ID   A0A194R166_PAPMA        Unreviewed;       892 AA.
AC   A0A194R166;
DT   05-OCT-2016, integrated into UniProtKB/TrEMBL.
DT   05-OCT-2016, sequence version 1.
DT   27-MAR-2024, entry version 14.
DE   SubName: Full=Glutamine-rich protein 2 {ECO:0000313|EMBL:KPJ11447.1};
GN   ORFNames=RR48_15086 {ECO:0000313|EMBL:KPJ11447.1};
OS   Papilio machaon (Old World swallowtail butterfly).
OC   Eukaryota; Metazoa; Ecdysozoa; Arthropoda; Hexapoda; Insecta; Pterygota;
OC   Neoptera; Endopterygota; Lepidoptera; Glossata; Ditrysia; Papilionoidea;
OC   Papilionidae; Papilioninae; Papilio.
OX   NCBI_TaxID=76193 {ECO:0000313|EMBL:KPJ11447.1, ECO:0000313|Proteomes:UP000053240};
RN   [1] {ECO:0000313|EMBL:KPJ11447.1, ECO:0000313|Proteomes:UP000053240}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=Ya'a_city_454_Pm {ECO:0000313|EMBL:KPJ11447.1};
RC   TISSUE=Whole body {ECO:0000313|EMBL:KPJ11447.1};
RX   PubMed=26354079; DOI=10.1038/ncomms9212;
RA   Li X., Fan D., Zhang W., Liu G., Zhang L., Zhao L., Fang X., Chen L.,
RA   Dong Y., Chen Y., Ding Y., Zhao R., Feng M., Zhu Y., Feng Y., Jiang X.,
RA   Zhu D., Xiang H., Feng X., Li S., Wang J., Zhang G., Kronforst M.R.,
RA   Wang W.;
RT   "Outbred genome sequencing and CRISPR/Cas9 gene editing in butterflies.";
RL   Nat. Commun. 6:8212-8212(2015).
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; KQ460883; KPJ11447.1; -; Genomic_DNA.
DR   AlphaFoldDB; A0A194R166; -.
DR   STRING; 76193.A0A194R166; -.
DR   InParanoid; A0A194R166; -.
DR   Proteomes; UP000053240; Unassembled WGS sequence.
DR   InterPro; IPR032013; DUF4795.
DR   PANTHER; PTHR47080; CHROMOSOME 16 OPEN READING FRAME 96; 1.
DR   PANTHER; PTHR47080:SF1; CHROMOSOME 16 OPEN READING FRAME 96; 1.
DR   Pfam; PF16043; DUF4795; 1.
PE   4: Predicted;
KW   Reference proteome {ECO:0000313|Proteomes:UP000053240}.
FT   DOMAIN          548..743
FT                   /note="DUF4795"
FT                   /evidence="ECO:0000259|Pfam:PF16043"
FT   REGION          75..180
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          869..892
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        80..109
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        118..157
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        872..892
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   892 AA;  98987 MW;  15492B60BC89CA4A CRC64;
     MSNYSIMSVK DMIEMAFGDP RIDVVNFKLI QTILFLLARQ LRLLGRRVEV NVEQPFLTPP
     RSNIIVTELK MQAAVPRKPK RATKLSETDS TDMTAEKTPS HRKPLKTGGG AHDSSKSDPR
     TTVIDSKKGI TDPKKTITEA TKRATDPRQD AVEPRRGVSD PRQGGTVARS RETDAKKTLV
     DARRGVSDPR YDVGSQDDQS IIGAIEEKRE RVLRVIRQRA DSREEAEKSP TPMASLDSIE
     MQYEKLLIVE RTSSEETRIG IEDPRSTTKK LRLSVVTQDQ FQALVEKVRE LQNQFGGVPS
     ARFPENIELM QQLRKGASLT DAMAALQLSA RLEAAEKTLG QMLSLITTIA GDTPGIDAAV
     SETLRRTTTK ARETTYGDKK LTEQFRAKDR DTSPAMKTAT LQPTTLKTIS EETKQPSTFA
     YTQSTAGQAK SVPEEPVITF GDLNHALEKL QGEILNEVRT INNANTESAN NALRLTKKLE
     LKIEALSQLA PKMNDLEKLV SNYAEQINAL DTGLSAQMTD YHENLNQMQH DLEVALETMA
     EALANTGSDT EVVAELNTKL GFVQEDIDRA AVNQKELLEM QNALHVELRG LWQEIEVLRE
     VKPDRDEVVD ALRDKAGLKA LNGLVSQNHF DAVRGDFQKS VAAAYDKFNN QEIVWQKAID
     DIYRELSEKA DLVQLNSLSN DIDNKLKILN SRAQLIMDIL GEPVAAATTK KLFRDSACLS
     CSTPAHMETT ETDTIPKLPE FPKPAQKVLD IEKTSKPAEE NVCIPGRPIP HALDPRSEFC
     KRYCGGGAVG RPIKKYEPIR FVSSSLKTTT IGTDGKTYKT EEPCQPCVPC NQTHSETIQP
     LEADQAPKFK EEHVSDVTAP SDFFMQEVSG LEQDPETANS VSVTPTLPLD ND
//