LOCUS       AEE79316.1               367 aa    PRT              PLN 23-MAR-2023
DEFINITION  Arabidopsis thaliana Papain family cysteine protease protein.
ACCESSION   CP002686-7842
PROTEIN_ID  AEE79316.1
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 23459830)
  AUTHORS   Salanoubat,M., Lemcke,K., Rieger,M., Ansorge,W., Unseld,M.,
            Fartmann,B., Valle,G., Blocker,H., Perez-Alonso,M., Obermaier,B.,
            Delseny,M., Boutry,M., Grivell,L.A., Mache,R., Puigdomenech,P., De
            Simone,V., Choisne,N., Artiguenave,F., Robert,C., Brottier,P.,
            Wincker,P., Cattolico,L., Weissenbach,J., Saurin,W., Quetier,F.,
            Schafer,M., Muller-Auer,S., Gabel,C., Fuchs,M., Benes,V.,
            Wurmbach,E., Drzonek,H., Erfle,H., Jordan,N., Bangert,S.,
            Wiedelmann,R., Kranz,H., Voss,H., Holland,R., Brandt,P.,
            Nyakatura,G., Vezzi,A., D'Angelo,M., Pallavicini,A., Toppo,S.,
            Simionati,B., Conrad,A., Hornischer,K., Kauer,G., Lohnert,T.H.,
            Nordsiek,G., Reichelt,J., Scharfe,M., Schon,O., Bargues,M.,
            Terol,J., Climent,J., Navarro,P., Collado,C., Perez-Perez,A.,
            Ottenwalder,B., Duchemin,D., Cooke,R., Laudie,M., Berger-Llauro,C.,
            Purnelle,B., Masuy,D., de Haan,M., Maarse,A.C., Alcaraz,J.P.,
            Cottet,A., Casacuberta,E., Monfort,A., Argiriou,A., flores,M.,
            Liguori,R., Vitale,D., Mannhaupt,G., Haase,D., Schoof,H., Rudd,S.,
            Zaccaria,P., Mewes,H.W., Mayer,K.F., Kaul,S., Town,C.D., Koo,H.L.,
            Tallon,L.J., Jenkins,J., Rooney,T., Rizzo,M., Walts,A.,
            Utterback,T., Fujii,C.Y., Shea,T.P., Creasy,T.H., Haas,B.,
            Maiti,R., Wu,D., Peterson,J., Van Aken,S., Pai,G., Militscher,J.,
            Sellers,P., Gill,J.E., Feldblyum,T.V., Preuss,D., Lin,X.,
            Nierman,W.C., Salzberg,S.L., White,O., Venter,J.C., Fraser,C.M.,
            Kaneko,T., Nakamura,Y., Sato,S., Kato,T., Asamizu,E., Sasamoto,S.,
            Kimura,T., Idesawa,K., Kawashima,K., Kishida,Y., Kiyokawa,C.,
            Kohara,M., Matsumoto,M., Matsuno,A., Muraki,A., Nakayama,S.,
            Nakazaki,N., Shinpo,S., Takeuchi,C., Wada,T., Watanabe,A.,
            Yamada,M., Yasuda,M. and Tabata,S.
  CONSRTM   European Union Chromosome 3 Arabidopsis Sequencing Consortium;
            Institute for Genomic Research; Kazusa DNA Research Institute
  TITLE     Sequence and analysis of chromosome 3 of the plant Arabidopsis
            thaliana
  JOURNAL   Nature 408 (6814), 820-822 (2000)
   PUBMED   11130713
REFERENCE   2  (bases 1 to 23459830)
  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 23459830)
  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="3"
                     /ecotype="Columbia"
     protein         /locus_tag="AT3G54940"
                     /inference="Similar to RNA sequence,
                     EST:INSD:BP838910.1,INSD:AV808595.1,INSD:BP642455.1,
                     INSD:BP833611.1,INSD:BP652550.1,INSD:AV557104.1,
                     INSD:BP595604.1,INSD:BP814191.1,INSD:BE522489.1,
                     INSD:BP832247.1,INSD:AV803629.1,INSD:BP562145.2,
                     INSD:BP816570.1,INSD:BP649527.1,INSD:EL048254.1,
                     INSD:BP839651.1,INSD:BP647749.1,INSD:BP657728.1,
                     INSD:BP642091.1,INSD:EL144451.1,INSD:Z17766.1,
                     INSD:BP824669.1,INSD:BP815777.1,INSD:BE525202.1,
                     INSD:BP817316.1,INSD:BP820429.1,INSD:BP822130.1,
                     INSD:BE524743.1,INSD:BP827269.1,INSD:BP644330.1,
                     INSD:EL090951.1,INSD:BP644506.1,INSD:BE523451.1,
                     INSD:AV828966.1,INSD:BP650883.1,INSD:BP655520.1,
                     INSD:BP830658.1,INSD:BP638960.1"
                     /inference="Similar to RNA sequence,
                     mRNA:INSD:AY070063.1,INSD:AK227032.1,INSD:AK221936.1"
                     /note="Papain family cysteine protease; FUNCTIONS IN:
                     cysteine-type endopeptidase activity, cysteine-type
                     peptidase activity; INVOLVED IN: proteolysis; LOCATED IN:
                     endomembrane system; EXPRESSED IN: embryo, sepal, carpel;
                     EXPRESSED DURING: 4 anthesis, C globular stage; 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: Papain family
                     cysteine protease (TAIR:AT2G21430.1); Has 7716 Blast hits
                     to 7658 proteins in 713 species: Archae - 63; Bacteria -
                     225; Metazoa - 3256; Fungi - 4; Plants - 1843; Viruses -
                     138; Other Eukaryotes - 2187 (source: NCBI BLink)."
                     /db_xref="TAIR:AT3G54940"
                     /db_xref="Araport:AT3G54940"
     intron_pos      156:0 (1/3)
     intron_pos      196:0 (2/3)
     intron_pos      277:1 (3/3)
BEGIN
        1 MVAKALAQLI TCIILFCHVV ASVEDLTIRQ VTADNRRIRP NLLGTHTESK FRLFMSDYGK
       61 NYSTREEYIH RLGIFAKNVL KAAEHQMMDP SAVHGVTQFS DLTEEEFKRM YTGVADVGGS
      121 RGGTVGAEAP MVEVDGLPED FDWREKGGVT EVKNQGACGS CWAFSTTGAA EGAHFVSTGK
      181 LLSLSEQQLV DCDQACDPKD KKACDNGCGG GLMTNAYEYL MEAGGLEEER SYPYTGKRGH
      241 CKFDPEKVAV RVLNFTTIPL DENQIAANLV RHGPLAVGLN AVFMQTYIGG VSCPLICSKR
      301 NVNHGVLLVG YGSKGFSILR LSNKPYWIIK NSWGKKWGEN GYYKLCRGHD ICGINSMVSA
      361 VATQVSS
//