LOCUS       UJP40821.1               953 aa    PRT              BCT 25-JAN-2022
DEFINITION  Cellulomonas palmilytica GNAT family N-acetyltransferase protein.
ACCESSION   CP062221-960
PROTEIN_ID  UJP40821.1
SOURCE      Cellulomonas palmilytica
  ORGANISM  Cellulomonas palmilytica
            Bacteria; Actinobacteria; Micrococcales; Cellulomonadaceae;
            Cellulomonas.
REFERENCE   1  (bases 1 to 3834012)
  AUTHORS   Siriatcharanon,A.-k., Sutheeworapong,S., Pason,P., Waeonukul,R.,
            Kosugi,A., Ratanakhanokchai,K. and Tachaapaikoon,C.
  TITLE     Cellulomonas coenopalmateriei, sp. nov., a novel species of genus
            Cellulomonas for degradation of raw lignocellulose biomass; oil
            palm empty fruit bunch
  JOURNAL   Unpublished
REFERENCE   2  (bases 1 to 3834012)
  AUTHORS   Siriatcharanon,A.-k., Sutheeworapong,S., Pason,P., Waeonukul,R.,
            Kosugi,A., Ratanakhanokchai,K. and Tachaapaikoon,C.
  TITLE     Direct Submission
  JOURNAL   Submitted (16-SEP-2020) Pilot Plant Development and Training
            Institute, King Mongkut's University of Technology Thonburi,
            Bangkuntien-Chaitalay, Bangkok 10150, Thailand
COMMENT     Bacteria and source DNA available from Enzyme Technology
            Laboratory, Pilot Plant Development and Training Institute, King
            Mongkut's University of Technology Thonburi.
            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/
            
            ##Genome-Assembly-Data-START##
            Assembly Date          :: 19-MAY-2020
            Assembly Method        :: unicycler v. v0.4.8
            Assembly Name          :: EW123_hybrid
            Genome Representation  :: Full
            Expected Final Version :: Yes
            Genome Coverage        :: 10.0x
            Sequencing Technology  :: Oxford Nanopore MinION; Illumina HiSeq
            ##Genome-Assembly-Data-END##
            
            ##Genome-Annotation-Data-START##
            Annotation Provider               :: NCBI
            Annotation Date                   :: 09/30/2020 19:03:08
            Annotation Pipeline               :: NCBI Prokaryotic Genome
                                                 Annotation Pipeline (PGAP)
            Annotation Method                 :: Best-placed reference protein
                                                 set; GeneMarkS-2+
            Annotation Software revision      :: 4.13
            Features Annotated                :: Gene; CDS; rRNA; tRNA; ncRNA;
                                                 repeat_region
            Genes (total)                     :: 3,454
            CDSs (total)                      :: 3,400
            Genes (coding)                    :: 3,351
            CDSs (with protein)               :: 3,351
            Genes (RNA)                       :: 54
            rRNAs                             :: 2, 2, 2 (5S, 16S, 23S)
            complete rRNAs                    :: 2, 2, 2 (5S, 16S, 23S)
            tRNAs                             :: 45
            ncRNAs                            :: 3
            Pseudo Genes (total)              :: 49
            CDSs (without protein)            :: 49
            Pseudo Genes (ambiguous residues) :: 0 of 49
            Pseudo Genes (frameshifted)       :: 8 of 49
            Pseudo Genes (incomplete)         :: 41 of 49
            Pseudo Genes (internal stop)      :: 2 of 49
            Pseudo Genes (multiple problems)  :: 2 of 49
            ##Genome-Annotation-Data-END##
FEATURES             Qualifiers
     source          /organism="Cellulomonas palmilytica"
                     /mol_type="genomic DNA"
                     /strain="EW123"
                     /isolation_source="Earthworm bio-fertilizer soil"
                     /type_material="type strain of Cellulomonas palmilytica"
                     /db_xref="taxon:2608402"
                     /country="Thailand: Bangkok"
                     /lat_lon="13.6771 N 100.4591 E"
                     /collection_date="Nov-2015"
                     /collected_by="Enzyme Technology Laboratory, KMUTT"
     protein         /locus_tag="F1D97_04875"
                     /inference="COORDINATES: protein motif:HMM:NF013927.1"
                     /inference="COORDINATES: similar to AA
                     sequence:RefSeq:WP_003814014.1"
                     /note="Derived by automated computational analysis using
                     gene prediction method: Protein Homology."
                     /transl_table=11
BEGIN
        1 MGTGAEVRRD AWGVPHVRAD DELALAHAQG RVTAHDRTWQ LRLLRAQVAG ASAALLGPTG
       61 LPWDVLARRV RLADTARRAY AALADDDRAW VDAYAAGVRE GLVAAGPTAE ERELDRVLPP
      121 RGPGAADTDD PWPAWAPLGA LHAYHVLFST FPRVLWHAHV VRLVRDATPG SPLAGLDPVR
      181 LLALFDPSEG GPTAGSNAWA VHGSRTASGA PLLAGDPHRL LDLPGTYQQV RLACPGYDVL
      241 GLAFVGVPGV PHFGHAGGAA WGITNAMAHS AEVVHERLRR GPDGTWQAWG PGGWEPTARA
      301 VEHVTVRGGD AVEVEVVETV RGPLVVRGLD VTAPARLHDE PRDRSDHEPG RGTGDDEPGH
      361 EDAYALRLPA RVDSDLGIAT ARRLLHARTA HDVHEAFTGW VDPVDRVVAA DTEGTVLAFD
      421 AGRVADRPRA QRLVPLVAWD PGHAPRPWRR LAAPVVVTGV HVDANERPAE PTRDHGTAYA
      481 PDRADRLRSL LTDRTGLTPA DMGALHGDTR LAEADRLVAL VARVGGLDGP AAALRDRLLA
      541 WDRRMDAAST DAAAYAAVRG ALARRLVAEP ALAALGAPHG LGAVLDPWLG VRGRVALVVP
      601 ALLDAPGTDL GIDGDALVRA ALVEVADGPE PGPWGERHTV LPAHVLDDVP GAVPPRVPSL
      661 PLSGDQDTVR CTGSVPGVTD RAYRGSVARW VWDLADRDRS RWGVPFGASG DPAGPHLADQ
      721 HAVWARARTV EVVIAWDTLT PDPQALGRTP SGEGPGAEAS SGEGPAGTSP VAWAVGPRGA
      781 VVADEDSQVG HLTWTVLDPD ADLPLLHQWV TARGTGFWGL AHLAPDELRD TYAFVDDLPH
      841 HHALIVHADG VPAGLVQVYD PALDPVGEVY DVRAGDVGMH VLVGARPPRG SVAGLLGAVV
      901 DLIGTRRGVR RVVAEPDAAN AAILRHARAL GFELGPEVDL PTKRARLVWR DSR
//