adibvafa commited on
Commit
e795403
·
verified ·
1 Parent(s): f190e8a

Upload organism_mapper.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. organism_mapper.json +409 -0
organism_mapper.json ADDED
@@ -0,0 +1,409 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "organism_to_idx": {
3
+ "<UNKNOWN>": 0,
4
+ "Aedes aegypti (Yellowfever mosquito) (Culex aegypti)": 1,
5
+ "Agrobacterium fabrum (strain C58 / ATCC 33970) (Agrobacterium tumefaciens (strain C58))": 2,
6
+ "Aliivibrio fischeri (strain ATCC 700601 / ES114) (Vibrio fischeri)": 3,
7
+ "Amycolatopsis orientalis (Nocardia orientalis)": 4,
8
+ "Anaplasma phagocytophilum (strain HZ)": 5,
9
+ "Anguilla japonica (Japanese eel)": 6,
10
+ "Anopheles gambiae (African malaria mosquito)": 7,
11
+ "Apis mellifera (Honeybee)": 8,
12
+ "Aquifex aeolicus (strain VF5)": 9,
13
+ "Arabidopsis thaliana (Mouse-ear cress)": 10,
14
+ "Archaeoglobus fulgidus (strain ATCC 49558 / DSM 4304 / JCM 9628 / NBRC 100126 / VC-16)": 11,
15
+ "Aspergillus fumigatus (strain ATCC MYA-4609 / CBS 101355 / FGSC A1100 / Af293) (Neosartorya fumigata)": 12,
16
+ "Aspergillus niger": 13,
17
+ "Aspergillus niger (strain ATCC MYA-4892 / CBS 513.88 / FGSC A1513)": 14,
18
+ "Aspergillus oryzae (strain ATCC 42149 / RIB 40) (Yellow koji mold)": 15,
19
+ "Aspergillus parasiticus (strain ATCC 56775 / NRRL 5862 / SRRC 143 / SU-1)": 16,
20
+ "Autographa californica nuclear polyhedrosis virus (AcMNPV)": 17,
21
+ "Bacillus anthracis": 18,
22
+ "Bacillus phage phi29 (Bacteriophage phi-29)": 19,
23
+ "Bacillus subtilis (strain 168)": 20,
24
+ "Bacteroides thetaiotaomicron (strain ATCC 29148 / DSM 2079 / JCM 5827 / CCUG 10774 / NCTC 10582 / VPI-5482 / E50)": 21,
25
+ "Bombyx mori (Silk moth)": 22,
26
+ "Borreliella burgdorferi (strain ATCC 35210 / DSM 4680 / CIP 102532 / B31) (Borrelia burgdorferi)": 23,
27
+ "Bos taurus (Bovine)": 24,
28
+ "Bovine herpesvirus 1.1 (strain Cooper) (BoHV-1) (Infectious bovine rhinotracheitis virus)": 25,
29
+ "Brucella abortus (strain 2308)": 26,
30
+ "Caenorhabditis elegans": 27,
31
+ "Campylobacter jejuni subsp. jejuni serotype O:2 (strain ATCC 700819 / NCTC 11168)": 28,
32
+ "Candida albicans (Yeast)": 29,
33
+ "Candida albicans (strain SC5314 / ATCC MYA-2876) (Yeast)": 30,
34
+ "Candida auris (Yeast)": 31,
35
+ "Candida glabrata (strain ATCC 2001 / BCRC 20586 / JCM 3761 / NBRC 0622 /": 32,
36
+ "Candida glabrata (strain ATCC 2001 / BCRC 20586 / JCM 3761 / NBRC 0622 / NRRL Y-65 / CBS 138) (Yeast) (Nakaseomyces glabratus)": 33,
37
+ "Candida parapsilosis (strain CDC 317 / ATCC MYA-4646) (Yeast) (Monilia parapsilosis)": 34,
38
+ "Canis lupus familiaris (Dog) (Canis familiaris)": 35,
39
+ "Capsicum annuum (Capsicum pepper)": 36,
40
+ "Catharanthus roseus (Madagascar periwinkle) (Vinca rosea)": 37,
41
+ "Caulobacter vibrioides (strain ATCC 19089 / CIP 103742 / CB 15) (Caulobacter crescentus)": 38,
42
+ "Cavia porcellus (Guinea pig)": 39,
43
+ "Cereibacter sphaeroides (strain ATCC 17023 / DSM 158 / JCM 6121 / CCUG 31486 / LMG 2827 / NBRC 12203 / NCIMB 8253 / ATH 2.4.1.) (Rhodobacter sphaeroides)": 40,
44
+ "Chaetomium thermophilum (strain DSM 1495 / CBS 144.50 / IMI 039719)": 41,
45
+ "Chaetomium thermophilum (strain DSM 1495 / CBS 144.50 / IMI 039719) (Thermochaetoides thermophila)": 42,
46
+ "Chlamydomonas reinhardtii (Chlamydomonas smithii)": 43,
47
+ "Clostridium acetobutylicum (strain ATCC 824 / DSM 792 / JCM 1419 / IAM 19013 / LMG 5710 / NBRC 13948 / NRRL B-527 / VKM B-1787 / 2291 / W)": 44,
48
+ "Corynebacterium glutamicum (strain ATCC 13032 / DSM 20300 / JCM 1318 / BCRC 11384 / CCUG 27702 / LMG 3730 / NBRC 12168 / NCIMB 10025 / NRRL B-2784 / 534)": 45,
