ID   TRY1_ANOGA              Reviewed;         274 AA.
AC   P35035; Q7PN85;
DT   01-FEB-1994, integrated into UniProtKB/Swiss-Prot.
DT   26-FEB-2008, sequence version 3.
DT   27-MAR-2024, entry version 143.
DE   RecName: Full=Trypsin-1;
DE            EC=3.4.21.4;
DE   AltName: Full=Antryp1;
DE   Flags: Precursor;
GN   Name=TRYP1; ORFNames=AGAP008296;
OS   Anopheles gambiae (African malaria mosquito).
OC   Eukaryota; Metazoa; Ecdysozoa; Arthropoda; Hexapoda; Insecta; Pterygota;
OC   Neoptera; Endopterygota; Diptera; Nematocera; Culicoidea; Culicidae;
OC   Anophelinae; Anopheles.
OX   NCBI_TaxID=7165;
RN   [1]
RP   NUCLEOTIDE SEQUENCE [MRNA], FUNCTION, SUBCELLULAR LOCATION, TISSUE
RP   SPECIFICITY, AND INDUCTION.
RC   STRAIN=Suakoko; TISSUE=Midgut;
RX   PubMed=8335004; DOI=10.1002/j.1460-2075.1993.tb05951.x;
RA   Mueller H.-M., Crampton J.M., della Torre A., Sinden R., Crisanti A.;
RT   "Members of a trypsin gene family in Anopheles gambiae are induced in the
RT   gut by blood meal.";
RL   EMBO J. 12:2891-2900(1993).
RN   [2]
RP   NUCLEOTIDE SEQUENCE [GENOMIC DNA], FUNCTION, SUBCELLULAR LOCATION, AND
RP   TISSUE SPECIFICITY.
RC   STRAIN=Suakoko; TISSUE=Midgut;
RX   PubMed=7498434; DOI=10.1006/expr.1995.1128;
RA   Mueller H.-M., Catteruccia F., Vizioli J., della Torre A., Crisanti A.;
RT   "Constitutive and blood meal-induced trypsin genes in Anopheles gambiae.";
RL   Exp. Parasitol. 81:371-385(1995).
RN   [3]
RP   NUCLEOTIDE SEQUENCE [LARGE SCALE GENOMIC DNA].
RC   STRAIN=PEST;
RX   PubMed=12364791; DOI=10.1126/science.1076181;
RA   Holt R.A., Subramanian G.M., Halpern A., Sutton G.G., Charlab R.,
RA   Nusskern D.R., Wincker P., Clark A.G., Ribeiro J.M.C., Wides R.,
RA   Salzberg S.L., Loftus B.J., Yandell M.D., Majoros W.H., Rusch D.B., Lai Z.,
RA   Kraft C.L., Abril J.F., Anthouard V., Arensburger P., Atkinson P.W.,
RA   Baden H., de Berardinis V., Baldwin D., Benes V., Biedler J., Blass C.,
RA   Bolanos R., Boscus D., Barnstead M., Cai S., Center A., Chaturverdi K.,
RA   Christophides G.K., Chrystal M.A.M., Clamp M., Cravchik A., Curwen V.,
RA   Dana A., Delcher A., Dew I., Evans C.A., Flanigan M.,
RA   Grundschober-Freimoser A., Friedli L., Gu Z., Guan P., Guigo R.,
RA   Hillenmeyer M.E., Hladun S.L., Hogan J.R., Hong Y.S., Hoover J.,
RA   Jaillon O., Ke Z., Kodira C.D., Kokoza E., Koutsos A., Letunic I.,
RA   Levitsky A.A., Liang Y., Lin J.-J., Lobo N.F., Lopez J.R., Malek J.A.,
RA   McIntosh T.C., Meister S., Miller J.R., Mobarry C., Mongin E., Murphy S.D.,
RA   O'Brochta D.A., Pfannkoch C., Qi R., Regier M.A., Remington K., Shao H.,
RA   Sharakhova M.V., Sitter C.D., Shetty J., Smith T.J., Strong R., Sun J.,
RA   Thomasova D., Ton L.Q., Topalis P., Tu Z.J., Unger M.F., Walenz B.,
RA   Wang A.H., Wang J., Wang M., Wang X., Woodford K.J., Wortman J.R., Wu M.,
RA   Yao A., Zdobnov E.M., Zhang H., Zhao Q., Zhao S., Zhu S.C., Zhimulev I.,
RA   Coluzzi M., della Torre A., Roth C.W., Louis C., Kalush F., Mural R.J.,
RA   Myers E.W., Adams M.D., Smith H.O., Broder S., Gardner M.J., Fraser C.M.,
RA   Birney E., Bork P., Brey P.T., Venter J.C., Weissenbach J., Kafatos F.C.,
RA   Collins F.H., Hoffman S.L.;
RT   "The genome sequence of the malaria mosquito Anopheles gambiae.";
RL   Science 298:129-149(2002).
