plannotate/Base_t0.95/feature_breakdown.json

{
  "model": "Base_t0.95",
  "n_sequences_annotated": 3147,
  "total_hits": 22764,
  "by_type": {
    "CDS": 7711,
    "promoter": 4281,
    "rep_origin": 2980,
    "terminator": 2875,
    "misc_feature": 1410,
    "protein_bind": 1276,
    "enhancer": 605,
    "polyA_signal": 385,
    "misc_RNA": 336,
    "ncRNA": 245,
    "LTR": 202,
    "RBS": 169,
    "intron": 137,
    "mobile_element": 43,
    "gene": 36,
    "repeat_region": 34,
    "oriT": 23,
    "sig_peptide": 8,
    "misc_recomb": 4,
    "3'UTR": 2,
    "5'UTR": 2
  },
  "by_type_and_description": [
    {
      "type": "rep_origin",
      "description": "high-copy-number ColE1/pMB1/pBR322/pUC origin of replication",
      "count": 1537
    },
    {
      "type": "terminator",
      "description": "transcription terminator T1 from the E. coli rrnB gene",
      "count": 1020
    },
    {
      "type": "promoter",
      "description": "bla",
      "count": 815
    },
    {
      "type": "terminator",
      "description": "phage T7 early transcription terminator",
      "count": 803
    },
    {
      "type": "CDS",
      "description": "\u03b2-lactamase; bla; confers resistance to ampicillin, carbenicillin, and related antibiotics",
      "count": 679
    },
    {
      "type": "CDS",
      "description": "aminoglycoside phosphotransferase; aph(3')-Ia; confers resistance to kanamycin in bacteria or G418 (Geneticin\u00ae) in eukaryotes",
      "count": 645
    },
    {
      "type": "enhancer",
      "description": "human cytomegalovirus immediate early enhancer",
      "count": 581
    },
    {
      "type": "CDS",
      "description": "lac repressor; lacI; The lac repressor binds to the lac operator to inhibit transcription in E. coli. This inhibition can be relieved by adding lactose or isopropyl-\u03b2-D-thiogalactopyranoside (IPTG).",
      "count": 573
    },
    {
      "type": "promoter",
      "description": "bacterial promoter (Registry of Standard Biological Parts BBa J23119)",
      "count": 573
    },
    {
      "type": "rep_origin",
      "description": "Plasmids containing the medium-copy-number p15A origin of replication can be propagated in E. coli cells that contain a second plasmid with the ColE1 origin.",
      "count": 536
    },
    {
      "type": "CDS",
      "description": "hfriFP is a fluorescent protein published in 2013, derived from Herbaspirillum frisingense.",
      "count": 515
    },
    {
      "type": "protein_bind",
      "description": "The lac repressor binds to the lac operator to inhibit transcription in E. coli. This inhibition can be relieved by adding lactose or isopropyl-\u03b2-D-thiogalactopyranoside (IPTG). lac repressor encoded by lacI",
      "count": 472
    },
    {
      "type": "protein_bind",
      "description": "CAP binding activates transcription in the presence of cAMP. E. coli catabolite activator protein",
      "count": 437
    },
    {
      "type": "promoter",
      "description": "promoter for bacteriophage T7 RNA polymerase",
      "count": 432
    },
    {
      "type": "misc_feature",
      "description": "basis of mobility region from pBR322",
      "count": 412
    },
    {
      "type": "promoter",
      "description": "bacterial promoter (Registry of Standard Biological Parts BBa J23119) modified to end with an SpeI site",
      "count": 380
    },
    {
      "type": "CDS",
      "description": "monomeric derivative of DsRed (Campbell et al., 2002)",
      "count": 376
    },
    {
      "type": "CDS",
      "description": "tetracycline efflux protein; tet; confers resistance to tetracycline",
      "count": 347
    },
    {
      "type": "rep_origin",
      "description": "f1 bacteriophage origin of replication; arrow indicates direction of (+) strand synthesis",
      "count": 327
    },
    {
      "type": "CDS",
      "description": "Rop protein, which maintains plasmids at low copy number; rop",
      "count": 317
    },
    {
      "type": "CDS",
      "description": "LacZ\u03b1 fragment of \u03b2-galactosidase; lacZ fragment",
      "count": 314
    },
    {
      "type": "terminator",
      "description": "transcription terminator from phage lambda",
      "count": 314
    },
    {
      "type": "promoter",
      "description": "promoter for the E. coli lac operon",
      "count": 299
    },
    {
      "type": "CDS",
      "description": "composite tag for in vivo biotinylation, TEV protease cleavage, and 6xHis tagging",
      "count": 292
    },
    {
      "type": "misc_RNA",
      "description": "guide RNA scaffold for the Streptococcus pyogenes CRISPR/Cas9 system",
      "count": 286
    },
    {
      "type": "ncRNA",
      "description": "Accession: RF00001 - 5S ribosomal RNA",
      "count": 232
    },
    {
      "type": "CDS",
      "description": "replication protein for the broad-host-range plasmid pBBR1 from Bordetella bronchiseptica",
      "count": 220
    },
    {
      "type": "rep_origin",
      "description": "replication origin of the broad-host-range plasmid pBBR1 from Bordetella bronchiseptica; requires the pBBR1 Rep protein for replication",
      "count": 219
    },
    {
      "type": "terminator",
      "description": "transcription terminator for bacteriophage T7 RNA polymerase",