49
+ "Coturnix japonica (Japanese quail) (Coturnix coturnix japonica)": 46,
50
+ "Cricetulus griseus (Chinese hamster) (Cricetulus barabensis griseus)": 47,
51
+ "Cryptococcus neoformans var. grubii serotype A (strain H99 / ATCC 208821 / CBS 10515 / FGSC 9487) (Filobasidiella neoformans var. grubii)": 48,
52
+ "Danio rerio (Zebrafish) (Brachydanio rerio)": 49,
53
+ "Deinococcus radiodurans (strain ATCC 13939 / DSM 20539 / JCM 16871 / CCUG 27074 / LMG 4051 / NBRC 15346 / NCIMB 9279 / VKM B-1422 / R1)": 50,
54
+ "Dickeya dadantii (strain 3937) (Erwinia chrysanthemi (strain 3937))": 51,
55
+ "Dictyostelium discoideum (Social amoeba)": 52,
56
+ "Drosophila melanogaster (Fruit fly)": 53,
57
+ "Emericella nidulans (Aspergillus nidulans)": 54,
58
+ "Emericella nidulans (strain FGSC A4 / ATCC 38163 / CBS 112.46 / NRRL 194 / M139) (Aspergillus nidulans)": 55,
59
+ "Entamoeba histolytica (strain ATCC 30459 / HM-1:IMSS / ABRM)": 56,
60
+ "Enterobacteria phage T4 (Bacteriophage T4)": 57,
61
+ "Epstein-Barr virus (strain B95-8) (HHV-4) (Human herpesvirus 4)": 58,
62
+ "Equus caballus (Horse)": 59,
63
+ "Escherichia coli": 60,
64
+ "Escherichia coli (strain K12)": 61,
65
+ "Escherichia coli O157:H7": 62,
66
+ "Escherichia phage T5 (Enterobacteria phage T5)": 63,
67
+ "Escherichia phage lambda (Bacteriophage lambda)": 64,
68
+ "Eubacterium barkeri (Clostridium barkeri)": 65,
69
+ "Gallus gallus (Chicken)": 66,
70
+ "Geobacillus stearothermophilus (Bacillus stearothermophilus)": 67,
71
+ "Giardia intestinalis (strain ATCC 50803 / WB clone C6) (Giardia lamblia)": 68,
72
+ "Glycine max (Soybean) (Glycine hispida)": 69,
73
+ "Gossypium hirsutum (Upland cotton) (Gossypium mexicanum)": 70,
74
+ "Haemophilus influenzae (strain ATCC 51907 / DSM 11121 / KW20 / Rd)": 71,
75
+ "Haloferax volcanii (strain ATCC 29605 / DSM 3757 / JCM 8879 / NBRC 14742 / NCIMB 2012 / VKM B-1768 / DS2) (Halobacterium volcanii)": 72,
76
+ "Helicobacter pylori (strain ATCC 700392 / 26695) (Campylobacter pylori)": 73,
77
+ "Homo sapiens (Human)": 74,
78
+ "Hordeum vulgare (Barley)": 75,
79
+ "Human adenovirus C serotype 2 (HAdV-2) (Human adenovirus 2)": 76,
80
+ "Human adenovirus C serotype 5 (HAdV-5) (Human adenovirus 5)": 77,
81
+ "Human cytomegalovirus (strain AD169) (HHV-5) (Human herpesvirus 5)": 78,
82
+ "Human cytomegalovirus (strain Merlin) (HHV-5) (Human herpesvirus 5)": 79,
83
+ "Human herpesvirus 1 (strain 17) (HHV-1) (Human herpes simplex virus 1)": 80,
84
+ "Human herpesvirus 8 (HHV-8) (Kaposi's sarcoma-associated herpesvirus)": 81,
85
+ "Human herpesvirus 8 type P (isolate GK18) (HHV-8) (Kaposi's sarcoma-associated herpesvirus)": 82,
86
+ "Hypocrea jecorina (Trichoderma reesei)": 83,
87
+ "Ictalurus punctatus (Channel catfish) (Silurus punctatus)": 84,
88
+ "Influenza A virus (strain A/Puerto Rico/8/1934 H1N1)": 85,
89
+ "Lactococcus lactis subsp. cremoris (strain MG1363)": 86,
90
+ "Lactococcus lactis subsp. lactis (strain IL1403) (Streptococcus lactis)": 87,
91
+ "Legionella pneumophila subsp. pneumophila (strain Philadelphia 1 / ATCC 33152 / DSM 7513)": 88,
92
+ "Leishmania major": 89,
93
+ "Listeria monocytogenes serovar 1/2a (strain ATCC BAA-679 / EGD-e)": 90,
94
+ "Lotus japonicus (Lotus corniculatus var. japonicus)": 91,
95
+ "Macaca fascicularis (Crab-eating macaque) (Cynomolgus monkey)": 92,
96
+ "Macaca mulatta (Rhesus macaque)": 93,
97
+ "Malus domestica (Apple) (Pyrus malus)": 94,
98
+ "Manduca sexta (Tobacco hawkmoth) (Tobacco hornworm)": 95,
99
+ "Medicago truncatula (Barrel medic) (Medicago tribuloides)": 96,
100
+ "Meleagris gallopavo (Wild turkey)": 97,
101
+ "Mesocricetus auratus (Golden hamster)": 98,
