make -k T0124-blast.rdb T0124-double-blast.rdb make[1]: Entering directory `/export/projects/compbio/experiments/casp4/t124' /projects/compbio/experiments/casp4/scripts/single-blast -q T0124.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0124-blast.rdb starting T0124 with E=10 /projects/compbio/experiments/casp4/scripts/double-blast -q T0124.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0124-double-blast.rdb starting T0124 with E=0.000050 T0124 T0124 blasting: T0124 gi|586121|sp|P37709|TRHY_RABIT_586:795 blasting: T0124 gi|586121|sp|P37709|TRHY_RABIT_630:860 blasting: T0124 gi|627059|pir||A45592_163:381 blasting: T0124 gi|627059|pir||A45592_282:500 blasting: T0124 gi|627059|pir||A45592_367:585 blasting: T0124 gi|627059|pir||A45592_554:772 blasting: T0124 gi|627059|pir||A45592_639:857 blasting: T0124 gi|627059|pir||A45592_384:592 blasting: T0124 gi|627059|pir||A45592_860:1068 blasting: T0124 gi|627059|pir||A45592_197:415 blasting: T0124 gi|627059|pir||A45592_1149:1367 blasting: T0124 gi|627059|pir||A45592_350:568 blasting: T0124 gi|627059|pir||A45592_707:925 blasting: T0124 gi|627059|pir||A45592_826:1044 blasting: T0124 gi|627059|pir||A45592_877:1077 blasting: T0124 gi|3929365|sp|Q26005|RESA_PLAFP_70:296 blasting: T0124 gi|11067|emb|CAA46548.1|_131:361 blasting: T0124 gi|284352|pir||S27002_850:1014 blasting: T0124 gi|284352|pir||S27002_763:1004 blasting: T0124 gi|1708901|sp|P50468|M21_STRPY_68:259 blasting: T0124 gi|86369|pir||S03166_1018:1235 blasting: T0124 gi|86369|pir||S03166_1029:1274 blasting: T0124 gi|86360|pir||A02990_107:326 blasting: T0124 gi|86362|pir||S06117_544:746 blasting: T0124 gi|86362|pir||S06117_378:587 blasting: T0124 gi|130221|sp|P10894|PIP1_BOVIN_939:1170 blasting: T0124 gi|130221|sp|P10894|PIP1_BOVIN_902:1135 blasting: T0124 gi|130223|sp|P10687|PIP1_RAT_939:1170 blasting: T0124 gi|130223|sp|P10687|PIP1_RAT_902:1135 blasting: T0124 gi|127759|sp|P14105|MYSN_CHICK_1005:1234 blasting: T0124 gi|127759|sp|P14105|MYSN_CHICK_822:1052 blasting: T0124 gi|109322|pir||A41604_1012:1232 blasting: T0124 gi|111999|pir||S21801_1004:1233 blasting: T0124 gi|124727|sp|P24708|INVO_AOTTR_295:507 blasting: T0124 gi|124727|sp|P24708|INVO_AOTTR_194:412 blasting: T0124 gi|124727|sp|P24708|INVO_AOTTR_247:468 blasting: T0124 gi|124727|sp|P24708|INVO_AOTTR_174:399 blasting: T0124 gi|124727|sp|P24708|INVO_AOTTR_150:388 blasting: T0124 gi|124729|sp|P24709|INVO_CEBAL_174:391 blasting: T0124 gi|124734|sp|P14591|INVO_PANPA_150:376 blasting: T0124 gi|124737|sp|P24712|INVO_SAGOE_193:417 blasting: T0124 gi|124737|sp|P24712|INVO_SAGOE_232:456 blasting: T0124 gi|124737|sp|P24712|INVO_SAGOE_149:356 blasting: T0124 gi|159333|gb|AAA20179.1|_20:207 blasting: T0124 gi|283424|pir||B38145_294:441 blasting: T0124 gi|161950|gb|AAA30149.1|_96:243 blasting: T0124 gi|1346644|sp|P35748|MYST_RABIT_1012:1232 blasting: T0124 gi|171959|gb|AAA34783.1|_1374:1606 blasting: T0124 gi|171959|gb|AAA34783.1|_1243:1471 blasting: T0124 gi|2144796|pir||I36912_1:210 blasting: T0124 gi|2144796|pir||I36912_80:295 blasting: T0124 gi|2144796|pir||I36912_50:265 blasting: T0124 gi|189036|gb|AAA36349.1|_291:520 blasting: T0124 gi|189036|gb|AAA36349.1|_108:338 blasting: T0124 gi|189036|gb|AAA36349.1|_834:1049 blasting: T0124 gi|212449|gb|AAA48985.1|_1012:1214 blasting: T0124 gi|212449|gb|AAA48985.1|_846:1055 blasting: T0124 gi|212450|gb|AAA48986.1|_1022:1224 blasting: T0124 gi|212450|gb|AAA48986.1|_856:1065 blasting: T0124 gi|212451|gb|AAA48987.1|_1033:1235 blasting: T0124 gi|212451|gb|AAA48987.1|_867:1076 blasting: T0124 gi|476389|pir||B43402_1043:1245 blasting: T0124 gi|476389|pir||B43402_877:1086 blasting: T0124 gi|422615|pir||A47297_1013:1229 blasting: T0124 gi|422615|pir||A47297_1086:1317 blasting: T0124 gi|226908|prf||1611219A_939:1170 blasting: T0124 gi|226908|prf||1611219A_902:1135 blasting: T0124 gi|586120|sp|Q07283|TRHY_HUMAN_502:721 blasting: T0124 gi|586120|sp|Q07283|TRHY_HUMAN_400:618 blasting: T0124 gi|586122|sp|P22793|TRHY_SHEEP_460:686 blasting: T0124 gi|586122|sp|P22793|TRHY_SHEEP_430:663 blasting: T0124 gi|586122|sp|P22793|TRHY_SHEEP_428:638 blasting: T0124 gi|586122|sp|P22793|TRHY_SHEEP_486:716 blasting: T0124 gi|422888|pir||S32763_695:920 blasting: T0124 gi|422888|pir||S32763_409:653 blasting: T0124 gi|1079311|pir||A48001_920:1162 blasting: T0124 gi|2134903|pir||I53799_696:921 blasting: T0124 gi|2134903|pir||I53799_410:654 blasting: T0124 gi|2134313|pir||I50590_503:700 blasting: T0124 gi|1708493|sp|P53352|INCE_CHICK_503:700 blasting: T0124 gi|419650|pir||S30283_124:330 blasting: T0124 gi|422336|pir||S33068_131:361 blasting: T0124 gi|423977|pir||A45493_1013:1171 blasting: T0124 gi|437639|gb|AAA72295.1|_44:274 blasting: T0124 gi|437639|gb|AAA72295.1|_41:243 blasting: T0124 gi|467292|gb|AAA17387.1|_333:534 blasting: T0124 gi|467292|gb|AAA17387.1|_333:534 blasting: T0124 gi|467292|gb|AAA17387.1|_353:567 blasting: T0124 gi|1078373|pir||B54128_75:303 blasting: T0124 gi|1363432|pir||S49551_85:279 blasting: T0124 gi|7441640|pir||JC5837_1878:2112 blasting: T0124 gi|1176553|sp|P46504|YLX8_CAEEL_341:558 blasting: T0124 gi|1176553|sp|P46504|YLX8_CAEEL_421:625 blasting: T0124 gi|1176553|sp|P46504|YLX8_CAEEL_307:547 blasting: T0124 gi|2144790|pir||I37060_224:449 blasting: T0124 gi|548352|sp|P35616|NFL_XENLA_59:288 blasting: T0124 gi|553596|gb|AAA59888.1|_1005:1234 blasting: T0124 gi|553596|gb|AAA59888.1|_822:1052 blasting: T0124 gi|1722856|sp|P50533|XCPE_XENLA_671:890 blasting: T0124 gi|608483|gb|AAA85818.1|_747:993 blasting: T0124 gi|625305|pir||A61231_1005:1234 blasting: T0124 gi|625305|pir||A61231_822:1052 blasting: T0124 gi|625305|pir||A61231_1548:1763 blasting: T0124 gi|1346640|sp|P35580|MYSO_HUMAN_1012:1236 blasting: T0124 gi|1346640|sp|P35580|MYSO_HUMAN_846:1055 blasting: T0124 