ID   A0A3Q1ERK6_9TELE        Unreviewed;      1335 AA.
AC   A0A3Q1ERK6;
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 alpha-1(I) chain-like {ECO:0000313|Ensembl:ENSAPOP00000006217.1};
OS   Acanthochromis polyacanthus (spiny chromis).
OC   Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
OC   Actinopterygii; Neopterygii; Teleostei; Neoteleostei; Acanthomorphata;
OC   Ovalentaria; Pomacentridae; Acanthochromis.
OX   NCBI_TaxID=80966 {ECO:0000313|Ensembl:ENSAPOP00000006217.1, ECO:0000313|Proteomes:UP000257200};
RN   [1] {ECO:0000313|Ensembl:ENSAPOP00000006217.1}
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   STRING; 80966.ENSAPOP00000006217; -.
DR   Ensembl; ENSAPOT00000007036.1; ENSAPOP00000006217.1; ENSAPOG00000008178.1.
DR   GeneTree; ENSGT00940000156584; -.
DR   InParanoid; A0A3Q1ERK6; -.
DR   Proteomes; UP000257200; 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; COLLAGEN ALPHA; 1.
DR   PANTHER; PTHR24023:SF1108; ENDOSTATIN DOMAIN-CONTAINING PROTEIN; 1.
DR   Pfam; PF01410; COLFI; 1.
DR   Pfam; PF01391; Collagen; 5.
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   Disulfide bond {ECO:0000256|ARBA:ARBA00023157};
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:UP000257200};
KW   Secreted {ECO:0000256|ARBA:ARBA00022530}; Signal {ECO:0000256|SAM:SignalP}.
FT   SIGNAL          1..22
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT   CHAIN           23..1335
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT                   /id="PRO_5018690689"
FT   DOMAIN          30..88
FT                   /note="VWFC"
FT                   /evidence="ECO:0000259|PROSITE:PS50184"
FT   DOMAIN          1105..1335
FT                   /note="Fibrillar collagen NC1"
FT                   /evidence="ECO:0000259|PROSITE:PS51461"
FT   REGION          94..1105
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        99..135
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        775..795
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        974..988
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        1053..1069
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   1335 AA;  126092 MW;  C91131CB6BB3184C CRC64;
     MFSFVDIRLA LLLSATVLLA RAQGEDDTFG SCTLDGQLYN DKDVWKPEPC QICVCDSGSV
     MCDEVICEDT TDCDDPIIPD GECCPICPDT DGPVGPPGND GIPGQPGLPG PPGPPGPPGL
     GGVGPMGPRG PPGPSGSSGP QGFTGPAGEP GEPGASGPMG SRGPAGPPGK NGDDGEPGKP
     GRPGERGAAG PQGARGFPGT PGLPGIKGHR GFSGLDGAKG DSGPSGPKGE AGAPGENGVP
     GAMGARGLPG ERGRPGPPGP AGARGNDGNT GAAGPPGATG PAGAPGFPGG AGAKGETGPQ
     GGRGNEGPQG ARGEPGNPGP SGPAGPAGAP GSDGSPGAKG SPGAAGIAGA PGFPGARGPA
     GAQGAVGTPG PKGNTQGDHG PSGPKGEPGA KGEPGPAGVQ GLPGPSGEEG KRGPRGEPGG
     AGPRGPPGER QGAPGERGAP GAMGAQGATG ESGSPGAPGA PGSKGVTGSP GSPGPDGKVG
     PAGAPGQDGR TGPAGPAGSR GQPGVMGFPG PKGAAGAPGK DGDVGAPGPS GAAGPAGEKG
     EQGPAGPPGF QQGLPGPQGA TGETGKPGEQ GERGFPGERG GPGPAGPAGA RGAPGPAGND
     GAKGEPGVGG APGGVGSPGM QGMPGERGAS GLPGVKGERG DGGGKGADGA PGKDGVRGLT
     GAIGVPGPPG AQGEKGEPGA MGVAGPSGPR GSPGERGETG PSGPAGFAGP PGADGQPGAK
     GETGDTGPKG DAGAPGPGGP VGAAGPQGPA GPPGAKGARG GAGSPGATGF PGPAGRVGPP
     GPAGAGGPPG PPGPVGKDGA RGARGETGAA GRPGEAGAAG VTGPGGEKGS PGADGAPGSP
     GLPGPQGIAG QRGVVGLPGQ RGERGFTGLP GPGGEPGKQG PSGPVGERGA PGPAGPPGLS
     GATGEAGREG SAGHDGAPGR DGAPGPKGDR GESGMPGPPG PPGTPGAPGT VGPSGKSGDR
     GEGQGPAGAK GDRGEAGEAG DRGHKGHRGF SGMQGLPGPA GAPGERGPAG ASGPAGPRGP
     SGSSGTVGKD GMNGMPGPIG PPGPRGRNGE MGPAGPPGPP GPPGPPGAPG GGFDFISQPL
     QEKAPDPLRG GYRADDPNVQ RDRDNEVDTT LKTLTQKVEK IRSPDGTQKS PARMCRDLRM
     CHPEWKSWVD PNQGSALDAI KVHCNMETGE TCVPPTRSNI PMKNWYQSKN SKKHVWFSES
     MTGGFQFQYG TDGADSEDVN IQMTFMRLMS NQASQNVTYH CKNSIAYMDS TTGNLKKALL
     LQGSNDVEIR AEGNSRFTYS VSEDGCTSHT GAWGKTVIDY KTTKTSRLPI IDIAPMDVGA
     PDQEFGVEVG PVCFL
//