102
+ "Methanocaldococcus jannaschii (strain ATCC 43067 / DSM 2661 / JAL-1 / JCM 10045 / NBRC 100440) (Methanococcus jannaschii)": 99,
103
+ "Methanococcus maripaludis (strain DSM 14266 / JCM 13030 / NBRC 101832 / S2 / LL)": 100,
104
+ "Methanothermobacter marburgensis (strain ATCC BAA-927 / DSM 2133 / JCM 14651 / NBRC 100331 / OCM 82 / Marburg) (Methanobacterium thermoautotrophicum)": 101,
105
+ "Mus musculus (Mouse)": 102,
106
+ "Mycobacterium bovis (strain ATCC BAA-935 / AF2122/97)": 103,
107
+ "Mycobacterium tuberculosis (strain ATCC 25618 / H37Rv)": 104,
108
+ "Mycobacterium tuberculosis (strain CDC 1551 / Oshkosh)": 105,
109
+ "Mycolicibacterium smegmatis (strain ATCC 700084 / mc(2)155) (Mycobacterium smegmatis)": 106,
110
+ "Mycoplasma pneumoniae (strain ATCC 29342 / M129 / Subtype 1) (Mycoplasmoides pneumoniae)": 107,
111
+ "Myxococcus xanthus (strain DK1622)": 108,
112
+ "Neisseria gonorrhoeae": 109,
113
+ "Neisseria gonorrhoeae (strain ATCC 700825 / FA 1090)": 110,
114
+ "Neisseria meningitidis serogroup B (strain ATCC BAA-335 / MC58)": 111,
115
+ "Nematostella vectensis (Starlet sea anemone)": 112,
116
+ "Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987)": 113,
117
+ "Nicotiana tabacum (Common tobacco)": 114,
118
+ "Nitratidesulfovibrio vulgaris (strain ATCC 29579 / DSM 644 / CCUG 34227 / NCIMB 8303 / VKM B-1760 / Hildenborough) (Desulfovibrio vulgaris)": 115,
119
+ "Nostoc sp. (strain PCC 7120 / SAG 25.82 / UTEX 2576)": 116,
120
+ "Oncorhynchus mykiss (Rainbow trout) (Salmo gairdneri)": 117,
121
+ "Oryctolagus cuniculus (Rabbit)": 118,
122
+ "Oryza nivara (Indian wild rice) (Oryza sativa f. spontanea)": 119,
123
+ "Oryza sativa (Rice)": 120,
124
+ "Oryza sativa subsp. indica (Rice)": 121,
125
+ "Oryza sativa subsp. japonica (Rice)": 122,
126
+ "Oryzias latipes (Japanese rice fish) (Japanese killifish)": 123,
127
+ "Ovis aries (Sheep)": 124,
128
+ "Panax ginseng (Korean ginseng)": 125,
129
+ "Papaver somniferum (Opium poppy)": 126,
130
+ "Penicillium brevicompactum": 127,
131
+ "Penicillium expansum (Blue mold rot fungus)": 128,
132
+ "Petunia hybrida (Petunia)": 129,
133
+ "Physcomitrium patens (Spreading-leaved earth moss) (Physcomitrella patens)": 130,
134
+ "Picea sitchensis (Sitka spruce) (Pinus sitchensis)": 131,
135
+ "Pisum sativum (Garden pea) (Lathyrus oleraceus)": 132,
136
+ "Plasmodium berghei (strain Anka)": 133,
137
+ "Plasmodium falciparum (isolate 3D7)": 134,
138
+ "Plasmodium falciparum (isolate HB3)": 135,
139
+ "Porphyromonas gingivalis (strain ATCC 33277 / DSM 20709 / CIP 103683 / JCM 12257 / NCTC 11834 / 2561)": 136,
140
+ "Pseudomonas aeruginosa": 137,
141
+ "Pseudomonas aeruginosa (strain ATCC 15692 / DSM 22644 / CIP 104116 / JCM 14847 / LMG 12228 / 1C / PRS 101 / PAO1)": 138,
142
+ "Pseudomonas fluorescens (strain ATCC BAA-477 / NRRL B-23932 / Pf-5)": 139,
143
+ "Pseudomonas putida (Arthrobacter siderocapsulatus)": 140,
144
+ "Pseudomonas putida (strain ATCC 47054 / DSM 6125 / CFBP 8728 / NCIMB 11950 / KT2440)": 141,
145
+ "Pseudomonas syringae pv. tomato (strain ATCC BAA-871 / DC3000)": 142,
146
+ "Pyricularia oryzae (strain 70-15 / ATCC MYA-4617 / FGSC 8958) (Rice blast fungus) (Magnaporthe oryzae)": 143,
147
+ "Pyrococcus abyssi (strain GE5 / Orsay)": 144,
148
+ "Pyrococcus furiosus (strain ATCC 43587 / DSM 3638 / JCM 8422 / Vc1)": 145,
149
+ "Pyrococcus horikoshii (strain ATCC 700860 / DSM 12428 / JCM 9974 / NBRC 100139 / OT-3)": 146,
150
+ "Ralstonia sp": 147,
151
+ "Rattus norvegicus (Rat)": 148,
152
+ "Rhizobium meliloti (strain 1021) (Ensifer meliloti) (Sinorhizobium meliloti)": 149,
153