gi|677198|gb|AAB00143.1|_450:659 blasting: T0124 gi|2119533|pir||I52300_1922:2145 blasting: T0124 gi|1730573|sp|Q01970|PIP3_HUMAN_1033:1197 blasting: T0124 gi|1730573|sp|Q01970|PIP3_HUMAN_946:1187 blasting: T0124 gi|7496461|pir||T15598_299:503 blasting: T0124 gi|7496462|pir||T15597_299:503 blasting: T0124 gi|1083573|pir||A53430_939:1151 blasting: T0124 gi|1083573|pir||A53430_902:1135 blasting: T0124 gi|1173565|gb|AAC51791.1|_195:416 blasting: T0124 gi|1173565|gb|AAC51791.1|_718:954 blasting: T0124 gi|2134446|pir||S68251_913:1154 blasting: T0124 gi|2134446|pir||S68251_880:1094 blasting: T0124 gi|1236759|emb|CAA58041.1|_340:561 blasting: T0124 gi|1236759|emb|CAA58041.1|_863:1099 blasting: T0124 gi|1289512|gb|AAC59911.1|_1090:1319 blasting: T0124 gi|7447790|pir||S70553_270:486 blasting: T0124 gi|1353761|gb|AAB01786.1|_222:444 blasting: T0124 gi|1354362|gb|AAB06613.1|_65:264 blasting: T0124 gi|1389568|dbj|BAA06608.1|_91:320 blasting: T0124 gi|1477559|gb|AAC47238.1|_1056:1281 blasting: T0124 gi|2498458|sp|P75471|HMW2_MYCPN_1373:1610 blasting: T0124 gi|7441402|pir||JC5420_1012:1232 blasting: T0124 gi|7441402|pir||JC5420_841:1088 blasting: T0124 gi|6166600|sp|P35749|MYST_HUMAN_897:1117 blasting: T0124 gi|6166600|sp|P35749|MYST_HUMAN_731:973 blasting: T0124 gi|2129174|pir||A64505_697:925 blasting: T0124 gi|2129174|pir||A64505_692:911 blasting: T0124 gi|2129174|pir||A64505_251:495 blasting: T0124 gi|2246532|gb|AAB62657.1|_625:858 blasting: T0124 gi|2246532|gb|AAB62657.1|_651:864 blasting: T0124 gi|2246532|gb|AAB62657.1|_625:844 blasting: T0124 gi|2246532|gb|AAB62657.1|_622:822 blasting: T0124 gi|2253417|gb|AAD09135.1|_781:1027 blasting: T0124 gi|7464160|pir||G64534_121:254 blasting: T0124 gi|7507856|pir||T32251_53:280 blasting: T0124 gi|7506052|pir||T32297_525:773 blasting: T0124 gi|7531285|sp|P51834|SMC_BACSU_169:386 blasting: T0124 gi|7451889|pir||H69378_237:479 blasting: T0124 gi|2674350|gb|AAB88727.1|_81:303 blasting: T0124 gi|7463576|pir||G70241_33:254 blasting: T0124 gi|7463576|pir||G70241_33:254 blasting: T0124 gi|7511962|pir||T13030_638:856 blasting: T0124 gi|2826443|gb|AAB99663.1|_697:925 blasting: T0124 gi|2826443|gb|AAB99663.1|_692:911 blasting: T0124 gi|2826443|gb|AAB99663.1|_251:495 blasting: T0124 gi|7446603|pir||B70356_340:550 blasting: T0124 gi|7514430|pir||A70387_207:404 blasting: T0124 gi|7514430|pir||A70387_219:460 blasting: T0124 gi|3043686|dbj|BAA25507.1|_421:652 blasting: T0124 gi|3043686|dbj|BAA25507.1|_384:617 blasting: T0124 gi|3044185|gb|AAC13303.1|_980:1220 blasting: T0124 gi|7491657|pir||T40387_16:224 blasting: T0124 gi|7494881|pir||T33283_675:785 blasting: T0124 gi|7494881|pir||T33283_522:556 blasting: T0124 gi|6166599|sp|P35579|MYSN_HUMAN_1005:1234 blasting: T0124 gi|6166599|sp|P35579|MYSN_HUMAN_822:1052 blasting: T0124 gi|6166599|sp|P35579|MYSN_HUMAN_1547:1762 blasting: T0124 gi|3205211|gb|AAC19403.1|_207:422 blasting: T0124 gi|3282557|gb|AAC24984.1|_468:707 blasting: T0124 gi|7489885|pir||T14867_1029:1253 blasting: T0124 gi|3660672|gb|AAC83556.1|_1005:1207 blasting: T0124 gi|3688530|emb|CAA09465.1|_898:1149 blasting: T0124 gi|3688530|emb|CAA09465.1|_878:1120 blasting: T0124 gi|7494280|pir||C71622_662:881 blasting: T0124 gi|7499530|pir||T21174_997:1216 blasting: T0124 gi|7499530|pir||T21174_1073:1298 blasting: T0124 gi|3915778|sp|P10587|MYSG_CHICK_1018:1235 blasting: T0124 gi|3915778|sp|P10587|MYSG_CHICK_1029:1274 blasting: T0124 gi|3941223|gb|AAC82221.1|_130:361 blasting: T0124 gi|4006911|emb|CAB16841.1|_632:859 blasting: T0124 gi|4099293|gb|AAD00571.1|_939:1170 blasting: T0124 gi|4099293|gb|AAD00571.1|_902:1135 blasting: T0124 gi|7489869|pir||T30330_703:872 blasting: T0124 gi|7489869|pir||T30330_558:576 blasting: T0124 gi|7489869|pir||T30330_561:580 blasting: T0124 gi|4102980|gb|AAD09328.1|_49:263 blasting: T0124 gi|4102980|gb|AAD09328.1|_33:263 blasting: T0124 gi|4115748|dbj|BAA36494.1|_1012:1236 blasting: T0124 gi|4115748|dbj|BAA36494.1|_846:1055 blasting: T0124 gi|4218005|gb|AAD12213.1|_408:633 blasting: T0124 gi|4240221|dbj|BAA74889.1|_1012:1232 blasting: T0124 gi|4240221|dbj|BAA74889.1|_846:1088 blasting: T0124 gi|4417214|dbj|BAA36971.1|_126:346 blasting: T0124 gi|4490537|emb|CAA73095.1|_781:1027 blasting: T0124 gi|4589644|dbj|BAA76844.1|_614:856 blasting: T0124 gi|4850405|gb|AAD31075.1|AC007357_24_450:666 blasting: T0124 gi|7512738|pir||T08700_81:325 blasting: T0124 gi|4894766|gb|AAD32609.1|AF128539_1_883:1107 blasting: T0124 gi|5052632|gb|AAD38646.1|AF145671_1_516:744 blasting: T0124 gi|5669894|gb|AAD46501.1|AF148805_6_697:898 blasting: T0124 gi|5669894|gb|AAD46501.1|AF148805_6_720:904 blasting: T0124 gi|5689499|dbj|BAA83033.1|_251:494 blasting: T0124 gi|7511518|pir||T37264_1282:1408 blasting: T0124 gi|7511518|pir||T37264_1129:1163 blasting: T0124 gi|6179894|gb|AAF05701.1|AF179426_1_1295:1421 blasting: T0124 gi|6179894|gb|AAF05701.1|AF179426_1_1130:1164 blasting: T0124 gi|6329742|dbj|BAA86438.1|_80:296 blasting: T0124 gi|6525240|gb|AAF15366.1|AF206632_1_11:229 blasting: T0124 gi|6598483|gb|AAC69932.2|_164:396 blasting: T0124 gi|6636514|gb|AAF20208.1|AF207901_1_914:1150 blasting: T0124 gi|6681583|dbj|BAA88763.1|_422:633 blasting: T0124 gi|6687775|emb|CAB65622.1|_386:581 blasting: T0124 gi|6692690|gb|AAF24824.1|AC007592_17_60:260 blasting: T0124 gi|6752411|gb|AAF27716.1|AF071821_1_94:348 blasting: T0124 gi|6807696|emb|CAB70664.1|_398:618 blasting: T0124 gi|6807700|emb|CAB70666.1|_679:891 blasting: T0124 gi|6807700|emb|CAB70666.1|_642:875 blasting: T0124 gi|7018360|emb|CAB75615.1|_2:205 blasting: T0124 gi|7243049|dbj|BAA92572.1|_725:969 blasting: T0124 gi|7274242|gb|AAF44722.1|AF155135_1_716:960 blasting: T0124 gi|7292701|gb|AAF48098.1|_1421:1640 blasting: T0124 gi|7292701|gb|AAF48098.1|_1360:1606 blasting: T0124 gi|7293082|gb|AAF48467.1|_577:806 