continuation_benchmark/validation_eval/metadata.tsv

accession	stratum	length_bp	gc	cds_count	ori_family	amr	rare_amr	has_p15A	has_ZeoR	has_R6K	has_pUC_family	pred_surp_shift	pred_comp_shift	pred_combined	description
OQ971745.1	D_intersection	12067	0.389	7	p15A	CmR|TetR	1	1	0	0	0	+1.776	+0.486	+1.131	Vector pSStarget, complete sequence
BD006803.1	D_intersection	1815	0.522	0	unannotated	ZeoR	1	0	1	0	0	+0.253	+0.617	+0.435	L-ricin-producible corynebacteria, replicable DNA among them, process for producing L-ricin, and str
MK234848.1	D_intersection	2599	0.455	1	p15A	TetR	1	1	0	0	0	+0.554	+0.601	+0.577	Cloning vector pTet-1, complete sequence
JX456191.1	D_intersection	3839	0.558	2	R6K	KanR|ZeoR	1	0	1	1	0	+0.909	-0.335	+0.287	Cloning vector pJW3, complete sequence
DI020703.1	D_intersection	4369	0.583	0	unannotated	ZeoR	1	0	1	0	0	+0.552	+0.530	+0.541	Plasmid autonomously replicable in Coryneform bacterium
LY657144.1	D_intersection	2589	0.348	0	unannotated	ZeoR	1	0	1	0	0	+0.785	+0.872	+0.828	KR 1020190061534-A/20: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA
KX709879.1	D_intersection	5419	0.594	2	unannotated	ZeoR	1	0	1	0	0	+0.665	+0.442	+0.554	Cloning vector pSET152 Ble (ble) and phi31 integrase genes, complete cds
RBZS01000460.1	D_intersection	4896	0.583	4	unannotated	ZeoR	1	0	1	0	0	+0.621	+0.388	+0.505	Sodalis-like symbiont of Bactericera trigonica isolate IL scaffold_3467, whole genome shotgun sequen
KY995191.1	D_intersection	4628	0.522	4	unannotated	ZeoR	1	0	1	0	0	+0.720	+0.478	+0.599	Cloning vector pBSc243Z, complete sequence
PP391868.1	D_intersection	3915	0.510	2	R6K	TetR|ZeoR	1	0	1	1	0	+1.026	-0.264	+0.381	Cloning vector pGPS-Zeo-rox plasmid pGPS-Zeo-rox, complete sequence
LY657153.1	D_intersection	3773	0.337	0	unannotated	ZeoR	1	0	1	0	0	+1.003	+0.889	+0.946	KR 1020190061534-A/29: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA
AF286462.1	D_intersection	7385	0.554	4	pBBR1	KanR|ZeoR	1	0	1	0	0	+0.978	+0.431	+0.705	Promoter probe vector pPROBE'-gfp[LVA], complete sequence
U82001.1	D_intersection	8296	0.559	4	RK2|F/oriV	KanR|ZeoR	1	0	1	0	0	+1.062	+0.424	+0.743	Expression vector pJB866, complete sequence
ON959466.1	D_intersection	6859	0.513	5	p15A	KanR|TetR	1	1	0	0	0	+1.011	+0.376	+0.694	Synthetic construct clone pML2003 sequence
LY657138.1	D_intersection	4060	0.404	0	unannotated	ZeoR	1	0	1	0	0	+0.898	+0.790	+0.844	KR 1020190061534-A/14: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA
LC870037.1	D_intersection	9521	0.433	2	unannotated	ZeoR	1	0	1	0	0	+1.455	+0.677	+1.066	Cloning vector pZCAS-ZyMATa2gRNA-rank2 DNA, complete sequence
MH029757.1	D_intersection	6896	0.541	3	p15A	SpecR	1	1	0	0	0	+0.953	+0.404	+0.679	Cloning vector pTHSSe_40, complete sequence