      "count": 197
    },
    {
      "type": "polyA_signal",
      "description": "SV40 polyadenylation signal",
      "count": 182
    },
    {
      "type": "promoter",
      "description": "promoter of the E. coli cat gene encoding chloramphenicol acetyltransferase",
      "count": 169
    },
    {
      "type": "RBS",
      "description": "efficient ribosome binding site from bacteriophage T7 gene 10 (Olins and Rangwala, 1989)",
      "count": 169
    },
    {
      "type": "CDS",
      "description": "solubility-enhancement tag derived from T7 phage gene 10B",
      "count": 164
    },
    {
      "type": "misc_feature",
      "description": "pBluescript multiple cloning site",
      "count": 142
    },
    {
      "type": "misc_feature",
      "description": "pUC18/19 multiple cloning site",
      "count": 138
    },
    {
      "type": "CDS",
      "description": "Protein predicted: Swiss-Prot protein existence level 4. From Escherichia coli.",
      "count": 133
    },
    {
      "type": "promoter",
      "description": "promoter for bacteriophage T3 RNA polymerase",
      "count": 127
    },
    {
      "type": "misc_feature",
      "description": "central polypurine tract and central termination sequence of HIV-1",
      "count": 123
    },
    {
      "type": "promoter",
      "description": "SV40 enhancer and early promoter",
      "count": 119
    },
    {
      "type": "promoter",
      "description": "lacI",
      "count": 118
    },
    {
      "type": "CDS",
      "description": "CAT_ECOLX - Experimental evidence at protein level: Swiss-Prot protein existence level 1. This enzyme is an effector of chloramphenicol resistance in bacteria. From Escherichia coli. This protein is used as a marker in many commonly used cloning vectors, such as pACYC184.",
      "count": 113
    },
    {
      "type": "terminator",
      "description": "Escherichia coli rrnB; transcription terminator T1 from the E. coli rrnB gene",
      "count": 109
    },
    {
      "type": "LTR",
      "description": "truncated 5' long terminal repeat (LTR) from HIV-1",
      "count": 106
    },
    {
      "type": "CDS",
      "description": "9xHis affinity tag",
      "count": 94
    },
    {
      "type": "misc_feature",
      "description": "woodchuck hepatitis virus posttranscriptional regulatory element",
      "count": 89
    },
    {
      "type": "promoter",
      "description": "promoter for bacteriophage SP6 RNA polymerase",
      "count": 86
    },
    {
      "type": "protein_bind",
      "description": "mutant version of attB; recombination site for the Gateway\u00ae BP reaction BP Clonase\u2122",
      "count": 85
    },
    {
      "type": "promoter",
      "description": "E. coli promoter for tetracycline efflux protein gene",
      "count": 85
    },
    {
      "type": "promoter",
      "description": "human cytomegalovirus (CMV) immediate early promoter",
      "count": 84
    },
    {
      "type": "polyA_signal",
      "description": "bovine growth hormone polyadenylation signal",
      "count": 83
    },
    {
      "type": "protein_bind",
      "description": "mutant version of attL; recombination site for the Gateway\u00ae LR reaction LR Clonase\u2122",
      "count": 81
    },
    {
      "type": "CDS",
      "description": "large T antigen from SV40 (simian virus 40)",
      "count": 80
    },
    {
      "type": "promoter",
      "description": "RNA polymerase III promoter for human U6 snRNA",
      "count": 79
    },
    {
      "type": "rep_origin",
      "description": "SV40 origin of replication",
      "count": 78
    },
    {
      "type": "rep_origin",
      "description": "Plasmids containing the RSF 1030 origin of replication can be propagated in E. coli cells that contain additional plasmids with compatible origins.",
      "count": 78
    },
    {
      "type": "terminator",
      "description": "transcription terminator T2 from the E. coli rrnB gene",
      "count": 75
    },
    {
      "type": "CDS",
      "description": "TN5P_ECOLX - Also known as tnp. Experimental evidence at protein level: Swiss-Prot protein existence level 1. Mediates transposition of transposon Tn5 by a 'cut and paste' mechanism. First, the monomeric transposase binds the 19 bp inverted DNA repeats flanking the transposon. Then, dimerization of the DNA- bound transposase creates a synaptic DNA complex. After nicking of the first DNA strand, excision of the transposon proceeds through a series of intermediates. The transposase then mediates the insertion of the transposon at a new site by strand transfer. The activity of the wild- type transposase is very low, and is further inhibited by dimerization with the transposase inhibitor (inh). From Escherichia coli.",
      "count": 73
    },
    {
      "type": "CDS",
      "description": "chloramphenicol acetyltransferase; cat; confers resistance to chloramphenicol",
      "count": 67
    },
    {
      "type": "misc_feature",
      "description": "The Rev response element (RRE) of HIV-1 allows for Rev-dependent mRNA export from the nucleus to the cytoplasm.",
      "count": 66
    },
    {
      "type": "misc_feature",
      "description": "universal suffix for all parts",
      "count": 65
    }
  ]
}