blasting: T0124 gi|7293243|gb|AAF48625.1|_250:466 blasting: T0124 gi|7296431|gb|AAF51718.1|_374:602 blasting: T0124 gi|7303851|gb|AAF58897.1|_686:905 blasting: T0124 gi|7381235|gb|AAF61445.1|AF139055_1_1012:1236 blasting: T0124 gi|7381235|gb|AAF61445.1|AF139055_1_846:1055 blasting: T0124 gi|9366632|emb|CAB95394.1|_442:643 blasting: T0124 gi|9367293|emb|CAB97309.1|_334:551 blasting: T0124 gi|9368448|emb|CAB98142.1|_939:1170 blasting: T0124 gi|9368448|emb|CAB98142.1|_902:1135 blasting: T0124 gi|9368450|emb|CAB98143.1|_939:1151 blasting: T0124 gi|9368450|emb|CAB98143.1|_902:1135 blasting: T0124 gi|9438229|gb|AAF86613.1|_934:1165 blasting: T0124 gi|9438229|gb|AAF86613.1|_897:1130 blasting: make[1]: Leaving directory `/export/projects/compbio/experiments/casp4/t124' make -k T0124.t2k.a2m.gz \ T0124.t2k.pa \ T0124.t2k.pa.html \ T0124.t2k.2d \ T0124.t2k.tree \ T0124.t2k_sorted.pa \ T0124.t2k.tree.ps \ T0124.t2k.tree-unroot.ps make[1]: Entering directory `/export/projects/compbio/experiments/casp4/t124' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0124.t2k \ -seed T0124.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-1655 @@@@ cp /export/projects/compbio/experiments/casp4/t124/T0124.seq m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:52 # About to count sequences in /projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 0.01, actual: 0.0001 prefilter: 1, actual: 0.0002 prefilter: 10, actual: 0.001 prefilter: 400, actual: 0.005 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.8, 0.7, 0.6, 0.5 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 541007 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: blast_max_report= 20000 /projects/compbio/experiments/models.97/scripts2k/target2k: db=/projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=1 constraints=1 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 @@@@ blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 0.01,1,10,400 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-beta-8632 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-1655/prefilter_1.fa, 0.01 For /export/projects/compbio/tmp/target2k-beta-1655/prefilter_2.fa, 1 For /export/projects/compbio/tmp/target2k-beta-1655/prefilter_3.fa, 10 For /export/projects/compbio/tmp/target2k-beta-1655/prefilter_4.fa, 400 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: db=/projects/compbio/data/nrp/nr @@@@ uniqueseq init -alignfile /export/projects/compbio/tmp/target2k-beta-1655/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/tmp/target2k-beta-1655/m0.a2m (1 sequences, 242 columns) as A2M alignment. Writing sequence output to init.a2m. No sequences have been dropped. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=400 V=20000 B=0 -gi > 1.fasta-blast.out Searched 541007 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-8632 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (1 sequences, 242 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (1 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_1-a -i tmp_1-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -26.4115278685381 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -14.874774 Database has 882 sequences with 894660 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_1-a.mult (15 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_1-a.mstat Writing sequence output to tmp_1-a-sort.a2m. @@@@ cat m0.a2m tmp_1-a-sort.a2m > tmp_1-a.train.seq @@@@ cat m0.cst tmp_1-a-md.cst > tmp_1-a.train.cst # About to count sequences in tmp_1-a.train.seq # num_seqs=16 nll_thresh=-22.4115278685381 frac_id=0.999999339553222 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999999339553222 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_1-a.train.seq (16 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 4 (of 16) duplicate sequences with differing IDs Dropping 3 (of 16) sequences with > 100.0% id 9 sequences left after dropping 7 of 16 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_1-a.train.seq (9 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -654.57 75.37 -209.97 196.72 15 0 243 @@@@ hmmscore tmp_1-b -i tmp_1-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.4115278685381 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(18): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -235.369110 Database has 16 sequences with 17448 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.a2m \ -insert /projects/compbio/lib/stiff-gap5.regularizer \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.a2m (16 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_2-a -i tmp_2-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -25.7183806877933 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_2.fa -constraints tmp_2-a.cst -constraints_out tmp_2-a-md.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ... Average NLL-Simple NULL score: -21.075584 Database has 2584 sequences with 2061299 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_2-a.mult (26 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_2-a.mstat Writing sequence output to tmp_2-a-sort.a2m. @@@@ cat m0.a2m tmp_2-a-sort.a2m > tmp_2-a.train.seq @@@@ cat m0.cst tmp_2-a-md.cst > tmp_2-a.train.cst # About to count sequences in tmp_2-a.train.seq # num_seqs=27 nll_thresh=-21.7183806877933 frac_id=0.999743224724788 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999743224724788 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_2-a.train.seq (27 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 7 (of 27) duplicate sequences with differing IDs Dropping 3 (of 27) sequences with > 100.0% id 17 sequences left after dropping 10 of 27 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-a.train.seq \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_2-a.train.seq (17 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_2-b -insert tmp_2-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_2-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_2-a.w -constraints tmp_2-a.train.