LC823835.1	D_intersection	4099	0.443	3	unannotated	ZeoR	1	0	1	0	0	+0.820	+0.629	+0.724	Expression vector pSD128 DNA, complete sequence
MT572317.1	D_intersection	7890	0.535	5	p15A|phiC31	CmR|TetR	1	1	0	0	0	+1.073	+0.344	+0.708	Cloning vector pMYC20, complete sequence
LT727213.1	D_intersection	7766	0.413	4	p15A	TetR|ErmR	1	1	0	0	0	+1.325	+0.557	+0.941	Vector pTRKH3, complete sequence
MW059023.1	D_intersection	6938	0.505	5	p15A	CmR|SpecR	1	1	0	0	0	+1.036	+0.387	+0.711	Expression vector pGED, complete sequence
OP654169.1	D_intersection	3222	0.462	2	p15A	TetR	1	1	0	0	0	+0.645	+0.556	+0.601	Cloning vector pRW12, complete sequence
KC537291.1	D_intersection	4785	0.486	1	unannotated	ZeoR	1	0	1	0	0	+0.819	+0.635	+0.727	Cloning vector pG-Sable, complete sequence
MW263055.1	D_intersection	9903	0.482	8	pBBR1	ZeoR	1	0	1	0	0	+1.384	+0.396	+0.890	Vector p5010, complete sequence
PV368684.1	D_intersection	5757	0.520	0	unannotated	ZeoR	1	0	1	0	0	+0.868	+0.621	+0.744	UNVERIFIED: Cloning vector pCR4-Pv.00443#1uH-P2A-ZeocinR-P2A-Or47a, complete sequence
PX512453.1	A_only	10534	0.329	5	unannotated	TetR|ErmR	1	0	0	0	0	+1.776	+0.075	+0.926	Cloning vector pCas9acr, complete sequence
AF190131.1	A_only	2042	0.514	1	unannotated	HygR	1	0	0	0	0	+0.319	-0.055	+0.132	Cloning vector pVO205 hygromycin-B-phosphotransferase (hph) gene, complete cds
AF327713.1	A_only	5329	0.618	4	RK2|F/oriV	ZeoR	1	0	1	0	0	+0.601	+0.338	+0.469	Cloning vector pCM51, complete sequence
AY733070.1	A_only	2175	0.486	1	R6K|F/oriV	SpecR	1	0	0	1	0	+0.785	-0.845	-0.030	Cloning vector pSW25, complete sequence
AF488696.1	A_only	2972	0.442	2	R6K	KanR|HygR	1	0	0	1	0	+1.026	-0.816	+0.105	Cloning vector pCpG-Neo delta CpG, complete sequence
PV368681.1	A_only	4406	0.535	0	unannotated	ZeoR	1	0	1	0	0	+0.661	+0.599	+0.630	UNVERIFIED: Cloning vector pCR4-Zeocin-P2A, complete sequence
KM403114.1	A_only	4730	0.515	3	R6K	AmpR|SpecR	1	0	0	1	0	+1.128	-0.958	+0.085	Cloning vector pBAMD1-4, complete sequence
PP391866.1	A_only	5516	0.492	3	R6K	TetR|ZeoR	1	0	1	1	0	+1.279	-0.274	+0.503	Cloning vector pGPS-Zeo-Kn-loxP plasmid pGPS-Zeo-Kn-loxP, complete sequence
MH488951.1	A_only	4828	0.569	3	unannotated	SpecR	1	0	0	0	0	+0.644	-0.206	+0.219	Cloning vector pTac-His-Sgr_rppA, complete sequence
JQ004008.1	A_only	2594	0.354	1	unannotated	TetR	1	0	0	0	0	+0.773	+0.179	+0.476	Veillonella parvula tetracycline resistance protein (tet(M)) gene, complete cds
AF286461.1	A_only	7382	0.554	4	pBBR1	KanR|ZeoR	1	0	1	0	0	+0.977	+0.430	+0.704	Promoter probe vector pPROBE-gfp[LVA], complete sequence
AJ277764.1	A_only	2568	0.407	1	unannotated	TetR	1	0	0	0	0	+0.653	+0.101	+0.377	Cloning vector pCCR9
OQ696835.1	A_only	5413	0.602	3	unannotated	HygR	1	0	0	0	0	+0.646	-0.255	+0.196	Vector pSEVAUO-M31605, complete sequence
