assembly_id	genome_id	genome_def	crispr_array_locus_merge	crispr_array_location_merge	crispr_locus_id	crispr_pred_method	array_in_prot	prot_within_array_20000	prot_in_genome	crispr_type_by_cas_prot	consensus_repeat	repeat_length	self-targeting_spacer_number	self-targeting_target_number	spacer_location	protospacer_location	repeat_type	spacer_locus_num	spacer_num	correct_crispr_type	genome_cas_prots	unknown_protein_around_crispr	L10	L10_domain	L9	L9_domain	L8	L8_domain	L7	L7_domain	L6	L6_domain	L5	L5_domain	L4	L4_domain	L3	L3_domain	L2	L2_domain	L1	L1_domain	R1	R1_domain	R2	R2_domain	R3	R3_domain	R4	R4_domain	R5	R5_domain	R6	R6_domain	R7	R7_domain	R8	R8_domain	R9	R9_domain	R10	R10_domain
GCF_000021785.1_ASM2178v1	NC_011773	Bacillus cereus AH820, complete genome	1	1108627-1108720	1	CRISPRCasFinder	no		cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	Orphan	GGTTTAAATACGTTAAATAGCAAAA	25	0	0	NA	NA	NA	1	1	Orphan	cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	NA|118aa|up_2|NC_011773.1_1105595_1105949_+,NA|280aa|up_1|NC_011773.1_1105945_1106785_-,NA|72aa|down_0|NC_011773.1_1110650_1110866_+,NA|156aa|down_8|NC_011773.1_1115817_1116285_+	NA|166aa|up_9|NC_011773.1_1095086_1095584_-	COG2329, COG2329, Uncharacterized enzyme involved in biosynthesis of extracellular polysaccharides [General function prediction only]	NA|706aa|up_8|NC_011773.1_1095711_1097829_+	TIGR02074, Includes:_Penicillin-insensitive_transglycosylase, penicillin-binding protein, 1A family	NA|349aa|up_7|NC_011773.1_1098008_1099055_+	PRK00115, hemE, uroporphyrinogen decarboxylase; Validated	NA|312aa|up_6|NC_011773.1_1099069_1100005_+	PRK12435, PRK12435, ferrochelatase; Provisional	NA|474aa|up_5|NC_011773.1_1100024_1101446_+	PRK11883, PRK11883, protoporphyrinogen oxidase; Reviewed	NA|451aa|up_4|NC_011773.1_1101485_1102838_-	pfam13218, DUF4026, Protein of unknown function (DUF4026)	NA|789aa|up_3|NC_011773.1_1103078_1105445_+	COG2374, COG2374, Predicted extracellular nuclease [General function prediction only]	NA|118aa|up_2|NC_011773.1_1105595_1105949_+	NA	NA|280aa|up_1|NC_011773.1_1105945_1106785_-	NA	NA|191aa|up_0|NC_011773.1_1107110_1107683_+	COG1309, AcrR, Transcriptional regulator [Transcription]	NA|72aa|down_0|NC_011773.1_1110650_1110866_+	NA	NA|102aa|down_1|NC_011773.1_1110902_1111208_+	pfam09860, DUF2087, Uncharacterized protein conserved in bacteria (DUF2087)	NA|118aa|down_2|NC_011773.1_1111234_1111588_-	pfam14470, bPH_3, Bacterial PH domain	NA|170aa|down_3|NC_011773.1_1111721_1112231_+	pfam00583, Acetyltransf_1, Acetyltransferase (GNAT) family	NA|338aa|down_4|NC_011773.1_1112468_1113482_+	COG1609, PurR, Transcriptional regulators [Transcription]	NA|43aa|down_5|NC_011773.1_1113521_1113650_-	pfam14149, YhfH, YhfH-like protein	NA|245aa|down_6|NC_011773.1_1113829_1114564_+	cd07716, RNaseZ_short-form-like_MBL-fold, uncharacterized bacterial subgroup of Ribonuclease Z, short form; MBL-fold metallo-hydrolase domain	NA|330aa|down_7|NC_011773.1_1114573_1115563_+	TIGR00545, Probable_lipoate-protein_ligase_A, lipoyltransferase and lipoate-protein ligase	NA|156aa|down_8|NC_011773.1_1115817_1116285_+	NA	NA|511aa|down_9|NC_011773.1_1116407_1117940_+	PRK07656, PRK07656, long-chain-fatty-acid--CoA ligase; Validated