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -649.46 -84.79 -232.95 118.35 8 0 243 @@@@ hmmscore tmp_2-b -i tmp_2-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.7183806877933 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(18): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -35.022785 Database has 509 sequences with 581947 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.a2m \ -insert /projects/compbio/lib/stiff-gap5.regularizer \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.a2m (27 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_3-a -i tmp_3-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -24.1089427738805 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_3.fa -constraints tmp_3-a.cst -constraints_out tmp_3-a-md.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ..... Average NLL-Simple NULL score: -22.559532 Database has 4253 sequences with 3098913 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_3-a.mult (35 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_3-a.mstat Writing sequence output to tmp_3-a-sort.a2m. @@@@ cat m0.a2m tmp_3-a-sort.a2m > tmp_3-a.train.seq @@@@ cat m0.cst tmp_3-a-md.cst > tmp_3-a.train.cst # About to count sequences in tmp_3-a.train.seq # num_seqs=36 nll_thresh=-20.1089427738805 frac_id=0.99701066598785 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.99701066598785 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_3-a.train.seq (36 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 9 (of 36) duplicate sequences with differing IDs Dropping 3 (of 36) sequences with > 99.7% id 24 sequences left after dropping 12 of 36 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_3-a.train.seq (24 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_3-b -insert tmp_3-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_3-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_3-a.w -constraints tmp_3-a.train.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -649.40 -76.31 -197.21 104.06 8 0 243 @@@@ hmmscore tmp_3-b -i tmp_3-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.1089427738805 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(18): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) .. Average NLL-Simple NULL score: -28.265829 Database has 1138 sequences with 1034225 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -aweight_bits 0.5\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.a2m (36 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_4-a -i tmp_4-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -22.4995048540528 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_4.fa -constraints tmp_4-a.cst -constraints_out tmp_4-a-md.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ........... Average NLL-Simple NULL score: -12.278717 Database has 10007 sequences with 6060679 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_4-a.mult (40 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_4-a.mstat Writing sequence output to tmp_4-a-sort.a2m. @@@@ cat m0.a2m tmp_4-a-sort.a2m > tmp_4-a.train.seq @@@@ cat m0.cst tmp_4-a-md.cst > tmp_4-a.train.cst # About to count sequences in tmp_4-a.train.seq # num_seqs=41 nll_thresh=-18.4995048540528 frac_id=0.991314790691271 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 0.991314790691271 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_4-a.train.seq (41 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 10 (of 41) duplicate sequences with differing IDs Dropping 8 (of 41) sequences with > 99.1% id 23 sequences left after dropping 18 of 41 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_4-a.train.seq \ -aweight_bits 0.5\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_4-a.train.seq (23 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_4-b -insert tmp_4-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_4-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/fssp-trained.regularizer -sequence_weights tmp_4-a.w -constraints tmp_4-a.train.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_3.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -650.86 -13.99 -176.33 112.34 8 0 243 @@@@ hmmscore tmp_4-b -i tmp_4-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.4995048540528 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.t2k_4.cst Reading parameter file tmp_4-b.mod tmp_4-b.mod(18): Reading MODEL -- Final model for run tmp_4-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -41.084179 Database has 221 sequences with 230136 residues. @@@@ cp -f tmp_4-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.t2k_4.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -aweight_bits 0.5\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.t2k_4.cst -constraints_out tmp_5-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_4.a2m (41 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_5-a -i tmp_5-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -22.4995048540528 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_4.fa -constraints tmp_5-a.cst -constraints_out tmp_5-a-md.cst Reading parameter file tmp_5-a.mod tmp_5-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k_4.