ID   A0A1D9Q2J7_SCLS1        Unreviewed;      1264 AA.
AC   A0A1D9Q2J7;
DT   10-MAY-2017, integrated into UniProtKB/TrEMBL.
DT   10-MAY-2017, sequence version 1.
DT   24-JAN-2024, entry version 32.
DE   RecName: Full=Histone-lysine N-methyltransferase, H3 lysine-4 specific {ECO:0000256|ARBA:ARBA00015839, ECO:0000256|PIRNR:PIRNR037104};
DE            EC=2.1.1.354 {ECO:0000256|ARBA:ARBA00012182, ECO:0000256|PIRNR:PIRNR037104};
GN   ORFNames=sscle_04g039340 {ECO:0000313|EMBL:APA09164.1};
OS   Sclerotinia sclerotiorum (strain ATCC 18683 / 1980 / Ss-1) (White mold)
OS   (Whetzelinia sclerotiorum).
OC   Eukaryota; Fungi; Dikarya; Ascomycota; Pezizomycotina; Leotiomycetes;
OC   Helotiales; Sclerotiniaceae; Sclerotinia.
OX   NCBI_TaxID=665079 {ECO:0000313|EMBL:APA09164.1, ECO:0000313|Proteomes:UP000177798};
RN   [1] {ECO:0000313|Proteomes:UP000177798}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=ATCC 18683 / 1980 / Ss-1 {ECO:0000313|Proteomes:UP000177798};
RX   PubMed=28204478; DOI=10.1093/gbe/evx030;
RA   Derbyshire M., Denton-Giles M., Hegedus D., Seifbarghy S., Rollins J.,
RA   van Kan J., Seidl M.F., Faino L., Mbengue M., Navaud O., Raffaele S.,
RA   Hammond-Kosack K., Heard S., Oliver R.;
RT   "The complete genome sequence of the phytopathogenic fungus Sclerotinia
RT   sclerotiorum reveals insights into the genome architecture of broad host
RT   range pathogens.";
RL   Genome Biol. Evol. 9:593-618(2017).
CC   -!- FUNCTION: Catalytic component of the COMPASS (Set1C) complex that
CC       specifically mono-, di- and trimethylates histone H3 to form
CC       H3K4me1/2/3, which subsequently plays a role in telomere length
CC       maintenance and transcription elongation regulation.
CC       {ECO:0000256|ARBA:ARBA00002789, ECO:0000256|PIRNR:PIRNR037104}.
CC   -!- CATALYTIC ACTIVITY:
CC       Reaction=L-lysyl(4)-[histone H3] + 3 S-adenosyl-L-methionine = 3 H(+) +
CC         N(6),N(6),N(6)-trimethyl-L-lysyl(4)-[histone H3] + 3 S-adenosyl-L-
CC         homocysteine; Xref=Rhea:RHEA:60260, Rhea:RHEA-COMP:15537, Rhea:RHEA-
CC         COMP:15547, ChEBI:CHEBI:15378, ChEBI:CHEBI:29969, ChEBI:CHEBI:57856,
CC         ChEBI:CHEBI:59789, ChEBI:CHEBI:61961; EC=2.1.1.354;
CC         Evidence={ECO:0000256|ARBA:ARBA00000944,
CC         ECO:0000256|PIRNR:PIRNR037104};
CC   -!- SUBUNIT: Component of the COMPASS (Set1C) complex.
CC       {ECO:0000256|ARBA:ARBA00011755, ECO:0000256|PIRNR:PIRNR037104}.
CC   -!- SUBCELLULAR LOCATION: Chromosome {ECO:0000256|ARBA:ARBA00004286}.
CC       Nucleus {ECO:0000256|ARBA:ARBA00004123, ECO:0000256|PIRNR:PIRNR037104}.
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; CP017817; APA09164.1; -; Genomic_DNA.
DR   RefSeq; XP_001596847.1; XM_001596797.1.
DR   AlphaFoldDB; A0A1D9Q2J7; -.
DR   EnsemblFungi; EDO00210; EDO00210; SS1G_03070.
DR   GeneID; 5492667; -.
DR   KEGG; ssl:SS1G_03070; -.
DR   VEuPathDB; FungiDB:sscle_04g039340; -.
DR   OMA; CHMTALF; -.
DR   OrthoDB; 950362at2759; -.
DR   Proteomes; UP000177798; Chromosome 4.
DR   GO; GO:0005694; C:chromosome; IEA:UniProtKB-SubCell.
DR   GO; GO:0048188; C:Set1C/COMPASS complex; IEA:InterPro.
