ID   A0A167P2N2_CALVF        Unreviewed;       801 AA.
AC   A0A167P2N2;
DT   06-JUL-2016, integrated into UniProtKB/TrEMBL.
DT   06-JUL-2016, sequence version 1.
DT   22-FEB-2023, entry version 22.
DE   RecName: Full=MSP domain-containing protein {ECO:0000259|PROSITE:PS50202};
GN   ORFNames=CALVIDRAFT_535431 {ECO:0000313|EMBL:KZO98355.1};
OS   Calocera viscosa (strain TUFC12733).
OC   Eukaryota; Fungi; Dikarya; Basidiomycota; Agaricomycotina; Dacrymycetes;
OC   Dacrymycetales; Dacrymycetaceae; Calocera.
OX   NCBI_TaxID=1330018 {ECO:0000313|EMBL:KZO98355.1, ECO:0000313|Proteomes:UP000076738};
RN   [1] {ECO:0000313|EMBL:KZO98355.1, ECO:0000313|Proteomes:UP000076738}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=TUFC12733 {ECO:0000313|EMBL:KZO98355.1,
RC   ECO:0000313|Proteomes:UP000076738};
RX   PubMed=26659563; DOI=10.1093/molbev/msv337;
RA   Nagy L.G., Riley R., Tritt A., Adam C., Daum C., Floudas D., Sun H.,
RA   Yadav J.S., Pangilinan J., Larsson K.H., Matsuura K., Barry K., Labutti K.,
RA   Kuo R., Ohm R.A., Bhattacharya S.S., Shirouzu T., Yoshinaga Y.,
RA   Martin F.M., Grigoriev I.V., Hibbett D.S.;
RT   "Comparative Genomics of Early-Diverging Mushroom-Forming Fungi Provides
RT   Insights into the Origins of Lignocellulose Decay Capabilities.";
RL   Mol. Biol. Evol. 33:959-970(2016).
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; KV417276; KZO98355.1; -; Genomic_DNA.
DR   AlphaFoldDB; A0A167P2N2; -.
DR   STRING; 1330018.A0A167P2N2; -.
DR   OrthoDB; 1343558at2759; -.
DR   Proteomes; UP000076738; Unassembled WGS sequence.
DR   Gene3D; 2.60.40.10; Immunoglobulins; 1.
DR   InterPro; IPR013783; Ig-like_fold.
DR   InterPro; IPR000535; MSP_dom.
DR   InterPro; IPR008962; PapD-like_sf.
DR   Pfam; PF00635; Motile_Sperm; 1.
DR   SUPFAM; SSF49354; PapD-like; 1.
DR   PROSITE; PS50202; MSP; 1.
PE   4: Predicted;
KW   Reference proteome {ECO:0000313|Proteomes:UP000076738}.
FT   DOMAIN          467..594
FT                   /note="MSP"
FT                   /evidence="ECO:0000259|PROSITE:PS50202"
FT   REGION          1..479
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          598..681
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        61..87
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        94..127
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        168..198
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        199..226
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        234..263
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        264..286
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        331..360
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        391..410
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        429..443
FT                   /note="Acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        598..654
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   801 AA;  87003 MW;  6BB826DD4BB9E071 CRC64;
     MLGSQQGQQR PPDQPGASAA AGAAAGGYPY SGYSQKLAKE QAYAQLHPGN VEEHHPPPSY
     HMATSPSTSP LSAAAQPQQQ QQQQKRTQQL RHKGRDRQVR DDTSSDQESF WEHAEREALR
     LEHGTPKPDS DSQYYASPGP LAPNRASYQD PQAYGPYATQ SPPPHDAHYG SPSAPPPPSA
     YRAPPPGSRE PQRPLPSPPQ SATSHGSHGS YPPSPSPQSQ GRPMSAPARS PPSRSPEQAR
     PPPQAPSPTR VQQPHSPAPA RPSHPPHLEH HSHEHEHEHE HPAAPTGPRH LMHAVPSAPH
     LTPEVLERDL PSLPHDSPSQ FSGSLPLHGE EPYPRGEERY EPLQDEMRLT RGDHGRESSG
     ETVKPGPGPG YDGEAYPSEL TPLLPGGLRM LRAERDAREE RPRAEFGRSE EEEEVAEEEG
     RAGRAQEEEQ DGDDDDDRDE EDEPGMHDLP GERRPLQPPP RIGTPEPLTI SPDTPDAPIL
     LPNGNTKLLF RVVNPNRAPV AFKVMTTQPR VYSVRPNFGL IPPSGTLDLE VHAPADVASR
     RRPAPGRGDR FAVLSRFLAQ EEEEELEEHE DFAALFPSKT TSAEGMRSQR FRIRPLMVPQ
     NQNQGQGQNQ GGQGMGSGMS ATTAGSLMSA FSPSQRPRAL SSSGSTTALS PTYTAAPLPS
     ILGPATTTPA APPGRPKSPS AIRFAPAVGA MASLAGVAGQ FAEAREAERR DEVLRESIGA
     VREGVGELKD RLDEVIRRMQ LEEEAKERAL APDQMPAEME YSYPEYHTPG KKRAGLHPGR
     VLGLALAVFV ATYYGRVFHV I
//