LOCUS       QJU58388.1              1344 aa    PRT              BCT 18-MAY-2020
DEFINITION  Sphingomonas sp. AP4-R1 amino acid adenylation domain-
            containing protein protein.
ACCESSION   CP053346-2357
PROTEIN_ID  QJU58388.1
SOURCE      Sphingomonas sp. AP4-R1
  ORGANISM  Sphingomonas sp. AP4-R1
            Bacteria; Proteobacteria; Alphaproteobacteria; Sphingomonadales;
            Sphingomonadaceae; Sphingomonas.
REFERENCE   1  (bases 1 to 5252057)
  AUTHORS   Heo,J., Kim,S.-J., Kim,J.-S., Hong,S.-B. and Kwon,S.-W.
  TITLE     Genome sequencing of strain KACC 21605
  JOURNAL   Unpublished
REFERENCE   2  (bases 1 to 5252057)
  AUTHORS   Heo,J., Kim,S.-J., Kim,J.-S., Hong,S.-B. and Kwon,S.-W.
  TITLE     Direct Submission
  JOURNAL   Submitted (08-MAY-2020) Agricultural Mircrobiology Division,
            National Institute of Agricultural Sciences, 166
            Nongsaengmyeong-ro, Iseo-myeon, Wanju-gun, Jeollabuk-do 55365,
            South Korea
COMMENT     The annotation was added by the NCBI Prokaryotic Genome Annotation
            Pipeline (PGAP). Information about PGAP can be found here:
            https://www.ncbi.nlm.nih.gov/genome/annotation_prok/
            This genome has a base modification file available.
            
            ##Genome-Assembly-Data-START##
            Assembly Date          :: APR-2020
            Assembly Method        :: RS HGAP Assembly v. 3.0
            Genome Representation  :: Full
            Expected Final Version :: Yes
            Genome Coverage        :: 99.0x
            Sequencing Technology  :: PacBio RSII
            ##Genome-Assembly-Data-END##
            
            ##Genome-Annotation-Data-START##
            Annotation Provider               :: NCBI
            Annotation Date                   :: 05/11/2020 21:04:38
            Annotation Pipeline               :: NCBI Prokaryotic Genome
                                                 Annotation Pipeline (PGAP)
            Annotation Method                 :: Best-placed reference protein
                                                 set; GeneMarkS-2+
            Annotation Software revision      :: 4.11
            Features Annotated                :: Gene; CDS; rRNA; tRNA; ncRNA;
                                                 repeat_region
            Genes (total)                     :: 4,788
            CDSs (total)                      :: 4,729
            Genes (coding)                    :: 4,613
            CDSs (with protein)               :: 4,613
            Genes (RNA)                       :: 59
            rRNAs                             :: 2, 2, 2 (5S, 16S, 23S)
            complete rRNAs                    :: 2, 2, 2 (5S, 16S, 23S)
            tRNAs                             :: 50
            ncRNAs                            :: 3
            Pseudo Genes (total)              :: 116
            CDSs (without protein)            :: 116
            Pseudo Genes (ambiguous residues) :: 0 of 116
            Pseudo Genes (frameshifted)       :: 56 of 116
            Pseudo Genes (incomplete)         :: 58 of 116
            Pseudo Genes (internal stop)      :: 26 of 116
            Pseudo Genes (multiple problems)  :: 22 of 116
            ##Genome-Annotation-Data-END##
FEATURES             Qualifiers
     source          /organism="Sphingomonas sp. AP4-R1"
                     /mol_type="genomic DNA"
                     /strain="AP4-R1"
                     /host="Malus prunifolia (crab apple)"
                     /culture_collection="KACC:21605"
                     /db_xref="taxon:2735134"
                     /geo_loc_name="South Korea: Naju-si"
                     /collection_date="23-Oct-2019"
                     /collected_by="Jun Heo, Soon-Wo Kwon"
                     /identified_by="Jun Heo, Soon-Wo Kwon"
     protein         /locus_tag="HL653_11930"
                     /inference="COORDINATES: similar to AA
                     sequence:RefSeq:WP_010160720.1"
                     /note="Derived by automated computational analysis using
                     gene prediction method: Protein Homology."
                     /transl_table=11
BEGIN
        1 MLENRPDLAV PPPEEALPTV YASITPAPAL REDEPYARDE LLHEIFDATC RAHLARCAVR
       61 LIGNDPENNR KTTLTYWELR ERSVRFARQL RAMGVERGDR VVLCLSRSLD QYMAILGTLW
      121 AGACYVPVDW TYPQDRIDFI AEDSGAVLIV TESERAADMP GRTLVVDAAL GDLAAHEARA
      181 IDRTESGAVP DDLAYIIYTS GTTGRPKGVA ITHRNACHLV RSECAILALE PEDKVFGGFS
      241 LAFDMSVETM WSAFFVGAEL LVANEALAKA GPDIAIVLAA EGVTIWHVVP SLLTLVETDM
      301 PTLRLLNLGG EACPPDLVNR WARPGLRMLN TYGPTETTVT ATWTELQPGR RVTIGRPLPG
      361 YTAWIVDEKL WPVPAGAEGE LVIGGPGVGA GYVNLPDLTA EKFVKTPFDG PDGAPALIYR
      421 SGDLVRLDAV GDIEFIGRID TQVKIRGFRV ELAEIEAVIA DDPSVAQAVV HLFRDEDGAE
      481 FLAAFVVARS GTAIDLDAVR ARVRDRLPNY MRPAAYQVLE ALPTLPASGK VDRKALQRPV
      541 VAPAEERETV APATPLEERL HAIWSEAFAP QKVSVLDDLF EDLGGHSLKA ARLVSAIRRF
      601 PGLAGVSIQD VYAAPTIRGL AARLADRIVP DKVAGQPFHC IAAWKRWLCW IAQTIALLPI
      661 YSVAGLQWFF PYVAYIHLAG DMNRVSALLL SGLSFILIPP LAMAASIVVK WVVIGRFRRG
      721 VYPLWGAYYF RWWFVRRFSE VIATPYLAGT PMIRTYYRLL GARVGQRAFI GRGNIDAADL
      781 VTIGDDAVIS DYAMLATSSV ERGLLHLGTA RIGNGGFVGS MAVVGRDAVI GEGAALEDLS
      841 ALPAGVHIPA GESWSGSPGR RISEGLPQRA DDTAGPVRRA LIGVALTIAA LILPIVSILP
      901 IAPGLISMIE IDWNSDNYTY LLISPLLAMT YVILMCVLTV LAKRLILGPV HPGRYSIHSW
      961 FYVRFWFVQQ INDLALRLLH PIYATLYVIP WYRALGVRVG RRAEISTAAA IVPDLVDIGP
     1021 ESFIADAVLF GAARVEPGAI VLAHTKIGRR SFIGNSALLP TGASIGDGVL IGVLSKPPED
     1081 GGAEKPDGTW FGSPPISLPV RQTIGLFDEG SRFNPGKRLI ATRLSIEAIR VTLSLALFIA
     1141 FFSLLLSAVG EIDELRYGGY KILYTFPFLY VGFALACGLS VVLLKWLVMG RYRATTQPLW
     1201 STFVWRTELI TATYENLAVP NLLEPLRGTP WLPAYLRLLG CRIGRRCYLD TTDVTEHDLV
     1261 RIGDDVALND FSGLQTHLFE DRVMKVSGVT VGDRATIGSY AIVLYDAEIG EDAQLGDLSV
     1321 VMKGETLPPG TSWEGSPAAL TRTG
//