KU378203.1	A_only	5821	0.523	3	unannotated	HygR	1	0	0	0	0	+0.869	-0.139	+0.365	Cloning vector pYL2, complete sequence
ON959467.1	A_only	6644	0.500	5	p15A	KanR|TetR	1	1	0	0	0	+1.014	+0.394	+0.704	Synthetic construct clone pML3009 sequence
PP737597.1	A_only	7383	0.449	3	p15A	TetR|GmR	1	1	0	0	0	+1.207	+0.539	+0.873	Vector pMQ808, complete sequence
U82000.1	A_only	7243	0.517	3	RK2|F/oriV	KanR|ZeoR	1	0	1	0	0	+1.044	+0.520	+0.782	Expression vector pJB861, complete sequence
AY299694.1	A_only	6290	0.571	1	pBBR1|F/oriV	SpecR	1	0	0	0	0	+0.819	-0.139	+0.340	Broad host range expression vector pMHE3, complete sequence
EU689032.1	A_only	5630	0.459	3	unannotated	AmpR|HygR	1	0	0	0	0	+0.985	-0.045	+0.470	Tagging vector pFA6a-hphMX6-P3nmt1-3FLAG, complete sequence
AY142483.1	A_only	6885	0.476	3	unannotated	AmpR|HygR	1	0	0	0	0	+1.094	-0.070	+0.512	Cloning vector pSM565, complete sequence
MN450172.1	A_only	7825	0.523	4	RK2	KanR|TetR	1	0	0	0	0	+1.092	-0.174	+0.459	Expression vector pSEVA221AID-T7RNAP plasmid pSEVA221AID-T7RNAP, complete sequence
MK775703.1	A_only	4403	0.400	2	p15A	SpecR	1	1	0	0	0	+0.956	+0.647	+0.801	Cloning vector pSKA417, complete sequence
MN623122.1	A_only	6266	0.456	5	p15A	CmR|TetR	1	1	0	0	0	+1.067	+0.459	+0.763	Cloning vector p15A-PTET-CreGTG-AAV-PBAD-FlpGTG, complete sequence
LY657143.1	A_only	3660	0.393	0	unannotated	ZeoR	1	0	1	0	0	+0.864	+0.807	+0.835	KR 1020190061534-A/19: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA
MW263054.1	A_only	10254	0.457	8	pBBR1	SpecR	1	0	0	0	0	+1.470	-0.218	+0.626	Vector p2118, complete sequence
OR043017.1	A_only	5906	0.551	3	pBBR1|RK2	HygR	1	0	0	0	0	+0.818	-0.180	+0.319	Vector pHBA010_BASIS-components_pH_3-prime, complete sequence
MN393463.1	A_only	8244	0.529	5	unannotated	SpecR	1	0	0	0	0	+1.121	-0.218	+0.452	Expression vector pS438D.colE3, complete sequence
MT304465.1	A_only	5358	0.545	3	unannotated	TetR|GmR	1	0	0	0	0	+0.764	-0.171	+0.297	Cloning vector pRGPDuo1, complete sequence
KR071148.1	A_only	6047	0.504	4	unannotated	AmpR|HygR	1	0	0	0	0	+0.937	-0.146	+0.395	Donor vector pTKDP-hph, complete sequence
GU339046.1	A_only	6432	0.538	4	pBBR1	HygR	1	0	0	0	0	+0.907	-0.196	+0.356	Cloning vector pMQ300, complete sequence
LY657134.1	B_only	5014	0.408	0	unannotated	ZeoR	1	0	1	0	0	+1.019	+0.784	+0.902	KR 1020190061534-A/10: SHUTTLE PLASMID REPLICABLE IN CLOSTRIDIUM AND ESCHERICHIA COLI, AND RECOMBINA
L36849.1	B_only	3451	0.528	1	pUC/ColE1	ZeoR	1	0	1	0	1	+0.536	+0.574	+0.555	Cloning vector pZEO (isolate SV1) phleomycin/zeocin-binding protein gene, complete cds
PP391867.1	B_only	3827	0.515	2	R6K	TetR|ZeoR	1	0	1	1	0	+1.003	-0.271	+0.366	Cloning vector pGPS-Zeo-mFRT plasmid pGPS-Zeo-mFRT, complete sequence
MN623121.1	B_only	3947	0.408	3	p15A	CmR|TetR	1	1	0	0	0	+0.874	+0.600	+0.737	Cloning vector p15A-RBS1-A118, complete sequence
