ID   A0A1Y2E988_9FUNG        Unreviewed;       720 AA.
AC   A0A1Y2E988;
DT   30-AUG-2017, integrated into UniProtKB/TrEMBL.
DT   30-AUG-2017, sequence version 1.
DT   13-SEP-2023, entry version 16.
DE   RecName: Full=Carbohydrate-binding domain-containing protein {ECO:0008006|Google:ProtNLM};
GN   ORFNames=LY90DRAFT_639742 {ECO:0000313|EMBL:ORY68138.1};
OS   Neocallimastix californiae.
OC   Eukaryota; Fungi; Fungi incertae sedis; Chytridiomycota;
OC   Chytridiomycota incertae sedis; Neocallimastigomycetes; Neocallimastigales;
OC   Neocallimastigaceae; Neocallimastix.
OX   NCBI_TaxID=1754190 {ECO:0000313|EMBL:ORY68138.1, ECO:0000313|Proteomes:UP000193920};
RN   [1] {ECO:0000313|EMBL:ORY68138.1, ECO:0000313|Proteomes:UP000193920}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=G1 {ECO:0000313|EMBL:ORY68138.1,
RC   ECO:0000313|Proteomes:UP000193920};
RG   DOE Joint Genome Institute;
RA   Haitjema C.H., Gilmore S.P., Henske J.K., Solomon K.V., De Groot R.,
RA   Kuo A., Mondo S.J., Salamov A.A., Labutti K., Zhao Z., Chiniquy J.,
RA   Barry K., Brewer H.M., Purvine S.O., Wright A.T., Boxma B., Van Alen T.,
RA   Hackstein J.H., Baker S.E., Grigoriev I.V., O'Malley M.A.;
RT   "A Parts List for Fungal Cellulosomes Revealed by Comparative Genomics.";
RL   Submitted (AUG-2016) to the EMBL/GenBank/DDBJ databases.
CC   -!- CAUTION: The sequence shown here is derived from an EMBL/GenBank/DDBJ
CC       whole genome shotgun (WGS) entry which is preliminary data.
CC       {ECO:0000313|EMBL:ORY68138.1}.
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; MCOG01000046; ORY68138.1; -; Genomic_DNA.
DR   AlphaFoldDB; A0A1Y2E988; -.
DR   STRING; 1754190.A0A1Y2E988; -.
DR   Proteomes; UP000193920; Unassembled WGS sequence.
DR   InterPro; IPR025584; Cthe_2159.
DR   Pfam; PF14262; Cthe_2159; 1.
PE   4: Predicted;
KW   Reference proteome {ECO:0000313|Proteomes:UP000193920};
KW   Signal {ECO:0000256|SAM:SignalP}.
FT   SIGNAL          1..21
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT   CHAIN           22..720
FT                   /note="Carbohydrate-binding domain-containing protein"
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT                   /id="PRO_5012914811"
FT   REGION          451..476
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          505..538
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          700..720
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        505..534
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   720 AA;  77044 MW;  DABC14F77AB66BBB CRC64;
     MKINNFIILL IIFAISGLVK ADDEEETTSL DITGDEEELE LIPGPVTCEY KKKDLNESYD
     VDSDISINCN GDSSTCISNH DGVTISEGVV EITTAGTYIV GGNLEGQLRI AATKDDFIHL
     VLNNANITSF DGPAIFGSKA DKVTITLVGE NLLNDPANYT LVDEDDEPDA CLFIDSDLAI
     NGSGNLTVIG NYKDAIRCKK DLRIVNGTIN VQSAVDKGIK VKNSLCIKDG NINVNSTDTG
     IKVTRDDDAE KGYIVIDGGN VVVSSGNDGI HAETHLTIND GFIDIQKSGE GLEGQMIDIL
     GGEIHIISSD DGINASKVGS SNEDDMGPMG GPMDDMQGMN SMNRTESMGP GGMSPPNGMP
     GGMPGGKSSE VDSSVYINIV GGKLYITSKG NDVDGIDSNG VLYIGGDAEV YVNVEGGNIY
     GNMAALDAEG TNAIVPGSTV FATGGGKNSM GGKNNIGGRN NMGSNKNNGM NGNDNFNNRP
     RFNETENNMN DFFDENRIDK DFIDENTTDS IDNEDSKDNE NKKDTSEEQN NIENKSENEM
     IISNAVNEEN TKKIEKEIVK KPKKIIIKKC KPKNISKVKP QAPPQQFESM DSNKNMNFTM
     PDNINGHNGN MNFTMHDNMN GGMGGGMGSE SGIVLQPYIQ TSIDTQEAGT EISIIDNEND
     KTIISYTPEI SYASILVSTP KLVEGKEYTI IAGDFTQTIT ASSPSSSEEI EPPSVTSHSN
//