GCF_000021785.1_ASM2178v1	NC_011773	Bacillus cereus AH820, complete genome	2	1228246-1228354	2	CRISPRCasFinder	no		cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	Orphan	TGTATGATTACCTTCCGCATGAGAA	25	0	0	NA	NA	NA	1	1	Orphan	cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	NA|124aa|up_3|NC_011773.1_1224783_1225155_+,NA	NA|515aa|up_9|NC_011773.1_1217316_1218861_+	PRK01642, cls, cardiolipin synthetase; Reviewed	NA|415aa|up_8|NC_011773.1_1218942_1220187_+	COG4469, CoiA, Competence protein CoiA-like family, contains a predicted nuclease    domain [General function prediction only]	NA|609aa|up_7|NC_011773.1_1220237_1222064_+	cd09608, M3B_PepF, Peptidase family M3B, oligopeptidase F (PepF)	NA|298aa|up_6|NC_011773.1_1222586_1223480_-	pfam13743, Thioredoxin_5, Thioredoxin	NA|133aa|up_5|NC_011773.1_1223479_1223878_-	cd14772, TrHb2_Bs-trHb-like_O, Truncated hemoglobins, group 2 (O); Bacillus subtilis TrHb like	NA|193aa|up_4|NC_011773.1_1224058_1224637_-	cd07762, CYTH-like_Pase_1, Uncharacterized subgroup 1 of the CYTH-like superfamily	NA|124aa|up_3|NC_011773.1_1224783_1225155_+	NA	NA|213aa|up_2|NC_011773.1_1225185_1225824_+	COG2357, COG2357, PpGpp synthetase catalytic domain [General function prediction only]	NA|266aa|up_1|NC_011773.1_1225842_1226640_+	PRK04885, ppnK, inorganic polyphosphate/ATP-NAD kinase; Provisional	NA|298aa|up_0|NC_011773.1_1226655_1227549_+	COG0564, RluA, Pseudouridylate synthases, 23S RNA-specific [Translation, ribosomal structure and biogenesis]	NA|247aa|down_0|NC_011773.1_1229126_1229867_-	PRK13625, PRK13625, bis(5'-nucleosyl)-tetraphosphatase PrpE; Provisional	NA|387aa|down_1|NC_011773.1_1229941_1231102_-	TIGR02210, Rod_shape-determining_protein_RodA, rod shape-determining protein RodA	NA|312aa|down_2|NC_011773.1_1231244_1232180_-	pfam00535, Glycos_transf_2, Glycosyl transferase family 2	NA|253aa|down_3|NC_011773.1_1232186_1232945_-	pfam13649, Methyltransf_25, Methyltransferase domain	NA|282aa|down_4|NC_011773.1_1233081_1233927_-	pfam05711, TylF, Macrocin-O-methyltransferase (TylF)	NA|296aa|down_5|NC_011773.1_1234049_1234937_-	pfam18573, BclA_C, BclA C-terminal domain	NA|367aa|down_6|NC_011773.1_1235102_1236203_+	cd02511, Beta4Glucosyltransferase, UDP-glucose LOS-beta-1,4 glucosyltransferase is required for biosynthesis of lipooligosaccharide	NA|230aa|down_7|NC_011773.1_1236354_1237044_+	pfam08242, Methyltransf_12, Methyltransferase domain	NA|229aa|down_8|NC_011773.1_1237040_1237727_+	pfam13712, Glyco_tranf_2_5, Glycosyltransferase like family	NA|227aa|down_9|NC_011773.1_1237739_1238420_+	pfam13712, Glyco_tranf_2_5, Glycosyltransferase like family