+ "Rhodobacter capsulatus (strain ATCC BAA-309 / NBRC 16581 / SB1003)": 150,
154
+ "Ricinus communis (Castor bean)": 151,
155
+ "Ruegeria pomeroyi (strain ATCC 700808 / DSM 15171 / DSS-3) (Silicibacter pomeroyi)": 152,
156
+ "Saccharolobus solfataricus (strain ATCC 35092 / DSM 1617 / JCM 11322 / P2) (Sulfolobus solfataricus)": 153,
157
+ "Saccharomyces cerevisiae (strain ATCC 204508 / S288c) (Baker's yeast)": 154,
158
+ "Salmo salar (Atlantic salmon)": 155,
159
+ "Salmonella typhimurium (strain 14028s / SGSC 2262)": 156,
160
+ "Salmonella typhimurium (strain LT2 / SGSC1412 / ATCC 700720)": 157,
161
+ "Salmonella typhimurium (strain SL1344)": 158,
162
+ "Schizosaccharomyces pombe (strain 972 / ATCC 24843) (Fission yeast)": 159,
163
+ "Serratia marcescens": 160,
164
+ "Severe acute respiratory syndrome coronavirus (SARS-CoV)": 161,
165
+ "Severe acute respiratory syndrome coronavirus 2 (2019-nCoV) (SARS-CoV-2)": 162,
166
+ "Shewanella oneidensis (strain ATCC 700550 / JCM 31522 / CIP 106686 / LMG 19005 / NCIMB 14063 / MR-1)": 163,
167
+ "Shigella flexneri": 164,
168
+ "Solanum lycopersicum (Tomato) (Lycopersicon esculentum)": 165,
169
+ "Solanum tuberosum (Potato)": 166,
170
+ "Spinacia oleracea (Spinach)": 167,
171
+ "Staphylococcus aureus": 168,
172
+ "Staphylococcus aureus (strain NCTC 8325 / PS 47)": 169,
173
+ "Streptococcus mutans serotype c (strain ATCC 700610 / UA159)": 170,
174
+ "Streptococcus pneumoniae (strain ATCC BAA-255 / R6)": 171,
175
+ "Streptococcus pneumoniae serotype 2 (strain D39 / NCTC 7466)": 172,
176
+ "Streptococcus pneumoniae serotype 4 (strain ATCC BAA-334 / TIGR4)": 173,
177
+ "Streptomyces coelicolor (strain ATCC BAA-471 / A3(2) / M145)": 174,
178
+ "Streptomyces niveus (Streptomyces spheroides)": 175,
179
+ "Sulfolobus acidocaldarius (strain ATCC 33909 / DSM 639 / JCM 8929 / NBRC 15157 / NCIMB 11770)": 176,
180
+ "Sus scrofa (Pig)": 177,
181
+ "Synechococcus elongatus (strain ATCC 33912 / PCC 7942 / FACHB-805) (Anacystis nidulans R2)": 178,
182
+ "Synechocystis sp. (strain ATCC 27184 / PCC 6803 / Kazusa)": 179,
183
+ "Tachypleus tridentatus (Japanese horseshoe crab)": 180,
184
+ "Taeniopygia guttata (Zebra finch) (Poephila guttata)": 181,
185
+ "Tetrahymena thermophila (strain SB210)": 182,
186
+ "Thermococcus kodakarensis (strain ATCC BAA-918 / JCM 12380 / KOD1) (Pyrococcus kodakaraensis (strain KOD1))": 183,
187
+ "Thermoplasma acidophilum (strain ATCC 25905 / DSM 1728 / JCM 9062 / NBRC 15155 / AMRC-C165)": 184,
188
+ "Thermotoga maritima (strain ATCC 43589 / DSM 3109 / JCM 10099 / NBRC 100826 / MSB8)": 185,
189
+ "Thermus thermophilus (strain ATCC 27634 / DSM 579 / HB8)": 186,
190
+ "Thermus thermophilus (strain ATCC BAA-163 / DSM 7039 / HB27)": 187,
191
+ "Triticum aestivum (Wheat)": 188,
192
+ "Trypanosoma brucei": 189,
193
+ "Trypanosoma brucei brucei": 190,
194
+ "Trypanosoma brucei brucei (strain 927/4 GUTat10.1)": 191,
195
+ "Vaccinia virus (strain Western Reserve) (VACV) (Vaccinia virus (strain WR))": 192,
196
+ "Vibrio cholerae serotype O1 (strain ATCC 39315 / El Tor Inaba N16961)": 193,
197
+ "Vibrio cholerae serotype O1 (strain ATCC 39541 / Classical Ogawa 395 / O395)": 194,
198
+ "Vibrio vulnificus (strain YJ016)": 195,
199
+ "Xanthomonas campestris pv. campestris (strain ATCC 33913 / DSM 3586 / NCPPB 528 / LMG 568 / P 25)": 196,
200
+ "Xenopus laevis (African clawed frog)": 197,
201
+ "Xenopus tropicalis (Western clawed frog) (Silurana tropicalis)": 198,
202
+ "Yersinia pestis": 199,
203
+ "Zea mays (Maize)": 200
204
+ },
205
+ "idx_to_organism": {
206
+ "0": "<UNKNOWN>",
207
+ "1": "Aedes aegypti (Yellowfever mosquito) (Culex aegypti)",
208