EU546822.1	B_only	7785	0.493	5	p15A|F/oriV	GmR	0	1	0	0	0	+0.473	+0.405	+0.439	Cloning vector pMQ125, complete sequence
KF536587.1	B_only	9903	0.561	7	p15A|pVS1	CmR	0	1	0	0	0	+0.533	+0.236	+0.385	Expression vector pAK501, complete sequence
MN882187.1	B_only	3323	0.515	1	p15A|pUC/ColE1	ZeoR	1	1	1	0	1	+0.545	+1.164	+0.855	Cloning vector pSyn_Mz_Mj_sfGFP_190-200(dest), complete sequence
MT012365.1	B_only	6241	0.499	5	p15A	KanR|TetR	1	1	0	0	0	+0.971	+0.397	+0.684	Cloning vector pYFP-lacY, complete sequence
L05669.1	B_only	7922	0.473	9	pBR322|pUC/ColE1	AmpR|ZeoR	1	0	1	0	1	+1.210	+0.374	+0.792	Cloning vector pNO3097 (incA) gene, partial cds; (stbA and stbB) complete cds; beta-lactamase comple
MH488942.1	B_only	7194	0.546	3	p15A	KanR	0	1	0	0	0	+0.294	+0.397	+0.346	Cloning vector pTac-VvSTS-Sc4CLm, complete sequence
MH029755.1	B_only	6488	0.547	3	p15A	SpecR	1	1	0	0	0	+0.896	+0.397	+0.646	Cloning vector pTHSSe_38, complete sequence
MN654101.1	B_only	5775	0.483	2	pUC/ColE1	ZeoR	1	0	1	0	1	+0.952	+0.605	+0.779	Cloning vector pAS59_yPSAT1_n, complete sequence
MK637405.1	B_only	10955	0.459	4	pBBR1|p15A	CmR	0	1	0	0	0	+0.849	+0.490	+0.670	Cloning vector pMBLcas9, complete sequence
EU496104.1	B_only	4342	0.523	2	p15A|pUC/ColE1	TetR	1	1	0	0	1	+0.677	+0.466	+0.572	BioBrick cloning vector pSB3T5-I52001, complete sequence
OM863780.1	B_only	3571	0.550	2	pBR322|pUC/ColE1	KanR|ZeoR	1	0	1	0	1	+0.507	+0.507	+0.507	Cloning vector pTS018, complete sequence
LC823836.1	B_only	4433	0.379	2	unannotated	ZeoR	1	0	1	0	0	+1.005	+0.756	+0.880	Expression vector pSD131 DNA, complete sequence
MN128719.1	B_only	5584	0.537	2	p15A	TetR	1	1	0	0	0	+0.810	+0.446	+0.628	Expression vector pDM1, complete sequence
JQ283946.1	B_only	3354	0.457	2	p15A	TetR	1	1	0	0	0	+0.676	+0.563	+0.619	Expression vector pMWO-074, complete sequence
GU327534.1	B_only	3251	0.460	2	p15A	CmR	0	1	0	0	0	-0.026	+0.559	+0.267	Landing Pad vector pTKS/CS, complete sequence
MW816822.1	B_only	2697	0.512	2	p15A|pUC/ColE1	AmpR|ZeoR	1	1	1	0	1	+0.445	+1.132	+0.789	Cloning vector pBla_natural, complete sequence
MH101733.1	B_only	5793	0.510	4	p15A	KanR	0	1	0	0	0	+0.214	+0.416	+0.315	Cloning vector pAJM.677, complete sequence
MT361991.1	B_only	3488	0.552	2	p15A	TetR	1	1	0	0	0	+0.490	+0.424	+0.457	Vector pPM910, complete sequence
MH101740.1	B_only	4558	0.467	4	p15A	KanR	0	1	0	0	0	+0.150	+0.478	+0.314	Cloning vector pAJM.969, complete sequence
L36850.1	B_only	6463	0.545	2	pUC/ColE1	ZeoR	1	0	1	0	1	+0.896	+0.514	+0.705	Cloning vector pZEO (isolate SVLacZ) beta-galactosidase (lacZ) gene, phleomycin/zeocin-binding prote
MN623123.1	B_only	3744	0.485	4	p15A	CmR|TetR	1	1	0	0	0	+0.674	+0.451	+0.563	Cloning vector p15A-HNS-GFP, complete sequence