GCF_000021785.1_ASM2178v1	NC_011773	Bacillus cereus AH820, complete genome	3	2785644-2785818	1	PILER-CR	no		cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	Orphan	ATTTCGGAATGAATGTTCATTCCTCTC	27	0	0	NA	NA	NA	2	2	Orphan	cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	NA,NA	NA|182aa|up_9|NC_011773.1_2771488_2772034_-	COG1670, RimL, Acetyltransferases, including N-acetylases of ribosomal proteins [Translation, ribosomal structure and biogenesis]	NA|234aa|up_8|NC_011773.1_2772049_2772751_-	cd05403, NT_KNTase_like, Nucleotidyltransferase (NT) domain of Staphylococcus aureus kanamycin nucleotidyltransferase, and similar proteins	NA|228aa|up_7|NC_011773.1_2772767_2773451_-	cd06561, AlkD_like, A new structural DNA glycosylase	NA|87aa|up_6|NC_011773.1_2773816_2774077_-	PRK10811, rne, ribonuclease E; Reviewed	NA|276aa|up_5|NC_011773.1_2774294_2775122_+	cd10944, CE4_SmPgdA_like, Catalytic NodB homology domain of Streptococcus mutans polysaccharide deacetylase PgdA, Bacillus subtilis YheN, and similar proteins	NA|221aa|up_4|NC_011773.1_2775281_2775944_+	pfam12952, DUF3841, Domain of unknown function (DUF3841)	NA|224aa|up_3|NC_011773.1_2776054_2776726_+	TIGR03717, R_switched_YjbE, integral membrane protein, YjbE family	NA|658aa|up_2|NC_011773.1_2776785_2778759_-	COG1368, MdoB, Phosphoglycerol transferase and related proteins, alkaline phosphatase superfamily [Cell envelope biogenesis, outer membrane]	NA|542aa|up_1|NC_011773.1_2779275_2780901_-	PRK15064, PRK15064, ABC transporter ATP-binding protein; Provisional	NA|283aa|up_0|NC_011773.1_2781278_2782127_-	PRK06761, PRK06761, hypothetical protein; Provisional	NA|189aa|down_0|NC_011773.1_2785835_2786402_-	pfam16295, TetR_C_10, Tetracycline repressor, C-terminal all-alpha domain	NA|386aa|down_1|NC_011773.1_2786671_2787829_-	COG4552, Eis, Predicted acetyltransferase involved in intracellular survival and related acetyltransferases [General function prediction only]	NA|430aa|down_2|NC_011773.1_2788116_2789406_-	PRK02427, PRK02427, 3-phosphoshikimate 1-carboxyvinyltransferase; Provisional	NA|367aa|down_3|NC_011773.1_2789422_2790523_-	PRK06545, PRK06545, prephenate dehydrogenase; Validated	NA|367aa|down_4|NC_011773.1_2790515_2791616_-	PRK01533, PRK01533, histidinol-phosphate aminotransferase; Validated	NA|391aa|down_5|NC_011773.1_2791634_2792807_-	PRK12463, PRK12463, chorismate synthase; Reviewed	NA|359aa|down_6|NC_011773.1_2793091_2794168_-	PRK12595, PRK12595, bifunctional 3-deoxy-7-phosphoheptulonate synthase/chorismate mutase; Reviewed	NA|1171aa|down_7|NC_011773.1_2794999_2798512_-	cd01406, SIR2-like, Sir2-like: Prokaryotic group of uncharacterized Sir2-like proteins which lack certain key catalytic residues and conserved zinc binding cysteines; and are members of the SIR2 superfamily of proteins, silent information regulator 2 (Sir2) enzymes which catalyze NAD+-dependent protein/histone deacetylation	NA|146aa|down_8|NC_011773.1_2798662_2799100_+	pfam10710, DUF2512, Protein of unknown function (DUF2512)	NA|177aa|down_9|NC_011773.1_2799248_2799779_-	cd01014, nicotinamidase_related, Nicotinamidase_ related amidohydrolases