+ "2": "Agrobacterium fabrum (strain C58 / ATCC 33970) (Agrobacterium tumefaciens (strain C58))",
209
+ "3": "Aliivibrio fischeri (strain ATCC 700601 / ES114) (Vibrio fischeri)",
210
+ "4": "Amycolatopsis orientalis (Nocardia orientalis)",
211
+ "5": "Anaplasma phagocytophilum (strain HZ)",
212
+ "6": "Anguilla japonica (Japanese eel)",
213
+ "7": "Anopheles gambiae (African malaria mosquito)",
214
+ "8": "Apis mellifera (Honeybee)",
215
+ "9": "Aquifex aeolicus (strain VF5)",
216
+ "10": "Arabidopsis thaliana (Mouse-ear cress)",
217
+ "11": "Archaeoglobus fulgidus (strain ATCC 49558 / DSM 4304 / JCM 9628 / NBRC 100126 / VC-16)",
218
+ "12": "Aspergillus fumigatus (strain ATCC MYA-4609 / CBS 101355 / FGSC A1100 / Af293) (Neosartorya fumigata)",
219
+ "13": "Aspergillus niger",
220
+ "14": "Aspergillus niger (strain ATCC MYA-4892 / CBS 513.88 / FGSC A1513)",
221
+ "15": "Aspergillus oryzae (strain ATCC 42149 / RIB 40) (Yellow koji mold)",
222
+ "16": "Aspergillus parasiticus (strain ATCC 56775 / NRRL 5862 / SRRC 143 / SU-1)",
223
+ "17": "Autographa californica nuclear polyhedrosis virus (AcMNPV)",
224
+ "18": "Bacillus anthracis",
225
+ "19": "Bacillus phage phi29 (Bacteriophage phi-29)",
226
+ "20": "Bacillus subtilis (strain 168)",
227
+ "21": "Bacteroides thetaiotaomicron (strain ATCC 29148 / DSM 2079 / JCM 5827 / CCUG 10774 / NCTC 10582 / VPI-5482 / E50)",
228
+ "22": "Bombyx mori (Silk moth)",
229
+ "23": "Borreliella burgdorferi (strain ATCC 35210 / DSM 4680 / CIP 102532 / B31) (Borrelia burgdorferi)",
230
+ "24": "Bos taurus (Bovine)",
231
+ "25": "Bovine herpesvirus 1.1 (strain Cooper) (BoHV-1) (Infectious bovine rhinotracheitis virus)",
232
+ "26": "Brucella abortus (strain 2308)",
233
+ "27": "Caenorhabditis elegans",
234
+ "28": "Campylobacter jejuni subsp. jejuni serotype O:2 (strain ATCC 700819 / NCTC 11168)",
235
+ "29": "Candida albicans (Yeast)",
236
+ "30": "Candida albicans (strain SC5314 / ATCC MYA-2876) (Yeast)",
237
+ "31": "Candida auris (Yeast)",
238
+ "32": "Candida glabrata (strain ATCC 2001 / BCRC 20586 / JCM 3761 / NBRC 0622 /",
239
+ "33": "Candida glabrata (strain ATCC 2001 / BCRC 20586 / JCM 3761 / NBRC 0622 / NRRL Y-65 / CBS 138) (Yeast) (Nakaseomyces glabratus)",
240
+ "34": "Candida parapsilosis (strain CDC 317 / ATCC MYA-4646) (Yeast) (Monilia parapsilosis)",
241
+ "35": "Canis lupus familiaris (Dog) (Canis familiaris)",
242
+ "36": "Capsicum annuum (Capsicum pepper)",
243
+ "37": "Catharanthus roseus (Madagascar periwinkle) (Vinca rosea)",
244
+ "38": "Caulobacter vibrioides (strain ATCC 19089 / CIP 103742 / CB 15) (Caulobacter crescentus)",
245
+ "39": "Cavia porcellus (Guinea pig)",
246
+ "40": "Cereibacter sphaeroides (strain ATCC 17023 / DSM 158 / JCM 6121 / CCUG 31486 / LMG 2827 / NBRC 12203 / NCIMB 8253 / ATH 2.4.1.) (Rhodobacter sphaeroides)",
247
+ "41": "Chaetomium thermophilum (strain DSM 1495 / CBS 144.50 / IMI 039719)",
248
+ "42": "Chaetomium thermophilum (strain DSM 1495 / CBS 144.50 / IMI 039719) (Thermochaetoides thermophila)",
249
+ "43": "Chlamydomonas reinhardtii (Chlamydomonas smithii)",
250
+ "44": "Clostridium acetobutylicum (strain ATCC 824 / DSM 792 / JCM 1419 / IAM 19013 / LMG 5710 / NBRC 13948 / NRRL B-527 / VKM B-1787 / 2291 / W)",
251
+ "45": "Corynebacterium glutamicum (strain ATCC 13032 / DSM 20300 / JCM 1318 / BCRC 11384 / CCUG 27702 / LMG 3730 / NBRC 12168 / NCIMB 10025 / NRRL B-2784 / 534)",
252
+ "46": "Coturnix japonica (Japanese quail) (Coturnix coturnix japonica)",
253
+ "47": "Cricetulus griseus (Chinese hamster) (Cricetulus barabensis griseus)",
254
+ "48": "Cryptococcus neoformans var. grubii serotype A (strain H99 / ATCC 208821 / CBS 10515 / FGSC 9487) (Filobasidiella neoformans var. grubii)",
