LOCUS       VTR94799.1              1348 aa    PRT              BCT 03-FEB-2020
DEFINITION  Gemmata massiliana Uncultured bacterium genome assembly
            Metasoil_fosmids_resub OS=uncultured bacterium PE=4 SV=
            1 protein.
ACCESSION   LR593886-4100
PROTEIN_ID  VTR94799.1
SOURCE      Gemmata massiliana
  ORGANISM  Gemmata massiliana
            Bacteria; Planctomycetes; Planctomycetia; Gemmatales; Gemmataceae;
            Gemmata.
REFERENCE   1
  AUTHORS   
  CONSRTM   Science for Life Laboratories
  JOURNAL   Submitted (14-MAY-2019) to the INSDC. DEPARTMENT OF CELL AND
            MOLECULAR BIOLOGY, Uppsala University, Molecular Evolution,
            Biomedicinskt centrum (BMC), Husargatan 3, 752 37 Uppsala, Sweden
FEATURES             Qualifiers
     source          /organism="Gemmata massiliana"
                     /chromosome="1"
                     /isolate="Soil9"
                     /mol_type="genomic DNA"
                     /isolation_source="soil"
                     /db_xref="taxon:1210884"
     protein         /locus_tag="SOIL9_29150"
                     /note="BLAST_uniprot:hit_1 ;
                     ACCESSION=tr|A0A090KG00|A0A090KG00_9BACT ;
                     ALN/Q_length_ratio=1.000 ; DESCRIPTION=Uncultured
                     bacterium genome assembly Metasoil_fosmids_resub
                     OS=uncultured bacterium PE=4 SV=1 ; EVALUE=0.0 ;
                     Q/S_length_ratio=0.993"
                     /note="BLAST_uniprot:hit_2 ;
                     ACCESSION=tr|L0DBH1|L0DBH1_SINAD ;
                     ALN/Q_length_ratio=0.473 ; DESCRIPTION=Uncharacterized
                     protein OS=Singulisphaera acidiphila (strain ATCC BAA-1392
                     / DSM 18658 / VKM B-2454 / MOB10) GN=Sinac_1840 PE=4 SV=1
                     ; EVALUE=3e-36 ; Q/S_length_ratio=1.071"
                     /note="BLAST_uniprot:hit_3 ;
                     ACCESSION=tr|E8QXR0|E8QXR0_ISOPI ;
                     ALN/Q_length_ratio=0.467 ; DESCRIPTION=Uncharacterized
                     protein OS=Isosphaera pallida (strain ATCC 43644 / DSM
                     9630 / IS1B) GN=Isop_3540 PE=4 SV=1 ; EVALUE=3e-32 ;
                     Q/S_length_ratio=1.039"
                     /note="BLAST_uniprot:hit_4 ;
                     ACCESSION=tr|A6C543|A6C543_9PLAN ;
                     ALN/Q_length_ratio=0.913 ; DESCRIPTION=Uncharacterized
                     protein OS=Planctomyces maris DSM 8797 GN=PM8797T_20958
                     PE=4 SV=1 ; EVALUE=6e-27 ; Q/S_length_ratio=1.081"
                     /note="BLAST_uniprot:hit_5 ;
                     ACCESSION=tr|A3ZTH8|A3ZTH8_9PLAN ;
                     ALN/Q_length_ratio=0.861 ; DESCRIPTION=Uncharacterized
                     protein OS=Blastopirellula marina DSM 3645
                     GN=DSM3645_19623 PE=4 SV=1 ; EVALUE=1e-19 ;
                     Q/S_length_ratio=1.118"
BEGIN
        1 MALLLRPPEE RESLPDRLAE LGRTRKRVAL AAGLLGFVGT VVGIVALSSL LDAAVHLSPF
       61 GRTLALVTLL ATGGIVWVRG ISRAQRYRTD ALSVALELED QFPSLNDALA SAVSFLEPRD
      121 EDAPDELPPV IPGVSNRLTA SAVRVAERRA GRLPLDYIVP TGRCWWNAWA CGAALAVALP
      181 LALFDTDRAG VAFARLADPF GAHPWPTKTR IEFLAPKEFP VRIPKGEAFE LRFAVRGELV
      241 GPATVSVRVK DGSEFEEPFP LARNNDPQVP GAAVVTARFD PSRVSSTFEV QVSSNDAVTD
      301 WQTVTVVPPP RLVPLDGRPS PQFHVSPPAY TRLSAIELPP GAAVIEIPTG TVVHFRAATD
      361 VKLSGAVLTF AGDKTAVTNA VPFAHLGQLD PIAATGAQAL ANEMAADIPL TVSEDGMRFS
      421 ATFVPLLSGP YALKLTDDTG LTGTRVLKID LTPDPVPKVT LNQPVTGRDP SYLTLTASVL
      481 VNALAEDPLY GVRGAYLEYR VGRDGPVRSI PLGAAGNQPV MALAGAAGGA AVVLAPPAGS
      541 LEAFARVPIA AFLRDDGTPV REGDLIVLRA AADDWDDVAA LKGRGRSVGE VEIRIAAPDA
      601 IDAWLQRELA TIRPELVRIR EQQRDAKQKT IEVLPLPGGT LAPADRDRLV GADLGQRQVT
      661 GKIADPAQGL RAKADLLRET VRANGLPKSN TTDRVEVVAT ELGRTADRDL GAAQQNLADA
      721 LRLAGQSPKP GQEKELTDYL RKAGRSQKNI EDTATSLLDL LALWGGAGEI RSEARVQKDM
      781 ILRQILGNEQ LKERVKEGKQ NPADDEQREL DRAALRADQS ADQARELIAR AANLAADKDK
      841 QADDLRSQAA LKEKEAAELK RQAAATENPV ERSSLNTQAD AAAASAADLK TAADKAEAEA
      901 KALRKGIEAA GGQGLADGLR NAAELLRKNK QSGAETALRS ASNRLGALAE SLAEKEIDPI
      961 PELTNSKIQR RAADQLDALA GNVDSLRNRI EAAARLNDPV QRAETLKILG QEQDKLIERG
     1021 REMLQKLTAE KAEDAARDLR SALDRMESTR DDLEKGQPNT RSQREAVERL DTARDKLDLA
     1081 AAQGGRQLSD EKRRKLADQV RALLEKQRAA VAEAARIHGE VAKQKGWDKL LLTSYSDIDA
     1141 VREKDIAIEV RKLAEADFAP LPVFARLLTD SAKAIDTACE KIKTRCDDAD LAAAFDADLE
     1201 ALGDRKVMRP MELALRRLEQ LADALKPDDK KPPAKNGNAP ENQPKAPNPP ANPNGGGEPD
     1261 VVPPLAQLKV LRALQAELNE RTAQFAKDHP EPDKLTDSEK EELGELEQTQ REITELFEQV
     1321 AKLFPSAEKE KDKGEKDGDG DAKEKQVP
//