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_000018845.1_ASM1884v1	NC_010172	Methylorubrum extorquens PA1, complete sequence	1	2134186-2134388	1	CRISPRCasFinder	no	csa3	DEDDh,csa3,WYL,cas3	Type I-A	TGCCCTCCCGCGGGCGGGAGGTG	23	0	0	NA	NA	NA	3	3	Orphan	DEDDh,csa3,WYL,cas3	NA|295aa|up_4|NC_010172.1_2129399_2130284_-,NA|196aa|up_3|NC_010172.1_2130488_2131076_-,NA|453aa|down_0|NC_010172.1_2134826_2136185_+,NA|119aa|down_2|NC_010172.1_2137891_2138248_+,NA|99aa|down_4|NC_010172.1_2139228_2139525_+,NA|108aa|down_9|NC_010172.1_2144890_2145214_-	NA|249aa|up_9|NC_010172.1_2125934_2126681_-	TIGR02690, arsenical_resistance_protein_ArsH_putative, arsenical resistance protein ArsH	csa3|120aa|up_8|NC_010172.1_2126731_2127091_+	COG0640, ArsR, Predicted transcriptional regulators [Transcription]	NA|176aa|up_7|NC_010172.1_2127083_2127611_+	cd16345, LMWP_ArsC, Arsenate reductase of the LMWP family	NA|142aa|up_6|NC_010172.1_2127610_2128036_+	PRK10026, PRK10026, arsenate reductase (glutaredoxin)	NA|432aa|up_5|NC_010172.1_2128070_2129366_+	PRK15445, PRK15445, arsenical efflux pump membrane protein ArsB	NA|295aa|up_4|NC_010172.1_2129399_2130284_-	NA	NA|196aa|up_3|NC_010172.1_2130488_2131076_-	NA	NA|106aa|up_2|NC_010172.1_2131176_2131494_+	pfam12840, HTH_20, Helix-turn-helix domain	NA|452aa|up_1|NC_010172.1_2131540_2132896_+	COG2072, TrkA, Predicted flavoprotein involved in K+ transport [Inorganic ion transport and metabolism]	NA|388aa|up_0|NC_010172.1_2132892_2134056_+	cd17355, MFS_YcxA_like, MFS-type transporter YcxA and similar proteins of the Major Facilitator Superfamily of transporters	NA|453aa|down_0|NC_010172.1_2134826_2136185_+	NA	NA|370aa|down_1|NC_010172.1_2136737_2137847_+	pfam11740, KfrA_N, Plasmid replication region DNA-binding N-term	NA|119aa|down_2|NC_010172.1_2137891_2138248_+	NA	NA|251aa|down_3|NC_010172.1_2138271_2139024_-	pfam13676, TIR_2, TIR domain	NA|99aa|down_4|NC_010172.1_2139228_2139525_+	NA	NA|184aa|down_5|NC_010172.1_2139527_2140079_-	cd07390, MPP_AQ1575, Aquifex aeolicus AQ1575 and related proteins, metallophosphatase domain	NA|203aa|down_6|NC_010172.1_2141511_2142120_+	COG0625, Gst, Glutathione S-transferase [Posttranslational modification, protein turnover, chaperones]	NA|399aa|down_7|NC_010172.1_2142296_2143493_+	COG3287, COG3287, Uncharacterized conserved protein [Function unknown]	NA|448aa|down_8|NC_010172.1_2143524_2144868_+	COG0642, BaeS, Signal transduction histidine kinase [Signal transduction mechanisms]	NA|108aa|down_9|NC_010172.1_2144890_2145214_-	NA
GCF_000018845.1_ASM1884v1	NC_010172	Methylorubrum extorquens PA1, complete sequence	2	2136420-2136510	2	CRISPRCasFinder	no	csa3	DEDDh,csa3,WYL,cas3	Type I-A	GATGGCGACGATACCCTGCCAAGCGA	26	0	0	NA	NA	NA	1	1	Orphan	DEDDh,csa3,WYL,cas3	NA|295aa|up_5|NC_010172.1_2129399_2130284_-,NA|196aa|up_4|NC_010172.1_2130488_2131076_-,NA|453aa|up_0|NC_010172.1_2134826_2136185_+,NA|119aa|down_1|NC_010172.1_2137891_2138248_+,NA|99aa|down_3|NC_010172.1_2139228_2139525_+,NA|108aa|down_8|NC_010172.1_2144890_2145214_-	csa3|120aa|up_9|NC_010172.1_2126731_2127091_+	COG0640, ArsR, Predicted transcriptional regulators [Transcription]	NA|176aa|up_8|NC_010172.1_2127083_2127611_+	cd16345, LMWP_ArsC, Arsenate reductase of the LMWP