255
+ "49": "Danio rerio (Zebrafish) (Brachydanio rerio)",
256
+ "50": "Deinococcus radiodurans (strain ATCC 13939 / DSM 20539 / JCM 16871 / CCUG 27074 / LMG 4051 / NBRC 15346 / NCIMB 9279 / VKM B-1422 / R1)",
257
+ "51": "Dickeya dadantii (strain 3937) (Erwinia chrysanthemi (strain 3937))",
258
+ "52": "Dictyostelium discoideum (Social amoeba)",
259
+ "53": "Drosophila melanogaster (Fruit fly)",
260
+ "54": "Emericella nidulans (Aspergillus nidulans)",
261
+ "55": "Emericella nidulans (strain FGSC A4 / ATCC 38163 / CBS 112.46 / NRRL 194 / M139) (Aspergillus nidulans)",
262
+ "56": "Entamoeba histolytica (strain ATCC 30459 / HM-1:IMSS / ABRM)",
263
+ "57": "Enterobacteria phage T4 (Bacteriophage T4)",
264
+ "58": "Epstein-Barr virus (strain B95-8) (HHV-4) (Human herpesvirus 4)",
265
+ "59": "Equus caballus (Horse)",
266
+ "60": "Escherichia coli",
267
+ "61": "Escherichia coli (strain K12)",
268
+ "62": "Escherichia coli O157:H7",
269
+ "63": "Escherichia phage T5 (Enterobacteria phage T5)",
270
+ "64": "Escherichia phage lambda (Bacteriophage lambda)",
271
+ "65": "Eubacterium barkeri (Clostridium barkeri)",
272
+ "66": "Gallus gallus (Chicken)",
273
+ "67": "Geobacillus stearothermophilus (Bacillus stearothermophilus)",
274
+ "68": "Giardia intestinalis (strain ATCC 50803 / WB clone C6) (Giardia lamblia)",
275
+ "69": "Glycine max (Soybean) (Glycine hispida)",
276
+ "70": "Gossypium hirsutum (Upland cotton) (Gossypium mexicanum)",
277
+ "71": "Haemophilus influenzae (strain ATCC 51907 / DSM 11121 / KW20 / Rd)",
278
+ "72": "Haloferax volcanii (strain ATCC 29605 / DSM 3757 / JCM 8879 / NBRC 14742 / NCIMB 2012 / VKM B-1768 / DS2) (Halobacterium volcanii)",
279
+ "73": "Helicobacter pylori (strain ATCC 700392 / 26695) (Campylobacter pylori)",
280
+ "74": "Homo sapiens (Human)",
281
+ "75": "Hordeum vulgare (Barley)",
282
+ "76": "Human adenovirus C serotype 2 (HAdV-2) (Human adenovirus 2)",
283
+ "77": "Human adenovirus C serotype 5 (HAdV-5) (Human adenovirus 5)",
284
+ "78": "Human cytomegalovirus (strain AD169) (HHV-5) (Human herpesvirus 5)",
285
+ "79": "Human cytomegalovirus (strain Merlin) (HHV-5) (Human herpesvirus 5)",
286
+ "80": "Human herpesvirus 1 (strain 17) (HHV-1) (Human herpes simplex virus 1)",
287
+ "81": "Human herpesvirus 8 (HHV-8) (Kaposi's sarcoma-associated herpesvirus)",
288
+ "82": "Human herpesvirus 8 type P (isolate GK18) (HHV-8) (Kaposi's sarcoma-associated herpesvirus)",
289
+ "83": "Hypocrea jecorina (Trichoderma reesei)",
290
+ "84": "Ictalurus punctatus (Channel catfish) (Silurus punctatus)",
291
+ "85": "Influenza A virus (strain A/Puerto Rico/8/1934 H1N1)",
292
+ "86": "Lactococcus lactis subsp. cremoris (strain MG1363)",
293
+ "87": "Lactococcus lactis subsp. lactis (strain IL1403) (Streptococcus lactis)",
294
+ "88": "Legionella pneumophila subsp. pneumophila (strain Philadelphia 1 / ATCC 33152 / DSM 7513)",
295
+ "89": "Leishmania major",
296
+ "90": "Listeria monocytogenes serovar 1/2a (strain ATCC BAA-679 / EGD-e)",
297
+ "91": "Lotus japonicus (Lotus corniculatus var. japonicus)",
298
+ "92": "Macaca fascicularis (Crab-eating macaque) (Cynomolgus monkey)",
299
+ "93": "Macaca mulatta (Rhesus macaque)",
300
+ "94": "Malus domestica (Apple) (Pyrus malus)",
301
+ "95": "Manduca sexta (Tobacco hawkmoth) (Tobacco hornworm)",
302
+ "96": "Medicago truncatula (Barrel medic) (Medicago tribuloides)",
303
+ "97": "Meleagris gallopavo (Wild turkey)",
304
+ "98": "Mesocricetus auratus (Golden hamster)",
305
+ "99": "Methanocaldococcus jannaschii (strain ATCC 43067 / DSM 2661 / JAL-1 / JCM 10045 / NBRC 100440) (Methanococcus jannaschii)",
