LOCUS       AEC10056.1              1215 aa    PRT              PLN 23-MAR-2023
DEFINITION  Arabidopsis thaliana hypothetical protein protein.
ACCESSION   CP002685-6385
PROTEIN_ID  AEC10056.1
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="AT2G41960"
                     /gene_synonym="T6D20.15"
                     /gene_synonym="T6D20_15"
                     /inference="Similar to RNA sequence,
                     EST:INSD:EG433802.1,INSD:DR371722.1,INSD:EH944214.1,
                     INSD:EG433811.1,INSD:ES207841.1,INSD:CK121881.1,
                     INSD:AV546442.1,INSD:ES151821.1,INSD:EL239754.1,
                     INSD:AI995142.1,INSD:EL019870.1,INSD:EH993309.1,
                     INSD:EH877954.1,INSD:EG433829.1,INSD:EH987863.1,
                     INSD:DR274100.1,INSD:EL268264.1,INSD:EL080588.1,
                     INSD:H76700.1,INSD:AV786132.1,INSD:EH982278.1,
                     INSD:EG433809.1,INSD:ES077501.1,INSD:ES162400.1,
                     INSD:AV547749.1,INSD:EG433806.1,INSD:BP829349.1,
                     INSD:EG433820.1,INSD:EL093694.1,INSD:EG433816.1,
                     INSD:EL082540.1,INSD:AV527369.1,INSD:AV784932.1,
                     INSD:AV790337.1,INSD:AV825167.1,INSD:EL215895.1,
                     INSD:EL221963.1,INSD:EL144682.1,INSD:AV543048.1,
                     INSD:AV520210.1,INSD:EL228856.1,INSD:ES039985.1,
                     INSD:CF652221.1,INSD:EG433797.1,INSD:AV823861.1,
                     INSD:EG433804.1,INSD:EL003629.1,INSD:EH940021.1,
                     INSD:AV529198.1,INSD:AV523508.1,INSD:EH896632.1,
                     INSD:ES168658.1,INSD:CF652220.1,INSD:EL330585.1,
                     INSD:AV520866.1,INSD:AV526351.1,INSD:EH929261.1,
                     INSD:EH864442.1"
                     /inference="similar to RNA sequence,
                     mRNA:INSD:AY093082.1,INSD:BT008414.1,INSD:AK222074.1,
                     INSD:AY065162.1"
                     /note="unknown protein; BEST Arabidopsis thaliana protein
                     match is: unknown protein (TAIR:AT3G58050.1); Has 11991
                     Blast hits to 7260 proteins in 458 species: Archae - 17;
                     Bacteria - 481; Metazoa - 5028; Fungi - 1325; Plants -
                     615; Viruses - 38; Other Eukaryotes - 4487 (source: NCBI
                     BLink)."
                     /db_xref="Araport:AT2G41960"
                     /db_xref="TAIR:AT2G41960"
     intron_pos      41:0 (1/7)
     intron_pos      154:0 (2/7)
     intron_pos      240:2 (3/7)
     intron_pos      288:0 (4/7)
     intron_pos      411:0 (5/7)
     intron_pos      455:0 (6/7)
     intron_pos      498:0 (7/7)
BEGIN
        1 MNKYKCKTMP GLTTHMNEHY SSSGFWSEDD DGLTYDQLDQ FWSELSSKAR HELLRIDKQT
       61 LFEQARKNMC CSRCLGLLLE GFAQILSAGR AAYEKRMMGP SKDNCKSNGT RKCTVAYQSP
      121 PVHRWGGLTT TRSGCITLLD CFLTAKTFKG LQNVFESNRA RERERELLYP DACGGGGRVW
      181 LSQGIAGFGK GHGTRETCNL HTTRLSCDTL VDFWSALEEH SRQSLLRMKE EDFVERLTYR
      241 FDCKKFCRDC RRNVIREFKE LKELKRIQRD PRCTDWFCVA DTAFQYEVDI DSVRADWSQY
      301 FTENAGYHHF EWAIGTGEGE SDILEFKYVG NDRSARVNGL DLRGLHECYI TLRAFKKNGR
      361 PSEISVKAHA LRGQQCVHSR LVVGDGFVSI KRGECIRMFF EHAEEAEEEE DEVLIDKDGN
      421 ELDGECLRPQ KHAKSPELAR EFLLDAATVI FKEQVEKAFR DGTARQNAHS IFVCLSSELL
      481 EQRVHIACKE IVTLEKQNKL LEEEEKEKRE EEERKERKRI KEREKKLRRK ERLKEKEREK
      541 EQKNPKFSDK AILPIMSREE EGSRNLDEDT NNTIRCEESG IENGDVDLSS PGSPDDQDEE
      601 CLDGCISPRV ETHSCDSTDK EIIDHEDENG CFTPRPAHKT ARLWKEVQTD HSLRLSEKRR
      661 FTEKTSFVSS SEAGYCNDRL EMSSGHFNGS DKNVRVKASK AGGSPNSSRS HEEFQCSDGR
      721 TGERYDYHSC SCKPINGYRE KVESNTSATR GMREPKSVFK SDSDLDVSKL NRANRYTQSG
      781 YRREIRSKMN NSRNACKMDP VNVRKVLDSV EPKHSRNSST SDVLSLTTYK AEEIKDVSPT
      841 VKPAGTPSLC KATDKLGNGS FNNSTEVDKK MEVHITLKND YLYSKDPMMS RSSSSNNGNI
      901 ESSSMSDSEV ASQQSEGREN LVDTQNDMPD CHEKMVEKVT EMSMDERDVL KIKNISNLPA
      961 DNGESKLSGT PFMVPSQNME NMVPGLNTGS YLSQPQNMIL PQMLNQSIPL PVFQAPSTMG
     1021 YYHQAPVSWS SASTNGLMQF PHPNHYVYTG PLGYSLNGES PLCMQYGTPL NHSAAPFFNS
     1081 GPVPIFHPFA ETNTMNTVDQ AQPLEPLEHS FLKEANERRF NEMPLMETPR KRCPQTDSDE
     1141 NFSLFHFGGP VALSTGSKAN PARSKDGILE DFSLQFSGDH VFGDPTGNSK KEKENTVGEE
     1201 YNLFATSNSL RFSIF
//