DR   GO; GO:0140999; F:histone H3K4 trimethyltransferase activity; IEA:UniProtKB-EC.
DR   GO; GO:0032259; P:methylation; IEA:UniProtKB-KW.
DR   CDD; cd20072; SET_SET1; 1.
DR   Gene3D; 3.30.70.330; -; 1.
DR   Gene3D; 2.170.270.10; SET domain; 1.
DR   InterPro; IPR024657; COMPASS_Set1_N-SET.
DR   InterPro; IPR012677; Nucleotide-bd_a/b_plait_sf.
DR   InterPro; IPR003616; Post-SET_dom.
DR   InterPro; IPR044570; Set1-like.
DR   InterPro; IPR017111; Set1_fungi.
DR   InterPro; IPR024636; SET_assoc.
DR   InterPro; IPR001214; SET_dom.
DR   InterPro; IPR046341; SET_dom_sf.
DR   PANTHER; PTHR45814; HISTONE-LYSINE N-METHYLTRANSFERASE SETD1; 1.
DR   PANTHER; PTHR45814:SF2; HISTONE-LYSINE N-METHYLTRANSFERASE SETD1; 1.
DR   Pfam; PF11764; N-SET; 1.
DR   Pfam; PF00856; SET; 1.
DR   Pfam; PF11767; SET_assoc; 1.
DR   PIRSF; PIRSF037104; Histone_H3-K4_mtfrase_Set1_fun; 2.
DR   SMART; SM01291; N-SET; 1.
DR   SMART; SM00508; PostSET; 1.
DR   SMART; SM00317; SET; 1.
DR   SUPFAM; SSF82199; SET domain; 1.
DR   PROSITE; PS50868; POST_SET; 1.
DR   PROSITE; PS51572; SAM_MT43_1; 1.
DR   PROSITE; PS50280; SET; 1.
PE   4: Predicted;
KW   Chromatin regulator {ECO:0000256|PIRNR:PIRNR037104};
KW   Chromosome {ECO:0000256|PIRNR:PIRNR037104};
KW   Methyltransferase {ECO:0000256|ARBA:ARBA00022603,
KW   ECO:0000256|PIRNR:PIRNR037104}; Nucleus {ECO:0000256|PIRNR:PIRNR037104};
KW   S-adenosyl-L-methionine {ECO:0000256|ARBA:ARBA00022691,
KW   ECO:0000256|PIRNR:PIRNR037104};
KW   Transferase {ECO:0000256|ARBA:ARBA00022679, ECO:0000256|PIRNR:PIRNR037104}.
FT   DOMAIN          1122..1239
FT                   /note="SET"
FT                   /evidence="ECO:0000259|PROSITE:PS50280"
FT   DOMAIN          1248..1264
FT                   /note="Post-SET"
FT                   /evidence="ECO:0000259|PROSITE:PS50868"
FT   REGION          1..38
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          64..153
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          193..236
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          372..438
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          548..596
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          654..675
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          691..811
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        19..33
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        74..153
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        390..422
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        739..763
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        770..788
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   1264 AA;  141591 MW;  3387692360A5D688 CRC64;
     MSRASGASFA QFFPSAPRAA KDKAKEREKS KAQQADSPAI LSLADTHINA RALTDNASIT
     RLSEDISIPM PDPPTLTTED TESAHGDTLN GVGSASSHSS TGSSLFSTNN QLSNSMHTFG
     GSRNINDLTP FTNTDSSPNR VASPSNAKAD VSVSATNNVV RENTKSEHVV AIPNSAPADH
     TPSEPRVLAR DPARGVKGKK CTYDPFHDPA IHSTKEKHNR RPHYKEFGLK DDAPPADPRL
     AKGSRLSYIN TDYHNALSRL NHSPFMLPKY KYNPKTHYGP GPPTEIVVTG YDPLINFMKV
     TNVFTQYGQI AESSNKLHPE TGSCLGFGTF RYRDTKRKDG SILTAAEAAK KAVMRGSSVV
     GLGPRIKVQF DSQGKRSTRM LESALEKSKP EPLPLPPREP PPPPKPEVVK TSGPPPTAPK
