LOCUS       AEC09755.1               555 aa    PRT              PLN 23-MAR-2023
DEFINITION  Arabidopsis thaliana flocculation protein protein.
ACCESSION   CP002685-5960
PROTEIN_ID  AEC09755.1
SOURCE      Arabidopsis thaliana (thale cress)
  ORGANISM  Arabidopsis thaliana
            Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
            Spermatophyta; Magnoliopsida; eudicotyledons; Gunneridae;
            Pentapetalae; rosids; malvids; Brassicales; Brassicaceae;
            Camelineae; Arabidopsis.
REFERENCE   1  (bases 1 to 19698289)
  AUTHORS   Lin,X., Kaul,S., Rounsley,S., Shea,T.P., Benito,M.I., Town,C.D.,
            Fujii,C.Y., Mason,T., Bowman,C.L., Barnstead,M., Feldblyum,T.V.,
            Buell,C.R., Ketchum,K.A., Lee,J., Ronning,C.M., Koo,H.L.,
            Moffat,K.S., Cronin,L.A., Shen,M., Pai,G., Van Aken,S., Umayam,L.,
            Tallon,L.J., Gill,J.E., Adams,M.D., Carrera,A.J., Creasy,T.H.,
            Goodman,H.M., Somerville,C.R., Copenhaver,G.P., Preuss,D.,
            Nierman,W.C., White,O., Eisen,J.A., Salzberg,S.L., Fraser,C.M. and
            Venter,J.C.
  TITLE     Sequence and analysis of chromosome 2 of the plant Arabidopsis
            thaliana
  JOURNAL   Nature 402 (6763), 761-768 (1999)
   PUBMED   10617197
REFERENCE   2  (bases 1 to 19698289)
  AUTHORS   Swarbreck,D., Lamesch,P., Wilks,C. and Huala,E.
  CONSRTM   TAIR
  TITLE     Direct Submission
  JOURNAL   Submitted (18-FEB-2011) Department of Plant Biology, Carnegie
            Institution, 260 Panama Street, Stanford, CA, USA
REFERENCE   3  (bases 1 to 19698289)
  AUTHORS   Krishnakumar,V., Cheng,C.-Y., Chan,A.P., Schobel,S., Kim,M.,
            Ferlanti,E.S., Belyaeva,I., Rosen,B.D., Micklem,G., Miller,J.R.,
            Vaughn,M. and Town,C.D.
  TITLE     Direct Submission
  JOURNAL   Submitted (17-MAY-2016) Plant Genomics, J. Craig Venter Institute,
            9704 Medical Center Dr, Rockville, MD 20850, USA
  REMARK    Protein update by submitter
FEATURES             Qualifiers
     source          /organism="Arabidopsis thaliana"
                     /mol_type="genomic DNA"
                     /db_xref="taxon:3702"
                     /chromosome="2"
                     /ecotype="Columbia"
     protein         /locus_tag="AT2G39950"
                     /gene_synonym="T28M21.11"
                     /gene_synonym="T28M21_11"
                     /inference="Similar to RNA sequence,
                     EST:INSD:ES054605.1,INSD:BP601829.1,INSD:EL089671.1,
                     INSD:AV533241.1,INSD:EL306873.1,INSD:BP794195.1,
                     INSD:BP786386.1,INSD:AV798613.1,INSD:EL250946.1,
                     INSD:EH836924.1,INSD:BE523079.1,INSD:ES026364.1,
                     INSD:ES062806.1,INSD:BP607038.1,INSD:EL252283.1,
                     INSD:BP782084.1,INSD:DR367323.1,INSD:EL209835.1,
                     INSD:CB256595.1,INSD:AV784161.1,INSD:CB257392.1,
                     INSD:BP783515.1,INSD:AV808596.1,INSD:BP785758.1,
                     INSD:ES029809.1,INSD:EL227423.1,INSD:EL278420.1,
                     INSD:AV806296.1,INSD:BP606216.1,INSD:BP787157.1,
                     INSD:ES215538.1"
                     /note="unknown protein; FUNCTIONS IN: molecular_function
                     unknown; INVOLVED IN: biological_process unknown; LOCATED
                     IN: cellular_component unknown; EXPRESSED IN: 24 plant
                     structures; EXPRESSED DURING: 15 growth stages; Has 941
                     Blast hits to 229 proteins in 79 species: Archae - 0;
                     Bacteria - 8; Metazoa - 89; Fungi - 54; Plants - 41;
                     Viruses - 0; Other Eukaryotes - 749 (source: NCBI BLink)."
                     /db_xref="Araport:AT2G39950"
                     /db_xref="TAIR:AT2G39950"
     intron_pos      37:0 (1/3)
     intron_pos      75:2 (2/3)
     intron_pos      157:0 (3/3)
BEGIN
        1 MQVMGACRGD ERLKPLLKLN VSNGMAEDRL LAHLSQHFEP AEIGMLARCF CIPLVSVRVG
       61 KIIKEGILMR PTPIRGNLSL MVLPTSDLRL SFIGDNGHSE QLFTYTSKSQ CSAVSIEEIT
      121 VDSSGRSFVI RIANGNAFYY WCSEKSKLLG TELRRKMKDL IKKKPSISEL TGIEESRLGS
      181 VASHLRLYLM GSVVPNIKGC QVPSPDSSSS SGFSETADSS SSASSKSLRA RHCGTQQTKT
      241 QGSLSPRASS FKENTLRNAS LRISSRDKSK GHSEGHFSIF DNSSITSIPT NVEGFIQSEG
      301 EVEEATENYN GIRQIIAFEE AESTPSTMTG PPPFPLKMGP PVFSPYYCWC PPTTSSLHAP
      361 SASYQFPPLS IELPSLPPLS SLLPASGSDG FLIPSSPLDL SDIPPLPLVH HIPIPGSSSS
      421 SSQQQMMIPI MCDPIVHIPV IDIFSSGQSY LVSAGPTGII STGIPPLPVE NDSLVEKGAR
      481 ETLRLLISGA NATTSTPLNH HGSRGLYSVS RDVSGVSLFA PIGLQQPSSV EGGDGGGESV
      541 SSSEAVPAPP RETSG
//