ID   W0RUS3_9BACT            Unreviewed;       953 AA.
AC   W0RUS3;
DT   19-MAR-2014, integrated into UniProtKB/TrEMBL.
DT   19-MAR-2014, sequence version 1.
DT   27-MAR-2024, entry version 35.
DE   SubName: Full=CHAT domain protein {ECO:0000313|EMBL:AHG93333.1};
GN   ORFNames=J421_5798 {ECO:0000313|EMBL:AHG93333.1};
OS   Gemmatirosa kalamazoonensis.
OG   Plasmid 2 {ECO:0000313|EMBL:AHG93333.1, ECO:0000313|Proteomes:UP000019151}.
OC   Bacteria; Gemmatimonadota; Gemmatimonadetes; Gemmatimonadales;
OC   Gemmatimonadaceae; Gemmatirosa.
OX   NCBI_TaxID=861299 {ECO:0000313|EMBL:AHG93333.1, ECO:0000313|Proteomes:UP000019151};
RN   [1] {ECO:0000313|EMBL:AHG93333.1, ECO:0000313|Proteomes:UP000019151}
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=KBS708 {ECO:0000313|EMBL:AHG93333.1,
RC   ECO:0000313|Proteomes:UP000019151};
RC   PLASMID=Plasmid 2 {ECO:0000313|Proteomes:UP000019151};
RX   PubMed=24699952;
RA   Debruyn J.M., Radosevich M., Wommack K.E., Polson S.W., Hauser L.J.,
RA   Fawaz M.N., Korlach J., Tsai Y.C.;
RT   "Genome Sequence and Methylome of Soil Bacterium Gemmatirosa
RT   kalamazoonensis KBS708T, a Member of the Rarely Cultivated Gemmatimonadetes
RT   Phylum.";
RL   Genome Announc. 2:e00226-14(2014).
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; CP007130; AHG93333.1; -; Genomic_DNA.
DR   AlphaFoldDB; W0RUS3; -.
DR   KEGG; gba:J421_5798; -.
DR   PATRIC; fig|861299.3.peg.5845; -.
DR   eggNOG; COG0457; Bacteria.
DR   eggNOG; COG4995; Bacteria.
DR   HOGENOM; CLU_002404_0_1_0; -.
DR   InParanoid; W0RUS3; -.
DR   OrthoDB; 434769at2; -.
DR   Proteomes; UP000019151; Plasmid 2.
DR   Gene3D; 1.25.40.10; Tetratricopeptide repeat domain; 2.
DR   InterPro; IPR024983; CHAT_dom.
DR   InterPro; IPR011990; TPR-like_helical_dom_sf.
DR   InterPro; IPR019734; TPR_repeat.
DR   PANTHER; PTHR10098; RAPSYN-RELATED; 1.
DR   PANTHER; PTHR10098:SF106; TETRATRICOPEPTIDE REPEAT PROTEIN 28; 1.
DR   Pfam; PF12770; CHAT; 1.
DR   Pfam; PF13424; TPR_12; 3.
DR   SMART; SM00028; TPR; 10.
DR   SUPFAM; SSF48452; TPR-like; 3.
DR   PROSITE; PS50005; TPR; 2.
PE   4: Predicted;
KW   Plasmid {ECO:0000313|EMBL:AHG93333.1};
KW   Reference proteome {ECO:0000313|Proteomes:UP000019151};
KW   Signal {ECO:0000256|SAM:SignalP};
KW   TPR repeat {ECO:0000256|PROSITE-ProRule:PRU00339}.
FT   SIGNAL          1..24
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT   CHAIN           25..953
FT                   /evidence="ECO:0000256|SAM:SignalP"
FT                   /id="PRO_5004794630"
FT   REPEAT          151..184
FT                   /note="TPR"
FT                   /evidence="ECO:0000256|PROSITE-ProRule:PRU00339"
FT   REPEAT          351..384
FT                   /note="TPR"
FT                   /evidence="ECO:0000256|PROSITE-ProRule:PRU00339"
FT   DOMAIN          664..952
FT                   /note="CHAT"
FT                   /evidence="ECO:0000259|Pfam:PF12770"
FT   REGION          623..655
FT                   /note="Disordered"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
FT   COMPBIAS        624..655
FT                   /note="Basic and acidic residues"
FT                   /evidence="ECO:0000256|SAM:MobiDB-lite"
SQ   SEQUENCE   953 AA;  99334 MW;  9ACE0CED96FA8DC9 CRC64;
     MRAAVGAFAL LAALVVPSAS PCRAQTPADS LMSLVGRGER QLGAGQRDSA LATFRAVLTH
     SRAVGERRSE GAALYGIGRV FLTIGQVDSA RGYYQSVLPL TRALGLRNAE AGALQDLAVV
     YTRLGQPDSA LAYDRLALAL YRAAGDRGGE ASMLTNIGVV FGRIGRPDSA LAYYREALAL
     HRAVGNHKNE AETLTTIGGE YFKTGRPDSA LVFLRPALAL RRAAGDGQGE AETLRVIGAV
     LEGIGRPDSA LACLRAALLL HRAVGDRAGE ATALASIGGV FSRTGQPDSA LFYYRAALPR
     VRAVGDRTGE AVTLSHLGWI FTGIGTLDSA LTYFRAALPL LRAVGDRRGE ALALSRMGVA
     YHRTGHVDSA LTYYRVALPL HRAVGDGGGE AETLGDIGRG FAERGQADSA LAYFRAALSL
     ARAVGDPSQQ AGTLSAISRI YGSIRRYDAA LHVLDSAMAL YATIRMHAGG DAGAVAFAED
     HHDAADMWVG AWLSRAASRD TSATVAVTAA LAAAERGRAQ GLRDLLARSG SAAGPTADST
     GWAHDTVPDA DLATEGTSEL DALRRAGSAA LYYFISPAAL TTWLLSPTGE LRVGGRRRLN
     GDSLAALVTT LRAALGADAA RTRMARGGDV EQERVARRSP DDTAGSRGVE DEASPEAQAR
     LRAVMAALAA TLLPPGLART VPAGTDLVIV PHGVLGLVPF GALPIVGDTL PLGARYALRY
     APSLRALAAA EAHAVAGAAG RALVVGDPAM PTVTAADGRR VKLRDLPAAR AEGDAVARRF
     GVAVLTDRGA TETAVRQALP NAHLVHLATH GLAYGSEARV RDSYVALAPD GKNDGLLTIG
     ELLDAVPPLS ADLVVLSACQ TGLGDLKRAE GTVGFQRALL AKGARSVLVS LWSVDDRATA
     LLMRQFYAHW LGADGQPARS KAEALRLAQT DVRLTPGFAS PRYWAAFQLV GAR
//