fn3.sto

这是一个基于HMM 模型的生物多序列比对算法的linux实现版本。hmmer

#=GS PTPB_HUMAN/907-984   AC    P23467
#=GS PTPB_HUMAN/112-192   AC    P23467
#=GS IL7R_HUMAN/129-221   AC    P16871
#=GS FINC_BOVIN/689-768   AC    P07589
#=GS KALM_CHICK/178-271   AC    P33005
#=GS TENA_HUMAN/1529-1608 AC    P24821
#=GS TENA_CHICK/1227-1306 AC    P10039
#=GS TENA_CHICK/1136-1215 AC    P10039
#=GS TENA_HUMAN/1255-1335 AC    P24821
#=GS TENA_CHICK/1045-1124 AC    P10039
#=GS 7LES_DROVI/1917-1997 AC    P20806
#=GS PTPB_HUMAN/22-103    AC    P23467
#=GS KALM_CHICK/544-642   AC    P33005

#=GS ITB4_HUMAN/1220-1310    DR PDB; 1qg3 A; 1220; 1310;
#=GS ITB4_HUMAN/1220-1310    DR PDB; 1qg3 B; 1220; 1310;
#=GS ITB4_HUMAN/1127-1208    DR PDB; 1qg3 A; 1127; 1208;
#=GS ITB4_HUMAN/1127-1208    DR PDB; 1qg3 B; 1127; 1208;
#=GS    NRG_DROME/717-799    DR PDB; 1cfb ; 717; 799;

EPA1_HUMAN/333-435                P.SAP.RNLSFSA...SGTQLSLRWEPPAD..TGGRQDVRYSVRCS..QC
EPA2_HUMAN/329-420                P.SAP.HYLTAVGM..GA.KVELRWTPPQD..SGGREDIVYSVTCEQCWP
EPA3_CHICK/325-421                P.SAP.RNV.ISNI..NETSVILDWSWPLD..TGGRKDVTFNIIC...KK
EPB2_CHICK/326-422                P.SAP.QAV.ISSV..NETSLMLEWTPPRD..SGGREDLVYNIIC...KS
NRCA_CHICK/623-709                P.NPP.LDLELTGQ..LERSIELSWVPGEE...NNSPITNFVIEY...ED
MYPF_CHICK/630-716                P.DPP.QSVRVTSV..GEDWAVLSWEAPPF..DGGMPITGYLMER...KK
MPSF_CHICK/801-887                P.GPA.YDLTVCEV..RNTSLVLLWKAPVY..EGKSPITGYLVDY...KE
MPSF_CHICK/699-785                P.SYP.HGITLLNC..DGHSMTLGWKAPKY..SGGSPILGYYIDKR...E
MPSF_CHICK/499-585                P.GPP.TNVHASEI..SKTYVVLSWDPPVP...RGREPLTYFIEK...SM
MPSF_CHICK/371-457                P.GAP.MDVKCHDA..NRDYVIVTWKPPNT..TSQNPVIGYFVDK...CE
KMLS_CHICK/1318-1403              P.DPPAGTPCASDI..RSSSLTLSWYGSSY..DGGSAVQSYTVEI...WN
AXO1_CHICK/602-692                PPGPP.GGVVVRDI..GDTTVQLSWSRGFD...NHSPIARYSIEAR...T
MPSF_CHICK/600-684                P.SAP.GRVVATRN..TKTSVVVQWDKPK....HEENLYGYYIDY...SV
LAR_DROME/322-404                 P.TAP.TDVQISEV..TATSVRLEWSYK.....GPEDLQYYVIQY...KP
MYPF_CHICK/923-1008               P.GPP.QAVRVMEV..WGSNALLQWEPPKD..DGNAEISGYTVQK...AD
TIE1_HUMAN/644-729                P.PAP.RHLHAQAL..SDSEIQLTWKHPEA...LPGPISKYVVEV...QV
NCA1_BOVIN/509-597                P.SSP.SIDQVEP...YSSTAQVQFDEPEA..TGGVPILKYKAEWR...A
EPA4_MOUSE/441-525                P.SSI.ALVQAKEV..TRYSVALAWLEPDR...PNGVILEYEVKY...YE
EPB2_CHICK/437-521                P.SAV.SIMHQVSR..TVDSITLSWSQPDQ...PNGVILDYELQY...YE
