make -k T0105-blast.rdb T0105-double-blast.rdb make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t105' /projects/compbio/experiments/casp4/scripts/single-blast -q T0105.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0105-blast.rdb starting T0105 with E=10 /projects/compbio/experiments/casp4/scripts/double-blast -q T0105.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0105-double-blast.rdb starting T0105 with E=0.000050 T0105 T0105 blasting: T0105 gi|6166538|sp|Q13342|LY10_HUMAN_580:667 blasting: T0105 gi|6175041|sp|P23497|SP10_HUMAN_595:688 blasting: T0105 gi|2133648|pir||S69214_211:301 blasting: T0105 gi|1362890|pir||B49515_215:292 blasting: T0105 gi|1389895|gb|AAC35994.1|_133:204 blasting: T0105 gi|2246694|gb|AAB62704.1|_133:204 blasting: T0105 gi|2340117|gb|AAC53506.1|_378:467 blasting: T0105 gi|2340121|gb|AAC53508.1|_378:467 blasting: T0105 gi|2340123|gb|AAC53509.1|_360:449 blasting: T0105 gi|2340131|gb|AAC53513.1|_360:449 blasting: T0105 gi|3252911|gb|AAC39790.1|_595:684 blasting: T0105 gi|3293440|gb|AAC25714.1|_133:204 blasting: T0105 gi|3293442|gb|AAC25715.1|_133:204 blasting: T0105 gi|3293444|gb|AAC25716.1|_133:204 blasting: T0105 gi|3293446|gb|AAC25717.1|_133:204 blasting: T0105 gi|3293448|gb|AAC25718.1|_133:204 blasting: T0105 gi|3293450|gb|AAC25719.1|_133:204 blasting: T0105 gi|3309563|gb|AAC79676.1|_201:272 blasting: T0105 gi|3309565|gb|AAC79677.1|_187:258 blasting: T0105 gi|3309567|gb|AAC79678.1|_201:272 blasting: T0105 gi|3309569|gb|AAC79679.1|_201:272 blasting: T0105 gi|7496508|pir||T19470_79:145 blasting: T0105 gi|7497426|pir||T19932_80:148 blasting: T0105 gi|5764636|gb|AAD51352.1|AF173868_1_86:152 blasting: T0105 gi|7021843|dbj|BAA91410.1|_86:152 blasting: T0105 gi|7239183|gb|AAF43108.1|AF169946_1_1:39 blasting: T0105 gi|7239185|gb|AAF43109.1|AF169947_1_1:33 blasting: T0105 gi|7239187|gb|AAF43110.1|AF169948_1_1:62 blasting: T0105 gi|7643907|gb|AAF65539.1|AF205780_1_93:159 blasting: T0105 gi|8118043|gb|AAF72874.1|AF210433_1_86:152 blasting: make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t105' make -k T0105.t2k.a2m.gz \ T0105.t2k.pa \ T0105.t2k.pa.html \ T0105.t2k.2d \ T0105.t2k.tree \ T0105.t2k_sorted.pa \ T0105.t2k.tree.ps \ T0105.t2k.tree-unroot.ps make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t105' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0105.t2k \ -seed T0105.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-eclipse-721 @@@@ cp /projects/compbio/experiments/casp4/t105/T0105.seq m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:44 # 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= 514491 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-eclipse-8961 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /projects/compbio/tmp/target2k-eclipse-721/prefilter_1.fa, 0.01 For /projects/compbio/tmp/target2k-eclipse-721/prefilter_2.fa, 1 For /projects/compbio/tmp/target2k-eclipse-721/prefilter_3.fa, 10 For /projects/compbio/tmp/target2k-eclipse-721/prefilter_4.fa, 400 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: db=/projects/compbio/data/nrp/nr @@@@ uniqueseq init -alignfile /projects/compbio/tmp/target2k-eclipse-721/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file /projects/compbio/tmp/target2k-eclipse-721/m0.a2m (1 sequences, 94 columns) as A2M alignment. Writing sequence output to init.a2m. No sequences have been droppd. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=400 V=20000 B=0 -gi > 1.fasta-blast.out Searched 514491 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-eclipse-8961 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file m0.a2m (1 sequences, 94 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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file m0.a2m (1 sequences, 94 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 514491 \ -simple_threshold -26.3612737131737 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.212765957446809 -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(23): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -48.890938 Database has 58 sequences with 28502 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_1-a.mult (31 sequences, 94 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=32 nll_thresh=-22.3612737131737 frac_id=0.999262293231936 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999262293231936 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (32 sequences, 94 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 10 (of 32) duplicate sequences with differing IDs Dropping 1 (of 32) sequences with > 99.9% id 21 sequences left after dropping 11 of 32 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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_1-a.train.seq (21 sequences, 94 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(23): 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 v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -267.87 4.27 -97.54 51.70 8 0 95 @@@@ 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 514491 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.3612737131737 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.212765957446809 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t105/T0105.t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(20): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -105.595413 Database has 37 sequences with 18072 residues. @@@@ cp -f tmp_1-b.mult /projects/compbio/experiments/casp4/t105/T0105.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /projects/compbio/experiments/casp4/t105/T0105.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 /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_1.a2m (37 sequences, 94 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 514491 \ -simple_threshold -25.6681265324194 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.212765957446809 -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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_1.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -68.880188 Database has 64 sequences with 29942 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_2-a.mult (44 sequences, 94 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=45 nll_thresh=-21.6681265324194 frac_id=0.99356726959932 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.99356726959932 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (45 sequences, 94 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 18 (of 45) duplicate sequences with differing IDs 27 sequences left after dropping 18 of 45 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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_2-a.train.seq (27 sequences, 94 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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -266.34 -33.62 -90.14 41.76 5 0 95 @@@@ 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 514491 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.6681265324194 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.212765957446809 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t105/T0105.t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(20): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -94.035187 Database has 45 sequences with 21750 residues. @@@@ cp -f tmp_2-b.mult /projects/compbio/experiments/casp4/t105/T0105.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /projects/compbio/experiments/casp4/t105/T0105.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 /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_2.a2m (45 sequences, 94 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 514491 \ -simple_threshold -24.0586886184303 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.212765957446809 -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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_2.