ID   A0A016V5L0_9BILA        Unreviewed;       942 AA.
AC   A0A016V5L0;
DT   11-JUN-2014, integrated into UniProtKB/TrEMBL.
DT   11-JUN-2014, sequence version 1.
DT   27-MAR-2024, entry version 20.
DE   RecName: Full=Integrase catalytic domain-containing protein {ECO:0000259|PROSITE:PS50994};
GN   Name=Acey_s0017.g3273 {ECO:0000313|EMBL:EYC22302.1};
GN   ORFNames=Y032_0017g3273 {ECO:0000313|EMBL:EYC22302.1};
OS   Ancylostoma ceylanicum.
OC   Eukaryota; Metazoa; Ecdysozoa; Nematoda; Chromadorea; Rhabditida;
OC   Rhabditina; Rhabditomorpha; Strongyloidea; Ancylostomatidae;
OC   Ancylostomatinae; Ancylostoma.
OX   NCBI_TaxID=53326 {ECO:0000313|EMBL:EYC22302.1, ECO:0000313|Proteomes:UP000024635};
RN   [1] {ECO:0000313|Proteomes:UP000024635}
RP   NUCLEOTIDE SEQUENCE.
RC   STRAIN=HY135 {ECO:0000313|Proteomes:UP000024635};
RX   PubMed=25730766; DOI=10.1038/ng.3237;
RA   Schwarz E.M., Hu Y., Antoshechkin I., Miller M.M., Sternberg P.W.,
RA   Aroian R.V.;
RT   "The genome and transcriptome of the zoonotic hookworm Ancylostoma
RT   ceylanicum identify infection-specific gene families.";
RL   Nat. Genet. 47:416-422(2015).
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:EYC22302.1}.
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; JARK01001353; EYC22302.1; -; Genomic_DNA.
DR   AlphaFoldDB; A0A016V5L0; -.
DR   STRING; 53326.A0A016V5L0; -.
DR   Proteomes; UP000024635; Unassembled WGS sequence.
DR   GO; GO:0003676; F:nucleic acid binding; IEA:InterPro.
DR   GO; GO:0015074; P:DNA integration; IEA:InterPro.
DR   Gene3D; 1.10.340.70; -; 1.
DR   Gene3D; 2.40.70.10; Acid Proteases; 1.
DR   Gene3D; 3.30.420.10; Ribonuclease H-like superfamily/Ribonuclease H; 1.
DR   InterPro; IPR001584; Integrase_cat-core.
DR   InterPro; IPR041588; Integrase_H2C2.
DR   InterPro; IPR021109; Peptidase_aspartic_dom_sf.
DR   InterPro; IPR012337; RNaseH-like_sf.
DR   InterPro; IPR036397; RNaseH_sf.
DR   PANTHER; PTHR37984:SF7; INTEGRASE CATALYTIC DOMAIN-CONTAINING PROTEIN; 1.
DR   PANTHER; PTHR37984; PROTEIN CBG26694; 1.
DR   Pfam; PF13975; gag-asp_proteas; 1.
DR   Pfam; PF17921; Integrase_H2C2; 1.
DR   Pfam; PF00665; rve; 1.
DR   SUPFAM; SSF50630; Acid proteases; 1.
DR   SUPFAM; SSF53098; Ribonuclease H-like; 1.
DR   PROSITE; PS50994; INTEGRASE; 1.
PE   4: Predicted;
KW   Reference proteome {ECO:0000313|Proteomes:UP000024635}.
FT   DOMAIN          602..755
FT                   /note="Integrase catalytic"
FT                   /evidence="ECO:0000259|PROSITE:PS50994"
FT   REGION          269..327
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          861..942
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        269..314
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        862..896
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   942 AA;  107151 MW;  A39F6BBE6E4BD6E2 CRC64;
     MPSSSQAMES EQAPRWLEEV LQVQFQHLQL LQQQNQRIAD LVSMLVEREK ASTSAADVTS
     PAPRVDPYGD LVRDLPTFNY EGDEDETFNA WYTRYGPVMD DRGKALSDDR KRNLIVEKLD
     KATYKTYSEH VLPLKPQEID LATTIDNLRK LFGPKRTLIR RRYEFLQSKC PPLNGAYVPY
     REYGNMIKRK FEDASMKDVD SDSLKCLVFL SGLTDPSHSE TRLRLLNQLN RLKESDPAPL
     LDDFINECET FVTLRTDNRA IESKEVNAAY QRKPAKQDRK HPYSPNKGFR YRCQPRDRSL
     HSPSRNERSA SPAKKRGTKR PKRKHRCKNI AASAHGARTY LKVRINGHPT RLQLDTGADI
     TMISRRTWED MKSPKLDRST ITIRTADGSA MNILGSFKAA FTIFDRKGRP TEGTGCCYVT
     ESTDLLEYRK TANFGQADAL SRLIAEQTTP SEDVVIAQAV QEAEADCRAI TSTLPVDMKM
     IAEESANDDI LKNVISYVQK DKWPHKPSAD VARYFALRQS LAIQDDCLFF GPRIVIPSKL
     RRRVLQLLHD GHPGTTRMKM LARSYVYWTN ITKDIEVYVR GCRNCQEVAK APLKTELFSW
     PNEKQPWSRV HIDYAGPLNG KMFLVIVDAY SKWPEIIEMT STTSAATIRQ LTRLFAQFGN
     PTTLVSDNGS QFASKEFAEF CSTNGITHVR SPPFHPQSNG QAERFVDTFK RALEKLKDSG
     TTSDALQKFL QTYRRTPCPA SPGGRSPAEN FLGRQLRTPL TMLTMPKSAA KERNRKMESQ
     FNFHNNARPK KFEPDDAVWV RNFGRGGARW TPGRVLARHG HATYDVLIDG RVHRRHSNQM
     RPNAPENSEK TLLDLFDLPI LPAQTPTNTT PASTDPQAQD TTLRRPSSSE PNEDSPDMSP
     ATADADTRTI PTPTPPRRSQ RNRRPPIRLD VNPTRKTYRN QS
//