NRCA_CHICK/928-1014               P.SPP.SFLKITNP..TLDSLTLEWGSPTH...PNGVLTSYILKF...QP
LAR_DROME/909-995                 PGGPP.SNITIRFQ..TPDVLCVTWDPPTRE.HRNGIITRYDVQFH..KK
ITB4_HUMAN/1641-1728              P.SAP.GPLVFTAL..SPDSLQLSWERPRR...PNGDIVGYLVTC...EM
ITB4_HUMAN/1528-1612              P.DTP.TRLVFSAL..GPTSLRVSWQEPR....CERPLQGYSVEY...QL
ITB4_HUMAN/1220-1310              P.SEP.GRLAFNVV..SSTVTQLSWAEPAE...TNGEITAYEVCY...GL
#=GR ITB4_HUMAN/1220-1310 SS     C.CCC.CEEEEEEC..CTTCCEEEEECCCS...CCCCEEEEEEEC...TT
#=GR ITB4_HUMAN/1220-1310 SA     6.221.36423442..44332211135347...864302212113...76
PTP9_DROME/171-259                P.SKP.QNLTILDV..SANSITMSWHPPKN...QNGAIAGYHVFH...IH
LAR_DROME/709-800                 P.GDP.QDVKATPL..NSTSIHVSWKPPLEK.DRNGIIRGYHIHA...QE
LAR_DROME/417-503                 E.SAP.RNVQVRTL..SSSTMVITWEPPET...PNGQVTGYKV.Y...YT
EPA2_HUMAN/436-519                Q.TEP.PKVRLEGR..STTSLSVSWSIPPP...QQSRVWKYEVTYR...K
ITB4_HUMAN/1127-1208              L.GAP.QNPNAKAA..GSRKIHFNWLPP......SGKPMGYRVKY...WI
#=GR ITB4_HUMAN/1127-1208 SS     C.CCC.CEEEEEEC..CTTCCEEEEECC......CSCCCCEEEEE...EE
#=GR ITB4_HUMAN/1127-1208 SA     6.221.36423442..443322111353......47864302212...11
CONT_CHICK/799-884                PTEVP.TDVSVKVL..SSSEISVSWHHVT.....EKSVEGYQIRY...WA
AXO1_CHICK/807-896                PKVAP.FRVTAKAV..LSSEMDVSWEPVEQG.DMTGVLLGYEIRY...WK
CAML_HUMAN/812-907                P.QAI.PELEGIEIL.NSSAVLVKWRPVDLA.QVKGHLRGYNVTY...WR
PTP1_DROME/958-1044               P.GRV.ERFHPTDV..QPSEINFEWSLPSS..EANGVIRQFSIAY...TN
NRG_DROME/917-1007                P.SPV.QGLDAYPL..GSSAFMLHWKKPLY...PNGKLTGYKIYY...EE
TENA_CHICK/1494-1571              L.DAP.KDLSATEV..QSETAVITWRPP......RAPVTDYLLTY...ES
TENA_CHICK/956-1033               L.DNP.KDLEVSDP..TETTLSLRWRRP......VAKFDRYRLTY...VS
TENA_CHICK/1406-1483              L.DSP.SGLVVMNI..TDSEALATWQPA......IAAVDNYIVSY...SS
TENA_CHICK/774-853                L.DAP.SQIEAKDV..TDTTALITWSKP......LAEIEGIELTY...GP
TENA_CHICK/1317-1395              V.GSP.KGISFSDI..TENSATVSWTPP......RSRVDSYRVSY...VP
FINC_BOVIN/1327-1406              L.DSP.SGIDFSDI..TANSFTVHWIAP......RATITGYRIRHH...P
FINC_RAT/1266-1346                V.PQL.TDLSFVDI..TDSSIGLRWTPLN.....SSTIIGYRITV...VA
TENA_CHICK/864-945                L.DAP.RNLKRVSQ..TDNSITLEWKNS......HANIDNYRIKF...AP
FINC_BOVIN/780-858                P.DAP.PDPTVDQV..DDTSIVVRWSRP......RAPITGYRIVY...SP
FINC_BOVIN/1782-1861              I.DAP.SNLRFLAT..TPNSLLVSWQPP......RARITGYIIKY...EK