     GPAALSGRPQ FRPGIAQPAI PTKPRQQILI EDEPIAQQLE DEPYIFISKD YVPVIPATIL
     HLKKRLKNHF LEDVRVDRTG YYVVFALSDE GRFEAERCYN SCNGTALFSY EMIMKLYVWG
     TGGRRLDHRD RTSERGHHRR TRSPDPRLIE QKRKRELEEI RKEEEADFEE EKRERAKNFD
     PAREAIEVIK RELMTHLMDK VKERIANPCL RNFMDPANHV AKRRKLNIHD PNAKTPFIEE
     DEDNTPAIGT PNSRFEDRNA LTVGKVNVTA LPRIRKRTKT EKKRNVGSTD SSARPTRKAY
     VRPMQFLIGR EDEDSDDDNE APSRTRGTEE RESRPISRMS TDDEASDDDT DSISQNHVKE
     RSPSLDTRDG ESVSESNFSE PTAQTKKRKL ELHVEAAKKR QKKTDEELFG VSVAKIEPLP
     ETPTLETNIP DIDGFQKTES ETEAALAVAA RKKAAKSAKR KKSKKQIFEE REALKRQQEG
     IPEEEIVPEE VEESEFEENI VDTAPVVTSV EWGISGEAPY PTVDDDFDNI LDIDGLQNIL
     KDDEDAGPAF EIFKTDFKLS DPATWAWRQG QIKSLNRNGY KGIVKDETTV PGYYVETSTG
     CARTEGTKKI LNSEKSLYLP HRIKVQRARE EREAQAKRAG KDVVAEAAEA AKIAAEKLLA
     RTSGRANRVN NRRYVADLND QKKTLGGDTD VLRFNQLKKR KKPVKFARSA IHNWGLYAME
     NIAMNDMIIE YVGEKVRQQV ADLRENRYLK SGIGSSYLFR IDENTVIDAT KKGGIARFIN
     HSCMPNCTAK IITVEKSKRI VIYALRDIAQ NEELTYDYKF EREIGSTDRI PCLCGTPACK
     GFLN
//

ID   A7ECN1_SCLS1            Unreviewed;      1264 AA.
AC   A7ECN1;
DT   11-SEP-2007, integrated into UniProtKB/TrEMBL.
DT   11-SEP-2007, sequence version 1.
DT   24-JAN-2024, entry version 107.
DE   RecName: Full=Histone-lysine N-methyltransferase, H3 lysine-4 specific {ECO:0000256|ARBA:ARBA00015839, ECO:0000256|PIRNR:PIRNR037104};
DE            EC=2.1.1.354 {ECO:0000256|ARBA:ARBA00012182, ECO:0000256|PIRNR:PIRNR037104};
GN   ORFNames=SS1G_03070 {ECO:0000313|EMBL:EDO00210.1};
OS   Sclerotinia sclerotiorum (strain ATCC 18683 / 1980 / Ss-1) (White mold)
OS   (Whetzelinia sclerotiorum).
OC   Eukaryota; Fungi; Dikarya; Ascomycota; Pezizomycotina; Leotiomycetes;
OC   Helotiales; Sclerotiniaceae; Sclerotinia.
OX   NCBI_TaxID=665079 {ECO:0000313|EMBL:EDO00210.1, ECO:0000313|Proteomes:UP000001312};
RN   [1] {ECO:0000313|Proteomes:UP000001312}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=ATCC 18683 / 1980 / Ss-1 {ECO:0000313|Proteomes:UP000001312};
RX   PubMed=21876677; DOI=.1371/journal.pgen.1002230;
RA   Amselem J., Cuomo C.A., van Kan J.A., Viaud M., Benito E.P., Couloux A.,
RA   Coutinho P.M., de Vries R.P., Dyer P.S., Fillinger S., Fournier E.,
RA   Gout L., Hahn M., Kohn L., Lapalu N., Plummer K.M., Pradier J.M.,
RA   Quevillon E., Sharon A., Simon A., ten Have A., Tudzynski B., Tudzynski P.,
RA   Wincker P., Andrew M., Anthouard V., Beever R.E., Beffa R., Benoit I.,
RA   Bouzid O., Brault B., Chen Z., Choquer M., Collemare J., Cotton P.,
RA   Danchin E.G., Da Silva C., Gautier A., Giraud C., Giraud T., Gonzalez C.,
RA   Grossetete S., Guldener U., Henrissat B., Howlett B.J., Kodira C.,
RA   Kretschmer M., Lappartient A., Leroch M., Levis C., Mauceli E.,
RA   Neuveglise C., Oeser B., Pearson M., Poulain J., Poussereau N.,
RA   Quesneville H., Rascle C., Schumacher J., Segurens B., Sexton A., Silva E.,
RA   Sirven C., Soanes D.M., Talbot N.J., Templeton M., Yandava C., Yarden O.,
RA   Zeng Q., Rollins J.A., Lebrun M.H., Dickman M.;
RT   "Genomic analysis of the necrotrophic fungal pathogens Sclerotinia
RT   sclerotiorum and Botrytis cinerea.";
RL   PLoS Genet. 7:E1002230-E1002230(2011).
