ID   A0A3Q1C456_AMPOC        Unreviewed;      1210 AA.
AC   A0A3Q1C456;
DT   10-APR-2019, integrated into UniProtKB/TrEMBL.
DT   10-APR-2019, sequence version 1.
DT   27-MAR-2024, entry version 25.
DE   SubName: Full=Collagen, type V, alpha 2a {ECO:0000313|Ensembl:ENSAOCP00000022122.1};
GN   Name=COL5A2 {ECO:0000313|Ensembl:ENSAOCP00000022122.1};
OS   Amphiprion ocellaris (Clown anemonefish).
OC   Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
OC   Actinopterygii; Neopterygii; Teleostei; Neoteleostei; Acanthomorphata;
OC   Ovalentaria; Pomacentridae; Amphiprion.
OX   NCBI_TaxID=80972 {ECO:0000313|Ensembl:ENSAOCP00000022122.1, ECO:0000313|Proteomes:UP000257160};
RN   [1] {ECO:0000313|Ensembl:ENSAOCP00000022122.1}
RP   IDENTIFICATION.
RG   Ensembl;
RL   Submitted (NOV-2023) to UniProtKB.
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   AlphaFoldDB; A0A3Q1C456; -.
DR   STRING; 80972.ENSAOCP00000022122; -.
DR   Ensembl; ENSAOCT00000008785.1; ENSAOCP00000022122.1; ENSAOCG00000007590.1.
DR   GeneTree; ENSGT00940000155675; -.
DR   OMA; CESPQVP; -.
DR   Proteomes; UP000257160; Unplaced.
DR   GO; GO:0005201; F:extracellular matrix structural constituent; IEA:InterPro.
DR   GO; GO:0046872; F:metal ion binding; IEA:UniProtKB-KW.
DR   Gene3D; 2.60.120.1000; -; 1.
DR   Gene3D; 2.10.70.10; Complement Module, domain 1; 1.
DR   InterPro; IPR008160; Collagen.
DR   InterPro; IPR000885; Fib_collagen_C.
DR   InterPro; IPR001007; VWF_dom.
DR   PANTHER; PTHR24023:SF861; ACETYLCHOLINESTERASE COLLAGENIC TAIL PEPTIDE; 1.
DR   PANTHER; PTHR24023; COLLAGEN ALPHA; 1.
DR   Pfam; PF01410; COLFI; 1.
DR   Pfam; PF01391; Collagen; 10.
DR   Pfam; PF00093; VWC; 1.
DR   SMART; SM00038; COLFI; 1.
DR   SMART; SM00214; VWC; 1.
DR   SUPFAM; SSF57603; FnI-like domain; 1.
DR   PROSITE; PS51461; NC1_FIB; 1.
DR   PROSITE; PS01208; VWFC_1; 1.
DR   PROSITE; PS50184; VWFC_2; 1.
PE   4: Predicted;
KW   Extracellular matrix {ECO:0000256|ARBA:ARBA00022530};
KW   Glycoprotein {ECO:0000256|ARBA:ARBA00023180};
KW   Hydroxylation {ECO:0000256|ARBA:ARBA00023278};
KW   Metal-binding {ECO:0000256|ARBA:ARBA00022723};
KW   Reference proteome {ECO:0000313|Proteomes:UP000257160};
KW   Secreted {ECO:0000256|ARBA:ARBA00022530}; Signal {ECO:0000256|SAM:SignalP}.
FT   SIGNAL          1..25
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT   CHAIN           26..1210
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT                   /id="PRO_5018713705"
FT   DOMAIN          34..92
FT                   /note="VWFC"
FT                   /evidence="ECO:0000259|PROSITE:PS50184"
FT   DOMAIN          978..1210
FT                   /note="Fibrillar collagen NC1"
FT                   /evidence="ECO:0000259|PROSITE:PS51461"
FT   REGION          99..154
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          179..453
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          474..976
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        642..656
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        843..857
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        918..936
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   1210 AA;  119735 MW;  4222C166F964D07A CRC64;
     MMSFVHLRTF LFLVVSVAQV LIVTCQDGNS GDDMSCTADG QVYTNRDIWK PEPCRICVCD
     NGQVLCDEIQ CDELTNCEKM SIPEGECCPI CQSDSSSSGG TGSFGEQGLR GPAGYDGEPG
     IPGQPGEAGP PGPPAHPGVS SAGSVVTDRK NTKLRGSQNT ISVVKVRCVS RITVLDDCVL
     QGQPGPTGVR GPEGAQGQRG ETGHLGRPGP VGIRGTMGTD GGPGTKGPVG NLGPQGPGGH
     SGPPGPPGPQ GSTGQPGIKG QLGDVGVVGF KGEAGPKGEP GPPGSQGVIG PQGEEGKRGQ
     RGDPGSVGPP GPVGERGSPG NRGFPGADGL PGPKGAQGDR GTSGPSGPKG SLGDPGRTGE
     PGLPGARGLT GTPGVQGAEG KPGPLGAPGE DGRPGPAGSI GNRGPAGTMG VPGPKGFNGD
     PGKTGEQGSA GVPGQRVSTG AAGDRGEQGP PGVNGFQVNF FFFQGIPGEL GSVGQIGPRG
     ERGIPGERGE LGPTGLQGPK GIPGAPGPDG PKGSPGPPGA LGDVGPPGLQ GMPGERGISG
     PPGPKGDRGT PGPVGPLGPA GPSGEKGARG DPGPIGAVGF AGPPGPDGQP GVKGEPGEQG
     QKGDAGSPGP QGLAGAHGPP VSNKDGPTGF PGSAGRVGPP GPTGPVGEPG PLGPPGKEGP
     AGLRGDHGAP GRQGERGPAG PPGSPGDKGD SGEDGPTGPD GPPGPAGTTG QRGIVGLPGQ
     RGERGMPGLP GPAGPPGKQG STGPAGDKGP PGPVGVPGAN GPRGDPGPDG PAGSDGPPGK
     DGVLGQRGDR GDSGPEGLVG PQGLPGPPGP VGAPGDAGRR GESVSRISPS RSFCSGPQGP
     RGDKGDLGDH GERGQKGHRG FTGLQGLPGP PLTSLFWDVF QGPPGPIGPH GKEGYMGQPG
     PMGPPGTRGL SGEIGPEGPP GEPGPPGPPG PPGPPMAAMD DLFGGPQDYD SGPPPPPEFS
     EDEALPNSNS STIVPIDPGV QATLKALSSQ IDSMKSPDGS RKHPARTCDD LKRCYPMKKS
     GEYWVDPNQG SAEDAIKVHC NMDTGETCIS ANPSSIPRKV WWSSSRNKPV WFGADINGGT
     HFTYGNKDQP ANSVTVQMTF IRLLSKEASQ SITYHCKNSV GYKDENTGNY KKAVILKGSN
     DLELKAEGNN RFRYTVVEDS CSQANGNWGK TVFEYRTQKT ARLPIVDIAP VDIGGSDQEF
     GVEIGPVCFL
//