ID   A0A091R2S5_9GRUI        Unreviewed;      1337 AA.
AC   A0A091R2S5;
DT   26-NOV-2014, integrated into UniProtKB/TrEMBL.
DT   26-NOV-2014, sequence version 1.
DT   27-MAR-2024, entry version 29.
DE   RecName: Full=Fibrillar collagen NC1 domain-containing protein {ECO:0000259|PROSITE:PS51461};
DE   Flags: Fragment;
GN   ORFNames=N332_02412 {ECO:0000313|EMBL:KFQ34090.1};
OS   Mesitornis unicolor (brown roatelo).
OC   Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi;
OC   Archelosauria; Archosauria; Dinosauria; Saurischia; Theropoda;
OC   Coelurosauria; Aves; Neognathae; Gruiformes; Mesitornithidae; Mesitornis.
OX   NCBI_TaxID=54374 {ECO:0000313|EMBL:KFQ34090.1, ECO:0000313|Proteomes:UP000053369};
RN   [1] {ECO:0000313|EMBL:KFQ34090.1, ECO:0000313|Proteomes:UP000053369}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=BGI_N332 {ECO:0000313|EMBL:KFQ34090.1};
RA   Zhang G., Li C.;
RT   "Genome evolution of avian class.";
RL   Submitted (APR-2014) to the EMBL/GenBank/DDBJ databases.
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; KK808863; KFQ34090.1; -; Genomic_DNA.
DR   Proteomes; UP000053369; Unassembled WGS sequence.
DR   GO; GO:0005201; F:extracellular matrix structural constituent; IEA:InterPro.
DR   Gene3D; 2.60.120.1000; -; 1.
DR   InterPro; IPR008160; Collagen.
DR   InterPro; IPR000885; Fib_collagen_C.
DR   PANTHER; PTHR24023; COLLAGEN ALPHA; 1.
DR   PANTHER; PTHR24023:SF1108; ENDOSTATIN DOMAIN-CONTAINING PROTEIN; 1.
DR   Pfam; PF01410; COLFI; 1.
DR   Pfam; PF01391; Collagen; 7.
DR   SMART; SM00038; COLFI; 1.
DR   PROSITE; PS51461; NC1_FIB; 1.
PE   4: Predicted;
KW   Disulfide bond {ECO:0000256|ARBA:ARBA00023157};
KW   Extracellular matrix {ECO:0000256|ARBA:ARBA00022530};
KW   Reference proteome {ECO:0000313|Proteomes:UP000053369};
KW   Secreted {ECO:0000256|ARBA:ARBA00022530}.
FT   DOMAIN          1102..1337
FT                   /note="Fibrillar collagen NC1"
FT                   /evidence="ECO:0000259|PROSITE:PS51461"
FT   REGION          1..1084
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        18..44
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        68..90
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        100..114
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        773..787
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        1061..1077
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   NON_TER         1
FT                   /evidence="ECO:0000313|EMBL:KFQ34090.1"
FT   NON_TER         1337
FT                   /evidence="ECO:0000313|EMBL:KFQ34090.1"
SQ   SEQUENCE   1337 AA;  126129 MW;  610529FA7E8E9164 CRC64;
     SFIFFQQGPR GDKGPQGERG PPGPPGRDGE DGPPGPPGPP GPPGLGGNFA AQYDPSKAAD
     FGPGPMGLMG PRGPPGASGP PGPPGFQGVP GEPGEPGQTG PQGPRGPPGP PGKAGEDGHP
     GKPGRPGERG VAGPQGARGF PGTPGLPGFK GIRGHNGLDG QKGQPGTPGT KGEPGAPGEN
     GTPGQPGARG LPGERGRVGA PGPAGARGSD GSAGPTGPAG PIGAAGPPGF PGAPGAKGEI
     GPAGNVGPSG PAGPRGEIGL PGSSGPVGPP GNPGANGLPG AKGAAGLPGV AGAPGLPGPR
     GIPGPPGPAG PSGARGLVGE PGPAGAKGES GNKGEPGAAG PAGPPGPSGE EGKRGSTGEP
     GSAGPPGPAG LRGVPGSRGL PGADGRAGVM GPAGNRGASG PVGAKGPSGD GGRPGEPGLM
     GPRGLPGQPG SPGPAGKEGP VGFPGADGRV GPIGPAGNRG EPGNIGFPGP KGPTGEPGKP
     GEKGNVGVAG PRGAPGPEGN NGAQGPPGVT GNQGGKGETG PAGPPGFQGL PGPSGPAGEA
     GKPGERGLHG EFGVPGPAGP RGERGLPGES GAVGPAGPIG SRGPSGPPGP DGNKGEPGNV
     GAAGGPGPAG PGGIPGERGV AGVPGGKGEK GAPGLRGDTG ATGRDGARGL PGAIGAPGPA
     GGTGDRGEGG PAGPAGPAGA RGIPGERGEP GPVGPSGFAG PPGAAGQPGA KGERGPKGPK
     GESGPTGAIG PIGASGPPGP AGAAGPAGPR GDAGPPGMTG FPGAAGRVGP PGPAGISGPP
     GPPGPAGKDG PRGLRGDVGP VGRTGEQGIA GPPGFAGEKG PSGEAGAAGP PGTPGPQGIL
     GAPGILGLPG SRGERGLPGI SGATGEPGPL GVSGPPGARG PSGPVGSPGP NGAPGEAGRD
     GNPGNDGPPG RDGAPGFKGE RGAPGNPGPS GALGAPGPHG QVGPSGKPGN RGDPGPAGVV
     GPAGAFGPRG LAGPQGPRGE KGEPGDKGPR GLPGLKGHNG LQGLPGLAGQ HGDQGPPGNT
     GPAGPRGQPG PSGPPGKDGR NGLPGPIGPA GVRGSHGSQG PAGPPGPPGP PGPPGPNGGG
     YEVGFDAEYF RADQPSLRPK DYEVDATLKT LNNQIETLLT PEGSRKNPAR TCRDLRLSHP
     EWSSGFYWID PNQGCSADAI RAYCNFATGE TCIHANPDHI PAKNWYVNKN PKDKKHVWFG
     ETINGGSQFE YNSEGVTTKD MATQLAFMRL LANHASQNIT YHCKNSIAYM DEETGNLKKA
     VILQGSNDVE LRAEGNSRFT YSVLVDGCSR KNNEWGKTII EYRTNKPSRL PILDIAPLDI
     GSPDQEVSLD IGPVCYK
//