FINC_BOVIN/1417-1499              S.DVP.RDLEVIAA..TPTSLLISWDAP......AVTVRYYRITY...GE
FINC_BOVIN/1601-1680              I.PAP.TNLKFTQV..TPTSLTAQWTAP......NVQLTGYRVRV...TP
FINC_BOVIN/1511-1590              I.DKP.SQMQVTDV..QDNSISVRWLPS......SSPVTGYRVTT...AP
FINC_BOVIN/875-955                KVPPP.RDLQFVEV..TDVKITIMWTPP......ESPVTGYRVDV...IP
TENA_CHICK/593-671                V.SPP.TELTVTNV..TDKTVNLEWKHE.......NLVNEYLVTY...VP
FINC_BOVIN/1693-1771              V.SPP.RRARVTDA..TETTITISWRTK......TETITGFQVDA...IP
FINC_BOVIN/1142-1225              PLSPP.TNLHLEANP.DTGVLTVSWERST.....TPDITGYRITT...TP
PTP1_DROME/405-485                P.LPV.RNLRSINDD.KTNTMIITWEADP.....ASTQDEYRIVYHE.LE
FINC_BOVIN/1236-1316              V.PPP.TDLRFTNV..GPDTMRVTWAPPS.....SIELTNLLVRY...SP
PHB_ALCFA/344-418                 G.SAP.TGLAVTAT..TSTSVSLSWNAV.......ANASSYGV.YR....
CHIX_STROI/169-240                P.PAPPTGLRTGSV..TATSVALSWSPV.......TGATGYAV.YR....
CHIT_STRLI/142-219                P.SAP.GTPTASNI..TDTSVKLSWSAAT....DDKGVKNYDV.LR....
GUNB_CELFI/651-733                P.TTP.GTPVATGV..TTVGASLSWAASTD...AGSGVAGYEL.YR...V
CHI1_BACCI/465-542                P.SVP.GNARSTGV..TANSVTLAWNAST....DNVGVTGYNV.YN....
APU_THETY/1165-1248               P.TAP.V.LQQPGI..ESSRVTLNWSPSA....DDVAIFGYEIYK...SS
APU_THETY/928-1009                A.PQPITDLKAVS...GNGKVDLSWSVV.......DKAVSYNI.YR...S
FINC_BOVIN/577-660                T.SGP.VQVIITETPSQPNSHPIQWSAPE.....SSHISKYILRW...KP
NRG_DROME/815-905                 PLDAP.TNFTMRQIT.SSTSGYMAWTPVSEE.SVRGHFKGYKIQT...WT
PTP6_DROME/332-425                Y.DPI.FIPKVETTGSTASTITIGWNPPPP..DLIDYIQYYELIV...SE
FAS2_SCHAM/530-616                P.SAV.LQVKMDVM..TATTVTFKFFGPGN..DGGLPTKNYAVQY...KQ
PTPZ_HUMAN/312-401                S.SEP.ENVQADPE..NYTSLLVTWERPRV..VYDTMIEKFAVLY...QQ
NCA1_BOVIN/610-691                P.SAP.KLEGQMGE..DGNSIKVKLIKQDD...GGSPIRHYLVKYR...A
FAS2_SCHAM/642-735                T.SGT.ENEVVVSP..YPNRYELRWQVPAD...NGEPITHYSVKS...CP
TIE2_HUMAN/543-626                L.PPP.RGLNLLPK..SQTTLNLTWQPIFP...SSEDDFYVEVERR...S
TENA_CHICK/682-767                L.PAP.EGLKFKSV..RETSVQVEWDPL......SISFDGWELVFRNMQK
UFO_HUMAN/327-411                 L.GPP.ENISATR...NGSQAFVHWQEPRA..PLQGTLLGYRLAY...QG
TIE1_HUMAN/545-632                PLLQP.WLEGWHVE..GTDRLRVSWSLPLV..PGPLVGDGFLLRL...WD
7LES_DROME/1799-1891              P.SPP.RNFSVRVL..SPRELEVSWLPPEQ...LRSESVYYTLHW...QQ
NRG_DROME/717-799                 ....P.DNVVGQGT..EPNNLVISWTPMPEI.EHNAPNFHYYVSW...K.