GCF_000021785.1_ASM2178v1	NC_011773	Bacillus cereus AH820, complete genome	4	3345737-3345839	3	CRISPRCasFinder	no	csa3	cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	Type I-A	AAGTTTAGGTTTCTTTTGAGAATGT	25	0	0	NA	NA	NA	1	1	Orphan	cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	NA|77aa|up_5|NC_011773.1_3340395_3340626_+,NA|218aa|down_0|NC_011773.1_3346478_3347132_-	NA|514aa|up_9|NC_011773.1_3334517_3336059_-	PRK09441, PRK09441, cytoplasmic alpha-amylase; Reviewed	NA|264aa|up_8|NC_011773.1_3336274_3337066_+	COG2162, NhoA, Arylamine N-acetyltransferase [Secondary metabolites biosynthesis, transport, and catabolism]	NA|596aa|up_7|NC_011773.1_3337182_3338970_+	cd09608, M3B_PepF, Peptidase family M3B, oligopeptidase F (PepF)	NA|378aa|up_6|NC_011773.1_3339005_3340139_-	pfam00144, Beta-lactamase, Beta-lactamase	NA|77aa|up_5|NC_011773.1_3340395_3340626_+	NA	NA|415aa|up_4|NC_011773.1_3340725_3341970_-	cd17475, MFS_MT3072_like, Mycobacterium tuberculosis uncharacterized MFS-type transporter MT3072 and similar transporters of the Major Facilitator Superfamily	NA|284aa|up_3|NC_011773.1_3342055_3342907_+	cd08442, PBP2_YofA_SoxR_like, The C-terminal substrate binding domain of LysR-type transcriptional regulators, YofA and SoxR, contains the type 2 periplasmic binding fold	NA|170aa|up_2|NC_011773.1_3342899_3343409_+	pfam13079, DUF3916, Protein of unknown function (DUF3916)	NA|226aa|up_1|NC_011773.1_3343502_3344180_+	cd06259, YdcF-like, YdcF-like	NA|315aa|up_0|NC_011773.1_3344229_3345174_-	cd08601, GDPD_SaGlpQ_like, Glycerophosphodiester phosphodiesterase domain of Staphylococcus aureus and similar proteins	NA|218aa|down_0|NC_011773.1_3346478_3347132_-	NA	NA|60aa|down_1|NC_011773.1_3347236_3347416_+	PRK12270, kgd, multifunctional oxoglutarate decarboxylase/oxoglutarate dehydrogenase thiamine pyrophosphate-binding subunit/dihydrolipoyllysine-residue succinyltransferase subunit	NA|540aa|down_2|NC_011773.1_3347748_3349368_-	pfam01494, FAD_binding_3, FAD binding domain	csa3|135aa|down_3|NC_011773.1_3349835_3350240_+	cd00090, HTH_ARSR, Arsenical Resistance Operon Repressor and similar prokaryotic, metal regulated homodimeric repressors	NA|333aa|down_4|NC_011773.1_3350349_3351348_+	cd05289, MDR_like_2, alcohol dehydrogenase and quinone reductase-like medium chain degydrogenases/reductases	NA|489aa|down_5|NC_011773.1_3351526_3352993_+	PRK00029, PRK00029, YdiU family protein	NA|365aa|down_6|NC_011773.1_3353247_3354342_+	pfam18801, RapH_N, response regulator aspartate phosphatase H, N terminal	NA|63aa|down_7|NC_011773.1_3354338_3354527_+	TIGR04429, hypothetical_protein_bmyco0001_31490, Phr family secreted Rap phosphatase inhibitor	NA|200aa|down_8|NC_011773.1_3354600_3355200_-	pfam04299, FMN_bind_2, Putative FMN-binding domain	NA|116aa|down_9|NC_011773.1_3355885_3356233_-	pfam14079, DUF4260, Domain of unknown function (DUF4260)
