ID   A0A3B4BDA6_9GOBI        Unreviewed;      1182 AA.
AC   A0A3B4BDA6;
DT   05-DEC-2018, integrated into UniProtKB/TrEMBL.
DT   05-DEC-2018, sequence version 1.
DT   27-MAR-2024, entry version 28.
DE   RecName: Full=Collagen, type I, alpha 1b {ECO:0008006|Google:ProtNLM};
OS   Periophthalmus magnuspinnatus.
OC   Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
OC   Actinopterygii; Neopterygii; Teleostei; Neoteleostei; Acanthomorphata;
OC   Gobiaria; Gobiiformes; Gobioidei; Gobiidae; Oxudercinae; Periophthalmus.
OX   NCBI_TaxID=409849 {ECO:0000313|Ensembl:ENSPMGP00000026439.1, ECO:0000313|Proteomes:UP000261520};
RN   [1] {ECO:0000313|Ensembl:ENSPMGP00000026439.1}
RP   IDENTIFICATION.
RG   Ensembl;
RL   Submitted (SEP-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; A0A3B4BDA6; -.
DR   STRING; 409849.ENSPMGP00000026439; -.
DR   Ensembl; ENSPMGT00000028157.1; ENSPMGP00000026439.1; ENSPMGG00000021321.1.
DR   Proteomes; UP000261520; 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; 6.
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   Secreted {ECO:0000256|ARBA:ARBA00022530}; Signal {ECO:0000256|SAM:SignalP}.
FT   SIGNAL          1..22
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT   CHAIN           23..1182
FT                   /note="Collagen, type I, alpha 1b"
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT                   /id="PRO_5017359238"
FT   DOMAIN          31..89
FT                   /note="VWFC"
FT                   /evidence="ECO:0000259|PROSITE:PS50184"
FT   DOMAIN          948..1182
FT                   /note="Fibrillar collagen NC1"
FT                   /evidence="ECO:0000259|PROSITE:PS51461"
FT   REGION          110..136
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          173..948
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        817..831
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        895..914
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        929..948
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   1182 AA;  113960 MW;  FEF271A22A9A5669 CRC64;
     MFSFVDIRIA LLLSAAVLLA RGQGEDDSLA GSCTSDGQLY NDKDVWKPEP CQICVCDSGS
     VLCDDVICEE GYDCEDPIIP DGECCPICPD GTVPRSPLHL IPAQWRHLGP AGPPGNDGFD
     GQPGLPGPPG PPGPPGLGGV SVPFSLLYRH YVIITCGLWS VCVRKGILEF GSLKGARGFP
     GTPGLPGIKG HRGFSGLDGA KGDSGPAGPK GEPGTAGENG IPGAMGETGP QGSRGSEGPQ
     GARGEAGNPG PAGPAGAAGV TGSPGTPGPD GKVGPSGAPG QDGRPGPPGP SGARGQPGVM
     GFPGPKGTNG EPGKPGERGP AGASGAVGAP GKDGDTGAPG PSGPAGAAGE KGEAGPAGPP
     GFQGLPGPQG ATGETGKPGE QGVPGEVGPP GPSGPRGDRG FPGERGGNGP AGPTGPRGSP
     GPAGNDGAKG EPGAAGAPGA AGAPGMQGMP GERGAGGLPG AKGERGDGGP KGPDGAPGKD
     GARGMTGAIG VPGPPGAQGE KGEPGAVGVA GPTGPRGSPG ERGETGPAGP AGFAGPPGID
     GQPGAKGETG DTGPKGDAGA PGPGGPVGAA GPQGPAGPTG AKGARGGAGP PGATGFPGPA
     GRVGPPGPAG AAGPPGPVGG IGKDGPRGPR GETGPAGRPG EVGAAGAVGL AGEKGSPGSD
     GSPGAPGLPG PQGIAGQRGI VGLPGQRGER GFPGLPGPGG EPGKQGPAGL VGERGPPGPA
     GPPGLSGAPG EAGREGSQGH DGAPGRDGSP GPKGDRGESG MAGPPGAPGA PGAPGAVGPS
     GKSGDRGETG PAGVSGPAGP AGVRGPAGPA GAKGDRGEAG EAGERGHKGH RGFSGMQGLP
     GPGPSGERGP AGASGPAGPR GSAGSNGSPG KDGVNGMPGP LGPPGPRGRN GEMGPAGPPG
     PPGPPGPPGP PGGGFDFVSQ PLQEKGPDPL RGGHYRADDP KAIADRDTEV DTTLKTLTQK
     IEKIRSPDGS QKSPIRMCRD LRMTHPEWKS GSYWVDPNQG SPLDAIKVHC NMDTGATCIY
     PSQSSIPMKN WYISQNREKK HIWFSESMTG GFQFQYGSEG SDPEDVNIQM TFMRLMSNEA
     LQNITYHCKN SIAYTDAATG NRKKALLLQG SNDVEIRAEG NSRFTYSVSE DGCTSHTGTW
     GKTVMDYKTT KTSRLPIIDI APMDVGAPDQ EFGVEVGPVC FL
//