added rubisco dataset

.ocamlinit

 module Top = Bistro_utils.Toplevel_eval.Make(struct let np = 8 let mem = 10 end)()
 open Top
-open Reviewphiltrans
+open Codepi
 
 let njplot (t : Biotope.Formats.newick Bistro.file) = Sys.command (Printf.sprintf "njplot %s" (path t))
 
-let n_h0 = 100
-let n_ha = 3
+let n_h0 = 50
+let n_ha = 50
 let npairs = 10
 let tree = Simulation_dataset.Pair_tree { branch_length1 = 3. ; branch_length2 = 3. ; npairs };;
-let sim = Simulation_dataset.convdet_simulation ~tree ~profiles:"example/aa_fitness/263SelectedProfiles.tsv" ~n_h0 ~n_ha () ~ne_s:(8.,8.);;
+let sim = Simulation_dataset.convdet_simulation ~tree ~profiles:"example/aa_fitness/263SelectedProfiles.tsv" ~n_h0 ~n_ha ();;
 let convergent_species = List.init npairs (Printf.sprintf "C%d");;
-
-let genotype = Gemma.genotype_of_fasta (Simulation_dataset.amino_acid_alignment sim)
-let phenotype = Gemma.phenotype_of_tree (Simulation_dataset.tree ~branch_length_unit:`Amino_acid sim);;
-let relatedness_matrix = Gemma.calculate_relatedness_matrix ~mode:`Standardized ~genotype ~phenotype;;
-let fit = Gemma.univariate_lmm ~lmm:`LRT ~genotype ~phenotype ~relatedness_matrix;;

app/lmm_benchmark.ml

@@ -4,7 +4,7 @@ let benchmark d =
   let open Simulation_dataset in
   Utils.recall_precision_curve
     ~oracle:(oracle d)
-    ~labels:[|"topological";"multinomial";"gemma_score";"inhouse";"tdg09"|]
+    ~labels:[| "topological"; "multinomial";"gemma_score";"inhouse"; "tdg09" |]
     ~results:[
       topological d ;
       multinomial_asymptotic_lrt d ;
@@ -17,9 +17,10 @@ let () =
   let sim =
     let open Simulation_dataset in
     convdet_simulation
-      ~tree:(NHX "example/trees4analyses_db/cyp_coding.Chrysithr_root.nhx")
+      (* ~tree:(NHX "example/trees4analyses_db/cyp_coding.Chrysithr_root.nhx") *)
+      ~tree:(NHX "example/trees_test/orthomam_rooted.nhx")
       ~profiles:"example/aa_fitness/263SelectedProfiles.tsv"
-      ~n_h0:100 ~n_ha:100 ~ne_s:(2., 2.) ()
+      ~n_h0:900 ~n_ha:100 ~ne_s:(2., 2.) ()
   in
   let w = benchmark sim in
   let loggers = [ Bistro_utils.Console_logger.create () ] in

data/rubisco/README.md

+# Rubisco dataset
+
+[reference](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0192697)

