From 290988b10f63f31c30a3b336eb0f462401ba3137 Mon Sep 17 00:00:00 2001 From: "cmzmasek@gmail.com" Date: Fri, 29 Jun 2012 06:42:55 +0000 Subject: [PATCH] in progress --- forester/test_data/gsdi_test_gene_tree_codes.xml | 672 ++++++++++ forester/test_data/gsdi_test_gene_tree_ids.xml | 266 ++++ forester/test_data/gsdi_test_gene_tree_sn.xml | 220 +++ forester/test_data/gsdi_test_gene_tree_sn_wnt.xml | 1398 ++++++++++++++++++++ forester/test_data/gsdi_test_species_tree.xml | 220 +++ forester/test_data/gsdi_test_species_tree_codes.nh | 1 + .../test_data/gsdi_test_species_tree_codes.xml | 186 +++ forester/test_data/gsdi_test_species_tree_ids.xml | 193 +++ forester/test_data/gsdi_test_species_tree_sn.nh | 1 + forester/test_data/gsdi_test_species_tree_sn.xml | 192 +++ 10 files changed, 3349 insertions(+) create mode 100644 forester/test_data/gsdi_test_gene_tree_codes.xml create mode 100644 forester/test_data/gsdi_test_gene_tree_ids.xml create mode 100644 forester/test_data/gsdi_test_gene_tree_sn.xml create mode 100644 forester/test_data/gsdi_test_gene_tree_sn_wnt.xml create mode 100644 forester/test_data/gsdi_test_species_tree.xml create mode 100644 forester/test_data/gsdi_test_species_tree_codes.nh create mode 100644 forester/test_data/gsdi_test_species_tree_codes.xml create mode 100644 forester/test_data/gsdi_test_species_tree_ids.xml create mode 100644 forester/test_data/gsdi_test_species_tree_sn.nh create mode 100644 forester/test_data/gsdi_test_species_tree_sn.xml diff --git a/forester/test_data/gsdi_test_gene_tree_codes.xml b/forester/test_data/gsdi_test_gene_tree_codes.xml new file mode 100644 index 0000000..6cb6fbc --- /dev/null +++ b/forester/test_data/gsdi_test_gene_tree_codes.xml @@ -0,0 +1,672 @@ + + + + + + + + + + + + + + + + + + + + PLAFA + + + A + + + + + PLAYO + + + A + + + + + + PLACH + + + A + + + + + + PLAYO + + + B + + + + + i have no species + + + + + Homo sapiens + + + X + + + + + + XXXXX + + + X + + + + + + 3093 + + + X + + + + + + + + + HUMAN + + + A + + + + + MOUSE + + + A + + + + + + YEAST + + + A + + + + + + + + HUMAN + + + E + + + + + YEAST + + + E + + + + + + MOUSE + + + F + + + + + + + + + NEMVE + + + C + + + + + PETMA + + + C + + + + + + + + + MYCGR + + + D + + + + + MYCGR + + + D1 + + + + + + MYCPJ + + + D + + + + + + + PYRHO + + + A + + + + + + + + + + + + + + + + PLAFA + + + A + + + + + PLAYO + + + A + + + + + + PLACH + + + A + + + + + + PLAYO + + + B + + + + + i have no species + + + + + Homo sapiens + + + X + + + + + + XXXXX + + + X + + + + + + 3093 + + + X + + + + + + + + + HUMAN + + + A + + + + + MOUSE + + + A + + + + + + YEAST + + + A + + + + + + + + HUMAN + + + E + + + + + YEAST + + + E + + + + + + MOUSE + + + F + + + + + + + + + NEMVE + + + C + + + + + PETMA + + + C + + + + + + + + + MYCGR + + + D + + + + + MYCGR + + + D1 + + + + + + MYCPJ + + + D + + + + + + + + + + + + + + + + + + PLAFA + + + A + + + + + PLAYO + + + A + + + + + + PLACH + + + A + + + + + + PLAYO + + + B + + + + + i have no species + + + + + Homo sapiens + + + X + + + + + + XXXXX + + + X + + + + + + 3093 + + + X + + + + + + + + + HUMAN + + + A + + + + + MOUSE + + + A + + + + + + YEAST + + + A + + + + + + + + HUMAN + + + E + + + + + YEAST + + + E + + + + + + MOUSE + + + F + + + + + + + + + + + + PLAFA + + + A + + + + + PLAYO + + + A + + + + + + PLACH + + + A + + + + + + PLAYO + + + B + + + + + + + NEMVE + + + C + + + + + PETMA + + + C + + + + + + + + + + MYCGR + + + D + + + + + MYCGR + + + D1 + + + + + + MYCPJ + + + D + + + + + + + + + + + + 266940 + KINRD + Kineococcus radiotolerans + + + A + + + + + 378753 + KOCRD + Kocuria rhizophila + + + A + + + + + + + MICPN + + + A + + + + + THEFY + + + A + + + + + + + STRCO + + + A + + + + + + BACTN + + + A + + + + + + \ No newline at end of