ID   A0A1Q9DHC8_SYMMI        Unreviewed;      2325 AA.
AC   A0A1Q9DHC8;
DT   12-APR-2017, integrated into UniProtKB/TrEMBL.
DT   12-APR-2017, sequence version 1.
DT   27-MAR-2024, entry version 20.
DE   SubName: Full=Dipeptidyl peptidase 1 {ECO:0000313|EMBL:OLP94569.1};
GN   Name=CTSC {ECO:0000313|EMBL:OLP94569.1};
GN   ORFNames=AK812_SmicGene23403 {ECO:0000313|EMBL:OLP94569.1};
OS   Symbiodinium microadriaticum (Dinoflagellate) (Zooxanthella
OS   microadriatica).
OC   Eukaryota; Sar; Alveolata; Dinophyceae; Suessiales; Symbiodiniaceae;
OC   Symbiodinium.
OX   NCBI_TaxID=2951 {ECO:0000313|EMBL:OLP94569.1, ECO:0000313|Proteomes:UP000186817};
RN   [1] {ECO:0000313|EMBL:OLP94569.1, ECO:0000313|Proteomes:UP000186817}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=CCMP2467 {ECO:0000313|EMBL:OLP94569.1,
RC   ECO:0000313|Proteomes:UP000186817};
RA   Aranda M., Li Y., Liew Y.J., Baumgarten S., Simakov O., Wilson M., Piel J.,
RA   Ashoor H., Bougouffa S., Bajic V.B., Ryu T., Ravasi T., Bayer T.,
RA   Micklem G., Kim H., Bhak J., Lajeunesse T.C., Voolstra C.R.;
RT   "Genome analysis of coral dinoflagellate symbionts highlights evolutionary
RT   adaptations to a symbiotic lifestyle.";
RL   Submitted (FEB-2016) to the EMBL/GenBank/DDBJ databases.
CC   -!- SIMILARITY: Belongs to the peptidase C1 family.
CC       {ECO:0000256|ARBA:ARBA00008455}.
CC   -!- CAUTION: The sequence shown here is derived from an EMBL/GenBank/DDBJ
CC       whole genome shotgun (WGS) entry which is preliminary data.
CC       {ECO:0000313|EMBL:OLP94569.1}.
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; LSRX01000537; OLP94569.1; -; Genomic_DNA.
DR   OrthoDB; 211155at2759; -.
DR   Proteomes; UP000186817; Unassembled WGS sequence.
DR   GO; GO:0016020; C:membrane; IEA:UniProtKB-KW.
DR   GO; GO:0008234; F:cysteine-type peptidase activity; IEA:InterPro.
DR   GO; GO:0006508; P:proteolysis; IEA:InterPro.
DR   Gene3D; 3.90.70.10; Cysteine proteinases; 1.
DR   Gene3D; 3.50.4.10; Hepatocyte Growth Factor; 1.
DR   InterPro; IPR038765; Papain-like_cys_pep_sf.
DR   InterPro; IPR000169; Pept_cys_AS.
DR   InterPro; IPR025660; Pept_his_AS.
DR   InterPro; IPR013128; Peptidase_C1A.
DR   InterPro; IPR000668; Peptidase_C1A_C.
DR   PANTHER; PTHR12411; CYSTEINE PROTEASE FAMILY C1-RELATED; 1.
DR   PANTHER; PTHR12411:SF942; DIPEPTIDYL PEPTIDASE 1; 1.
DR   Pfam; PF00112; Peptidase_C1; 1.
DR   SMART; SM00645; Pept_C1; 1.
DR   SUPFAM; SSF54001; Cysteine proteinases; 1.
DR   PROSITE; PS00139; THIOL_PROTEASE_CYS; 1.
DR   PROSITE; PS00639; THIOL_PROTEASE_HIS; 1.
PE   3: Inferred from homology;
KW   Glycoprotein {ECO:0000256|ARBA:ARBA00023180};
KW   Hydrolase {ECO:0000256|ARBA:ARBA00022801};
KW   Membrane {ECO:0000256|SAM:Phobius};
KW   Protease {ECO:0000256|ARBA:ARBA00022670};
KW   Reference proteome {ECO:0000313|Proteomes:UP000186817};
KW   Thiol protease {ECO:0000256|ARBA:ARBA00022807};
KW   Transmembrane {ECO:0000256|SAM:Phobius};
KW   Transmembrane helix {ECO:0000256|SAM:Phobius};
KW   Zymogen {ECO:0000256|ARBA:ARBA00023145}.
