUMBOXES=1000,\tANCESTPINT=0.90000,\tGENSBACK=2,\tMIGRPRIOR=0.01000,\tPRINTQHAT=0,\tPRINTQSUM=1,\tALPHA=1.0000,\tFREQSCORR=1,\tFPRIORMEAN=0.0100,\tFPRIORSD=0.0500,\tONEFST=0,\tLAMBDA=1.0000,\tUNIFPRIORALPHA=1,\tALPHAMAX=10.0000,\tALPHAPRIORA=1.0000,\tALPHAPRIORB=2.0000,\tALPHAPROPSD=0.0250,\tSTARTATPOPINFO=0,\tRANDOMIZE=0,\tLINKAGE=0,\tMETROFREQ=10,\tREPORTHITRATE=0,\tMARKOVPHASE=0,\tPHASED=0,\tPLOIDY=2,\tPHASEINFO=0\tLOCPRIOR=0, \tLOCPRIORINIT=1.000000, \tLOCDATA=1, \tLOCISPOP=1, \tLOCPRIORSTEP=0.100000, \tMAXLOCPRIOR=20.000000, \tSEED=2245,\t\n+[STRAT parameters]: NUMSIMSTATS=1000,\tPHENOTYPECOL=-9,\tPOOLFREQ=10,\tLOCUSxONLY=0,\tEMERROR=0.00100,\tMISSINGPHENO=-9,\t\n\\ No newline at end of file\n' |