LOCUS       AEC08915.1               345 aa    PRT              PLN 23-MAR-2023
DEFINITION  Arabidopsis thaliana Cysteine proteinases superfamily
            protein protein.
ACCESSION   CP002685-4832
PROTEIN_ID  AEC08915.1
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="AT2G34080"
                     /gene_synonym="T14G11.20"
                     /gene_synonym="T14G11_20"
                     /inference="Similar to RNA sequence,
                     EST:INSD:BP602870.1,INSD:AU228291.1,INSD:EH815916.1,
                     INSD:AU237254.1,INSD:AV537584.1"
                     /inference="similar to RNA sequence, mRNA:INSD:AK228746.1"
                     /note="Cysteine proteinases superfamily protein; FUNCTIONS
                     IN: cysteine-type peptidase activity, cysteine-type
                     endopeptidase activity; INVOLVED IN: proteolysis; LOCATED
                     IN: endomembrane system; CONTAINS InterPro DOMAIN/s:
                     Peptidase C1A, papain (InterPro:IPR013128), Proteinase
                     inhibitor I29, cathepsin propeptide (InterPro:IPR013201),
                     Peptidase C1A, papain C-terminal (InterPro:IPR000668),
                     Peptidase, cysteine peptidase active site
                     (InterPro:IPR000169); BEST Arabidopsis thaliana protein
                     match is: Cysteine proteinases superfamily protein
                     (TAIR:AT1G29090.1); Has 1344 Blast hits to 1324 proteins
                     in 29 species: Archae - 0; Bacteria - 0; Metazoa - 0;
                     Fungi - 2; Plants - 1342; Viruses - 0; Other Eukaryotes -
                     0 (source: NCBI BLink)."
                     /db_xref="Araport:AT2G34080"
                     /db_xref="TAIR:AT2G34080"
     intron_pos      152:1 (1/1)
BEGIN
        1 MASIMVLVTV LIILFTGFRI SQATSRTVIF REQSMVDKHE QWMARFSREY RDELEKNMRR
       61 DVFKKNLKFI ENFNKKGNKS YKLGVNEFAD WTNEEFLAIH TGLKGLTEVS PSKVVAKTIS
      121 SQTWNVSDMV VESKDWRAEG AVTPVKYQGQ CGCCWAFSAV AAVEGVAKIA GGNLVSLSEQ
      181 QLLDCDREYD RGCDGGIMSD AFNYVVQNRG IASENDYSYQ GSDGGCRSNA RPAARISGFQ
      241 TVPSNNERAL LEAVSRQPVS VSMDATGDGF MHYSGGVYDG PCGTSSNHAV TFVGYGTSQD
      301 GTKYWLAKNS WGETWGEKGY IRIRRDVAWP QGMCGVAQYA FYPVA
//