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ........... Average NLL-Simple NULL score: -12.592363 Database has 10007 sequences with 6060679 residues. @@@@ sortseq tmp_5-a-sort -alignfile tmp_5-a.mult \ -NLLfile tmp_5-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_5-a.mult (39 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_5-a.mstat Writing sequence output to tmp_5-a-sort.a2m. @@@@ cat m0.a2m tmp_5-a-sort.a2m > tmp_5-a.train.seq @@@@ cat m0.cst tmp_5-a-md.cst > tmp_5-a.train.cst @@@@ cp tmp_5-a.train.seq /export/projects/compbio/experiments/casp4/t124/T0124.t2k.a2m @@@@ cp tmp_5-a.train.cst /export/projects/compbio/experiments/casp4/t124/T0124.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-1655 < /dev/null gzip -f T0124.t2k.a2m T0124.t2k_*.a2m prettyalign T0124.t2k.a2m.gz -m8 -i -n -L3333 > T0124.t2k.pa SAM: prettyalign v3.2 (July 31, 2000) compiled 07/31/00_16:52:38 gunzip -c T0124.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0124.t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.2 (July 31, 2000) compiled 07/31/00_16:52:38 rm tmp.a2m echo ReadNeuralNet /projects/compbio/usr/karplus/predict-2nd/testing/networks/overrep-2500-IDaa13-5-10-7-10-5-10-11-ehl2-seeded9-stride-trained.net > tmp.script echo ReadA2M T0124.t2k.a2m.gz >> tmp.script echo PrintPrediction T0124.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0124.t2k.2d.seq >> tmp.script echo PrintRDB T0124.t2k.2d.rdb >> tmp.script predict-2nd < tmp.script # command:# Neural network set to overrep-2500-IDaa13-5-10-7-10-5-10-11-ehl2-seeded9-stride-trained.net # command:# Reading A2M format from T0124.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0124.t2k.a2m with 40 sequences, total weight= 19.948 avg weight= 0.498701 38 iterations Regularizing alignment for T0124.t2k.a2m.gz # After reading T0124.t2k.a2m.gz, have 242 columns in 1 chains # command:# Initializing Gain for FinalLayer # Initializing Gain for ordering_layer # Initializing Gain for SecondLayer # Initializing Gain for FirstLayer # Network initialization done # Printing prediction to T0124.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0124.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0124.t2k.2d.rdb # command:rm tmp.script gunzip -f T0124.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0124.t2k T0124.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0124.t2k.a2m (40 sequences) as A2M alignment. Alignment T0124.t2k.a2m read. Adding sequences:0 10 20 30 One dot for every 10 merges: .... Merges done. CPU = user 0: 0:33 system 0: 0: 0 gzip -f T0124.t2k.a2m gzip -f T0124.t2k_sorted.a2m rm T0124.t2k.phytrace T0124.t2k.tree_weight prettyalign T0124.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0124.t2k_sorted.pa SAM: prettyalign v3.2 (July 31, 2000) compiled 07/31/00_16:52:38 /projects/compbio/usr/karplus/src/phytree/dg T0124.t2k.tree /projects/compbio/usr/karplus/src/phytree/dtree T0124.t2k.tree make[1]: Leaving directory `/export/projects/compbio/experiments/casp4/t124' echo "WeightingRegularizer /projects/compbio/lib/recode3.20comp" > tmp.script echo "SequenceWeight EntropyWeight 0.5 10.0" >> tmp.script echo "ReadA2M T0124.t2k.a2m.gz" >> tmp.script echo "SavingsRegularizer /projects/compbio/lib/recode3.20comp" >> tmp.script echo "PrintSavings T0124.t2k.saves" >> tmp.script echo "exit" >> tmp.script estimate-dist < tmp.script # command:Weighting regularizer set to recode3.20comp # command:Sequence weighting on input set to EntropyWeight(0.5, 10) # command:Reading A2M format from T0124.t2k.a2m.gz % using regularizer recode3.20comp % T0124.t2k.a2m.gz with 40 sequences, total weight= 3.91091 avg weight= 0.0977726 After reading T0124.t2k.a2m.gz, have 242 columns, totalling 869.245 Using SequenceWeight EntropyWeight(0.5, 10) Using regularizer recode3.20compfor sequence weight regularizer. # command:Savings regularizer set to recode3.20comp # command:% Computing savings using regularizer recode3.20comp Printed 242 columns to T0124.t2k.saves # command:rm tmp.script if test -e T0124.t2k-logo.labels ;\ then makelogo -b 60 -t T0124.t2k -o T0124.t2k-logo.eps -l T0124.t2k-logo.labels T0124.t2k.saves ;\ else makelogo -b 60 -t T0124.t2k -o T0124.t2k-logo.eps -lf T0124.t2k.2d.seq T0124.t2k.saves ;\ fi /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0124.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0124.t2k-w0.5-pdb.rdb PATH=.:/projects/compbio/experiments/models.97/scripts99:/projects/compbio/bin:/projects/compbio/bin/alpha:/projects/compbio/bin/hmmscripts:/projects/compbio/bin/scripts:/sbin:/usr/sbin:/bin:/usr/bin:/usr/local/gnu/bin:/usr/local/share/request/bin:/usr/local/bin @@@@ mkdir /projects/compbio/tmp/score-target-14107 @@@@ mkdir /projects/compbio/tmp/score-target-14107/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-14107/for-scorescript -a2msfile /projects/compbio/tmp/score-target-14107/score-target.a2m \ -buildscript /projects/compbio/bin/scripts/w0.5 -seqfile /projects/compbio/data/pdb/all-protein -Emax 40.0 -viterbi 0 \ -sw_score 2 -output /projects/compbio/tmp/score-target-14107/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-14107/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-14107/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /export/projects/compbio/experiments/casp4/t124/T0124.t2k.a2m.gz /projects/compbio/tmp/score-target-14107/for-scorescript/split-tmp/beta-11631/T0124.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-24872 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-24872/tmp -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.t2k.a2m.gz (40 sequences, 242 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-24872/tmp.a2m. Dropping 10 (of 40) duplicate sequences with differing IDs Dropping 17 (of 40) sequences with > 80.0% id 13 sequences left after dropping 27 of 40 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-24872/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-24872/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-24872/tmp.a2m (13 sequences, 242 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-24872/tmp.mod /projects/compbio/tmp/score-target-14107/for-scorescript/split-tmp/beta-11631/T0124.