ID   DEGP4_ARATH             Reviewed;         518 AA.
AC   Q9SHZ0; O04481; Q1PFG5;
DT   24-JAN-2006, integrated into UniProtKB/Swiss-Prot.
DT   01-MAY-2000, sequence version 1.
DT   03-AUG-2022, entry version 125.
DE   RecName: Full=Protease Do-like 4, mitochondrial;
DE            EC=3.4.21.-;
DE   Flags: Precursor;
GN   Name=DEGP4; OrderedLocusNames=At1g65640; ORFNames=F1E22.2, F5I14.17;
OS   Arabidopsis thaliana (Mouse-ear cress).
OC   Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
OC   Spermatophyta; Magnoliopsida; eudicotyledons; Gunneridae; Pentapetalae;
OC   rosids; malvids; Brassicales; Brassicaceae; Camelineae; Arabidopsis.
OX   NCBI_TaxID=3702;
RN   [1]
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=cv. Columbia;
RX   PubMed=11130712; DOI=10.1038/35048500;
RA   Theologis A., Ecker J.R., Palm C.J., Federspiel N.A., Kaul S., White O.,
RA   Alonso J., Altafi H., Araujo R., Bowman C.L., Brooks S.Y., Buehler E.,
RA   Chan A., Chao Q., Chen H., Cheuk R.F., Chin C.W., Chung M.K., Conn L.,
RA   Conway A.B., Conway A.R., Creasy T.H., Dewar K., Dunn P., Etgu P.,
RA   Feldblyum T.V., Feng J.-D., Fong B., Fujii C.Y., Gill J.E., Goldsmith A.D.,
RA   Haas B., Hansen N.F., Hughes B., Huizar L., Hunter J.L., Jenkins J.,
RA   Johnson-Hopson C., Khan S., Khaykin E., Kim C.J., Koo H.L.,
RA   Kremenetskaia I., Kurtz D.B., Kwan A., Lam B., Langin-Hooper S., Lee A.,
RA   Lee J.M., Lenz C.A., Li J.H., Li Y.-P., Lin X., Liu S.X., Liu Z.A.,
RA   Luros J.S., Maiti R., Marziali A., Militscher J., Miranda M., Nguyen M.,
RA   Nierman W.C., Osborne B.I., Pai G., Peterson J., Pham P.K., Rizzo M.,
RA   Rooney T., Rowley D., Sakano H., Salzberg S.L., Schwartz J.R., Shinn P.,
RA   Southwick A.M., Sun H., Tallon L.J., Tambunga G., Toriumi M.J., Town C.D.,
RA   Utterback T., Van Aken S., Vaysberg M., Vysotskaia V.S., Walker M., Wu D.,
RA   Yu G., Fraser C.M., Venter J.C., Davis R.W.;
RT   "Sequence and analysis of chromosome 1 of the plant Arabidopsis thaliana.";
RL   Nature 408:816-820(2000).
RN   [2]
RP   GENOME REANNOTATION.
RC   STRAIN=cv. Columbia;
RX   PubMed=27862469; DOI=10.1111/tpj.13415;
RA   Cheng C.Y., Krishnakumar V., Chan A.P., Thibaud-Nissen F., Schobel S.,
RA   Town C.D.;
RT   "Araport11: a complete reannotation of the Arabidopsis thaliana reference
RT   genome.";
RL   Plant J. 89:789-804(2017).
RN   [3]
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE MRNA] (ISOFORM 2).
RC   STRAIN=cv. Columbia;
RX   PubMed=17147637; DOI=10.1111/j.1467-7652.2006.00183.x;
RA   Underwood B.A., Vanderhaeghen R., Whitford R., Town C.D., Hilson P.;
RT   "Simultaneous high-throughput recombinational cloning of open reading
RT   frames in closed and open configurations.";
RL   Plant Biotechnol. J. 4:317-324(2006).
RN   [4]
RP   GENE FAMILY, AND NOMENCLATURE.