CC   -!- FUNCTION: Major function may be to aid in digestion of the blood meal.
CC       {ECO:0000269|PubMed:7498434, ECO:0000269|PubMed:8335004}.
CC   -!- CATALYTIC ACTIVITY:
CC       Reaction=Preferential cleavage: Arg-|-Xaa, Lys-|-Xaa.; EC=3.4.21.4;
CC   -!- SUBCELLULAR LOCATION: Secreted {ECO:0000269|PubMed:7498434,
CC       ECO:0000269|PubMed:8335004}.
CC   -!- TISSUE SPECIFICITY: Constitutively expressed at low level in the gut of
CC       adult females. Also expressed in the gut of male and female pupae.
CC       {ECO:0000269|PubMed:7498434, ECO:0000269|PubMed:8335004}.
CC   -!- INDUCTION: By blood meal. {ECO:0000269|PubMed:8335004}.
CC   -!- SIMILARITY: Belongs to the peptidase S1 family. {ECO:0000255|PROSITE-
CC       ProRule:PRU00274}.
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; Z18889; CAA79327.1; -; mRNA.
DR   EMBL; Z22930; CAA80512.1; -; Genomic_DNA.
DR   EMBL; AAAB01008964; EAA12590.3; -; Genomic_DNA.
DR   PIR; S35339; S35339.
DR   RefSeq; XP_317170.2; XM_317170.2.
DR   AlphaFoldDB; P35035; -.
DR   SMR; P35035; -.
DR   STRING; 7165.P35035; -.
DR   MEROPS; S01.130; -.
DR   PaxDb; 7165-AGAP008296-PA; -.
DR   EnsemblMetazoa; AGAP008296-RA; AGAP008296-PA; AGAP008296.
DR   GeneID; 1277688; -.
DR   KEGG; aga:AgaP_AGAP008296; -.
DR   CTD; 1277688; -.
DR   VEuPathDB; VectorBase:AGAP008296; -.
DR   eggNOG; KOG3627; Eukaryota.
DR   HOGENOM; CLU_006842_7_0_1; -.
DR   InParanoid; P35035; -.
DR   OMA; HNCGGSV; -.
DR   OrthoDB; 2910936at2759; -.
DR   PhylomeDB; P35035; -.
DR   Proteomes; UP000007062; Chromosome 3R.
DR   GO; GO:0005576; C:extracellular region; IEA:UniProtKB-SubCell.
DR   GO; GO:0004252; F:serine-type endopeptidase activity; IBA:GO_Central.
DR   GO; GO:0007586; P:digestion; IEA:UniProtKB-KW.
DR   GO; GO:0006508; P:proteolysis; IEA:UniProtKB-KW.
DR   CDD; cd00190; Tryp_SPc; 1.
DR   Gene3D; 2.40.10.10; Trypsin-like serine proteases; 1.
DR   InterPro; IPR009003; Peptidase_S1_PA.
DR   InterPro; IPR043504; Peptidase_S1_PA_chymotrypsin.
