ID   A7TMA5_VANPO            Unreviewed;       954 AA.
AC   A7TMA5;
DT   02-OCT-2007, integrated into UniProtKB/TrEMBL.
DT   02-OCT-2007, sequence version 1.
DT   27-MAR-2024, entry version 49.
DE   RecName: Full=Arrestin C-terminal-like domain-containing protein {ECO:0000259|SMART:SM01017};
GN   ORFNames=Kpol_520p20 {ECO:0000313|EMBL:EDO16599.1};
OS   Vanderwaltozyma polyspora (strain ATCC 22028 / DSM 70294 / BCRC 21397 / CBS
OS   2163 / NBRC 10782 / NRRL Y-8283 / UCD 57-17) (Kluyveromyces polysporus).
OC   Eukaryota; Fungi; Dikarya; Ascomycota; Saccharomycotina; Saccharomycetes;
OC   Saccharomycetales; Saccharomycetaceae; Vanderwaltozyma.
OX   NCBI_TaxID=436907 {ECO:0000313|Proteomes:UP000000267};
RN   [1] {ECO:0000313|EMBL:EDO16599.1, ECO:0000313|Proteomes:UP000000267}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=ATCC 22028 / DSM 70294 / BCRC 21397 / CBS 2163 / NBRC 10782 /
RC   NRRL Y-8283 / UCD 57-17 {ECO:0000313|Proteomes:UP000000267};
RX   PubMed=17494770; DOI=10.1073/pnas.0608218104;
RA   Scannell D.R., Frank A.C., Conant G.C., Byrne K.P., Woolfit M., Wolfe K.H.;
RT   "Independent sorting-out of thousands of duplicated gene pairs in two yeast
RT   species descended from a whole-genome duplication.";
RL   Proc. Natl. Acad. Sci. U.S.A. 104:8397-8402(2007).
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; DS480421; EDO16599.1; -; Genomic_DNA.
DR   RefSeq; XP_001644457.1; XM_001644407.1.
DR   AlphaFoldDB; A7TMA5; -.
DR   STRING; 436907.A7TMA5; -.
DR   GeneID; 5544760; -.
DR   KEGG; vpo:Kpol_520p20; -.
DR   eggNOG; KOG3780; Eukaryota.
DR   HOGENOM; CLU_006239_0_0_1; -.
DR   InParanoid; A7TMA5; -.
DR   OMA; NMELPTY; -.
DR   OrthoDB; 2056731at2759; -.
DR   PhylomeDB; A7TMA5; -.
DR   Proteomes; UP000000267; Unassembled WGS sequence.
DR   Gene3D; 2.60.40.640; -; 1.
DR   InterPro; IPR014752; Arrestin-like_C.
DR   InterPro; IPR011022; Arrestin_C-like.
DR   PANTHER; PTHR11188; ARRESTIN DOMAIN CONTAINING PROTEIN; 1.
DR   PANTHER; PTHR11188:SF168; TRANSCRIPTION FACTOR CSR2; 1.
DR   SMART; SM01017; Arrestin_C; 1.
PE   4: Predicted;
KW   Reference proteome {ECO:0000313|Proteomes:UP000000267}.
FT   DOMAIN          520..812
FT                   /note="Arrestin C-terminal-like"
FT                   /evidence="ECO:0000259|SMART:SM01017"
FT   REGION          24..102
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          200..261
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          429..462
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          886..908
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        35..71
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        86..102
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        429..445
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   954 AA;  106498 MW;  FCD978CC376C2A33 CRC64;
     MSANHPDLPH RKPSVIRHAI SSILGTGSPV EPQPFNRPRR NTTFHSSTGH SNSISPRGIH
     GSNNHSSHNL LQPIIDDRGK NRRHSTNSIS HPNPIHNNKR DSVISSSSDA ITFNDSASSS
     PTIPGSEISF GKEFLTEYLL ERGFLPQKVV IDKQNVQISV ATSGNCVFLP TMSSTDDEYL
     SRLNGLVGDD LDFQTEVGSI SQSTNTDNAN NMQRANTQSS SITNNSQFST SNNNLTTPSA
     RSSRSSNARQ MNQSRTTPSL EVDDSMTNYT VAVILSLKKK LKLSEIKVNL CSRIRIYWHD
     GVPPTKTFKE EVYHAGSSSW SLTSDNFNLF VPSNVSKSEK IVENKSELRP TVLFKNLDDQ
     NKNYIDKQKT KQNMLKSLNT KSPQYLAPGD YVFILPIIFT NHIPESLYLP SARVGYRLCV
     AMKTLDNPLS TGASDMPSQD KNSTSHSKIN ESDHGSNHAS KGNSIFNKVK KQLHIQSHSQ
     KSDSDNSNGI YTEYPINIVR APPPISLSTA NKSIYINRVW SNALSYEISF GQKFVPLSGK
     FPIKIKLAPL IKNISVKRIR VSIVEKITFV SKNLEYEYDQ IDILAKDPYN PYYSEFESRR
     KKDRNLALLE IRTKEKGSRA IREEIIDNCI NENLLSYSTI KKESKDKKHE EIVGFNDSIT
     ILSNLEFPKY ADLDQKTAKT IPPYGIDLFN MEAVPEVSRK DSQSHKGSIV GFLAGRRSSF
     NAKQPDSPSI KDPRYHETKF TSSSEIPVKY HTKLNKAKRG LYLDSLNFPN IHSRHKLEIM
     FRICRPDAND PERFRNYEVL IDIPIFLVSE LCNSGNLELP TYAVATSEPL LPQEMVLTSP
     PTFEEAISVP ASPVASPILS PLGSPNMGPD FYGDNLNIQQ LTLSRQSSIS GPSGSMPHSE
     SRGHISSVQN TTMNRTESGN RYNNLDDVLT GSTALSHSFG EVERTTSRKT CEEP
//