plannotate/SFT_t0.95/feature_breakdown.json

{
  "model": "SFT_t0.95",
  "n_sequences_annotated": 3999,
  "total_hits": 68080,
  "by_type": {
    "CDS": 27172,
    "promoter": 12317,
    "rep_origin": 8319,
    "terminator": 6286,
    "protein_bind": 5563,
    "misc_feature": 4570,
    "RBS": 1483,
    "enhancer": 619,
    "ncRNA": 465,
    "polyA_signal": 339,
    "misc_RNA": 330,
    "mobile_element": 195,
    "intron": 132,
    "LTR": 93,
    "oriT": 74,
    "gene": 33,
    "sig_peptide": 27,
    "repeat_region": 22,
    "5'UTR": 13,
    "3'UTR": 13,
    "misc_recomb": 9,
    "tRNA": 4,
    "misc_signal": 2
  },
  "by_type_and_description": [
    {
      "type": "rep_origin",
      "description": "high-copy-number ColE1/pMB1/pBR322/pUC origin of replication",
      "count": 4111
    },
    {
      "type": "promoter",
      "description": "bla",
      "count": 3044
    },
    {
      "type": "misc_feature",
      "description": "basis of mobility region from pBR322",
      "count": 2740
    },
    {
      "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": 2701
    },
    {
      "type": "CDS",
      "description": "tetracycline efflux protein; tet; confers resistance to tetracycline",
      "count": 2423
    },
    {
      "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": 2419
    },
    {
      "type": "CDS",
      "description": "\u03b2-lactamase; bla; confers resistance to ampicillin, carbenicillin, and related antibiotics",
      "count": 2283
    },
    {
      "type": "CDS",
      "description": "Rop protein, which maintains plasmids at low copy number; rop",
      "count": 2146
    },
    {
      "type": "protein_bind",
      "description": "CAP binding activates transcription in the presence of cAMP. E. coli catabolite activator protein",
      "count": 1917
    },
    {
      "type": "promoter",
      "description": "promoter for bacteriophage T7 RNA polymerase",
      "count": 1890
    },
    {
      "type": "RBS",
      "description": "efficient ribosome binding site from bacteriophage T7 gene 10 (Olins and Rangwala, 1989)",
      "count": 1483
    },
    {
      "type": "terminator",
      "description": "transcription terminator T1 from the E. coli rrnB gene",
      "count": 1285
    },
    {
      "type": "CDS",
      "description": "aminoglycoside phosphotransferase; aph(3')-Ia; confers resistance to kanamycin in bacteria or G418 (Geneticin\u00ae) in eukaryotes",
      "count": 1269
    },
    {
      "type": "CDS",
      "description": "LacZ\u03b1 fragment of \u03b2-galactosidase; lacZ fragment",
      "count": 1266
    },
    {
      "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": 1244
    },
    {
      "type": "rep_origin",
      "description": "f1 bacteriophage origin of replication; arrow indicates direction of (+) strand synthesis",
      "count": 1214
    },
    {
      "type": "terminator",
      "description": "transcription terminator for bacteriophage T7 RNA polymerase",
      "count": 1146
    },
    {
      "type": "terminator",
      "description": "phage T7 early transcription terminator",
      "count": 1106
    },
    {
      "type": "CDS",
      "description": "Protein predicted: Swiss-Prot protein existence level 4. From Escherichia coli.",
      "count": 1036
    },
    {
      "type": "CDS",
      "description": "solubility-enhancement tag derived from T7 phage gene 10B",
      "count": 1025
    },
    {
      "type": "promoter",
      "description": "lacI",
      "count": 956
    },
    {
      "type": "promoter",
      "description": "promoter for the E. coli lac operon",
      "count": 891
    },
    {
      "type": "terminator",
      "description": "Escherichia coli rrnB; transcription terminator T1 from the E. coli rrnB gene",
      "count": 816
    },
    {
      "type": "CDS",
      "description": "composite tag for in vivo biotinylation, TEV protease cleavage, and 6xHis tagging",
      "count": 719
    },
    {
      "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": 699
    },
    {
      "type": "promoter",
      "description": "strong E. coli promoter; hybrid between the trp and lac UV5 promoters",
      "count": 683
    },
    {
      "type": "promoter",
      "description": "E. coli promoter for tetracycline efflux protein gene",
      "count": 656
    },
    {
      "type": "CDS",
      "description": "hfriFP is a fluorescent protein published in 2013, derived from Herbaspirillum frisingense.",
      "count": 622
    },
    {
      "type": "enhancer",
      "description": "human cytomegalovirus immediate early enhancer",
      "count": 610
    },
    {
      "type": "promoter",
      "description": "promoter of the E. coli cat gene encoding chloramphenicol acetyltransferase",
      "count": 602
    },
    {