306
+ "100": "Methanococcus maripaludis (strain DSM 14266 / JCM 13030 / NBRC 101832 / S2 / LL)",
307
+ "101": "Methanothermobacter marburgensis (strain ATCC BAA-927 / DSM 2133 / JCM 14651 / NBRC 100331 / OCM 82 / Marburg) (Methanobacterium thermoautotrophicum)",
308
+ "102": "Mus musculus (Mouse)",
309
+ "103": "Mycobacterium bovis (strain ATCC BAA-935 / AF2122/97)",
310
+ "104": "Mycobacterium tuberculosis (strain ATCC 25618 / H37Rv)",
311
+ "105": "Mycobacterium tuberculosis (strain CDC 1551 / Oshkosh)",
312
+ "106": "Mycolicibacterium smegmatis (strain ATCC 700084 / mc(2)155) (Mycobacterium smegmatis)",
313
+ "107": "Mycoplasma pneumoniae (strain ATCC 29342 / M129 / Subtype 1) (Mycoplasmoides pneumoniae)",
314
+ "108": "Myxococcus xanthus (strain DK1622)",
315
+ "109": "Neisseria gonorrhoeae",
316
+ "110": "Neisseria gonorrhoeae (strain ATCC 700825 / FA 1090)",
317
+ "111": "Neisseria meningitidis serogroup B (strain ATCC BAA-335 / MC58)",
318
+ "112": "Nematostella vectensis (Starlet sea anemone)",
319
+ "113": "Neurospora crassa (strain ATCC 24698 / 74-OR23-1A / CBS 708.71 / DSM 1257 / FGSC 987)",
320
+ "114": "Nicotiana tabacum (Common tobacco)",
321
+ "115": "Nitratidesulfovibrio vulgaris (strain ATCC 29579 / DSM 644 / CCUG 34227 / NCIMB 8303 / VKM B-1760 / Hildenborough) (Desulfovibrio vulgaris)",
322
+ "116": "Nostoc sp. (strain PCC 7120 / SAG 25.82 / UTEX 2576)",
323
+ "117": "Oncorhynchus mykiss (Rainbow trout) (Salmo gairdneri)",
324
+ "118": "Oryctolagus cuniculus (Rabbit)",
325
+ "119": "Oryza nivara (Indian wild rice) (Oryza sativa f. spontanea)",
326
+ "120": "Oryza sativa (Rice)",
327
+ "121": "Oryza sativa subsp. indica (Rice)",
328
+ "122": "Oryza sativa subsp. japonica (Rice)",
329
+ "123": "Oryzias latipes (Japanese rice fish) (Japanese killifish)",
330
+ "124": "Ovis aries (Sheep)",
331
+ "125": "Panax ginseng (Korean ginseng)",
332
+ "126": "Papaver somniferum (Opium poppy)",
333
+ "127": "Penicillium brevicompactum",
334
+ "128": "Penicillium expansum (Blue mold rot fungus)",
335
+ "129": "Petunia hybrida (Petunia)",
336
+ "130": "Physcomitrium patens (Spreading-leaved earth moss) (Physcomitrella patens)",
337
+ "131": "Picea sitchensis (Sitka spruce) (Pinus sitchensis)",
338
+ "132": "Pisum sativum (Garden pea) (Lathyrus oleraceus)",
339
+ "133": "Plasmodium berghei (strain Anka)",
340
+ "134": "Plasmodium falciparum (isolate 3D7)",
341
+ "135": "Plasmodium falciparum (isolate HB3)",
342
+ "136": "Porphyromonas gingivalis (strain ATCC 33277 / DSM 20709 / CIP 103683 / JCM 12257 / NCTC 11834 / 2561)",
343
+ "137": "Pseudomonas aeruginosa",
344
+ "138": "Pseudomonas aeruginosa (strain ATCC 15692 / DSM 22644 / CIP 104116 / JCM 14847 / LMG 12228 / 1C / PRS 101 / PAO1)",
345
+ "139": "Pseudomonas fluorescens (strain ATCC BAA-477 / NRRL B-23932 / Pf-5)",
346
+ "140": "Pseudomonas putida (Arthrobacter siderocapsulatus)",
347
+ "141": "Pseudomonas putida (strain ATCC 47054 / DSM 6125 / CFBP 8728 / NCIMB 11950 / KT2440)",
348
+ "142": "Pseudomonas syringae pv. tomato (strain ATCC BAA-871 / DC3000)",
349
+ "143": "Pyricularia oryzae (strain 70-15 / ATCC MYA-4617 / FGSC 8958) (Rice blast fungus) (Magnaporthe oryzae)",
350
+ "144": "Pyrococcus abyssi (strain GE5 / Orsay)",
351
+ "145": "Pyrococcus furiosus (strain ATCC 43587 / DSM 3638 / JCM 8422 / Vc1)",
352
+ "146": "Pyrococcus horikoshii (strain ATCC 700860 / DSM 12428 / JCM 9974 / NBRC 100139 / OT-3)",
353
+ "147": "Ralstonia sp",
354
+ "148": "Rattus norvegicus (Rat)",
355
+ "149": "Rhizobium meliloti (strain 1021) (Ensifer meliloti) (Sinorhizobium meliloti)",
356