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-24872 m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:52 # About to count sequences in /projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 1000, actual: 0.1 prefilter: 1000, actual: 1 prefilter: 2000, actual: 10 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.8, 0.7, 0.6 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 553635 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: blast_max_report= 20000 /projects/compbio/experiments/models.97/scripts2k/target2k: db=/projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=1 constraints=1 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 @@@@ blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 1000,1000,2000 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-beta-5274 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-21671/prefilter_1.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-21671/prefilter_2.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-21671/prefilter_3.fa, 2000 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: db=/projects/compbio/data/nrp/nr @@@@ uniqueseq init -alignfile /export/projects/compbio/tmp/target2k-beta-21671/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/tmp/target2k-beta-21671/m0.a2m (40 sequences, 242 columns) as A2M alignment. Writing sequence output to init.a2m. Dropping 10 (of 40) duplicate sequences with differing IDs Dropping 5 (of 40) sequences with > 100.0% id 25 sequences left after dropping 15 of 40 sequences. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=2000 V=20000 B=0 -gi > 1.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 2.fasta E=2000 V=20000 B=0 -gi > 2.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 2.fasta < /dev/null @@@@ rm -f 2.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 3.fasta E=2000 V=20000 B=0 -gi > 3.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 3.fasta < /dev/null @@@@ rm -f 3.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 4.fasta E=2000 V=20000 B=0 -gi > 4.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 4.fasta < /dev/null @@@@ rm -f 4.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 5.fasta E=2000 V=20000 B=0 -gi > 5.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 5.fasta < /dev/null @@@@ rm -f 5.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 6.fasta E=2000 V=20000 B=0 -gi > 6.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 6.fasta < /dev/null @@@@ rm -f 6.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 7.fasta E=2000 V=20000 B=0 -gi > 7.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 7.fasta < /dev/null @@@@ rm -f 7.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 8.fasta E=2000 V=20000 B=0 -gi > 8.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 8.fasta < /dev/null @@@@ rm -f 8.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 9.fasta E=2000 V=20000 B=0 -gi > 9.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 9.fasta < /dev/null @@@@ rm -f 9.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 10.fasta E=2000 V=20000 B=0 -gi > 10.fasta-blast.out EXIT CODE 26 *** Error: /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: /projects/compbio/bin/wu-blastp failed *** Error: /projects/compbio/experiments/models.97/scripts2k/target2k: command failed: blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 1000,1000,2000 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 make: *** [T0124.remote-t2k.a2m.gz] Error 2 /projects/compbio/experiments/models.97/scripts2k/target2k -out T0124.remote-t2k \ -seed T0124.t2k.a2m.gz -all \ -iter 3 \ -thresholds 0.1,1,10 \ -prefilter_thresholds 1000,1000,2000 @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-16208 @@@@ gunzip -c /export/projects/compbio/experiments/casp4/t124/T0124.t2k.a2m.gz > m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:52 # About to count sequences in /projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 1000, actual: 0.1 prefilter: 1000, actual: 1 prefilter: 2000, actual: 10 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.8, 0.7, 0.6 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 553635 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: blast_max_report= 20000 /projects/compbio/experiments/models.97/scripts2k/target2k: db=/projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=1 constraints=1 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 @@@@ blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 1000,1000,2000 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-beta-3774 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-16208/prefilter_1.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-16208/prefilter_2.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-16208/prefilter_3.fa, 2000 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: db=/projects/compbio/data/nrp/nr @@@@ uniqueseq init -alignfile /export/projects/compbio/tmp/target2k-beta-16208/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/tmp/target2k-beta-16208/m0.a2m (40 sequences, 242 columns) as A2M alignment. Writing sequence output to init.a2m. Dropping 10 (of 40) duplicate sequences with differing IDs Dropping 5 (of 40) sequences with > 100.0% id 25 sequences left after dropping 15 of 40 sequences. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=2000 V=20000 B=0 -gi > 1.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 2.fasta E=2000 V=20000 B=0 -gi > 2.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 2.fasta < /dev/null @@@@ rm -f 2.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 3.fasta E=2000 V=20000 B=0 -gi > 3.