#=GR NRG_DROME/717-799    SS     ....C.CCCCCCCC..EEEEEEECSSEEEEE.EECCCCTTSCCCE...E.
#=GR NRG_DROME/717-799    SA     ....9.84520430..514324538430203.0544233506152...0.
NRCA_CHICK/726-810                ....P.SNVQGIGS..EPDNLVITWESLKGF.QSNGPGLQYKVSWR..QK
NGCA_CHICK/700-794                PERNP.GGVHGEGN..ETGNLVITWEPLPPQ.AWNAPWARYRVQWR...P
TIE2_HUMAN/639-724                P.PQP.ENIKISNI..THSSAVISWTILD.....GYSISSITIRY...KV
LAR_DROME/515-598                 P.SQP.SNFRATDI..GETAVTLQWTKPTH...SSENIVHYELYW...ND
PTP6_DROME/236-321                V.PQV.SIDFAKAV..GANKIYLNWTVND....GNDPIQKFFITL...QE
TIE2_HUMAN/444-529                L.PKPLNAPNVIDT..GHNFAVINISSEPY..FGDGPIKSKKLLY...KP
TIE1_HUMAN/446-533                P.PVPLAAPRLLTK..QSRQLVVSPLVSFS...GDGPISTVRLHYR..PQ
PTPK_MOUSE/290-376                P.PRPIAPPQLLGV..GPTYLLIQLNANSI..IGDGPIILKEVEYR...M
PTPB_HUMAN/1355-1434              P.DKI.QNLHCRPQ..NSTAIACSWIPP......DSDFDGYSIECR...K
PTP1_DROME/583-661                P.NPP.RNMTIETV..RSNSVLVHWSPPE.....SGEFTEYSIRYR...T
PTP1_DROME/312-394                P.LRP.LNVTFDRDFITSNSFRVLWEAPK....GISEFDKYQVSV...AT
PTP1_DROME/217-301                P.NTP.GKFIVWFR..NETTLLVLWQPPY....PAGIYTHYKVSI...EP
PTP1_DROME/123-205                P.DPP.SNLSVQVR..SGKNAIILWSPPT.....QGSYTAFKIKV...LG
PTPB_HUMAN/1261-1344              P.SPP.SLMSFADI..ANTSLAITWKGPP....DWTDYNDFELQW...LP
PTP1_DROME/864-944                P.EPI.TQLHATNI..TDTEISLRWDLP......KGEYNDFDIAY...LT
PTPB_HUMAN/1173-1250              P.ASV.SHLRGSNRN.TTDSLWFNWSPA......SGDFDFYELIL...YN
PTPB_HUMAN/1085-1162              P.AAV.TDLRITEN..STRHLSFRWTAS......EGELSWYNIFL...YN
PTPB_HUMAN/467-543                P.LAV.LQLRVKHA..NETSLSIMWQTP......VAEWEKYIISL...AD
PTPB_HUMAN/995-1074               P.ASV.QGVIADNAY.SSYSLIVSWQKA......AGVAERYDILL...LT
PTPB_HUMAN/731-808                P.DKV.QGVSVSNSA.RSDYLRVSWVHA......TGDFDHYEVTI...KN
PTPB_HUMAN/643-725                P.SSV.SGVTVNNSG.RNDYLSVSWLVA......PGDVDNYEVTL...SH
PTPB_HUMAN/554-632                P.AQV.TDLHVANQG.MTSSLFTNWTQA......QGDVEFYQVLL...IH
PTPB_HUMAN/907-984                P.SAV.KNIHISPNG.ATDSLTVNWTPG......GGDVDSYTVSA...FR
PTPB_HUMAN/112-192                P.PAR.FGVSKEKT..TSTGLHVWWTPS......SGKVTSYEVQL...FD
IL7R_HUMAN/129-221                P.EAP.FDLSVIYRE.GANDFVVTFNTSHLQ.KKYVKVLMHDVAYR..QE
FINC_BOVIN/689-768                P.VVA.TSESVTEI..TASSFVVSWVSA......SDTVSGFRVEY...EL
KALM_CHICK/178-271                P.LKPRKELKFIEL..QSGDLEVKWSSKFN...ISIEPVIYVVQRR..WN
TENA_HUMAN/1529-1608              L.PLL.ENLTISDI..NPYGFTVSWMAS......ENAFDSFLVTV...VD