CC   -!- FUNCTION: Catalytic component of the COMPASS (Set1C) complex that
CC       specifically mono-, di- and trimethylates histone H3 to form
CC       H3K4me1/2/3, which subsequently plays a role in telomere length
CC       maintenance and transcription elongation regulation.
CC       {ECO:0000256|ARBA:ARBA00002789, ECO:0000256|PIRNR:PIRNR037104}.
CC   -!- CATALYTIC ACTIVITY:
CC       Reaction=L-lysyl(4)-[histone H3] + 3 S-adenosyl-L-methionine = 3 H(+) +
CC         N(6),N(6),N(6)-trimethyl-L-lysyl(4)-[histone H3] + 3 S-adenosyl-L-
CC         homocysteine; Xref=Rhea:RHEA:60260, Rhea:RHEA-COMP:15537, Rhea:RHEA-
CC         COMP:15547, ChEBI:CHEBI:15378, ChEBI:CHEBI:29969, ChEBI:CHEBI:57856,
CC         ChEBI:CHEBI:59789, ChEBI:CHEBI:61961; EC=2.1.1.354;
CC         Evidence={ECO:0000256|ARBA:ARBA00000944,
CC         ECO:0000256|PIRNR:PIRNR037104};
CC   -!- SUBUNIT: Component of the COMPASS (Set1C) complex.
CC       {ECO:0000256|ARBA:ARBA00011755, ECO:0000256|PIRNR:PIRNR037104}.
CC   -!- SUBCELLULAR LOCATION: Chromosome {ECO:0000256|ARBA:ARBA00004286}.
CC       Nucleus {ECO:0000256|ARBA:ARBA00004123, ECO:0000256|PIRNR:PIRNR037104}.
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; CH476623; EDO00210.1; -; Genomic_DNA.
DR   RefSeq; XP_001596847.1; XM_001596797.1.
DR   AlphaFoldDB; A7ECN1; -.
DR   STRING; 665079.A7ECN1; -.
DR   EnsemblFungi; EDO00210; EDO00210; SS1G_03070.
DR   GeneID; 5492667; -.
DR   KEGG; ssl:SS1G_03070; -.
DR   VEuPathDB; FungiDB:sscle_04g039340; -.
DR   eggNOG; KOG1080; Eukaryota.
DR   HOGENOM; CLU_004391_1_0_1; -.
DR   InParanoid; A7ECN1; -.
DR   OMA; CHMTALF; -.
DR   OrthoDB; 950362at2759; -.
DR   Proteomes; UP000001312; Unassembled WGS sequence.
DR   GO; GO:0005694; C:chromosome; IEA:UniProtKB-SubCell.
DR   GO; GO:0048188; C:Set1C/COMPASS complex; IBA:GO_Central.
DR   GO; GO:0042800; F:histone H3K4 methyltransferase activity; IBA:GO_Central.
DR   GO; GO:0140999; F:histone H3K4 trimethyltransferase activity; IEA:UniProtKB-EC.
DR   GO; GO:0032259; P:methylation; IEA:UniProtKB-KW.
DR   CDD; cd20072; SET_SET1; 1.
DR   Gene3D; 3.30.70.330; -; 1.
DR   Gene3D; 2.170.270.10; SET domain; 1.
DR   InterPro; IPR024657; COMPASS_Set1_N-SET.
DR   InterPro; IPR012677; Nucleotide-bd_a/b_plait_sf.
DR   InterPro; IPR003616; Post-SET_dom.
DR   InterPro; IPR044570; Set1-like.
DR   InterPro; IPR017111; Set1_fungi.
DR   InterPro; IPR024636; SET_assoc.
DR   InterPro; IPR001214; SET_dom.
DR   InterPro; IPR046341; SET_dom_sf.
DR   PANTHER; PTHR45814; HISTONE-LYSINE N-METHYLTRANSFERASE SETD1; 1.
DR   PANTHER; PTHR45814:SF2; HISTONE-LYSINE N-METHYLTRANSFERASE SETD1; 1.
DR   Pfam; PF11764; N-SET; 1.
DR   Pfam; PF00856; SET; 1.
DR   Pfam; PF11767; SET_assoc; 1.
DR   PIRSF; PIRSF037104; Histone_H3-K4_mtfrase_Set1_fun; 2.
DR   SMART; SM01291; N-SET; 1.
DR   SMART; SM00508; PostSET; 1.
DR   SMART; SM00317; SET; 1.
DR   SUPFAM; SSF82199; SET domain; 1.
DR   PROSITE; PS50868; POST_SET; 1.
