ID   A9UW31_MONBE            Unreviewed;       890 AA.
AC   A9UW31;
DT   05-FEB-2008, integrated into UniProtKB/TrEMBL.
DT   05-FEB-2008, sequence version 1.
DT   24-JAN-2024, entry version 58.
DE   RecName: Full=Fibrillar collagen NC1 domain-containing protein {ECO:0000259|PROSITE:PS51461};
GN   ORFNames=MONBRDRAFT_31892 {ECO:0000313|EMBL:EDQ90696.1};
OS   Monosiga brevicollis (Choanoflagellate).
OC   Eukaryota; Choanoflagellata; Craspedida; Salpingoecidae; Monosiga.
OX   NCBI_TaxID=81824 {ECO:0000313|EMBL:EDQ90696.1, ECO:0000313|Proteomes:UP000001357};
RN   [1] {ECO:0000313|EMBL:EDQ90696.1, ECO:0000313|Proteomes:UP000001357}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=MX1 / ATCC 50154 {ECO:0000313|Proteomes:UP000001357};
RX   PubMed=18273011; DOI=10.1038/nature06617;
RG   JGI Sequencing;
RA   King N., Westbrook M.J., Young S.L., Kuo A., Abedin M., Chapman J.,
RA   Fairclough S., Hellsten U., Isogai Y., Letunic I., Marr M., Pincus D.,
RA   Putnam N., Rokas A., Wright K.J., Zuzow R., Dirks W., Good M.,
RA   Goodstein D., Lemons D., Li W., Lyons J.B., Morris A., Nichols S.,
RA   Richter D.J., Salamov A., Bork P., Lim W.A., Manning G., Miller W.T.,
RA   McGinnis W., Shapiro H., Tjian R., Grigoriev I.V., Rokhsar D.;
RT   "The genome of the choanoflagellate Monosiga brevicollis and the origin of
RT   metazoans.";
RL   Nature 451:783-788(2008).
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; CH991547; EDQ90696.1; -; Genomic_DNA.
DR   RefSeq; XP_001744747.1; XM_001744695.1.
DR   AlphaFoldDB; A9UW31; -.
DR   STRING; 81824.A9UW31; -.
DR   EnsemblProtists; EDQ90696; EDQ90696; MONBRDRAFT_31892.
DR   GeneID; 5889859; -.
DR   KEGG; mbr:MONBRDRAFT_31892; -.
DR   eggNOG; KOG3544; Eukaryota.
DR   eggNOG; KOG4509; Eukaryota.
DR   InParanoid; A9UW31; -.
DR   OMA; TEMHARN; -.
DR   Proteomes; UP000001357; Unassembled WGS sequence.
DR   GO; GO:0005201; F:extracellular matrix structural constituent; IEA:InterPro.
DR   Gene3D; 2.60.120.1000; -; 2.
DR   Gene3D; 3.30.870.30; MITD, C-terminal phospholipase D-like domain; 1.
DR   Gene3D; 1.20.58.80; Phosphotransferase system, lactose/cellobiose-type IIA subunit; 1.
DR   InterPro; IPR000885; Fib_collagen_C.
DR   InterPro; IPR036056; Fibrinogen-like_C.
DR   InterPro; IPR007330; MIT_dom.
DR   InterPro; IPR036181; MIT_dom_sf.
DR   InterPro; IPR032341; MITD1_C.
DR   InterPro; IPR038113; MITD1_C_sf.
DR   PANTHER; PTHR21222:SF1; MIT DOMAIN-CONTAINING PROTEIN 1; 1.
DR   PANTHER; PTHR21222; UNCHARACTERIZED; 1.
DR   Pfam; PF01410; COLFI; 2.
DR   Pfam; PF04212; MIT; 1.
DR   Pfam; PF16565; MIT_C; 1.
DR   SMART; SM00038; COLFI; 1.
DR   SUPFAM; SSF56496; Fibrinogen C-terminal domain-like; 1.
DR   SUPFAM; SSF116846; MIT domain; 1.
DR   PROSITE; PS51461; NC1_FIB; 2.
PE   4: Predicted;
KW   Reference proteome {ECO:0000313|Proteomes:UP000001357};
KW   Signal {ECO:0000256|SAM:SignalP}.
FT   SIGNAL          1..24
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT   CHAIN           25..890
FT                   /note="Fibrillar collagen NC1 domain-containing protein"
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT                   /id="PRO_5002742420"
FT   DOMAIN          211..432
FT                   /note="Fibrillar collagen NC1"
FT                   /evidence="ECO:0000259|PROSITE:PS51461"
FT   DOMAIN          434..657
FT                   /note="Fibrillar collagen NC1"
FT                   /evidence="ECO:0000259|PROSITE:PS51461"
SQ   SEQUENCE   890 AA;  98984 MW;  47FF40D1D885625B CRC64;
     MALPWLRRGA VLLLLLTTVW SGLGAEPSME VTEGTIVMEA TDVEFVVLDG NYRTSVVQMR
     NALQANISSL AGTIADTNQQ LNISLQATIR ELDELFTNSL NVTADTISTN LLQEIDEAIT
     HSQLVLSQLN ELRAQTQSNI SALAEAAATA RSVLRTETQA NFSALAETEM HARNQLREEA
     HANLTALQSS NQEVTDQLEA DLTVVTETTL PALSARVDEV AHNLSTILVR DGSSRGAAAA
     SCQAIFNVNL GLTNGTYWLD PNGQSTHDAV QLKCERVDNT VYTVLPAPPA LPMGGHFSAD
     ASADRWESVR SINDTVFQYG DIPDDQLRAL LARSSSGRQS IQLDCRGVIS SLWDDVDWYY
     EYPVVLVGLS GEVWTFPTAD DLGFQGRVFR PNIVFDNCSQ NHVDELGLSI YDMEGPATAL
     PIVDMWLSDI GNANESFGFS LSEVRLSEAF QGPVVAYGTR MRPGKSCLDI FMHGYGSNDT
     YYYIDPNGGL RNDSVRVFCN MTGGGWTGIA PLEQVPFKAW NPSGTDGYRF FSLHTGGYEI
     TYDMADHQLD LLLASSSEAF QVLTVACQDA LVYYYDSSNL YSYAFRYKGY NDVLWTYESD
     GLNVPVDNCK ANDATTRSTV VEFTGTPGDL PIRDFAPRDM GGATEFIGVH FSFVWAVKFD
     KEARYDLALN NYRVALELLV PCIAPQSTLP VDMRGNLQQR IRDYMSRAEI VKEAARKERL
     CADQAAKAHS AEVLHIKQND VGYDYQTLFG KYFTGAQVVT VEDPYLYRPH QIINLVHFFE
     AALAGIGRDN FKMAVVRTKH QQDGVNQAEV FAGLESNLQE YGVRLVVEYE DFHDRCVRFD
     NGYIIGLGAG LDIYLRPERQ FQLGMHDYRL RKCRETRIVA SYNSREDRRT
//