DR   InterPro; IPR001314; Peptidase_S1A.
DR   InterPro; IPR001254; Trypsin_dom.
DR   InterPro; IPR018114; TRYPSIN_HIS.
DR   InterPro; IPR033116; TRYPSIN_SER.
DR   PANTHER; PTHR24276:SF100; AT20289P-RELATED; 1.
DR   PANTHER; PTHR24276; POLYSERASE-RELATED; 1.
DR   Pfam; PF00089; Trypsin; 1.
DR   PRINTS; PR00722; CHYMOTRYPSIN.
DR   SMART; SM00020; Tryp_SPc; 1.
DR   SUPFAM; SSF50494; Trypsin-like serine proteases; 1.
DR   PROSITE; PS50240; TRYPSIN_DOM; 1.
DR   PROSITE; PS00134; TRYPSIN_HIS; 1.
DR   PROSITE; PS00135; TRYPSIN_SER; 1.
PE   2: Evidence at transcript level;
KW   Digestion; Disulfide bond; Hydrolase; Protease; Reference proteome;
KW   Secreted; Serine protease; Signal; Zymogen.
FT   SIGNAL          1..18
FT                   /evidence="ECO:0000255"
FT   PROPEP          19..47
FT                   /note="Activation peptide"
FT                   /id="PRO_0000028243"
FT   CHAIN           48..274
FT                   /note="Trypsin-1"
FT                   /id="PRO_0000028244"
FT   DOMAIN          48..273
FT                   /note="Peptidase S1"
FT                   /evidence="ECO:0000255|PROSITE-ProRule:PRU00274"
FT   ACT_SITE        88
FT                   /note="Charge relay system"
FT                   /evidence="ECO:0000250"
FT   ACT_SITE        133
FT                   /note="Charge relay system"
FT                   /evidence="ECO:0000250"
FT   ACT_SITE        229
FT                   /note="Charge relay system"
FT                   /evidence="ECO:0000250"
FT   SITE            223
FT                   /note="Required for specificity"
FT                   /evidence="ECO:0000250"
FT   DISULFID        73..89
FT                   /evidence="ECO:0000255|PROSITE-ProRule:PRU00274"
FT   DISULFID        198..214
FT                   /evidence="ECO:0000255|PROSITE-ProRule:PRU00274"
FT   DISULFID        225..249
FT                   /evidence="ECO:0000255|PROSITE-ProRule:PRU00274"
FT   CONFLICT        93
FT                   /note="A -> R (in Ref. 1; CAA79327)"
FT                   /evidence="ECO:0000305"
FT   CONFLICT        95
FT                   /note="P -> T (in Ref. 1; CAA79327 and 2; CAA80512)"
FT                   /evidence="ECO:0000305"
FT   CONFLICT        101
FT                   /note="R -> P (in Ref. 1; CAA79327)"
FT                   /evidence="ECO:0000305"
FT   CONFLICT        148
FT                   /note="S -> A (in Ref. 2; CAA80512)"
FT                   /evidence="ECO:0000305"
FT   CONFLICT        204
FT                   /note="E -> D (in Ref. 1; CAA79327 and 2; CAA80512)"
FT                   /evidence="ECO:0000305"
SQ   SEQUENCE   274 AA;  29057 MW;  7055CA51C6CEF3F8 CRC64;
     MSNKIAILLA VLVAVVACAE AQANQRHRLV RPSPSFSPRP RYAVGQRIVG GFEIDVSDAP
     YQVSLQYNKR HNCGGSVLSS KWVLTAAHCT AGASPSSLTV RLGTSRHASG GTVVRVARVV
     QHPKYDSSSI DFDYSLLELE DELTFSDSVQ PVGLPKQDET VKDGTMTTVS GWGNTQSAAE
     SNAVLRAANV PTVNQKECNK AYSEFGGVTD RMLCAGYQQG GKDACQGDSG GPLVADGKLV
     GVVSWGYGCA QAGYPGVYSR VAVVRDWVRE NSGV
//