LOCUS       VTR93922.1              1217 aa    PRT              BCT 03-FEB-2020
DEFINITION  Gemmata massiliana Forkhead-associated protein OS=Isosphaera
            pallida (strain ATCC 43644 / DSM 9630 / IS1B) GN=Isop_3075
            PE=4 SV=1: PQQ: PQQ_2 protein.
ACCESSION   LR593886-3223
PROTEIN_ID  VTR93922.1
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_37920"
                     /note="BLAST_uniprot:hit_1 ;
                     ACCESSION=tr|E8R3D0|E8R3D0_ISOPI ;
                     ALN/Q_length_ratio=0.484 ; DESCRIPTION=Forkhead-associated
                     protein OS=Isosphaera pallida (strain ATCC 43644 / DSM
                     9630 / IS1B) GN=Isop_3075 PE=4 SV=1 ; EVALUE=9e-16 ;
                     Q/S_length_ratio=1.032"
                     /note="BLAST_uniprot:hit_2 ;
                     ACCESSION=tr|L0DIZ1|L0DIZ1_SINAD ;
                     ALN/Q_length_ratio=0.615 ; DESCRIPTION=Uncharacterized
                     protein OS=Singulisphaera acidiphila (strain ATCC BAA-1392
                     / DSM 18658 / VKM B-2454 / MOB10) GN=Sinac_5197 PE=4 SV=1
                     ; EVALUE=2e-10 ; Q/S_length_ratio=1.038"
                     /note="BLAST_uniprot:hit_3 ;
                     ACCESSION=tr|A6CAA8|A6CAA8_9PLAN ;
                     ALN/Q_length_ratio=0.380 ; DESCRIPTION=Uncharacterized
                     protein OS=Planctomyces maris DSM 8797 GN=PM8797T_27065
                     PE=4 SV=1 ; EVALUE=4e-10 ; Q/S_length_ratio=1.002"
                     /note="BLAST_uniprot:hit_4 ;
                     ACCESSION=tr|F0SMB0|F0SMB0_PLABD ;
                     ALN/Q_length_ratio=0.478 ; DESCRIPTION=Uncharacterized
                     protein OS=Planctomyces brasiliensis (strain ATCC 49424 /
                     DSM 5305 / JCM 21570 / NBRC 103401 / IFAM 1448)
                     GN=Plabr_4518 PE=4 SV=1 ; EVALUE=1e-08 ;
                     Q/S_length_ratio=1.036"
                     /note="Pfam_scan:hit_1 (444..481); Pfam:PF01011.16:PQQ;
                     Pfam_type:Repeat;HMM_aln_Length:31; HMM_Length:38;
                     EVALUE:3.9e-05; BITSCORE: 22.9"
                     /note="Pfam_scan:hit_2 (768..970); Pfam:PF13360.1:PQQ_2;
                     Pfam_type:Domain;HMM_aln_Length:157; HMM_Length:238;
                     EVALUE:7.5e-07; BITSCORE: 28.8"
BEGIN
        1 MSIVAQCPHC ETRFNLQPEM NGKSMRCPNL ECRQVFTVQA MEAVAPPAPI PELPPEPKAP
       61 PRSPAPLPPP PRAKSSKSAK PAVVEARVVE ATIVEAAVVA PPKMKEVVWS EGTDIPPPPL
      121 PKKGKKPLKA DTTDDVDDDF IVRRKKKSNR RPMILAGMGI TIVALIGFSL LYIDRVGRLK
      181 EVQLADKANE EYKKGDYGSS AKLYDKLSKD YPDSKRIDEY KFFADLSEMQ TVVRSVTNRN
      241 DYAPAVTRLN AFIEAHKESP LAKPATGYGH DVLEAGKKLG EDIAGFAGDR VKAFQANRTK
      301 SDELPLADKA IANGRELLPV LDPFRGPDDP PLDKIRSALD QTEKDVKRER DRSAAIARAR
      361 TQLEKPTDAL IQSAEADLRT AGFLEDDEAQ KLIAAAKGKL LDLVQFVEEP AAAQPPPPTA
      421 AASLLFTTPV GKMKPRESGP GDATTVFLCV ARGILYAFNE DTGALIWATR VGPDVTDPPP
      481 VARVDLERGP TDLAVVTSNV GNAPAVVGYE LRANKLVWYQ PLPAAPAGPA VVVGNHAFVP
      541 LRDTTGSVYE FDLKTGLRIG YIRFGQSVAE RGLVARPGTN LLYVAADARR VYAIDAGGRD
      601 DAGNRINPRC VQVIATGHLA GTLKVPPLFI GPEGIEPAER WMVLSQADGT TVTKLRVFSV
      661 GAISPPPADG STVPETPAVP VVALPVPGWV WFPPVSDGER LAVASDTGQL RLFGVNQAGN
      721 LDKPLFPLPA PAQAPVADDK PLRGLVIPVG ESEYWLLSGG YVQKARLALV PSRGQEVVLA
      781 GPRLNVGEPV HAAQINARKD TACFVVRSPN SSGCRAVAFD LRSGEVRWQR QLGLVPAKTS
      841 AEQFVAPIPQ GDNFVLVDED GGIVVVPAAS GVQLGETLTA PDGWVIAPTP TNATGPTVVA
      901 STADGKLVFA VTPVAGTEGA KFVVRQVAGG KLVQQDEVNA PAALAGQPAV VGGILYIPTA
      961 DGFVNRFTPG AGVANPASLT PGPAWRSDRP PANAVCSVTV VSESSFVTSD GGKKLNRWEW
     1021 GNAANARWSP AGTWELQERV AGSGVALPPA EPGGPPRFMV ADTSGSVQLF AADKPGQQLR
     1081 RWRSPQPGRP SSALVAQPAD AARVVVTHVI DGKWAVALNP DNEDVLWTAH TSDDANGAIM
     1141 GAPQPAGENR WIVTDLAGRI VLIDGANGDA LARLNAGLPG GVPATASSVA ANTVLTQLSD
     1201 GSAVVVELPK KEPPKKE
//