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 3.fasta < /dev/null @@@@ rm -f 3.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 4.fasta E=2000 V=20000 B=0 -gi > 4.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 4.fasta < /dev/null @@@@ rm -f 4.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 5.fasta E=2000 V=20000 B=0 -gi > 5.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 5.fasta < /dev/null @@@@ rm -f 5.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 6.fasta E=2000 V=20000 B=0 -gi > 6.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 6.fasta < /dev/null @@@@ rm -f 6.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 7.fasta E=2000 V=20000 B=0 -gi > 7.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 7.fasta < /dev/null @@@@ rm -f 7.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 8.fasta E=2000 V=20000 B=0 -gi > 8.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 8.fasta < /dev/null @@@@ rm -f 8.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 9.fasta E=2000 V=20000 B=0 -gi > 9.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 9.fasta < /dev/null @@@@ rm -f 9.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 10.fasta E=2000 V=20000 B=0 -gi > 10.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 10.fasta < /dev/null @@@@ rm -f 10.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 11.fasta E=2000 V=20000 B=0 -gi > 11.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 11.fasta < /dev/null @@@@ rm -f 11.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 12.fasta E=2000 V=20000 B=0 -gi > 12.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 12.fasta < /dev/null @@@@ rm -f 12.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 13.fasta E=2000 V=20000 B=0 -gi > 13.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 13.fasta < /dev/null @@@@ rm -f 13.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 14.fasta E=2000 V=20000 B=0 -gi > 14.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 14.fasta < /dev/null @@@@ rm -f 14.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 15.fasta E=2000 V=20000 B=0 -gi > 15.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 15.fasta < /dev/null @@@@ rm -f 15.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 16.fasta E=2000 V=20000 B=0 -gi > 16.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 16.fasta < /dev/null @@@@ rm -f 16.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 17.fasta E=2000 V=20000 B=0 -gi > 17.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 17.fasta < /dev/null @@@@ rm -f 17.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 18.fasta E=2000 V=20000 B=0 -gi > 18.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 18.fasta < /dev/null @@@@ rm -f 18.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 19.fasta E=2000 V=20000 B=0 -gi > 19.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 19.fasta < /dev/null @@@@ rm -f 19.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 20.fasta E=2000 V=20000 B=0 -gi > 20.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 20.fasta < /dev/null @@@@ rm -f 20.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 21.fasta E=2000 V=20000 B=0 -gi > 21.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 21.fasta < /dev/null @@@@ rm -f 21.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 22.fasta E=2000 V=20000 B=0 -gi > 22.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 22.fasta < /dev/null @@@@ rm -f 22.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 23.fasta E=2000 V=20000 B=0 -gi > 23.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 23.fasta < /dev/null @@@@ rm -f 23.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 24.fasta E=2000 V=20000 B=0 -gi > 24.fasta-blast.out WARNING: Descriptions of 7067 database sequences were not reported due to the limiting value of parameter V = 20,000. NOTE: You might consider using a low-complexity sequence filter to reduce the number of spurious matches that may be appearing in the output. See the -filter option. Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 24.fasta < /dev/null @@@@ rm -f 24.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 25.fasta E=2000 V=20000 B=0 -gi > 25.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 25.fasta < /dev/null @@@@ rm -f 25.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-3774 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (40 sequences, 242 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (40 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_1-a -i tmp_1-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -19.5268458162001 -Emax 0.1 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ...................................................................... Average NLL-Simple NULL score: -14.989828 Database has 69941 sequences with 32469749 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_1-a.mult (40 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_1-a.mstat Writing sequence output to tmp_1-a-sort.a2m. @@@@ cat m0.a2m tmp_1-a-sort.a2m > tmp_1-a.train.seq @@@@ cat m0.cst tmp_1-a-md.cst > tmp_1-a.train.cst # About to count sequences in tmp_1-a.train.seq # num_seqs=80 nll_thresh=-15.5268458162001 frac_id=0.899556899158685 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.899556899158685 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_1-a.train.seq (80 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 20 (of 80) duplicate sequences with differing IDs Dropping 20 (of 80) duplicate sequences with identical IDs Dropping 26 (of 80) sequences with > 90.0% id 15 sequences left after dropping 65 of 80 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_1-a.train.seq (15 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -651.41 -93.44 -483.38 229.92 40 0 243 @@@@ hmmscore tmp_1-b -i tmp_1-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -19.5268458162001 -Emax 0.1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 0.1 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(18): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ..... Average NLL-Simple NULL score: -14.036697 Database has 4968 sequences with 3220458 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.a2m \ -insert /projects/compbio/lib/stiff-gap5.regularizer \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.a2m (81 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_2-a -i tmp_2-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -17.2242590975847 -Emax 1 \ -adpstyle 1 \ -align_short 0 -mdEmax 1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_2.fa -constraints tmp_2-a.cst -constraints_out tmp_2-a-md.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ...................................................................... Average NLL-Simple NULL score: -19.244352 Database has 69941 sequences with 32469749 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_2-a.mult (40 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_2-a.mstat Writing sequence output to tmp_2-a-sort.a2m. @@@@ cat m0.a2m tmp_2-a-sort.a2m > tmp_2-a.train.seq @@@@ cat m0.cst tmp_2-a-md.cst > tmp_2-a.train.cst # About to count sequences in tmp_2-a.train.seq # num_seqs=80 nll_thresh=-13.2242590975847 frac_id=0.871440372132186 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.871440372132186 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_2-a.train.seq (80 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 20 (of 80) duplicate sequences with differing IDs Dropping 20 (of 80) duplicate sequences with identical IDs Dropping 27 (of 80) sequences with > 87.1% id 14 sequences left after dropping 66 of 80 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-a.train.seq \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_2-a.train.seq (14 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_2-b -insert tmp_2-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_2-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_2-a.w -constraints tmp_2-a.train.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -647.05 -95.08 -471.21 232.36 40 0 243 @@@@ hmmscore tmp_2-b -i tmp_2-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -17.2242590975847 -Emax 1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 1 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(18): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ............. Average NLL-Simple NULL score: -11.835285 Database has 12007 sequences with 4544797 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.a2m (80 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_3-a -i tmp_3-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -14.9216577482315 -Emax 10 \ -adpstyle 1 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_3.fa -constraints tmp_3-a.cst -constraints_out tmp_3-a-md.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ...................................................................... Average NLL-Simple NULL score: -13.332334 Database has 69941 sequences with 32469749 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_3-a.mult (44 sequences, 242 columns) as A2M alignment. Reading scores from file tmp_3-a.mstat Writing sequence output to tmp_3-a-sort.a2m. @@@@ cat m0.a2m tmp_3-a-sort.a2m > tmp_3-a.train.seq @@@@ cat m0.cst tmp_3-a-md.cst > tmp_3-a.train.cst # About to count sequences in tmp_3-a.train.seq # num_seqs=84 nll_thresh=-10.9216577482315 frac_id=0.828694556012579 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.828694556012579 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_3-a.train.seq (84 sequences, 242 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 20 (of 84) duplicate sequences with differing IDs Dropping 20 (of 84) duplicate sequences with identical IDs Dropping 31 (of 84) sequences with > 82.9% id 17 sequences left after dropping 67 of 84 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_3-a.train.seq (17 sequences, 242 columns) as A2M alignment. @@@@ buildmodel tmp_3-b -insert tmp_3-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_3-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/fssp-trained.regularizer -sequence_weights tmp_3-a.w -constraints tmp_3-a.train.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -650.54 -6.02 -309.71 282.59 40 0 243 @@@@ hmmscore tmp_3-b -i tmp_3-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -14.9216577482315 -Emax 10 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0826446280991736 \ -align_short 5 -mdEmax 10 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(18): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) .............. Average NLL-Simple NULL score: -10.372711 Database has 13284 sequences with 7459998 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_3.a2m @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_3.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_3.a2m (84 sequences, 242 columns) as A2M alignment. @@@@ hmmscore tmp_4-a -i tmp_4-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -14.9216577482315 -Emax 10 \ -adpstyle 5 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0826446280991736 -db prefilter_3.fa -constraints tmp_4-a.cst -constraints_out tmp_4-a-md.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t124/T0124.remote-t2k_3.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ...........................Error: out of memory allocating 79820520 bytes *** Error: /projects/compbio/experiments/models.97/scripts2k/target2k: hmmscore to select sequences failed make: *** [T0124.remote-t2k.a2m.gz] Error 2