RX   PubMed=11299370; DOI=10.1104/pp.125.4.1912;
RA   Adam Z., Adamska I., Nakabayashi K., Ostersetzer O., Haussuhl K.,
RA   Manuell A., Zheng B., Vallon O., Rodermel S.R., Shinozaki K., Clarke A.K.;
RT   "Chloroplast and mitochondrial proteases in Arabidopsis. A proposed
RT   nomenclature.";
RL   Plant Physiol. 125:1912-1918(2001).
CC   -!- FUNCTION: Putative serine protease.
CC   -!- SUBCELLULAR LOCATION: Mitochondrion membrane {ECO:0000305}.
CC   -!- ALTERNATIVE PRODUCTS:
CC       Event=Alternative splicing; Named isoforms=2;
CC       Name=1;
CC         IsoId=Q9SHZ0-1; Sequence=Displayed;
CC       Name=2;
CC         IsoId=Q9SHZ0-2; Sequence=VSP_035497, VSP_035498;
CC   -!- MISCELLANEOUS: [Isoform 2]: May be due to a competing donor splice
CC       site. {ECO:0000305}.
CC   -!- SIMILARITY: Belongs to the peptidase S1C family. {ECO:0000305}.
CC   -!- SEQUENCE CAUTION:
CC       Sequence=AAB60913.1; Type=Erroneous gene model prediction; Evidence={ECO:0000305};
CC   ---------------------------------------------------------------------------
CC   Copyrighted by the UniProt Consortium, see https://www.uniprot.org/terms
CC   Distributed under the Creative Commons Attribution (CC BY 4.0) License
CC   ---------------------------------------------------------------------------
DR   EMBL; AC001229; AAB60913.1; ALT_SEQ; Genomic_DNA.
DR   EMBL; AC007234; AAF23846.1; -; Genomic_DNA.
DR   EMBL; CP002684; AEE34406.1; -; Genomic_DNA.
DR   EMBL; CP002684; ANM60216.1; -; Genomic_DNA.
DR   EMBL; DQ446398; ABE65743.1; -; mRNA.
DR   PIR; D96681; D96681.
DR   RefSeq; NP_001322516.1; NM_001334218.1. [Q9SHZ0-1]
DR   RefSeq; NP_564857.2; NM_105237.2. [Q9SHZ0-2]
DR   AlphaFoldDB; Q9SHZ0; -.
DR   SMR; Q9SHZ0; -.
DR   BioGRID; 28096; 1.
DR   STRING; 3702.AT1G65640.1; -.
DR   MEROPS; S01.A02; -.
DR   PaxDb; Q9SHZ0; -.
DR   PRIDE; Q9SHZ0; -.
DR   EnsemblPlants; AT1G65640.1; AT1G65640.1; AT1G65640. [Q9SHZ0-2]
DR   EnsemblPlants; AT1G65640.2; AT1G65640.2; AT1G65640. [Q9SHZ0-1]
DR   GeneID; 842875; -.
DR   Gramene; AT1G65640.1; AT1G65640.1; AT1G65640. [Q9SHZ0-2]
DR   Gramene; AT1G65640.2; AT1G65640.2; AT1G65640. [Q9SHZ0-1]
DR   KEGG; ath:AT1G65640; -.
DR   Araport; AT1G65640; -.
DR   TAIR; locus:2018481; AT1G65640.
DR   eggNOG; KOG1320; Eukaryota.
DR   HOGENOM; CLU_020120_10_2_1; -.
DR   InParanoid; Q9SHZ0; -.
DR   OMA; LICNCAN; -.
DR   OrthoDB; 594175at2759; -.
DR   PhylomeDB; Q9SHZ0; -.
DR   PRO; PR:Q9SHZ0; -.
DR   Proteomes; UP000006548; Chromosome 1.
DR   ExpressionAtlas; Q9SHZ0; baseline and differential.