data/rubisco/rubisco.nhx

+((((Halimione_pedunculata:0.00864425,Halimione_verrucifera:0.00092984)99:0.00537145,(((((Axyris_prostrata:0.01534606,(Ceratocarpus_arenarius:0.02990907,Krascheninnikovia_ceratoides:0.01600814)99:0.01061137)97:0.01138461,((((Suckleya_suckleyana:0.02012189,(Cycloloma_atriplicifolium:0.00640215,(((Chenopodium_cristatum:0.00634437,Dysphania_glomulifera:0.00288888)82:0.00460287,Chenopodium_ambrosioides:0.00969603)22:0.00000102,Chenopodium_botrys:0.00526699)53:0.00107999)78:0.00625852)94:0.00776160,Teloxys_aristata:0.01280784)60:0.00226243,((((Hablitzia_tamnoides:0.01134794,(Aphanisma_blitoides:0.00619394,Patellifolia_patellaris:0.00764319)86:0.00433032)81:0.00373440,(Beta_vulgaris:0.00636735,Beta_nana:0.00208042)100:0.00762631)56:0.00483380,(((((Ptilotus_manglesii:0.01107055,(((Iresine_palmeri:0.00424920,((Gomphrena_elegans:0.00663687,(Pseudoplantago_friesii:0.00419924,Hebanthe_occidentalis:0.00000102)100:0.00949326)96:0.00646777,(((Guilleminea_densa:0.01097833,(Gomphrena_serrata:0.00106511,Gomphrena_haageana:0.00317777)95:0.00215240)73:0.00100613,Blutaparon_vermiculare:0.00106592)93:0.00746116,((Alternanthera_pungens:0.00211324,(Alternanthera_caracasana:0.00105849,Alternanthera_repens:0.00000102)70:0.00000102)100:0.01201192,Tidestromia_lanuginosa:0.02218561)74:0.00114104)66:0.00511913)79:0.00349103)36:0.00101479,Aerva_javanica:0.01510976)17:0.00000102,(Pupalia_lappacea:0.00526750,(((Sericostachys_scandens:0.00745715,(Achyranthes_aspera:0.00105486,Nototrichium_humile:0.00419384)94:0.00318201)42:0.00101179,Pandiaka_angustifolia:0.00633305)14:0.00000102,Calicorema_capitata:0.00209471)10:0.00000102)63:0.00209457)59:0.00062618)100:0.01733079,(((Chamissoa_altissima:0.02775692,((Amaranthus_greggii:0.00000102,Amaranthus_tricolor:0.00105299)83:0.00000102,(Amaranthus_blitum:0.00000102,Amaranthus_hypochondriacus:0.00643206)96:0.00318172)100:0.01451714)100:0.01188603,(Deeringia_amaranthoides:0.01401420,(Hermbstaedtia_glauca:0.01188740,(Celosia_trigyna:0.00334626,Celosia_argentea:0.00847134)100:0.01103714)89:0.00739590)78:0.00290398)96:0.01207656,(Charpentiera_ovata:0.00000102,Charpentiera_obovata:0.00209837)100:0.02101136)51:0.00404498)90:0.00873580,Bosea_yervamora:0.01246853)55:0.00123834,((Nitrophila_occidentalis:0.00423941,Hemichroa_diandra:0.00313045)100:0.00491046,Polycnemum_perenne:0.01602915)100:0.01564853)62:0.00340750,Oreobliton_thesioides:0.02566195)25:0.00231295)6:0.00112808,((((((Halocharis_hispida:0.00853137,(Salsola_vermiculata:0.01173181,(Salsola_implicata:0.00524366,((Salsola_orientalis:0.00000102,Salsola_dshungarica:0.00000102)96:0.00210063,Salsola_micranthera:0.00105274)89:0.00209641)51:0.00000102)96:0.00426190)96:0.00395543,((((Petrosimonia_glaucescens:0.00000102,Petrosimonia_squarrosa:0.00000102)100:0.00322210,Petrosimonia_nigdeensis:0.01301656)94:0.00193353,Petrosimonia_sibirica:0.00758872)91:0.00287087,(((Halimocnemis_villosa:0.00000102,Halimocnemis_karelinii:0.00000102)100:0.01067822,((Salsola_sukaczevii:0.00000102,(Salsola_ferganica:0.00000102,Salsola_heptapotamica:0.00000102)17:0.00000102)30:0.00000102,Climacoptera_lanata:0.00000102)99:0.00316698)85:0.00115767,(Salsola_affinis:0.00480242,Climacoptera_brachiata:0.00210931)82:0.00143556)94:0.00353572)93:0.00540349)77:0.00242058,(Nanophyton_erinaceum:0.01724365,(((((Kochia_americana:0.00536817,Bassia_diffusa:0.00421106)99:0.00431594,((Bassia_dasyphylla:0.00531623,(Maireana_brevifolia:0.00104529,(Sclerolaena_obliquicuspis:0.00315592,(Roycea_divaricata:0.00104718,Dissocarpus_paradoxus:0.00105135)41:0.00000102)64:0.00105266)74:0.00102656)83:0.00214954,((Kochia_densiflora:0.00848085,(Chenoleoides_tomentosa:0.00313108,(Bassia_prostrata:0.01079383,Panderia_pilosa:0.00868129)68:0.00199012)31:0.00000102)96:0.00634913,(Bassia_sedoides:0.00519018,Camphorosma_monspeliaca:0.01051475)97:0.00478526)83:0.00325729)60:0.00095378)100:0.01175947,((Sympegma_regelii:0.00955615,Halothamnus_bottae:0.00439455)53:0.00217134,((((((Salsola_rosacea:0.00167187,Noaea_mucronata:0.00464541)80:0.00215133,Ofaiston_monandrum:0.01030439)94:0.00355407,Rhaphidophyton_regelii:0.00208826)16:0.00000102,Salsola_arbusculiformis:0.00000102)14:0.00000102,Salsola_laricifolia:0.00209005)54:0.00104353,(((Anabasis_brevifolia:0.00000102,Anabasis_truncata:0.00314889)84:0.00104267,(Anabasis_eriopoda:0.00104311,(Anabasis_aphylla:0.00210649,(Anabasis_salsa:0.00000102,Anabasis_elatior:0.00104471)97:0.00209836)94:0.00210361)92:0.00211717)85:0.00209977,(((Girgensohnia_oppositiflora:0.00635314,(Halogeton_glomeratus:0.00638604,(Haloxylon_ammodendron:0.00000102,Haloxylon_persicum:0.00000102)100:0.00421249)47:0.00105843)19:0.00000102,((Haloxylon_tamariscifolium:0.00209455,(Horaninovia_ulicina:0.01192778,Halogeton_arachnoideus:0.00426781)66:0.00206553)12:0.00000102,Iljinia_regelii:0.00000102)8:0.00000102)64:0.00105483,Salsola_foliosa:0.00634975)69:0.00209463)20:0.00000102)94:0.00506880)62:0.00115837)56:0.00324816,(Salsola_arbuscula:0.00211160,(Salsola_kali:0.00104118,((Salsola_chinghaiensis:0.00104318,(Salsola_zaidamica:0.00104394,((Salsola_komarovii:0.00000102,Salsola_ruthenica:0.00000102)15:0.00000102,Salsola_collina:0.00000102)21:0.00000102)28:0.00000102)61:0.00104205,(Salsola_praecox:0.00000102,(Salsola_pellucida:0.00000102,Salsola_paulsenii:0.00000102)17:0.00000102)26:0.00000102)24:0.00000102)87:0.00207039)100:0.00528234)27:0.00105494,Salsola_genistoides:0.00314018)20:0.00104526)6:0.00000102)93:0.01140271,((((((Arthrocnemum_macrostachyum:0.00208856,(Sarcocornia_utahensis:0.00430842,Salicornia_europaea:0.01084361)45:0.00208472)28:0.00214026,((Tecticornia_disarticulata:0.00213150,Sclerostegia_moniliformis:0.00212837)94:0.00426304,(Tecticornia_australasica:0.00105460,((Salicornia_dolichostachya:0.01671719,Halosarcia_indica:0.00632785)54:0.00650166,Pachycornia_triandra:0.00319160)8:0.00000102)4:0.00000102)18:0.00107232)41:0.00217706,((Halostachys_belangeriana:0.00142728,Halopeplis_amplexicaulis:0.00498422)54:0.00319933,(Kalidium_cuspidatum:0.00536000,(Kalidium_caspicum:0.00424783,Kalidium_foliatum:0.00000102)29:0.00000102)84:0.00285700)76:0.00467946)38:0.00134451,Allenrolfea_occidentalis:0.00724180)62:0.00692387,Bienertia_cycloptera:0.01313946)79:0.00702054,((Suaeda_maritima:0.00490738,Suaeda_crassifolia:0.00388120)100:0.01891477,((Suaeda_physophora:0.00588870,Suaeda_microphylla:0.00486985)82:0.00972204,Suaeda_altissima:0.01306847)65:0.00725815)56:0.00443597)80:0.00709752)100:0.01330392,(Agriophyllum_squarrosum:0.01187852,(Corispermum_filifolium:0.00957955,Anthochlamys_multinervis:0.00119607)94:0.00642820)92:0.00603656)35:0.00283291,Acroglochin_chenopodioides:0.01944356)15:0.00152637)14:0.00377071)12:0.00227794,(((Monolepis_nuttalliana:0.00314556,Spinacia_oleracea:0.02411154)100:0.01335566,Chenopodium_foliosum:0.00648643)34:0.00205671,Chenopodium_bonushenricus:0.00310884)39:0.00219374)19:0.00092256)97:0.00745230,Chenopodium_coronopus:0.00690985)99:0.00615396,(Microgynoecium_tibeticum:0.01320943,((((Chenopodium_acuminatum:0.00209272,((Chenopodium_album:0.00000102,Chenopodium_murale:0.00104331)96:0.00314773,Chenopodium_sanctaeclarae:0.00423868)18:0.00000102)5:0.00000102,Chenopodium_frutescens:0.00000102)25:0.00000102,Micromonolepis_pusilla:0.00526085)69:0.00099815,((Einadia_nutans:0.00104063,Rhagodia_drummondi:0.00000102)88:0.00208881,(Chenopodium_desertorum:0.00104282,Chenopodium_auricomum:0.00104393)38:0.00000102)64:0.00321817)100:0.01116813)80:0.00067388)99:0.00433628,(Manochlamys_albicans:0.00519597,Archiatriplex_nanpinensis:0.00861502)61:0.00212072)63:0.00206883)100:0.00649188,(((((Atriplex_parryi:0.00104219,((Atriplex_phyllostegia:0.00104244,Atriplex_serenana:0.00000102)43:0.00000102,Atriplex_powellii:0.00104263)87:0.00209024)11:0.00000102,((Atriplex_lampa:0.00209727,Atriplex_undulata:0.00104916)67:0.00103801,Atriplex_lentiformis:0.00104296)12:0.00000102)38:0.00000102,(((Atriplex_spongiosa:0.00104854,Atriplex_rosea:0.00313774)73:0.00000102,Atriplex_centralasiatica:0.00419604)53:0.00105750,Atriplex_glauca:0.00419623)72:0.00209055)42:0.00104288,Atriplex_coriacea:0.00419172)61:0.00104689,(Atriplex_halimus:0.00208849,Cremnophyton_lanfrancoi:0.00000102)16:0.00000102)28:0.00000102)58:0.00104026,(Atriplex_australasica:0.00000102,Atriplex_patula:0.00000102)62:0.00000102,Atriplex_aucherii:0.00208586);

