LOCUS       ASS93974.1               593 aa    PRT              BCT 08-AUG-2017
DEFINITION  Peribacillus simplex NBRC 15720 = DSM 1321 phosphomethylpyrimidine
            synthase ThiC protein.
ACCESSION   CP017704-1664
PROTEIN_ID  ASS93974.1
SOURCE      Peribacillus simplex NBRC 15720 = DSM 1321
  ORGANISM  Peribacillus simplex NBRC 15720 = DSM 1321
            Bacteria; Firmicutes; Bacilli; Bacillales; Bacillaceae;
            Peribacillus.
REFERENCE   1  (bases 1 to 5645783)
  AUTHORS   Park,M.-K., Lee,Y.-J., Yi,H., Bahn,Y.-S., Kim,J.F. and Lee,D.-W.
  TITLE     The whole genome sequencing and assembly of Bacillus simplex DSM
            1321 strain
  JOURNAL   Unpublished
REFERENCE   2  (bases 1 to 5645783)
  AUTHORS   Park,M.-K., Lee,Y.-J., Yi,H., Bahn,Y.-S., Kim,J.F. and Lee,D.-W.
  TITLE     Direct Submission
  JOURNAL   Submitted (17-OCT-2016) Kyungpook National University, School of
            Applied Biosciences, 80 Daehak-Ro, Bukgu, Daegu 41566, South Korea
COMMENT     Annotation was added by the NCBI Prokaryotic Genome Annotation
            Pipeline (released 2013). Information about the Pipeline 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 Method       :: SMRT analysis 2.3 v. HGAP protocol 2
            Genome Coverage       :: missing
            Sequencing Technology :: PacBio
            ##Genome-Assembly-Data-END##
            
            ##Genome-Annotation-Data-START##
            Annotation Provider               :: NCBI
            Annotation Date                   :: 10/17/2016 13:55:10
            Annotation Pipeline               :: NCBI Prokaryotic Genome
                                                 Annotation Pipeline
            Annotation Method                 :: Best-placed reference protein
                                                 set; GeneMarkS+
            Annotation Software revision      :: 3.3
            Features Annotated                :: Gene; CDS; rRNA; tRNA; ncRNA;
                                                 repeat_region
            Genes (total)                     :: 5,348
            CDS (total)                       :: 5,228
            Genes (coding)                    :: 5,118
            CDS (coding)                      :: 5,118
            Genes (RNA)                       :: 120
            rRNAs                             :: 13, 12, 12 (5S, 16S, 23S)
            complete rRNAs                    :: 13, 12, 12 (5S, 16S, 23S)
            tRNAs                             :: 77
            ncRNAs                            :: 6
            Pseudo Genes (total)              :: 110
            Pseudo Genes (ambiguous residues) :: 0 of 110
            Pseudo Genes (frameshifted)       :: 73 of 110
            Pseudo Genes (incomplete)         :: 32 of 110
            Pseudo Genes (internal stop)      :: 34 of 110
            Pseudo Genes (multiple problems)  :: 28 of 110
            ##Genome-Annotation-Data-END##
FEATURES             Qualifiers
     source          /organism="Peribacillus simplex NBRC 15720 = DSM 1321"
                     /mol_type="genomic DNA"
                     /strain="DSM 1321"
                     /isolation_source="soil"
                     /type_material="type strain of Bacillus simplex"
                     /db_xref="taxon:1349754"
                     /collection_date="1989"
     protein         /locus_tag="BS1321_08345"
                     /inference="EXISTENCE: similar to AA
                     sequence:RefSeq:WP_009335527.1"
                     /note="catalyzes the formation of
                     4-amino-2-methyl-5-phosphomethylpyrimidine from
                     5-amino-1-(5-phospho-D-ribosyl)imidazole and
                     S-adenosyl-L-methionine in thiamine biosynthesis; Derived
                     by automated computational analysis using gene prediction
                     method: Protein Homology."
                     /transl_table=11
BEGIN
        1 MMSNSVNDMN VSIMSSFAGS KKVYVEGSRP DIKVPMREIK LSPTTGAFGE EDNPPLRVYD
       61 TSGFYTDSEY PIDIHKGLAP IRRSWVLERE DVEEYEGREI KPEDNGYKKV ESQSNAEVFP
      121 GLKRKPLRAV KGQNVTQLHY ARKGIITPEM EFISIRENVA PEFVREEVAS GRAIIPANIN
      181 HPESEPMIIG RNFHVKINAN IGNSAVSSSI EAEVEKMTWA TRWGADNIMD LSTGKNIHTT
      241 REWIIRNSPV PVGTVPIYQA LEKVNGVAED LNWEVFRDTL IEQAEQGVDY FTIHAGVLLR
      301 YIPMTAKRVT GIVSRGGSIM AQWCLAHHQE SFLYTHFEEI CEIMKAYDVS FSLGDGLRPG
      361 SIADANDEAQ FAELETLGEL TKIAWKHDVQ VMVEGPGHVP MHLIKENMDK QLEVCQEAPF
      421 YTLGPLTTDI APGYDHITSA IGAAMIGWFG TAMLCYVTPK EHLGLPNKED VRVGVITYKI
      481 AAHAADLAKG HPHARKRDDA LSKARFEFRW RDQFNLSLDP ERAVEYHDET LPAEGAKTAH
      541 FCSMCGPKFC SMRISQDIRD LAKEKGLGFE SVIDEGLKEK ANEFRKTDGE IYQ
//