FT   TRANSMEM        29..54
FT                   /note="Helical"
FT                   /evidence="ECO:0000256|SAM:Phobius"
FT   TRANSMEM        1135..1168
FT                   /note="Helical"
FT                   /evidence="ECO:0000256|SAM:Phobius"
FT   TRANSMEM        1174..1200
FT                   /note="Helical"
FT                   /evidence="ECO:0000256|SAM:Phobius"
FT   TRANSMEM        1207..1229
FT                   /note="Helical"
FT                   /evidence="ECO:0000256|SAM:Phobius"
FT   TRANSMEM        1235..1257
FT                   /note="Helical"
FT                   /evidence="ECO:0000256|SAM:Phobius"
FT   DOMAIN          1357..1557
FT                   /note="Peptidase C1A papain C-terminal"
FT                   /evidence="ECO:0000259|SMART:SM00645"
FT   REGION          194..228
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          1590..1658
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          1695..1752
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          1769..1807
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          1823..1853
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        1604..1618
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        1642..1657
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        1832..1846
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   2325 AA;  258077 MW;  F8C77E68CE283176 CRC64;
     MFWLLLQRWL LLLLPLCLAR LLLLFLLLPL LLLLPLLLLL LLLLMLPLFL LLLLPSWLSF
     ISSHASACSL DSELELSSSD CCLLLAKRSN FATVKSKVQG TNEYLGLTPS LSDERWRVKG
     FGNPTAGPPE VPAAVRRGAS AALRRRPQCY TLLSVPAWSP WLLLTFRSTA CVTRLLAIGS
     FTEDLLGQGA ARAGTSFRTT RPPSHRWSYR KWPSNPQRRN XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX
     XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXXXXXXX XXXXLLLLLL
     LLLLLLLLLL LLLLLLLLLL LLLLLLLLLL LPLLLLLLLL LLLLLLLLLL LLLLLLLLLL
     LLLLLPLLLL LLLLFLLLVL VLVLVLLLLL PLLLLLLLLF LLLVLVLVLV LASLAAAPPR
     AAPMPRASEE RLNSTYHDSF AATLNLLQDW WTAKVYDRFV GRTLHEINSM AGILRPFSQA
     KRKEFDPYFG NGHGESVPSF LQQARARTKA VKGRRPLPSA WDWRNVSGVN YLDEVIDQGT
     CGSCYIVATT HMLAARYRIQ HQNPSFDGFS FNFPLFCSEY NQGCNGGYAF LASRWAQDVG
     LVPKNCSHYD PDKLLGSCEL KCDVAALQKT WRATNHHYAA WTERVMNSFF GELVERGPLV
     VSFEPQSDIV YYTEGIYTSA PHQRAEWEPV DHAVLLVGYG LEAGCTPDRF GESLYDFAVK
     QAGLLHFMDF HFWFVCEMLL ATQIDEESDG ERSITATEIE EVPPAEDASD RPAAETLPER
     CDEVLATLPY LPPESPDQAG MLAKSSVASS PGKQGSYAQM RANREAGMLA KSSVASSPGK
     QGSYAQMRAN REALQPSPHV GYRPPEDGRR RGHADFANAV TRPPRALGGS ASLGRPPTPA
     RSGTRPHRDT YPSQISLRML ESTALQILKQ DRASTEHPTP SCLAGVGGRP SEAEPPSLEE
     RVGNWQDLDD VPKATVERAL SPKLQGMLRL PPSPQPAQPA QPASPPRSPF QDELAEATAE
     VALPSVSTTL RRHALKAFLD ETCGTVANSF DVMAGLALKS SIGGSGTPED RLRFMFSEQD
     FRVALTGLGY GLGVKDAWWS ELFAAMDVVI FAESSPETWR RNQEFGLPPQ SVIWVRSATL
     FSMVPVSPKF KEGVGLRDGS ATLFSMVPVS PKFKAESQGF DLERALSQVI LEEYPEEPLG
     RLEPLRATRS AEAPLTLTVA PCARAGRSIT DSESWDRFWR QLQFRGLKLR AWRDGQHVAG
     RMALRPDVPV QILKCAYVSA KAARLLLLKG SPGARMMEDR EMLTESQAQE ALRGSELPAA
     SDDALRGALA EDYTLLDEGP CFVPNTKYMP ANMPNEDRTV EELGVVVLLV EPPRYWPNRG
     CHLQSMEARP QFASRVTAGP PDCREGSRMK SCFHESTKFE PVNMPGQRRT QVGSVLECQL
     RCRQTQGCEH FSLWPDGGCH LQDANASEAF SAADFLFSCI LPDLW
//