data/rubisco/rubisco_species

+Achyranthes_aspera	C3
+Acroglochin_chenopodioides C3
+Aerva_javanica	C4
+Agriophyllum_squarrosum	C3
+Allenrolfea_occidentalis	C3
+Alternanthera_caracasana	C4
+Alternanthera_pungens	C4
+Alternanthera_repens	C4
+Amaranthus_blitum	C4
+Amaranthus_greggii	C4
+Amaranthus_hypochondriacus	C4
+Amaranthus_tricolor	C4
+Anabasis_aphylla	C4
+Anabasis_brevifolia	C4
+Anabasis_elatior	C4
+Anabasis_eriopoda	C4
+Anabasis_salsa	C4
+Anabasis_truncata	C4
+Anthochlamys_multinervis	C3
+Aphanisma_blitoides	C3
+Archiatriplex_nanpinensis	C3
+Arthrocnemum_macrostachyum	C3
+Atriplex_aucherii	C3
+Atriplex_australasica	C3
+Atriplex_centralasiatica	C4
+Atriplex_coriacea	C4
+Atriplex_glauca	C4
+Atriplex_halimus	C4
+Atriplex_lampa	C4
+Atriplex_lentiformis	C4
+Atriplex_parryi	C4
+Atriplex_patula	C3
+Atriplex_phyllostegia	C4
+Atriplex_powellii	C4
+Atriplex_rosea	C4
+Atriplex_serenana	C4
+Atriplex_spongiosa	C4
+Atriplex_undulata	C4
+Axyris_prostrata	C3
+Bassia_dasyphylla	C3
+Bassia_diffusa	C3
+Bassia_prostrata	C4
+Bassia_sedoides	C4
+Beta_nana	C3
+Beta_vulgaris	C3
+Bienertia_cycloptera	C4
+Blutaparon_vermiculare	C4
+Bosea_yervamora	C3
+Calicorema_capitata	C3
+Camphorosma_monspeliaca	C4
+Celosia_argentea	C3
+Celosia_trigyna	C3
+Ceratocarpus_arenarius	C3
+Chamissoa_altissima	C3
+Charpentiera_obovata	C3
+Charpentiera_ovata	C3
+Chenoleoides_tomentosa	C4
+Chenopodium_acuminatum	C3
+Chenopodium_album	C3
+Chenopodium_ambrosioides	C3
+Chenopodium_auricomum	C3
+Chenopodium_bonushenricus	C3
+Chenopodium_botrys	C3
+Chenopodium_coronopus	C3
+Chenopodium_cristatum	C3
+Chenopodium_desertorum	C3
+Chenopodium_foliosum	C3
+Chenopodium_frutescens	C3
+Chenopodium_murale	C3
+Chenopodium_sanctaeclarae	C3
+Climacoptera_brachiata	C4
+Climacoptera_lanata	C4
+Corispermum_filifolium	C3
+Cremnophyton_lanfrancoi	C3
+Cycloloma_atriplicifolium	C3
+Deeringia_amaranthoides	C3
+Dissocarpus_paradoxus	C3
+Dysphania_glomulifera	C3
+Einadia_nutans	C3
+Girgensohnia_oppositiflora	C4
+Gomphrena_elegans	C3
+Gomphrena_haageana	C4
+Gomphrena_serrata	C4
+Guilleminea_densa	C4
+Hablitzia_tamnoides	C3
+Halimione_pedunculata	C3
+Halimione_verrucifera	C3
+Halimocnemis_karelinii	C4
+Halimocnemis_villosa	C4
+Halocharis_hispida	C4
+Halogeton_arachnoideus	C4
+Halogeton_glomeratus	C4
+Halopeplis_amplexicaulis	C3
+Halosarcia_indica	C4
+Halostachys_belangeriana	C3
+Halothamnus_bottae	C4
+Haloxylon_ammodendron	C4
+Haloxylon_persicum	C4
+Haloxylon_tamariscifolium	C4
+Hebanthe_occidentalis	C3
+Hemichroa_diandra	C3
+Hermbstaedtia_glauca	C3
+Horaninovia_ulicina	C4
+Iljinia_regelii	C4
+Iresine_palmeri	C3
+Kalidium_caspicum	C3
+Kalidium_cuspidatum	C3
+Kalidium_foliatum	C3
+Kochia_americana	C3
+Kochia_densiflora	C4
+Krascheninnikovia_ceratoides	C3
+Maireana_brevifolia	C3
+Manochlamys_albicans	C3
+Microgynoecium_tibeticum	C3
+Micromonolepis_pusilla	C3
+Monolepis_nuttalliana	C3
+Nanophyton_erinaceum	C4
+Nitrophila_occidentalis	C3
+Noaea_mucronata	C4
+Nototrichium_humile	C3
+Ofaiston_monandrum	C4
+Oreobliton_thesioides	C3
+Pachycornia_triandra	C3
+Panderia_pilosa	C4
+Pandiaka_angustifolia	C3
+Patellifolia_patellaris	C3
+Petrosimonia_glaucescens	C4
+Petrosimonia_nigdeensis	C4
+Petrosimonia_sibirica	C4
+Petrosimonia_squarrosa	C4
+Polycnemum_perenne	C3
+Pseudoplantago_friesii	C3
+Ptilotus_manglesii	C3
+Pupalia_lappacea	C3
+Rhagodia_drummondi	C3
+Rhaphidophyton_regelii	C3
+Roycea_divaricata	C3
+Salicornia_dolichostachya	C3
+Salicornia_europaea	C3
+Salsola_affinis	C4
+Salsola_arbuscula	C4
+Salsola_arbusculiformis	C3
+Salsola_chinghaiensis	C4
+Salsola_collina	C4
+Salsola_dshungarica	C4
+Salsola_ferganica	C4
+Salsola_foliosa	C4
+Salsola_genistoides	C3
+Salsola_heptapotamica	C4
+Salsola_implicata	C4
+Salsola_kali	C4
+Salsola_komarovii	C4
+Salsola_laricifolia	C3
+Salsola_micranthera	C4
+Salsola_orientalis	C4
+Salsola_paulsenii	C4
+Salsola_pellucida	C4
+Salsola_praecox	C4
+Salsola_rosacea	C4
+Salsola_ruthenica	C4
+Salsola_sukaczevii	C4
+Salsola_vermiculata	C4
+Salsola_zaidamica	C4
+Sarcocornia_utahensis	C3
+Sclerolaena_obliquicuspis	C3
+Sclerostegia_moniliformis	C3
+Sericostachys_scandens	C3
+Spinacia_oleracea	C3
+Suaeda_altissima	C4
+Suaeda_crassifolia	C3
+Suaeda_maritima	C3
+Suaeda_microphylla	C4
+Suaeda_physophora	C3
+Suckleya_suckleyana	C3
+Sympegma_regelii	C3
+Tecticornia_australasica	C3
+Tecticornia_disarticulata	C3
+Teloxys_aristata	C3
+Tidestromia_lanuginosa	C4