family	NA|142aa|up_7|NC_010172.1_2127610_2128036_+	PRK10026, PRK10026, arsenate reductase (glutaredoxin)	NA|432aa|up_6|NC_010172.1_2128070_2129366_+	PRK15445, PRK15445, arsenical efflux pump membrane protein ArsB	NA|295aa|up_5|NC_010172.1_2129399_2130284_-	NA	NA|196aa|up_4|NC_010172.1_2130488_2131076_-	NA	NA|106aa|up_3|NC_010172.1_2131176_2131494_+	pfam12840, HTH_20, Helix-turn-helix domain	NA|452aa|up_2|NC_010172.1_2131540_2132896_+	COG2072, TrkA, Predicted flavoprotein involved in K+ transport [Inorganic ion transport and metabolism]	NA|388aa|up_1|NC_010172.1_2132892_2134056_+	cd17355, MFS_YcxA_like, MFS-type transporter YcxA and similar proteins of the Major Facilitator Superfamily of transporters	NA|453aa|up_0|NC_010172.1_2134826_2136185_+	NA	NA|370aa|down_0|NC_010172.1_2136737_2137847_+	pfam11740, KfrA_N, Plasmid replication region DNA-binding N-term	NA|119aa|down_1|NC_010172.1_2137891_2138248_+	NA	NA|251aa|down_2|NC_010172.1_2138271_2139024_-	pfam13676, TIR_2, TIR domain	NA|99aa|down_3|NC_010172.1_2139228_2139525_+	NA	NA|184aa|down_4|NC_010172.1_2139527_2140079_-	cd07390, MPP_AQ1575, Aquifex aeolicus AQ1575 and related proteins, metallophosphatase domain	NA|203aa|down_5|NC_010172.1_2141511_2142120_+	COG0625, Gst, Glutathione S-transferase [Posttranslational modification, protein turnover, chaperones]	NA|399aa|down_6|NC_010172.1_2142296_2143493_+	COG3287, COG3287, Uncharacterized conserved protein [Function unknown]	NA|448aa|down_7|NC_010172.1_2143524_2144868_+	COG0642, BaeS, Signal transduction histidine kinase [Signal transduction mechanisms]	NA|108aa|down_8|NC_010172.1_2144890_2145214_-	NA	NA|223aa|down_9|NC_010172.1_2145526_2146195_-	pfam06035, Peptidase_C93, Bacterial transglutaminase-like cysteine proteinase BTLCP
GCF_000018845.1_ASM1884v1	NC_010172	Methylorubrum extorquens PA1, complete sequence	3	2700341-2700612	3	CRISPRCasFinder	no		DEDDh,csa3,WYL,cas3	Orphan	GGCAACAACGTCGTGCTCGGCGG	23	0	0	NA	NA	NA	4	4	Orphan	DEDDh,csa3,WYL,cas3	NA|292aa|up_3|NC_010172.1_2660906_2661782_+,NA|89aa|down_9|NC_010172.1_2726449_2726716_+	NA|716aa|up_9|NC_010172.1_2651972_2654120_-	pfam05402, PqqD, Coenzyme PQQ synthesis protein D (PqqD)	NA|629aa|up_8|NC_010172.1_2654131_2656018_-	TIGR01730, COG0845:_Membrane-fusion_protein, RND family efflux transporter, MFP subunit	NA|99aa|up_7|NC_010172.1_2656101_2656398_-	pfam11950, DUF3467, Protein of unknown function (DUF3467)	NA|351aa|up_6|NC_010172.1_2656784_2657837_+	pfam00891, Methyltransf_2, O-methyltransferase	NA|220aa|up_5|NC_010172.1_2657833_2658493_+	PRK08233, PRK08233, hypothetical protein; Provisional	NA|796aa|up_4|NC_010172.1_2658522_2660910_+	pfam04820, Trp_halogenase, Tryptophan halogenase	NA|292aa|up_3|NC_010172.1_2660906_2661782_+	NA	NA|311aa|up_2|NC_010172.1_2661799_2662732_+	TIGR04545, rSAM_ahbD_hemeb, heme b synthase	NA|310aa|up_1|NC_010172.1_2662863_2663793_-	PRK09685, PRK09685, DNA-binding transcriptional activator FeaR; Provisional	NA|267aa|up_0|NC_010172.1_2664727_2665528_+	pfam07277, SapC, SapC	NA|272aa|down_0|NC_010172.1_2713374_2714190_+	pfam13640, 2OG-FeII_Oxy_3, 2OG-Fe(II) oxygenase superfamily	NA|264aa|down_1|NC_010172.1_2714194_2714986_+	COG2226, UbiE, Methylase involved in ubiquinone/menaquinone biosynthesis [Coenzyme metabolism]	NA|460aa|down_2|NC_010172.1_2715124_2716504_+	COG1032, COG1032, Fe-S oxidoreductase [Energy production and conversion]	NA|438aa|down_3|NC_010172.1_2716500_2717814_+	COG1032, COG1032, Fe-S oxidoreductase [Energy production and conversion]	NA|480aa|down_4|NC_010172.1_2717921_2719361_-	COG2132, SufI, Putative multicopper oxidases [Secondary metabolites biosynthesis, transport, and catabolism]	NA|479aa|down_5|NC_010172.1_2719742_2721179_+	PRK01490, tig, trigger factor; Provisional	NA|209aa|down_6|NC_010172.1_2721310_2721937_+	PRK00277, clpP, ATP-dependent Clp protease proteolytic subunit; Reviewed	NA|424aa|down_7|NC_010172.1_2722188_2723460_+	PRK05342, clpX, ATP-dependent Clp protease ATP-binding subunit ClpX	NA|807aa|down_8|NC_010172.1_2723727_2726148_+	COG0466, Lon, ATP-dependent Lon protease, bacterial type [Posttranslational modification, protein turnover, chaperones]	NA|89aa|down_9|NC_010172.1_2726449_2726716_+	NA
GCF_000018845.1_ASM1884v1	NC_010172	Methylorubrum extorquens PA1, complete sequence	4	4012808-4012892	4	CRISPRCasFinder	no		DEDDh,csa3,WYL,cas3	Orphan	AAAACAAAAGGCGAGAGCATCGT	23	1	3	4012831-4012869|4012831-4012869|4012831-4012869	NC_010172.1_2717903-2717865|NC_010172.1_4640786-4640824|NC_010172.1_5229969-5229931	NA	1	1	Orphan	DEDDh,csa3,WYL,cas3	NA|73aa|up_5|NC_010172.1_4009486_4009705_+,NA|78aa|up_4|NC_010172.1_4009946_4010180_+,NA|126aa|down_1|NC_010172.1_4014050_4014428_-,NA|235aa|down_2|NC_010172.1_4014594_4015299_+,NA|57aa|down_5|NC_010172.1_4017638_4017809_-	NA|307aa|up_9|NC_010172.1_4005795_4006716_-	PRK06197, PRK06197, short chain dehydrogenase; Provisional	NA|191aa|up_8|NC_010172.1_4006839_4007412_+	COG2335, COG2335, Secreted and surface protein containing fasciclin-like repeats [Cell envelope biogenesis, outer membrane]	NA|279aa|up_7|NC_010172.1_4007658_4008495_+	COG0596, MhpC, Predicted hydrolases or acyltransferases (alpha/beta hydrolase superfamily) [General function prediction only]	NA|173aa|up_6|NC_010172.1_4008907_4009426_+	pfam13185, GAF_2, GAF domain	NA|73aa|up_5|NC_010172.1_4009486_4009705_+	NA	NA|78aa|up_4|NC_010172.1_4009946_4010180_+	NA	NA|83aa|up_3|NC_010172.1_4010185_4010434_+	COG3514, COG3514, Uncharacterized protein conserved in bacteria [Function unknown]	NA|245aa|up_2|NC_010172.1_4010510_4011245_+	PRK09421, modB, molybdate ABC transporter permease subunit	NA|120aa|up_1|NC_010172.1_4011483_4011843_+	pfam13103, TonB_2, TonB C terminal	NA|219aa|up_0|NC_010172.1_4012015_4012672_-	cd03189, GST_C_GTT1_like, C-terminal, alpha helical domain of GTT1-like Glutathione S-transferases	NA|365aa|down_0|NC_010172.1_4012935_4014030_+	COG4148, ModC, ABC-type molybdate transport system, ATPase component [Inorganic ion transport and metabolism]	NA|126aa|down_1|NC_010172.1_4014050_4014428_-	NA	NA|235aa|down_2|NC_010172.1_4014594_4015299_+	NA	NA|350aa|down_3|NC_010172.1_4015323_4016373_+	PRK05312, pdxA, 4-hydroxythreonine-4-phosphate dehydrogenase PdxA	NA|297aa|down_4|NC_010172.1_4016381_4017272_+	PRK00274, ksgA, 16S rRNA (adenine(1518)-N(6)/adenine(1519)-N(6))-dimethyltransferase RsmA	NA|57aa|down_5|NC_010172.1_4017638_4017809_-	NA	NA|349aa|down_6|NC_010172.1_4017919_4018966_-	TIGR01730, COG0845:_Membrane-fusion_protein, RND family efflux transporter, MFP subunit	NA|424aa|down_7|NC_010172.1_4018962_4020234_-	cd06423, CESA_like, CESA_like is  the cellulose synthase superfamily	NA|380aa|down_8|NC_010172.1_4020750_4021890_-	COG0596, MhpC, Predicted hydrolases or acyltransferases (alpha/beta hydrolase superfamily) [General function prediction only]	NA|502aa|down_9|NC_010172.1_4022089_4023595_-	COG0659, SUL1, Sulfate permease and related transporters (MFS superfamily) [Inorganic ion transport and metabolism]