DR   Genevisible; Q9SHZ0; AT.
DR   GO; GO:0031966; C:mitochondrial membrane; IEA:UniProtKB-SubCell.
DR   GO; GO:0004252; F:serine-type endopeptidase activity; IBA:GO_Central.
DR   GO; GO:0006508; P:proteolysis; IEA:UniProtKB-KW.
DR   Gene3D; 2.30.42.10; -; 1.
DR   Gene3D; 2.40.10.10; -; 2.
DR   InterPro; IPR041517; DEGP_PDZ.
DR   InterPro; IPR036034; PDZ_sf.
DR   InterPro; IPR009003; Peptidase_S1_PA.
DR   InterPro; IPR043504; Peptidase_S1_PA_chymotrypsin.
DR   InterPro; IPR001940; Peptidase_S1C.
DR   Pfam; PF17815; PDZ_3; 1.
DR   PRINTS; PR00834; PROTEASES2C.
DR   SUPFAM; SSF50156; SSF50156; 1.
DR   SUPFAM; SSF50494; SSF50494; 1.
PE   2: Evidence at transcript level;
KW   Alternative splicing; Hydrolase; Membrane; Mitochondrion; Protease;
KW   Reference proteome; Serine protease; Transit peptide.
FT   TRANSIT         1..23
FT                   /note="Mitochondrion"
FT                   /evidence="ECO:0000255"
FT   CHAIN           24..518
FT                   /note="Protease Do-like 4, mitochondrial"
FT                   /id="PRO_0000045832"
FT   DOMAIN          278..358
FT                   /note="PDZ"
FT   REGION          98..262
FT                   /note="Serine protease"
FT   ACT_SITE        116
FT                   /note="Charge relay system"
FT                   /evidence="ECO:0000250"
FT   ACT_SITE        147
FT                   /note="Charge relay system"
FT                   /evidence="ECO:0000250"
FT   ACT_SITE        225
FT                   /note="Charge relay system"
FT                   /evidence="ECO:0000250"
FT   VAR_SEQ         434..436
FT                   /note="LAD -> IIS (in isoform 2)"
FT                   /evidence="ECO:0000303|PubMed:17147637"
FT                   /id="VSP_035497"
FT   VAR_SEQ         437..518
FT                   /note="Missing (in isoform 2)"
FT                   /evidence="ECO:0000303|PubMed:17147637"
FT                   /id="VSP_035498"
FT   CONFLICT        301
FT                   /note="G -> E (in Ref. 3; ABE65743)"
FT                   /evidence="ECO:0000305"
SQ   SEQUENCE   518 AA;  57970 MW;  ACCBDC642A842FB8 CRC64;
     MLFRFLQTLA RFCRFLLISV LGFRFSPLLL LGYVKLQDEN KHNSESALAS GTDAKQPEAA
     ENVTSSSIDF AVNSVVKVFT VYSMPSVLQP WRNWPQQESG GSGFVISGKK ILTNAHVVAD
     HIFLQVRKHG SPTKYKAQVR AIGHECDLAI LEIDNEEFWE DMIPLELGEI PSLDESVAVF
     GYPTGGDSVS ITKGYVSRVE YTRYAHGGTT LLAIQTDAAI NPGNSGGPAI IGNKMAGVAF
     QKDPSADNIG YIIPTPVIKH FLTAVEENGQ YGGFCTLDIS YQLMENSQLR NHFKMGPEMT
     GILINEINPL SDAYKRLRKD DIILAIDDVL IGNDAKVTFR NKERINFNHF VSMKKLDETV
     LLQVLRDGKE HEFHIMVKPV PPLVPGHQYD KLPSYYIFAG FVFVPLTQPY IDSTLICNCA
     IKYMPEKAGE QLVLADDINA GYTDFKNLKV IKVNGVQVEN LKHLTELVET CWTEDLRLDL
     ENEKVVVLNY ANAKEATSLI LELHRIPSAN EYDYQWQS