      "type": "promoter",
      "description": "bacterial promoter (Registry of Standard Biological Parts BBa J23119)",
      "count": 591
    },
    {
      "type": "terminator",
      "description": "transcription terminator from phage lambda",
      "count": 583
    },
    {
      "type": "CDS",
      "description": "9xHis affinity tag",
      "count": 583
    },
    {
      "type": "misc_feature",
      "description": "pUC18/19 multiple cloning site",
      "count": 562
    },
    {
      "type": "CDS",
      "description": "Experimental evidence at protein level: Swiss-Prot protein existence level 1. GST isoenzymes appear to play a central role in the parasite detoxification system. Other functions are also suspected including a role in increasing the solubility of haematin in the parasite gut. From Schistosoma japonicum (Blood fluke).",
      "count": 455
    },
    {
      "type": "promoter",
      "description": "lacI (mutant); In the lacIq allele, a single base change in the promoter boosts expression of the lacI gene about 10-fold.",
      "count": 450
    },
    {
      "type": "CDS",
      "description": "6xHis affinity tag",
      "count": 444
    },
    {
      "type": "misc_feature",
      "description": "pBluescript multiple cloning site",
      "count": 431
    },
    {
      "type": "promoter",
      "description": "araBAD; promoter of the L-arabinose operon of E. coli; the araC regulatory gene is transcribed in the opposite direction (Guzman et al., 1995)",
      "count": 379
    },
    {
      "type": "ncRNA",
      "description": "Accession: RF00001 - 5S ribosomal RNA",
      "count": 371
    },
    {
      "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": 367
    },
    {
      "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": 367
    },
    {
      "type": "CDS",
      "description": "RNAAM_ECOLI - Also known as trpH From Escherichia coli (strain K12).",
      "count": 357
    },
    {
      "type": "CDS",
      "description": "tobacco etch virus (TEV) protease recognition and cleavage site",
      "count": 330
    },
    {
      "type": "terminator",
      "description": "transcription terminator T2 from the E. coli rrnB gene",
      "count": 326
    },
    {
      "type": "terminator",
      "description": "putative bacterial transcription terminator",
      "count": 319
    },
    {
      "type": "CDS",
      "description": "KKA2_KLEPN - Also known as kan, nptII. Experimental evidence at protein level: Swiss-Prot protein existence level 1. Resistance to kanamycin, neomycin, paromomycin, ribostamycin, butirosin and gentamicin B. From Klebsiella pneumoniae.",
      "count": 310
    },
    {
      "type": "CDS",
      "description": "L-arabinose regulatory protein; araC",
      "count": 299
    },
    {
      "type": "CDS",
      "description": "monomeric derivative of DsRed (Campbell et al., 2002)",
      "count": 292
    },
    {
      "type": "promoter",
      "description": "bacterial promoter (Registry of Standard Biological Parts BBa J23119) modified to end with an SpeI site",
      "count": 276
    },
    {
      "type": "CDS",
      "description": "maltose binding protein from E. coli; malE (mutated); This version of the gene does not encode a signal sequence, so MBP will remain in the cytosol.",
      "count": 271
    },
    {
      "type": "CDS",
      "description": "pIII; III; minor coat protein",
      "count": 268
    },
    {
      "type": "rep_origin",
      "description": "M13 bacteriophage origin of replication; arrow indicates direction of (+) strand synthesis",
      "count": 263
    },
    {
      "type": "CDS",
      "description": "chloramphenicol acetyltransferase; cat; confers resistance to chloramphenicol",
      "count": 253
    },
    {
      "type": "CDS",
      "description": "leader peptide from bacteriophage T7 gene 10 promotes efficient translation in E. coli",
      "count": 252
    },
    {
      "type": "CDS",
      "description": "replication protein for the broad-host-range plasmid pBBR1 from Bordetella bronchiseptica",
      "count": 233
    },
    {
      "type": "misc_RNA",
      "description": "guide RNA scaffold for the Streptococcus pyogenes CRISPR/Cas9 system",
      "count": 231
    },
    {
      "type": "promoter",
      "description": "promoter for bacteriophage T3 RNA polymerase",
      "count": 225
    },
    {
      "type": "rep_origin",
      "description": "replication origin of the broad-host-range plasmid pBBR1 from Bordetella bronchiseptica; requires the pBBR1 Rep protein for replication",
      "count": 218
    },
    {
      "type": "CDS",
      "description": "\u03b2-lactamase lacking the signal sequence; bla(M); allows cytosolic expression of \u03b2-lactamase",
      "count": 186
    }
  ]
}