GCF_000021785.1_ASM2178v1	NC_011773	Bacillus cereus AH820, complete genome	5	4538833-4538940	4	CRISPRCasFinder	no		cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	Orphan	TATATCAGCGATTTTTTGAATATATC	26	0	0	NA	NA	NA	1	1	Orphan	cas3,csa3,WYL,cas14k,DinG,DEDDh,RT,cas14j	NA|99aa|up_3|NC_011773.1_4536522_4536819_+,NA|145aa|down_4|NC_011773.1_4542457_4542892_-,NA|221aa|down_8|NC_011773.1_4544612_4545275_+	NA|230aa|up_9|NC_011773.1_4531540_4532230_-	COG0745, OmpR, Response regulators consisting of a CheY-like receiver domain and a winged-helix DNA-binding domain [Signal transduction mechanisms / Transcription]	NA|485aa|up_8|NC_011773.1_4532231_4533686_-	COG0642, BaeS, Signal transduction histidine kinase [Signal transduction mechanisms]	NA|227aa|up_7|NC_011773.1_4533835_4534516_+	sd00045, ANK, ankyrin repeats	NA|309aa|up_6|NC_011773.1_4534595_4535522_+	COG0673, MviM, Predicted dehydrogenases and related proteins [General function prediction only]	NA|133aa|up_5|NC_011773.1_4535650_4536049_+	PRK13955, mscL, large conductance mechanosensitive channel protein MscL	NA|91aa|up_4|NC_011773.1_4536099_4536372_-	pfam13055, DUF3917, Protein of unknown function (DUF3917)	NA|99aa|up_3|NC_011773.1_4536522_4536819_+	NA	NA|79aa|up_2|NC_011773.1_4536900_4537137_+	pfam13133, DUF3949, Protein of unknown function (DUF3949)	NA|121aa|up_1|NC_011773.1_4537138_4537501_+	pfam14119, DUF4288, Domain of unknown function (DUF4288)	NA|333aa|up_0|NC_011773.1_4537535_4538534_-	TIGR01481, catabolite_control_protein_A, catabolite control protein A	NA|339aa|down_0|NC_011773.1_4539145_4540162_-	COG4851, CamS, Protein involved in sex pheromone biosynthesis [General function prediction only]	NA|109aa|down_1|NC_011773.1_4540279_4540606_-	pfam11009, DUF2847, Protein of unknown function (DUF2847)	NA|186aa|down_2|NC_011773.1_4540605_4541163_-	COG4768, COG4768, Uncharacterized protein containing a divergent version of the methyl-accepting chemotaxis-like domain [General function prediction only]	NA|372aa|down_3|NC_011773.1_4541305_4542421_+	COG2309, AmpS, Leucyl aminopeptidase (aminopeptidase T) [Amino acid transport and metabolism]	NA|145aa|down_4|NC_011773.1_4542457_4542892_-	NA	NA|135aa|down_5|NC_011773.1_4543086_4543491_-	pfam06713, bPH_4, Bacterial PH domain	NA|185aa|down_6|NC_011773.1_4543581_4544136_-	COG1670, RimL, Acetyltransferases, including N-acetylases of ribosomal proteins [Translation, ribosomal structure and biogenesis]	NA|115aa|down_7|NC_011773.1_4544271_4544616_+	COG1695, COG1695, Predicted transcriptional regulators [Transcription]	NA|221aa|down_8|NC_011773.1_4544612_4545275_+	NA	NA|437aa|down_9|NC_011773.1_4545330_4546641_-	PRK00421, murC, UDP-N-acetylmuramate--L-alanine ligase; Provisional