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -60.345161 Database has 72 sequences with 32007 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_3-a.mult (44 sequences, 94 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=45 nll_thresh=-20.0586886184303 frac_id=0.990833087160319 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.990833087160319 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (45 sequences, 94 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 18 (of 45) duplicate sequences with differing IDs 27 sequences left after dropping 18 of 45 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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_3-a.train.seq (27 sequences, 94 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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -266.41 -30.83 -86.03 41.48 5 0 95 @@@@ 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 514491 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.0586886184303 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.212765957446809 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t105/T0105.t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(20): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -89.548820 Database has 45 sequences with 21750 residues. @@@@ cp -f tmp_3-b.mult /projects/compbio/experiments/casp4/t105/T0105.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /projects/compbio/experiments/casp4/t105/T0105.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 /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_3.a2m (45 sequences, 94 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 514491 \ -simple_threshold -22.4492506982216 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.212765957446809 -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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_3.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -17.340014 Database has 368 sequences with 103222 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_4-a.mult (44 sequences, 94 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=45 nll_thresh=-18.4492506982216 frac_id=0.98695586409101 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 0.98695586409101 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_4-a.train.seq (45 sequences, 94 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 18 (of 45) duplicate sequences with differing IDs Dropping 5 (of 45) sequences with > 98.7% id 22 sequences left after dropping 23 of 45 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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_4-a.train.seq (22 sequences, 94 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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -266.88 -30.78 -82.70 45.52 5 0 95 @@@@ 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 514491 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.4492506982216 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.212765957446809 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t105/T0105.t2k_4.cst Reading parameter file tmp_4-b.mod tmp_4-b.mod(20): Reading MODEL -- Final model for run tmp_4-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -82.328209 Database has 47 sequences with 22559 residues. @@@@ cp -f tmp_4-b.mult /projects/compbio/experiments/casp4/t105/T0105.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /projects/compbio/experiments/casp4/t105/T0105.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 /projects/compbio/experiments/casp4/t105/T0105.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_4.a2m (47 sequences, 94 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 514491 \ -simple_threshold -22.4492506982216 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.212765957446809 -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(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k_4.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -17.970955 Database has 368 sequences with 103222 residues. @@@@ sortseq tmp_5-a-sort -alignfile tmp_5-a.mult \ -NLLfile tmp_5-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_5-a.mult (54 sequences, 94 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 /projects/compbio/experiments/casp4/t105/T0105.t2k.a2m @@@@ cp tmp_5-a.train.cst /projects/compbio/experiments/casp4/t105/T0105.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-eclipse-721 < /dev/null gzip -f T0105.t2k.a2m T0105.t2k_*.a2m prettyalign T0105.t2k.a2m.gz -m8 -i -n -L3333 > T0105.t2k.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 gunzip -c T0105.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0105.t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 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 T0105.t2k.a2m.gz >> tmp.script echo PrintPrediction T0105.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0105.t2k.2d.seq >> tmp.script echo PrintRDB T0105.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 T0105.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0105.t2k.a2m with 55 sequences, total weight= 13.6189 avg weight= 0.247616 46 iterations Regularizing alignment for T0105.t2k.a2m.gz # After reading T0105.t2k.a2m.gz, have 94 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 T0105.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0105.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0105.t2k.2d.rdb # command:rm tmp.script gunzip -f T0105.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0105.t2k T0105.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0105.t2k.a2m (55 sequences) as A2M alignment. Alignment T0105.t2k.a2m read. Adding sequences:0 10 20 30 40 50 One dot for every 10 merges: ..... Merges done. CPU = user 0: 0:10 system 0: 0: 0 gzip -f T0105.t2k.a2m gzip -f T0105.t2k_sorted.a2m rm T0105.t2k.phytrace T0105.t2k.tree_weight prettyalign T0105.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0105.t2k_sorted.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 /projects/compbio/usr/karplus/src/phytree/dg T0105.t2k.tree /projects/compbio/usr/karplus/src/phytree/dtree T0105.t2k.tree make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t105' /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0105.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0105.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-9592 @@@@ mkdir /projects/compbio/tmp/score-target-9592/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-9592/for-scorescript -a2msfile /projects/compbio/tmp/score-target-9592/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-9592/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-9592/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-9592/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /projects/compbio/experiments/casp4/t105/T0105.t2k.a2m.gz /projects/compbio/tmp/score-target-9592/for-scorescript/split-tmp/eclipse-7260/T0105.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443/tmp -alignfile /projects/compbio/experiments/casp4/t105/T0105.t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file /projects/compbio/experiments/casp4/t105/T0105.t2k.a2m.gz (55 sequences, 94 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443/tmp.a2m. Dropping 28 (of 55) duplicate sequences with differing IDs Dropping 14 (of 55) sequences with > 80.0% id 13 sequences left after dropping 42 of 55 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443/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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443/tmp.a2m (13 sequences, 94 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443/tmp.mod /projects/compbio/tmp/score-target-9592/for-scorescript/split-tmp/eclipse-7260/T0105.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-eclipse-19443