+ "150": "Rhodobacter capsulatus (strain ATCC BAA-309 / NBRC 16581 / SB1003)",
357
+ "151": "Ricinus communis (Castor bean)",
358
+ "152": "Ruegeria pomeroyi (strain ATCC 700808 / DSM 15171 / DSS-3) (Silicibacter pomeroyi)",
359
+ "153": "Saccharolobus solfataricus (strain ATCC 35092 / DSM 1617 / JCM 11322 / P2) (Sulfolobus solfataricus)",
360
+ "154": "Saccharomyces cerevisiae (strain ATCC 204508 / S288c) (Baker's yeast)",
361
+ "155": "Salmo salar (Atlantic salmon)",
362
+ "156": "Salmonella typhimurium (strain 14028s / SGSC 2262)",
363
+ "157": "Salmonella typhimurium (strain LT2 / SGSC1412 / ATCC 700720)",
364
+ "158": "Salmonella typhimurium (strain SL1344)",
365
+ "159": "Schizosaccharomyces pombe (strain 972 / ATCC 24843) (Fission yeast)",
366
+ "160": "Serratia marcescens",
367
+ "161": "Severe acute respiratory syndrome coronavirus (SARS-CoV)",
368
+ "162": "Severe acute respiratory syndrome coronavirus 2 (2019-nCoV) (SARS-CoV-2)",
369
+ "163": "Shewanella oneidensis (strain ATCC 700550 / JCM 31522 / CIP 106686 / LMG 19005 / NCIMB 14063 / MR-1)",
370
+ "164": "Shigella flexneri",
371
+ "165": "Solanum lycopersicum (Tomato) (Lycopersicon esculentum)",
372
+ "166": "Solanum tuberosum (Potato)",
373
+ "167": "Spinacia oleracea (Spinach)",
374
+ "168": "Staphylococcus aureus",
375
+ "169": "Staphylococcus aureus (strain NCTC 8325 / PS 47)",
376
+ "170": "Streptococcus mutans serotype c (strain ATCC 700610 / UA159)",
377
+ "171": "Streptococcus pneumoniae (strain ATCC BAA-255 / R6)",
378
+ "172": "Streptococcus pneumoniae serotype 2 (strain D39 / NCTC 7466)",
379
+ "173": "Streptococcus pneumoniae serotype 4 (strain ATCC BAA-334 / TIGR4)",
380
+ "174": "Streptomyces coelicolor (strain ATCC BAA-471 / A3(2) / M145)",
381
+ "175": "Streptomyces niveus (Streptomyces spheroides)",
382
+ "176": "Sulfolobus acidocaldarius (strain ATCC 33909 / DSM 639 / JCM 8929 / NBRC 15157 / NCIMB 11770)",
383
+ "177": "Sus scrofa (Pig)",
384
+ "178": "Synechococcus elongatus (strain ATCC 33912 / PCC 7942 / FACHB-805) (Anacystis nidulans R2)",
385
+ "179": "Synechocystis sp. (strain ATCC 27184 / PCC 6803 / Kazusa)",
386
+ "180": "Tachypleus tridentatus (Japanese horseshoe crab)",
387
+ "181": "Taeniopygia guttata (Zebra finch) (Poephila guttata)",
388
+ "182": "Tetrahymena thermophila (strain SB210)",
389
+ "183": "Thermococcus kodakarensis (strain ATCC BAA-918 / JCM 12380 / KOD1) (Pyrococcus kodakaraensis (strain KOD1))",
390
+ "184": "Thermoplasma acidophilum (strain ATCC 25905 / DSM 1728 / JCM 9062 / NBRC 15155 / AMRC-C165)",
391
+ "185": "Thermotoga maritima (strain ATCC 43589 / DSM 3109 / JCM 10099 / NBRC 100826 / MSB8)",
392
+ "186": "Thermus thermophilus (strain ATCC 27634 / DSM 579 / HB8)",
393
+ "187": "Thermus thermophilus (strain ATCC BAA-163 / DSM 7039 / HB27)",
394
+ "188": "Triticum aestivum (Wheat)",
395
+ "189": "Trypanosoma brucei",
396
+ "190": "Trypanosoma brucei brucei",
397
+ "191": "Trypanosoma brucei brucei (strain 927/4 GUTat10.1)",
398
+ "192": "Vaccinia virus (strain Western Reserve) (VACV) (Vaccinia virus (strain WR))",
399
+ "193": "Vibrio cholerae serotype O1 (strain ATCC 39315 / El Tor Inaba N16961)",
400
+ "194": "Vibrio cholerae serotype O1 (strain ATCC 39541 / Classical Ogawa 395 / O395)",
401
+ "195": "Vibrio vulnificus (strain YJ016)",
402
+ "196": "Xanthomonas campestris pv. campestris (strain ATCC 33913 / DSM 3586 / NCPPB 528 / LMG 568 / P 25)",
403
+ "197": "Xenopus laevis (African clawed frog)",
404
+ "198": "Xenopus tropicalis (Western clawed frog) (Silurana tropicalis)",
405
+ "199": "Yersinia pestis",
406
+ "200": "Zea mays (Maize)"
407
+ },
408
+ "vocab_size": 201
409
+ }