ID   A0A058ZAN4_FONAL        Unreviewed;      1172 AA.
AC   A0A058ZAN4;
DT   09-JUL-2014, integrated into UniProtKB/TrEMBL.
DT   09-JUL-2014, sequence version 1.
DT   27-MAR-2024, entry version 38.
DE   RecName: Full=XPG N-terminal domain-containing protein {ECO:0008006|Google:ProtNLM};
GN   ORFNames=H696_01947 {ECO:0000313|EMBL:KCV71001.1};
OS   Fonticula alba (Slime mold).
OC   Eukaryota; Rotosphaerida; Fonticulaceae; Fonticula.
OX   NCBI_TaxID=691883 {ECO:0000313|EMBL:KCV71001.1};
RN   [1] {ECO:0000313|EMBL:KCV71001.1}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=ATCC 38817 {ECO:0000313|EMBL:KCV71001.1};
RG   The Broad Institute Genomics Platform;
RA   Russ C., Cuomo C., Burger G., Gray M.W., Holland P.W.H., King N.,
RA   Lang F.B.F., Roger A.J., Ruiz-Trillo I., Brown M., Walker B., Young S.,
RA   Zeng Q., Gargeya S., Fitzgerald M., Haas B., Abouelleil A., Allen A.W.,
RA   Alvarado L., Arachchi H.M., Berlin A.M., Chapman S.B., Gainer-Dewar J.,
RA   Goldberg J., Griggs A., Gujja S., Hansen M., Howarth C., Imamovic A.,
RA   Ireland A., Larimer J., McCowan C., Murphy C., Pearson M., Poon T.W.,
RA   Priest M., Roberts A., Saif S., Shea T., Sisk P., Sykes S., Wortman J.,
RA   Nusbaum C., Birren B.;
RT   "The Genome Sequence of Fonticula alba ATCC 38817.";
RL   Submitted (APR-2013) to the EMBL/GenBank/DDBJ databases.
CC   -!- COFACTOR:
CC       Name=Mg(2+); Xref=ChEBI:CHEBI:18420;
CC         Evidence={ECO:0000256|ARBA:ARBA00001946};
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; KB932203; KCV71001.1; -; Genomic_DNA.
DR   RefSeq; XP_009494124.1; XM_009495849.1.
DR   AlphaFoldDB; A0A058ZAN4; -.
DR   STRING; 691883.A0A058ZAN4; -.
DR   EnsemblProtists; KCV71001; KCV71001; H696_01947.
DR   GeneID; 20526672; -.
DR   eggNOG; KOG2520; Eukaryota.
DR   OrthoDB; 26655at2759; -.
DR   Proteomes; UP000030693; Unassembled WGS sequence.
DR   GO; GO:0003677; F:DNA binding; IEA:InterPro.
DR   GO; GO:0004520; F:DNA endonuclease activity; IEA:UniProt.
DR   GO; GO:0046872; F:metal ion binding; IEA:UniProtKB-KW.
DR   Gene3D; 1.10.150.20; 5' to 3' exonuclease, C-terminal subdomain; 1.
DR   Gene3D; 3.40.50.1010; 5'-nuclease; 2.
DR   InterPro; IPR036279; 5-3_exonuclease_C_sf.
DR   InterPro; IPR008918; HhH2.
DR   InterPro; IPR029060; PIN-like_dom_sf.
DR   InterPro; IPR006086; XPG-I_dom.
DR   InterPro; IPR006084; XPG/Rad2.
DR   InterPro; IPR006085; XPG_DNA_repair_N.
DR   PANTHER; PTHR11081:SF54; FI23547P1; 1.
DR   PANTHER; PTHR11081; FLAP ENDONUCLEASE FAMILY MEMBER; 1.
DR   Pfam; PF00867; XPG_I; 1.
DR   Pfam; PF00752; XPG_N; 1.
DR   PRINTS; PR00853; XPGRADSUPER.
DR   SMART; SM00279; HhH2; 1.
DR   SMART; SM00484; XPGI; 1.
DR   SMART; SM00485; XPGN; 1.