DR   PROSITE; PS51572; SAM_MT43_1; 1.
DR   PROSITE; PS50280; SET; 1.
PE   4: Predicted;
KW   Chromatin regulator {ECO:0000256|PIRNR:PIRNR037104};
KW   Chromosome {ECO:0000256|PIRNR:PIRNR037104};
KW   Methyltransferase {ECO:0000256|ARBA:ARBA00022603,
KW   ECO:0000256|PIRNR:PIRNR037104}; Nucleus {ECO:0000256|PIRNR:PIRNR037104};
KW   Reference proteome {ECO:0000313|Proteomes:UP000001312};
KW   S-adenosyl-L-methionine {ECO:0000256|ARBA:ARBA00022691,
KW   ECO:0000256|PIRNR:PIRNR037104};
KW   Transferase {ECO:0000256|ARBA:ARBA00022679, ECO:0000256|PIRNR:PIRNR037104}.
FT   DOMAIN          1122..1239
FT                   /note="SET"
FT                   /evidence="ECO:0000259|PROSITE:PS50280"
FT   DOMAIN          1248..1264
FT                   /note="Post-SET"
FT                   /evidence="ECO:0000259|PROSITE:PS50868"
FT   REGION          1..38
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          64..153
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          193..236
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          372..438
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          548..596
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          654..675
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   REGION          691..811
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        19..33
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        74..153
FT                   /note="Polar residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        390..422
FT                   /note="Pro residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        739..763
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        770..788
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   1264 AA;  141591 MW;  3387692360A5D688 CRC64;
     MSRASGASFA QFFPSAPRAA KDKAKEREKS KAQQADSPAI LSLADTHINA RALTDNASIT
     RLSEDISIPM PDPPTLTTED TESAHGDTLN GVGSASSHSS TGSSLFSTNN QLSNSMHTFG
     GSRNINDLTP FTNTDSSPNR VASPSNAKAD VSVSATNNVV RENTKSEHVV AIPNSAPADH
     TPSEPRVLAR DPARGVKGKK CTYDPFHDPA IHSTKEKHNR RPHYKEFGLK DDAPPADPRL
     AKGSRLSYIN TDYHNALSRL NHSPFMLPKY KYNPKTHYGP GPPTEIVVTG YDPLINFMKV
     TNVFTQYGQI AESSNKLHPE TGSCLGFGTF RYRDTKRKDG SILTAAEAAK KAVMRGSSVV
     GLGPRIKVQF DSQGKRSTRM LESALEKSKP EPLPLPPREP PPPPKPEVVK TSGPPPTAPK
     GPAALSGRPQ FRPGIAQPAI PTKPRQQILI EDEPIAQQLE DEPYIFISKD YVPVIPATIL
     HLKKRLKNHF LEDVRVDRTG YYVVFALSDE GRFEAERCYN SCNGTALFSY EMIMKLYVWG
     TGGRRLDHRD RTSERGHHRR TRSPDPRLIE QKRKRELEEI RKEEEADFEE EKRERAKNFD
     PAREAIEVIK RELMTHLMDK VKERIANPCL RNFMDPANHV AKRRKLNIHD PNAKTPFIEE
     DEDNTPAIGT PNSRFEDRNA LTVGKVNVTA LPRIRKRTKT EKKRNVGSTD SSARPTRKAY
     VRPMQFLIGR EDEDSDDDNE APSRTRGTEE RESRPISRMS TDDEASDDDT DSISQNHVKE
     RSPSLDTRDG ESVSESNFSE PTAQTKKRKL ELHVEAAKKR QKKTDEELFG VSVAKIEPLP
     ETPTLETNIP DIDGFQKTES ETEAALAVAA RKKAAKSAKR KKSKKQIFEE REALKRQQEG
     IPEEEIVPEE VEESEFEENI VDTAPVVTSV EWGISGEAPY PTVDDDFDNI LDIDGLQNIL
     KDDEDAGPAF EIFKTDFKLS DPATWAWRQG QIKSLNRNGY KGIVKDETTV PGYYVETSTG
     CARTEGTKKI LNSEKSLYLP HRIKVQRARE EREAQAKRAG KDVVAEAAEA AKIAAEKLLA
     RTSGRANRVN NRRYVADLND QKKTLGGDTD VLRFNQLKKR KKPVKFARSA IHNWGLYAME
     NIAMNDMIIE YVGEKVRQQV ADLRENRYLK SGIGSSYLFR IDENTVIDAT KKGGIARFIN
     HSCMPNCTAK IITVEKSKRI VIYALRDIAQ NEELTYDYKF EREIGSTDRI PCLCGTPACK
     GFLN
//