TENA_CHICK/1227-1306              E.PEV.DNLLVSDA..TPDGFRLSWTAD......DGVFDSFVLKIR..DT
TENA_CHICK/1136-1215              H.PEV.GELTVSDI..TPESFNLSWTTT......NGDFDAFTIEI...ID
TENA_HUMAN/1255-1335              E.VPDMGNLTVTEV..SWDALRLNWTTP......DGTYDQFTIQV...QE
TENA_CHICK/1045-1124              E.PEL.GNLSVSET..GWDGFQLTWTAA......DGAYENFVIQV...QQ
7LES_DROVI/1917-1997              S.YAPLPPLQLIEL..NAYGMTLAWPGT......PDALSSLTLEC...QS
PTPB_HUMAN/22-103                 AEPER.CNFTLAESKASSHSVSIQWRIL.......GSPCNFSLIY...SS
KALM_CHICK/544-642                L.AKP.ENLSASFIV.QEGNITGHFSWKISKAVLHQPMTGFQVTW...AE
#=GC SS_cons                      C.CCC.CEEEEEEC..CTTCCEEEEECCCCE.ECCCCCCCEEEEE...EC
#=GC SA_cons                      6.224.55422441..433323223342343.0755433303122...34
#=GC seq_cons                     P.ssP.pslphpsh..sssslplsWpss......suslssYplph....p

EPA1_HUMAN/333-435                QGTAQDGGPCQPCGVGVHFSPGARALT....TP..AVHVNGLEPYANYTF
EPA2_HUMAN/329-420                E.SGECGP....CEASVRYS...EPPHGL.TRT..SVTVSDLEPHMNYTF
EPA3_CHICK/325-421                CGGSSKICE...PCSDNVRF...LPRQTG.LTNT.TVTVVDLLAHTNYTF
EPB2_CHICK/326-422                CGSGRGACT...RCGDNVQF...APRQLGLTEP..RIYISDLLAHTQYTF
NRCA_CHICK/623-709                GLHEPG........VWHYQT...EVPG....SH..TTVQLKLSPYVNYSF
MYPF_CHICK/630-716                KGSMRW........MKLNFE...VFPD....T...TYESTKMIEGVFYEM
MPSF_CHICK/801-887                VDTED..........WITAN...EKPT....SHR.YFKVTDLHQGHTYVF
MPSF_CHICK/699-785                ANHKN..........WHEVNSSVISRT....I....YTVEDLTEDAFYEF
MPSF_CHICK/499-585                VGSGS..........WQRVNAQVAVKS....P...RYAVFDLAEGKPYVF
MPSF_CHICK/371-457                VGLEN..........WVQCN...DAPV....KIC.KYPVTGLYEGRSYIF
KMLS_CHICK/1318-1403              SVDNK..........WTDLT...TCRS....T...SFNVQDLQADREYKF
AXO1_CHICK/602-692                LLSNKWKQ.....MRTNPVN...IEGN....AE..TAQVVNLIPWMDYEF
MPSF_CHICK/600-684                VGSNQWE.......PANHKP...INYN....R....FVVHGLETGEQYIF
LAR_DROME/322-404                 KNANQ..........AFSEI...SGII....TM..YYVVRALSPYTEYEF
MYPF_CHICK/923-1008               TRTME..........WFTVL...EHSR....PT..RCTVSELVMGNEYRF
TIE1_HUMAN/644-729                AGGAGD.........PLWID...VDRP....EET.STIIRGLNASTRYLF
NCA1_BOVIN/509-597                MGEEVW........HSKWYD...AKEA....SMEGIVTIVGLKPETTYAV
EPA4_MOUSE/441-525                KDQN...........ERSYR...IVRT....AAR.NTDIKGLNPLTSYVF
EPB2_CHICK/437-521                KNLSE..........LNSTA...VKSP....TN..TVTVQNLKAGTIYVF
NRCA_CHICK/928-1014               INNTHEL......GPLVEIR...IPAN....ES..SLILKNLNYSTRYKF