file diff --git a/forester/test_data/gsdi_test_gene_tree_ids.xml b/forester/test_data/gsdi_test_gene_tree_ids.xml new file mode 100644 index 0000000..0beef5d --- /dev/null +++ b/forester/test_data/gsdi_test_gene_tree_ids.xml @@ -0,0 +1,266 @@ + + + + + + + + + + + + + + + + + + 5833 + + + A + + + + + 73239 + Plasmodium yoelii yoelii + + + A + + + + + + 5825 + Plasmodium chabaudi + + + A + + + + + + 73239 + Plasmodium yoelii yoelii + + + B + + + + + i have no species + + + + + 9606 + HUMAN + Homo sapiens + Human + species + + + X + + + + + + XXXXX + + + X + + + + + + 3093 + Characium perforatum + species + + + X + + + + + + + + + 9606 + HUMAN + Homo sapiens + Human + species + + + A + + + + + 10090 + MOUSE + Mus musculus + Mouse + species + + + A + + + + + + 559292 + YEAST + Saccharomyces cerevisiae (strain ATCC 204508 / S288c) + Baker's yeast + + + A + + + + + + + + 9606 + HUMAN + Homo sapiens + Human + species + + + E + + + + + 559292 + YEAST + Saccharomyces cerevisiae (strain ATCC 204508 / S288c) + Baker's yeast + + + E + + + + + + 10090 + MOUSE + Mus musculus + Mouse + species + + + F + + + + + + + + + 45351 + NEMVE + Nematostella vectensis + Starlet sea anemone + species + + + C + + + + + 7757 + PETMA + Petromyzon marinus + Sea lamprey + species + + + C + + + + + + + + + 1047171 + MYCGR + Mycosphaerella graminicola + Speckled leaf blotch fungus + Septoria tritici + species + + + D + + + + + 1047171 + MYCGR + Mycosphaerella graminicola + Speckled leaf blotch fungus + Septoria tritici + species + + + D1 + + + + + + 64363 + MYCPJ + Mycosphaerella pini + Red band needle blight disease fungus + Dothistroma pini + species + + + D + + + + + + + 70601 + PYRHO + Pyrococcus horikoshii (strain ATCC 700860 / DSM 12428 / JCM 9974 / NBRC 100139 / OT-3) + + + A + + + + + + 226186 + BACTN + Bacteroides thetaiotaomicron (strain ATCC 29148 / DSM 2079 / NCTC 10582 / E50 / VPI-5482) + + + A + + + + + \ No newline at end of file diff --git a/forester/test_data/gsdi_test_gene_tree_sn.xml b/forester/test_data/gsdi_test_gene_tree_sn.xml new file mode 100644 index 0000000..940e103 --- /dev/null +++ b/forester/test_data/gsdi_test_gene_tree_sn.xml @@ -0,0 +1,220 @@ + + + + + + + + + + + + + + + + + + Plasmodium falciparum (maybe) + + + A + + + + + Plasmodium yoelii yoelii + + + A + + + + + + Plasmodium chabaudi strain lame + + + A + + + + + + Plasmodium yoelii yoelii + + + B + + + + + i have no species + + + + + Homo sapiens + Human + + + X + + + + + + big lizard + + + X + + + + + + 3093 + Characium perforatum + + + X + + + + + + + + + HUMAN + Homo sapiens + Human + + + A + + + + + Mus musculus subspecies balb + + + A + + + + + + Saccharomyces cerevisiae (strain ATCC 204508 / S288c) + + + A + + + + + + + + Homo sapiens + + + E + + + + + Saccharomyces cerevisiae subsection strange + + + E + + + + + + Mus musculus nielsson + + + F + + + + + + + + + NEMVE + Nematostella vectensis + Starlet sea anemone + + + C + + + + + Petromyzon marinus + Sea lamprey + + + C + + + + + + + + + Mycosphaerella graminicola + Septoria tritici + species + + + D + + + + + Mycosphaerella graminicola + + + D1 + + + + + + 64363 + Mycosphaerella pini + + + D + + + + + + + 70601 + Pyrococcus horikoshii (strain ATCC 700860 / DSM 12428 / JCM 9974 / NBRC 100139 / OT-3) + + + A + + + + + + BACTN + Bacteroides thetaiotaomicron (strain ATCC 29148 / DSM 2079 / NCTC 10582 / E50 / VPI-5482) + + + A + + + + + diff --git a/forester/test_data/gsdi_test_gene_tree_sn_wnt.xml b/forester/test_data/gsdi_test_gene_tree_sn_wnt.xml new file mode 100644 index 0000000..6ba1209 --- /dev/null +++ b/forester/test_data/gsdi_test_gene_tree_sn_wnt.xml @@ -0,0 +1,1398 @@ + + + + + + ref_XP_002434188_1_mites___ticks_ + 0.436934 + + Ixodes scapularis + + + XP_002434188 + AmphiWnt4, putative + + + + 0.0 + + segmented_worms + 0.0977774 + + gb_ADF31344_1_segmented_worms_ + 0.342506 + + Perionyx excavatus + + + GU938470.1 + Perionyx excavatus WNT11 + + + + gb_ADK38674_2_segmented_worms_ + 0.331094 + + Platynereis dumerilii + + + HM179276.2 + Platynereis dumerilii (Dumeril's clam worm) Wnt11 + + + + + 0.0810781 + + 0.0127274 + + ref_NP_001161493_1_hemichordates_ + 0.366952 + + Saccoglossus kowalevskii + + + NP_001161493 + wingless-type MMTV integration site family, member 11 precursor + + + + 0.14851 + + 0.101195 + + 0.0254976 + + hemichordates + 0.164216 + + ref_XP_002737259_1_hemichordates_ + 0.0123794 + + Saccoglossus kowalevskii + + + XP_002737259 + PREDICTED: wingless-type MMTV integration site family member 4 + + + + gb_ADB22653_1_hemichordates_ + 0.0 + + Saccoglossus kowalevskii + + + GU224244.1 + Saccoglossus kowalevskii partial wingless-type MMTV integration site family + + + + + 0.0284849 + + 0.116947 + + 0.00640349 + + 0.022288 + + frogs___toads + 0.0144378 + + dbj_BAE16611_1_frogs___toads_ + 0.00998333 + + Rana rugosa + + + AB204854.1 + Rana rugosa Wnt-4 protein + + + + 0.00869688 + + 0.00400211 + + ref_NP_001239014_1_frogs___toads_ + 0.00252727 + + Xenopus laevis + + + NP_001239014 + protein Wnt-4 isoform 2 precursor + + + + ref_NP_001081197_1_frogs___toads_ + 0.00668951 + + Xenopus laevis + + + NP_001081197 NP_001081198 + protein Wnt-4 isoform 1 + + + + + ref_NP_001239015_1_frogs___toads_ + 0.0145957 + + Xenopus + + + NP_001239015 XP_002937081 + protein Wnt-4 precursor + + + + + + birds + 0.0458081 + + 0.00212171 + + ref_XP_002194190_1_birds_ + 0.0 + + Taeniopygia guttata + + + XP_002194190 + PREDICTED: wingless-type MMTV integration site family, member 4 + + + + ref_XP_003212403_1_birds_ + 0.00758143 + + Meleagris gallopavo + + + XP_003212403 + PREDICTED: protein Wnt-4-like + + + + + ref_NP_990114_1_birds_ + 0.00699759 + + Gallus gallus + + + NP_990114 + protein Wnt-4 precursor + + + + + + 0.0327454 + + marsupials + 0.0220392 + + gb_AAY18780_1_marsupials_ + 0.00829078 + + Macropus eugenii + + + AY940685.1 + Macropus eugenii (tammar wallaby) wingless-related MMTV integration site 4 + + + + ref_XP_001376793_2_marsupials_ + 0.00731079 + + Monodelphis domestica + + + XP_001376793 + PREDICTED: protein Wnt-4-like + + + + + 0.0422827 + + ref_XP_002919583_1_carnivores_ + 0.00681767 + + Ailuropoda melanoleuca + + + XP_002919583 + PREDICTED: LOW QUALITY PROTEIN: protein Wnt-4-like + + + + 0.00249228 + + ref_XP_002750404_1_primates_ + 0.00517047 + + Callithrix jacchus + + + XP_002750404 + PREDICTED: protein Wnt-4-like + + + + 6.4578E-4 + + 9.93478E-4 + + 5.01604E-4 + + 0.00125419 + + 0.00119591 + + ref_XP_003581950_1_even_toed_ungulates_ + 0.02026 + + Bos taurus + + + XP_003581950 + PREDICTED: protein Wnt-4-like + + + + ref_XP_001501560_2_odd_toed_ungulates_ + 0.0 + + Equus caballus + + + XP_001501560 + PREDICTED: protein Wnt-4 + + + + + gb_AFH66793_1_even_toed_ungulates_ + 2.77911E-4 + + Bubalus bubalis + + + JQ326275.1 + Bubalus bubalis (water buffalo) WNT4 + + + + + 0.00574521 + + 0.00724651 + + ref_XP_002716079_1_rabbits___hares_ + 0.0359451 + + Oryctolagus cuniculus + + + XP_002716079 + PREDICTED: wingless-type MMTV integration site family, member 4 + + + + ref_XP_002802264_1_primates_ + 0.0 + + Macaca mulatta + + + XP_002802264 + PREDICTED: protein Wnt-4 isoform 2 + + + + + ref_XP_003585839_1_even_toed_ungulates_ + 0.0 + + Bos taurus + + + XP_003585839 + PREDICTED: protein Wnt-4-like + + + + + + rodents + 0.00522595 + + gb_EHB08913_1_rodents_ + 0.013784 + + Heterocephalus glaber + + + JH170405.1 + Heterocephalus glaber (naked mole-rat) Protein Wnt-4 + + + + ref_XP_003471186_1_rodents_ + 0.0 + + Cavia porcellus + + + XP_003471186 + PREDICTED: protein Wnt-4-like + + + + + + 9.314E-4 + + gb_EHH14426_1_primates_ + 0.0 + + Macaca mulatta + + + CM001253.1 + Macaca mulatta (Rhesus monkey) partial hypothetical protein + + + + 9.20304E-4 + + primates + 4.4792E-4 + + 1.50754E-4 + + dbj_BAC23080_1_primates_ + 0.00282125 + + Homo sapiens + + + AB061675.1 + Homo sapiens (human) WNT4 + + + + gb_AAG38658_1_primates_ + 0.005812 + + Homo sapiens + + + AY009398.1 + Homo sapiens (human) WNT4 precursor + + + + + ref_NP_110388_2_primates_ + 0.0 + + Homo sapiens + + + NP_110388 + protein Wnt-4 precursor + + + + + rodents + 0.00846645 + + 1.70192E-4 + + ref_NP_033549_1_rodents_ + 0.00262035 + + Mus musculus + + + NP_033549 + protein Wnt-4 precursor + + + + 0.00602544 + + gb_AAH98752_1_rodents_ + 0.0 + + Rattus norvegicus + + + BC098752.1 + Rattus norvegicus (Norway rat) wingless-type MMTV integration site family, + + + + ref_NP_445854_1_rodents_ + 0.00292772 + + Rattus norvegicus + + + NP_445854 + protein Wnt-4 precursor + + + + + + ref_XP_003503693_1_rodents_ + 0.0033169 + + Cricetulus griseus + + + XP_003503693 + PREDICTED: protein Wnt-4-like + + + + + + + + + + + + bony_fishes + 0.0459602 + + 0.0244715 + + 0.0102135 + + 0.00313174 + + ref_XP_003442666_1_bony_fishes_ + 0.00605392 + + Oreochromis niloticus + + + XP_003442666 + PREDICTED: protein Wnt-4a-like + + + + emb_CAF96944_1_bony_fishes_ + 0.0253017 + + Tetraodon nigroviridis + + + CAAE01014528.1 + Tetraodon nigroviridis hypothetical protein + + + + + 0.00109057 + + emb_CBN80604_1_bony_fishes_ + 0.00582779 + + Dicentrarchus labrax + + + FQ310506.3 + Dicentrarchus labrax (European seabass) Protein Wnt + + + + ref_NP_001153911_1_bony_fishes_ + 0.0346242 + + Oryzias latipes + + + NP_001153911 + wingless-type MMTV integration site family member 4a precursor + + + + + + 0.00334737 + + gb_AER52059_1_bony_fishes_ + 0.0193135 + + Oncorhynchus mykiss + + + JF815553.1 + Oncorhynchus mykiss (rainbow trout) wingless-type MMTV integration site + + + + gb_AER52060_1_bony_fishes_ + 0.0116537 + + Oncorhynchus mykiss + + + JF815554.1 + Oncorhynchus mykiss (rainbow trout) wingless-type MMTV integration site + + + + + + 0.0503382 + + ref_NP_001035477_1_bony_fishes_ + 0.00103857 + + Danio rerio + + + NP_001035477 NP_571022 + protein Wnt-4a precursor + + + + gb_AAA96518_1_bony_fishes_ + 0.00777218 + + Danio rerio + + + U51267.1 + Danio rerio (zebrafish) Wnt4 + + + + + + + lancelets + 0.183281 + + ref_XP_002613927_1_lancelets_ + 3.2603E-4 + + Branchiostoma floridae + + + XP_002613927 + hypothetical protein BRAFLDRAFT_56711 + + + + gb_AAC80431_1_lancelets_ + 0.0111029 + + Branchiostoma floridae + + + AF061973.1 + Branchiostoma floridae (Florida lancelet) AmphiWnt4 + + + + + + + 0.0261016 + + 0.02683 + + emb_CAD37166_2_segmented_worms_ + 0.206153 + + Platynereis dumerilii + + + AJ491798.2 + Platynereis dumerilii (Dumeril's clam worm) Wnt4 protein + + + + gb_ABD16196_1_cephalopods_ + 0.304059 + + Euprymna scolopes + + + DQ351545.1 + Euprymna scolopes Wnt4 + + + + + gb_ADF31339_1_segmented_worms_ + 0.290633 + + Perionyx excavatus + + + GU938465.1 + Perionyx excavatus WNT4a + + + + + + ref_XP_003448336_1_bony_fishes_ + 0.402974 + + Oreochromis niloticus + + + XP_003448336 + PREDICTED: protein Wnt-5a-like + + + + + + 0.0262246 + + lancelets + 0.376048 + + gb_AAF80555_1_lancelets_ + 0.00289093 + + Branchiostoma floridae + + + AF187553.1 + Branchiostoma floridae (Florida lancelet) Wnt11 + + + + ref_XP_002593786_1_lancelets_ + 0.00295707 + + Branchiostoma floridae + + + XP_002593786 + hypothetical protein BRAFLDRAFT_271417 + + + + + 0.106179 + + 0.0440517 + + birds + 0.0905522 + + 0.118515 + + ref_XP_003208322_1_birds_ + 0.0361106 + + Meleagris gallopavo + + + XP_003208322 + PREDICTED: protein Wnt-11b-like + + + + ref_NP_001124216_1_birds_ + 0.0274937 + + Gallus gallus + + + NP_001124216 + protein Wnt-11 precursor + + + + + ref_XP_002189037_1_birds_ + 0.21354 + + Taeniopygia guttata + + + XP_002189037 + PREDICTED: similar to wingless-type MMTV integration site family, + + + + + 0.0283196 + + dbj_BAF37827_1_turtles_ + 0.0650947 + + Pelodiscus sinensis + + + AB204883.1 + Pelodiscus sinensis (Chinese soft-shelled turtle) partial Wnt11b + + + + 0.00958915 + + frogs___toads + 0.103554 + + 0.00915644 + + ref_NP_001084327_1_frogs___toads_ + 0.0 + + Xenopus laevis + + + NP_001084327 NP_001084328 + protein Wnt-11b precursor + + + + gb_AAA19697_1_frogs___toads_ + 0.00339381 + + Xenopus laevis + + + L23542.1 + Xenopus laevis (African clawed frog) maternal protein + + + + + 0.021572 + + ref_NP_001016735_1_frogs___toads_ + 0.00530629 + + Xenopus + + + NP_001016735 + protein Wnt-11b-2 precursor + + + + ref_NP_001008133_1_frogs___toads_ + 0.00920827 + + Xenopus + + + NP_001008133 + protein Wnt-11b-1 precursor + + + + + + bony_fishes + 0.199333 + + gb_AAI62630_1_bony_fishes_ + 0.00127615 + + Danio rerio + + + BC162630.1 + Danio rerio (zebrafish) wnt11 protein + + + + 0.00164817 + + ref_NP_001138276_1_bony_fishes_ + 0.00118889 + + Danio rerio + + + NP_001138276 NP_571031 XP_001331379 + protein Wnt-11 precursor + + + + sp_O73864_1_bony_fishes_ + 0.0134104 + + Danio rerio + + + wnt11 + O73864 + Protein Wnt-11 + + + + + + + + + 0.112925 + + bony_fishes + 0.0434939 + + 0.0183845 + + ref_XP_003459019_1_bony_fishes_ + 0.0717209 + + Oreochromis niloticus + + + XP_003459019 + PREDICTED: protein Wnt-11-like + + + + emb_CAF87061_1_bony_fishes_ + 0.106306 + + Tetraodon nigroviridis + + + CAAE01000518.1 + Tetraodon nigroviridis hypothetical protein + + + + + ref_NP_571151_1_bony_fishes_ + 0.058741 + + Danio rerio + + + NP_571151 + protein Wnt-11 precursor + + + + + 0.0330987 + + 0.018843 + + ref_XP_003429117_1_monotremes_ + 0.0696105 + + Ornithorhynchus anatinus + + + XP_003429117 + PREDICTED: LOW QUALITY PROTEIN: protein Wnt-11-like + + + + 0.0090824 + + frogs___toads + 0.0696925 + + ref_NP_001121530_1_frogs___toads_ + 0.0199744 + + Xenopus + + + NP_001121530 + protein Wnt-11 precursor + + + + 0.00618226 + + ref_NP_001087079_1_frogs___toads_ + 0.00333662 + + Xenopus laevis + + + NP_001087079 + protein Wnt-11 precursor + + + + gb_AAH78589_1_frogs___toads_ + 0.0 + + Xenopus laevis + + + BC078589.1 + Xenopus laevis (African clawed frog) partial WNT11-R protein + + + + + + 0.0214024 + + 0.00542893 + + ref_XP_002199577_1_birds_ + 0.0219833 + + Taeniopygia guttata + + + XP_002199577 + PREDICTED: wingless-type MMTV integration site family, member 11, + + + + ref_XP_003225479_1_lizards_ + 0.0392092 + + Anolis carolinensis + + + XP_003225479 + PREDICTED: protein Wnt-11-like + + + + + birds + 0.00775104 + + ref_XP_002187913_1_birds_ + 0.00781053 + + Taeniopygia guttata + + + XP_002187913 + PREDICTED: wingless-type MMTV integration site family, member 11 + + + + 0.00834971 + + 0.0012329 + + ref_XP_003203619_1_birds_ + 1.88713E-4 + + Meleagris gallopavo + + + XP_003203619 + PREDICTED: protein Wnt-11-like + + + + ref_NP_990115_1_birds_ + 0.00264015 + + Gallus gallus + + + NP_990115 + protein Wnt-11 precursor + + + + + sp_P51891_1_birds_ + 0.00159998 + + Coturnix coturnix japonica + + + WNT11 + P51891 + Protein Wnt-11 + + + + + + + + + 0.048018 + + gb_AES09804_1_carnivores_ + 0.0 + + Mustela putorius furo + + + JP021206.1 + Mustela putorius furo (domestic ferret) partial wingless-type MMTV + + + + 0.0224188 + + ref_XP_001495213_3_odd_toed_ungulates_ + 0.0058944 + + Equus caballus + + + XP_001495213 + PREDICTED: protein Wnt-11-like + + + + 0.00853522 + + rodents + 0.00784751 + + 0.00133001 + + ref_NP_536326_1_rodents_ + 6.88651E-4 + + Rattus norvegicus + + + NP_536326 XP_001065413 XP_238122 + wingless-type MMTV integration site family, member 11 + + + + 0.0056165 + + ref_NP_033545_1_rodents_ + 7.4424E-5 + + Mus musculus + + + NP_033545 + protein Wnt-11 precursor + + + + dbj_BAE23841_1_rodents_ + 0.0 + + Mus musculus + + + AK138967.1 + Mus musculus (house mouse) hypothetical protein + + + + + + ref_XP_003507131_1_rodents_ + 0.00380006 + + Cricetulus griseus + + + XP_003507131 + PREDICTED: protein Wnt-11 + + + + + 0.00363426 + + 0.00122167 + + rodents + 0.00592959 + + ref_XP_003468598_1_rodents_ + 0.00108834 + + Cavia porcellus + + + XP_003468598 + PREDICTED: protein Wnt-11-like + + + + gb_EHB07727_1_rodents_ + 0.00764545 + + Heterocephalus glaber + + + JH169882.1 + Heterocephalus glaber (naked mole-rat) Protein Wnt-11 + + + + + 0.0015897 + + ref_XP_003420125_1_placentals_ + 0.00897318 + + Loxodonta africana + + + XP_003420125 + PREDICTED: protein Wnt-11-like + + + + ref_NP_001075693_1_rabbits___hares_ + 0.00960427 + + Oryctolagus cuniculus + + + NP_001075693 + WNT-11 protein + + + + + + 7.44351E-4 + + 0.00183438 + + ref_NP_001075925_1_even_toed_ungulates_ + 0.01148578 + + Bos taurus + + + NP_001075925 XP_868944 + protein Wnt-11 + + + + carnivores + 0.00280575 + + ref_XP_542301_2_carnivores_ + 4.54548E-4 + + Canis lupus familiaris + + + XP_542301 + PREDICTED: protein Wnt-11 + + + + ref_XP_002915341_1_carnivores_ + 0.00237431 + + Ailuropoda melanoleuca + + + XP_002915341 + PREDICTED: protein Wnt-11-like + + + + + + 0.00220231 + + primates + 0.00346845 + + gb_EHH23261_1_primates_ + 3.5416E-4 + + Macaca mulatta + + + CM001266.1 + Macaca mulatta (Rhesus monkey) hypothetical protein + + + + ref_XP_001086955_1_primates_ + 0.0024747 + + Macaca mulatta + + + XP_001086955 + PREDICTED: protein Wnt-11 + + + + + 0.00205086 + + ref_XP_003357253_1_even_toed_ungulates_ + 0.0107583 + + Sus scrofa + + + XP_003357253 + PREDICTED: protein Wnt-11-like + + + + 6.71784E-4 + + ref_XP_002754856_1_primates_ + 0.0111473 + + Callithrix jacchus + + + XP_002754856 + PREDICTED: protein Wnt-11-like + + + + 2.78463E-4 + + ref_XP_003254741_1_primates_ + 0.0 + + Nomascus leucogenys + + + XP_003254741 + PREDICTED: protein Wnt-11 + + + + 0.00289741 + + emb_CAA73223_1_primates_ + 0.00827541 + + Homo sapiens + + + Y12692.1 + Homo sapiens (human) hypothetical protein + + + + 2.51548E-4 + + ref_NP_004617_2_primates_ + 0.0 + + Homo sapiens + + + NP_004617 + protein Wnt-11 precursor + + + + 4.31084E-4 + + gb_AAV38299_1_primates_ + 0.00256993 + + Homo sapiens + + + BT019492.1 + Homo sapiens (human) wingless-type MMTV integration site family, member 11 + + + + 5.20012E-4 + + other_sequences + 0.00231386 + + gb_AAX36829_1_other_sequences_ + 0.0 + + synthetic construct + + + AY893792.1 + synthetic construct partial wingless-type MMTV integration site family + + + + gb_AAX41552_1_other_sequences_ + 0.0 + + synthetic construct + + + AY888610.1 + synthetic construct wingless-type MMTV integration site family member 11 + + + + + primates + 0.0300714 + + dbj_BAC11683_1_primates_ + 0.0302193 + + Homo sapiens + + + AK075540.1 + Homo sapiens (human) hypothetical protein + + + + gb_AEG64815_1_primates_ + 0.0 + + Homo sapiens + + + JF800675.1 + Homo sapiens (human) Wnt11 isoform 3 + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/forester/test_data/gsdi_test_species_tree.xml b/forester/test_data/gsdi_test_species_tree.xml new file mode 100644 index 0000000..d8f0091 --- /dev/null +++ b/forester/test_data/gsdi_test_species_tree.xml @@ -0,0 +1,220 @@ + + + + + cellular_organisms + + + Neomura + + + + 2759 + Eukaryota + superkingdom + + + + 33154 + Opisthokonta + Fungi/Metazoa group + + + Bilateria_Cnidaria + + + 7742 + Vertebrata + + + + 314146 + Euarchontoglires + superorder + + + + 9606 + HUMAN + Homo sapiens + Human + species + + + + + 10090 + MOUSE + Mus musculus + Mouse + species + + + + + + 7757 + PETMA + Petromyzon marinus + Sea lamprey + species + + + + + + 45351 + NEMVE + Nematostella vectensis + Starlet sea anemone + species + + + + + Pezizomycotina_Saccharomycetales + + + 41254 + Mycosphaerella + genus + + + + 54734 + MYCGR + Mycosphaerella graminicola + Speckled leaf blotch fungus + Septoria tritici + species + + + + + 64363 + MYCPJ + Mycosphaerella pini + Red band needle blight disease fungus + Dothistroma septosporum + Dothistroma pini + species + + + + + + 4932 + YEAST + Saccharomyces cerevisiae + Baker's yeast + species + + + + + + + 5820 + Plasmodium + genus + + + + 5825 + PLACH + Plasmodium chabaudi + species + + + + + 5833 + PLAFA + Plasmodium falciparum + species + + + + + 73239 + PLAYO + Plasmodium yoelii yoelii + subspecies + + + + + + + + 53953 + PYRHO + Pyrococcus horikoshii + species + + + + i have no species! + + + + + b_193 + + b_115 + + KINRD + + 266940 + KINRD + Kineococcus radiotolerans (strain ATCC BAA-149 / DSM 14245 / SRS30216) + + + + KOCRD + + 378753 + KOCRD + Kocuria rhizophila (strain ATCC 9341 / DSM 348 / NBRC 103217 / DC2201) + + + + STRCO + + 1902 + STRCO + Streptomyces coelicolor + species + + + + THEFY + + 269800 + THEFY + Thermobifida fusca (strain YX) + + + + + 1032480 + MICPN + Microlunatus phosphovorus (strain ATCC 700054 / DSM 10555 / JCM 9379 / NBRC 101784 / NCIMB 13414 / VKM Ac-1990 / NM-1) + Microlunatus phosphovorus NM-1 + strain + + + + + BACTN + + 818 + BACTN + Bacteroides thetaiotaomicron + species + + + + + + \ No newline at end of file diff --git a/forester/test_data/gsdi_test_species_tree_codes.nh b/forester/test_data/gsdi_test_species_tree_codes.nh new file mode 100644 index 0000000..0c74dd5 --- /dev/null +++ b/forester/test_data/gsdi_test_species_tree_codes.nh @@ -0,0 +1 @@ +(((((((HUMAN,MOUSE)Euarchontoglires,PETMA)Vertebrata,NEMVE)Bilateria_Cnidaria,((MYCGR,MYCPJ)Mycosphaerella,YEAST)Pezizomycotina_Saccharomycetales)Opisthokonta,(PLACH,PLAFA,PLAYO)Plasmodium)Eukaryota,PYRHO)Neomura,((KINRD,KOCRD,STRCO,THEFY,MICPN)b_115,BACTN)b_193)cellular_organisms; \ No newline at end of file diff --git a/forester/test_data/gsdi_test_species_tree_codes.xml b/forester/test_data/gsdi_test_species_tree_codes.xml new file mode 100644 index 0000000..d5294c3 --- /dev/null +++ b/forester/test_data/gsdi_test_species_tree_codes.xml @@ -0,0 +1,186 @@ + + + + + cellular_organisms + + + Neomura + + + + 2759 + Eukaryota + superkingdom + + + + 33154 + Opisthokonta + Fungi/Metazoa group + + + Bilateria_Cnidaria + + + 7742 + Vertebrata + + + + 314146 + Euarchontoglires + superorder + + + + HUMAN + + + + + MOUSE + + + + + + PETMA + + + + + + + NEMVE + + + + + nemve sister + + + + + + Pezizomycotina_Saccharomycetales + + + 41254 + Mycosphaerella + genus + + + + MYCGR + + + + + MYCPJ + + + + + + YEAST + + YEAST + + + + + WOAMI + + + + + + + + + PLACH + + + + PLAFA + + PLAFA + + + + + PLAYO + + + + + + + + PYRHO + + + + i have no species information! + + + + + b_193 + + b_115 + + KINRD + + 266940 + KINRD + + + + KOCRD + + 378753 + KOCRD + Kocuria rhizophila (strain ATCC 9341 / DSM 348 / NBRC 103217 / DC2201) + + + + STRCO + + 1902 + STRCO + Streptomyces coelicolor + species + + + + THEFY + + 269800 + THEFY + Thermobifida fusca (strain YX) + + + + + 1032480 + MICPN + Microlunatus phosphovorus NM-1 + strain + + + + + BACTN + + 818 + BACTN + Bacteroides thetaiotaomicron + species + + + + + + \ No newline at end of file diff --git a/forester/test_data/gsdi_test_species_tree_ids.xml b/forester/test_data/gsdi_test_species_tree_ids.xml new file mode 100644 index 0000000..c3f3242 --- /dev/null +++ b/forester/test_data/gsdi_test_species_tree_ids.xml @@ -0,0 +1,193 @@ + + + + + cellular_organisms + + + Neomura + + + + 2759 + Eukaryota + superkingdom + + + + 33154 + Opisthokonta + Fungi/Metazoa group + + + Bilateria_Cnidaria + + + 7742 + Vertebrata + + + + 314146 + Euarchontoglires + superorder + + + + 9606 + Human + + + + + 10090 + Mouse + + + + + + 7757 + Sea lamprey + + + + + NEMVE + + 45351 + Starlet sea anemone + + + + + Pezizomycotina_Saccharomycetales + + + 41254 + Mycosphaerella + genus + + + MYCGR + + 54734 + Speckled leaf blotch fungus + + + + MYCPJ + + 64363 + Red band needle blight disease fungus + + + + + + YEAST + + 4932 + Baker's yeast + + + + ihave no species information! + + + + + + + 5820 + Plasmodium + genus + + + + 5825 + PLACH + Plasmodium chabaudi + species + + + + + 5833 + + + + + 73239 + PLAYO + Plasmodium yoelii yoelii + subspecies + + + + + + + + 53953 + PYRHO + Pyrococcus horikoshii + species + + + + + WOAMI + + + + + + b_193 + + b_115 + + + 266940 + KINRD + + + + + 378753 + KOCRD + + + + + 1902 + STRCO + species + + + + + 269800 + THEFY + Thermobifida fusca (strain YX) + + + + + 1032480 + MICPN + Microlunatus phosphovorus NM-1 + strain + + + + + + 818 + BACTN + + + + + + \ No newline at end of file diff --git a/forester/test_data/gsdi_test_species_tree_sn.nh b/forester/test_data/gsdi_test_species_tree_sn.nh new file mode 100644 index 0000000..4e9e5e0 --- /dev/null +++ b/forester/test_data/gsdi_test_species_tree_sn.nh @@ -0,0 +1 @@ +(((((((Homo_sapiens,Mus_musculus)Euarchontoglires,Petromyzon_marinus)Vertebrata,Nematostella_vectensis)Bilateria_Cnidaria,((Mycosphaerella_graminicola,Mycosphaerella_pini)Mycosphaerella,Saccharomyces_cerevisiae)Pezizomycotina_Saccharomycetales)Opisthokonta,(Plasmodium_chabaudi,Plasmodium_falciparum,Plasmodium_yoelii_yoelii)Plasmodium)Eukaryota,Pyrococcus_horikoshii)Neomura,((Kineococcus_radiotolerans,Kocuria_rhizophila,Streptomyces_coelicolor,Thermobifida_fusca,Microlunatus_phosphovorus),Bacteroides_thetaiotaomicron))cellular_organisms; \ No newline at end of file diff --git a/forester/test_data/gsdi_test_species_tree_sn.xml b/forester/test_data/gsdi_test_species_tree_sn.xml new file mode 100644 index 0000000..cb0b027 --- /dev/null +++ b/forester/test_data/gsdi_test_species_tree_sn.xml @@ -0,0 +1,192 @@ + + + + + cellular_organisms + + + Neomura + + + + 2759 + Eukaryota + superkingdom + + + + 33154 + Opisthokonta + Fungi/Metazoa group + + + Bilateria_Cnidaria + + + 7742 + Vertebrata + + + + Euarchontoglires + + + + Homo sapiens + + + + + Mus musculus + + + + + + Petromyzon marinus + + + + + NEMVE + + Nematostella vectensis + + + + + Pezizomycotina_Saccharomycetales + + + 41254 + Mycosphaerella + genus + + + MYCGR + + Mycosphaerella graminicola + + + + MYCPJ + + Mycosphaerella pini + + + + + + YEAST + + Saccharomyces cerevisiae + + + + + WOAMI + + + + + + + + 5820 + Plasmodium + genus + + + PLACH + + Plasmodium chabaudi + + + + PLAFA + + 5833 + PLAFA + Plasmodium falciparum + species + + + + PLAYO + + 73239 + PLAYO + Plasmodium yoelii yoelii + subspecies + + + + + + + PYRHO + + 53953 + PYRHO + Pyrococcus horikoshii + species + + + + i have no species information! + + + + + b_193 + + b_115 + + KINRD + + 266940 + KINRD + Kineococcus radiotolerans (strain ATCC BAA-149 / DSM 14245 / SRS30216) + + + + KOCRD + + 378753 + KOCRD + Kocuria rhizophila (strain ATCC 9341 / DSM 348 / NBRC 103217 / DC2201) + + + + STRCO + + 1902 + STRCO + Streptomyces coelicolor + species + + + + THEFY + + Thermobifida fusca (strain YX) + + + + + Microlunatus phosphovorus (strain ATCC 700054 / DSM 10555 / JCM 9379 / NBRC 101784 / NCIMB 13414 / VKM Ac-1990 / NM-1) + + + + + BACTN + + 818 + Bacteroides thetaiotaomicron + species + + + + + + \ No newline at end of file -- 1.7.10.2