DR   SUPFAM; SSF47807; 5' to 3' exonuclease, C-terminal subdomain; 1.
DR   SUPFAM; SSF88723; PIN domain-like; 1.
PE   4: Predicted;
KW   Hydrolase {ECO:0000256|ARBA:ARBA00022801};
KW   Magnesium {ECO:0000256|ARBA:ARBA00022842};
KW   Metal-binding {ECO:0000256|ARBA:ARBA00022723};
KW   Nuclease {ECO:0000256|ARBA:ARBA00022722};
KW   Reference proteome {ECO:0000313|Proteomes:UP000030693}.
FT   DOMAIN          1..113
FT                   /note="XPG N-terminal"
FT                   /evidence="ECO:0000259|SMART:SM00485"
FT   DOMAIN          847..924
FT                   /note="XPG-I"
FT                   /evidence="ECO:0000259|SMART:SM00484"
FT   REGION          385..546
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          559..579
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          671..747
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          802..827
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          1120..1153
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        495..523
FT                   /note="Acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   1172 AA;  120653 MW;  4DA03C2FD056B723 CRC64;
     MGVQQLWSLV DPAGRPVDFR RDLEGKRVAV DGSGWLHALA AGFRHQAERD ALGPGVDSDQ
     ARRRFLLLHM VRRVLALYTL GVTHVVVVFD HPRGGPPLKE KVLAARRAQR ALALSRAHQN
     ALRLALAGRL ADLAAGTADY SVPASLGPGP AGPAGPAVAR QAVADPAAEQ AAALMAALRQ
     TGGQMSDEEL QAALRPLSVA GRQMVLAGMA GTGFTSAGDA QAPAVSPHDE DAEEDVWAGF
     GRRATALLDA TFGREPLPGG QPTQDPLAEF SRSQVRSAVL RARVKHSLRQ LDEEEMPDDG
     SAIKRIRYLP LKEEEAQAAA ALSAEPALDL DPAALSSCLP LPDGLLAAEE TPGPAPGQGL
     LVAGESPFLS RTSFLSGTIR RAGARDLASR PTAHPSSELA KEEHPVSVAG AGAPRPPPAP
     PVKEEPACSL DEHSSQARGA VSAVGPSSSG LAGGPAQGHG APQVGAPAKV AEGLEAGQEA
     AASDSRGDCL RGDDLEDNGL EDDDLEDNGL EDDDLEDDDF EDIPVSSPAA APPPDSPQPH
     EPADILAYLA SVVGEVTGSM GDAPAAGSPS PPAPATGEAE LPTMLTDEPV TVHAAEPMAV
     GVGEPTPVHV DGPATMHDGE LATVHAAVPM PEPATLHGAV SAPLSEPTGT AAGAAATAAV
     EADIATGDAI GSVAGSAPSS RGDTDEGEAA PGPGATSTGL TASRPYFEPE VDVGLPSSPA
     SDMEEPAFAF SSDSESDGED VSAGAASVRL DPGRLAAAIS SLDRQLRRDA AHAVSPFRPD
     AGGAALSQHA EQVAEQVASL LPSARGSEPP APAPSSDGPG LLPEADHPAA MAFTSPDLMD
     ELAVALLAVG AGWLTARTRP GGLVEDAEAR CGLLSQRGQV DVVLSDDNDA LLFGSRTVVR
     GLFGSRPGAL RLYSLAALRG NLGLSRSRLI QLAHLLGSDF SEGLFGVGPV LACEILAAFA
     DDHDEAKPDV LLQRFAAWWR GYPNMTPAAR SGLSPATRAL ARALGALRSP PTAAGAPAEG
     SPPAGLRLPE DFPDPRVTAL YLHVWPSVGR EPREEEAALA DLAIDSDALF RVFRRNGIHQ
     HQAQTDGFVR PAIERRAAIL GYDAAGSQVP ITHFFYRDPG SERLRDTAPD GPASAPADGD
     LRLGPRRFDR TPWSGVRGQK ALAILQASLP PP
//