LAR_DROME/909-995                 IDHGL..........GSERN...MTLR....K....AVFTNLEENTEYIF
ITB4_HUMAN/1641-1728              AQGGGPA.......TAFRVD...GDSP....ES..RLTVPGLSENVPYKF
ITB4_HUMAN/1528-1612              LNGGE..........LHRLN...IPNP....AQT.SVVVEDLLPNHSYVF
ITB4_HUMAN/1220-1310              VNDDNRPI.....GPMKKVL...VDNP....KNR.MLLIENLRESQPYRY
#=GR ITB4_HUMAN/1220-1310 SS     CCGGCCEE.....EECSSCE...EECC....CCC.TCCEEEEEEEEECTC
#=GR ITB4_HUMAN/1220-1310 SA     44673454.....4346432...3227....543.223211110011586
PTP9_DROME/171-259                DNQTGVE......IVKNSRN...SVET....LI..HFELQNLRPYTDYRV
LAR_DROME/709-800                 LRDEGKGF....LNEPFKFD...VVDT....L...EFNVTGLQPDTKYSI
LAR_DROME/417-503                 TNSNQPE......ASWNSQM...VDNS....E...LTTVSDVTPHAIYTV
EPA2_HUMAN/436-519                KGDS............NSYN...VRRT....EGF.SVTLDDLAPDTTYLV
ITB4_HUMAN/1127-1208              QGDSES.........EAHLL...DSKV....P...SVELTNLYPYCDYEM
#=GR ITB4_HUMAN/1127-1208 SS     CTTCCG.........GCCEE...EECS....S...CEEECCCCCTCCEEE
#=GR ITB4_HUMAN/1127-1208 SA     376446.........73454...4346....4...323227543223211
CONT_CHICK/799-884                AHDKEA........AAQRVQ...VSNQ....EY..STKLENLKPNTRYHI
AXO1_CHICK/807-896                DGDKEEA.......ADRVRT...AGLV....T...SAHVTGLNPNTKYHV
CAML_HUMAN/812-907                EGSQRKHSK..RHIHKDHVV...VPAN....TT..SVILSGLRPYSSYHL
PTP1_DROME/958-1044               INNLT..........DAGMQ...DFES....EEA.FGVIKNLKPGETYVF
NRG_DROME/917-1007                V.KESYVGE..RREYDPHIT...DPRV....T...RMKMAGLKPNSKYRI
TENA_CHICK/1494-1571              I.DGR..........VKEVI...LDPE....TT..SYTLTELSPSTQYTV
TENA_CHICK/956-1033               P.SGK..........KNEME...IPVD....ST..SFILRGLDAGTEYTI
TENA_CHICK/1406-1483              EDEP...........EVTQM...VSGN....TV..EYDLNGLRPATEYTL
TENA_CHICK/774-853                KDVPGD.........RTTID...LSED....EN..QYSIGNLRPHTEYEV
TENA_CHICK/1317-1395              ITGGT..........PNVVT...VDGS....KT..RTKLVKLVPGVDYNV
FINC_BOVIN/1327-1406              ENMGGR.........PREDR...VPPS....RN..SITLTNLNPGTEYVV
FINC_RAT/1266-1346                AGEGIP.........IFEDF...VDSS....VG..YYTVTGLEPGIDYDI
TENA_CHICK/864-945                ISGGD..........HTELT...VPKGNQ.ATT..RATLTGLRPGTEYGI
FINC_BOVIN/780-858                SVEGS..........STELN...LPET....AN..SVTLSDLQPGVQYNI
FINC_BOVIN/1782-1861              PGSPPR........EVVPRP...RPGV....T...EATITGLEPGTEYTI
FINC_BOVIN/1417-1499              TGGSSP.........VQEFT...VPGS....KS..TATISGLKPGVDYTI
FINC_BOVIN/1601-1680              KEKTGP.........MKEIN...LAPD....SS..SVVVSGLMVATKYEV