GCF_000018845.1_ASM1884v1	NC_010172	Methylorubrum extorquens PA1, complete sequence	5	4640799-4640887	5	CRISPRCasFinder	no		DEDDh,csa3,WYL,cas3	Orphan	CGCCGGCTTTCGGAAAAAGATGATGC	26	0	0	NA	NA	NA	1	1	Orphan	DEDDh,csa3,WYL,cas3	NA|79aa|up_9|NC_010172.1_4628922_4629159_-,NA|123aa|up_4|NC_010172.1_4636414_4636783_+,NA|66aa|up_3|NC_010172.1_4636961_4637159_+,NA|114aa|up_2|NC_010172.1_4637225_4637567_-,NA|65aa|down_2|NC_010172.1_4643164_4643359_-	NA|79aa|up_9|NC_010172.1_4628922_4629159_-	NA	NA|730aa|up_8|NC_010172.1_4629228_4631418_-	PRK10917, PRK10917, ATP-dependent DNA helicase RecG; Provisional	NA|99aa|up_7|NC_010172.1_4631609_4631906_+	COG2938, COG2938, Uncharacterized conserved protein [Function unknown]	NA|1197aa|up_6|NC_010172.1_4632135_4635726_+	COG1197, Mfd, Transcription-repair coupling factor (superfamily II helicase) [DNA replication, recombination, and repair / Transcription]	NA|70aa|up_5|NC_010172.1_4636102_4636312_+	COG1278, CspC, Cold shock proteins [Transcription]	NA|123aa|up_4|NC_010172.1_4636414_4636783_+	NA	NA|66aa|up_3|NC_010172.1_4636961_4637159_+	NA	NA|114aa|up_2|NC_010172.1_4637225_4637567_-	NA	NA|467aa|up_1|NC_010172.1_4637825_4639226_-	COG0318, CaiC, Acyl-CoA synthetases (AMP-forming)/AMP-acid ligases II [Lipid metabolism / Secondary metabolites biosynthesis, transport, and catabolism]	NA|418aa|up_0|NC_010172.1_4639523_4640777_+	PRK13557, PRK13557, histidine kinase; Provisional	NA|121aa|down_0|NC_010172.1_4640976_4641339_+	cd18161, REC_hyHK_blue-like, phosphoacceptor receiver (REC) domain of hybrid sensor histidine kinase/response regulators similar to Pseudomonas savastanoi blue-light-activated histidine kinase	NA|544aa|down_1|NC_010172.1_4641394_4643026_-	PRK08162, PRK08162, acyl-CoA synthetase; Validated	NA|65aa|down_2|NC_010172.1_4643164_4643359_-	NA	NA|603aa|down_3|NC_010172.1_4643608_4645417_+	COG1807, ArnT, 4-amino-4-deoxy-L-arabinose transferase and related glycosyltransferases of PMT family [Cell envelope biogenesis, outer membrane]	NA|258aa|down_4|NC_010172.1_4645413_4646187_+	cd04179, DPM_DPG-synthase_like, DPM_DPG-synthase_like is a member of the Glycosyltransferase 2 superfamily	NA|110aa|down_5|NC_010172.1_4646191_4646521_+	COG3952, COG3952, Predicted membrane protein [Function unknown]	NA|156aa|down_6|NC_010172.1_4646536_4647004_+	pfam11026, DUF2721, Protein of unknown function (DUF2721)	NA|504aa|down_7|NC_010172.1_4647004_4648516_-	COG2072, TrkA, Predicted flavoprotein involved in K+ transport [Inorganic ion transport and metabolism]	NA|312aa|down_8|NC_010172.1_4648512_4649448_-	pfam07859, Abhydrolase_3, alpha/beta hydrolase fold	NA|275aa|down_9|NC_010172.1_4649450_4650275_-	cd05374, 17beta-HSD-like_SDR_c, 17beta hydroxysteroid dehydrogenase-like, classical (c) SDRs
