make -k T0097-blast.rdb T0097-double-blast.rdb make[1]: Entering directory `/export/projects/compbio/experiments/casp4/t97' /projects/compbio/experiments/casp4/scripts/single-blast -q T0097.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0097-blast.rdb starting T0097 with E=10 /projects/compbio/experiments/casp4/scripts/double-blast -q T0097.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0097-double-blast.rdb starting T0097 with E=0.000050 T0097 T0097 blasting: T0097 gi|729442|sp|P38661|ERP5_MEDSA_270:363 blasting: T0097 gi|2507015|sp|P52555|ER29_RAT_156:260 blasting: T0097 gi|7489183|pir||T03644_265:358 blasting: T0097 gi|3287888|sp|O13811|PDI2_SCHPO_264:354 blasting: T0097 gi|7488158|pir||T00437_264:357 blasting: T0097 gi|2627440|gb|AAB86685.1|_267:363 blasting: T0097 gi|2895202|gb|AAC02944.1|_148:257 blasting: make[1]: Leaving directory `/export/projects/compbio/experiments/casp4/t97' make -k T0097.t2k.a2m.gz \ T0097.t2k.pa \ T0097.t2k.pa.html \ T0097.t2k.2d \ T0097.t2k.tree \ T0097.t2k_sorted.pa \ T0097.t2k.tree.ps \ T0097.t2k.tree-unroot.ps make[1]: Entering directory `/export/projects/compbio/experiments/casp4/t97' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0097.t2k \ -seed T0097.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-17245 @@@@ cp /export/projects/compbio/experiments/casp4/t97/T0097.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= 507064 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-25480 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-17245/prefilter_1.fa, 0.01 For /export/projects/compbio/tmp/target2k-beta-17245/prefilter_2.fa, 1 For /export/projects/compbio/tmp/target2k-beta-17245/prefilter_3.fa, 10 For /export/projects/compbio/tmp/target2k-beta-17245/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-17245/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file /export/projects/compbio/tmp/target2k-beta-17245/m0.a2m (1 sequences, 105 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 507064 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-25480 < /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, 105 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, 105 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 507064 \ -simple_threshold -26.3467328791272 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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: -53.342045 Database has 11 sequences with 3538 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 (6 sequences, 105 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=7 nll_thresh=-22.3467328791272 frac_id=0.999999999999989 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999999999999989 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (7 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 7) duplicate sequences with differing IDs 6 sequences left after dropping 1 of 7 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 (6 sequences, 105 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 -287.48 -96.22 -139.92 75.58 10 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.3467328791272 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.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: -147.327118 Database has 7 sequences with 1971 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 /export/projects/compbio/experiments/casp4/t97/T0097.t2k_1.a2m (7 sequences, 105 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 507064 \ -simple_threshold -25.6535856983701 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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 /export/projects/compbio/experiments/casp4/t97/T0097.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: -44.142586 Database has 28 sequences with 18679 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 (12 sequences, 105 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=13 nll_thresh=-21.6535856983701 frac_id=0.999999953310568 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999999953310568 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (13 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 13) duplicate sequences with differing IDs 12 sequences left after dropping 1 of 13 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 (12 sequences, 105 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 /export/projects/compbio/experiments/casp4/t97/T0097.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 -286.36 -27.11 -94.04 64.80 6 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.6535856983701 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.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: -101.945206 Database has 13 sequences with 3690 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 /export/projects/compbio/experiments/casp4/t97/T0097.t2k_2.a2m (13 sequences, 105 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 507064 \ -simple_threshold -24.0441477843583 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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 /export/projects/compbio/experiments/casp4/t97/T0097.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: -29.153633 Database has 62 sequences with 38353 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 (12 sequences, 105 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=13 nll_thresh=-20.0441477843583 frac_id=0.999999838977056 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.999999838977056 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (13 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 13) duplicate sequences with differing IDs 12 sequences left after dropping 1 of 13 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 (12 sequences, 105 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 /export/projects/compbio/experiments/casp4/t97/T0097.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 -286.51 -25.38 -90.73 65.29 3 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.0441477843583 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.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: -97.866974 Database has 13 sequences with 3690 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 /export/projects/compbio/experiments/casp4/t97/T0097.t2k_3.a2m (13 sequences, 105 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 507064 \ -simple_threshold -22.4347098640356 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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 /export/projects/compbio/experiments/casp4/t97/T0097.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: -11.276077 Database has 833 sequences with 318511 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 (12 sequences, 105 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=13 nll_thresh=-18.4347098640356 frac_id=0.999999444662775 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 0.999999444662775 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_4-a.train.seq (13 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 13) duplicate sequences with differing IDs 12 sequences left after dropping 1 of 13 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 (12 sequences, 105 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 /export/projects/compbio/experiments/casp4/t97/T0097.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 -287.21 -25.72 -88.33 66.49 4 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.4347098640356 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.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: -94.943108 Database has 13 sequences with 3690 residues. @@@@ cp -f tmp_4-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 /export/projects/compbio/experiments/casp4/t97/T0097.t2k_4.a2m (13 sequences, 105 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 507064 \ -simple_threshold -22.4347098640356 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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 /export/projects/compbio/experiments/casp4/t97/T0097.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: -11.273365 Database has 833 sequences with 318511 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 (12 sequences, 105 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/t97/T0097.t2k.a2m @@@@ cp tmp_5-a.train.cst /export/projects/compbio/experiments/casp4/t97/T0097.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-17245 < /dev/null gzip -f T0097.t2k.a2m T0097.t2k_*.a2m prettyalign T0097.t2k.a2m.gz -m8 -i -n -L3333 > T0097.t2k.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 gunzip -c T0097.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0097.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-IDaa13-5-9-7-10-5-10-11-ehl2-seeded4-stride-trained.net > tmp.script echo ReadA2M T0097.t2k.a2m.gz >> tmp.script echo PrintPrediction T0097.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0097.t2k.2d.seq >> tmp.script echo PrintRDB T0097.t2k.2d.rdb >> tmp.script predict-2nd < tmp.script # command:# Neural network set to overrep-2500-IDaa13-5-9-7-10-5-10-11-ehl2-seeded4-stride-trained.net # command:# Reading A2M format from T0097.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0097.t2k.a2m with 13 sequences, total weight= 9.69344 avg weight= 0.745649 37 iterations Regularizing alignment for T0097.t2k.a2m.gz # After reading T0097.t2k.a2m.gz, have 105 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 T0097.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0097.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0097.t2k.2d.rdb # command:rm tmp.script gunzip -f T0097.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0097.t2k T0097.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0097.t2k.a2m (13 sequences) as A2M alignment. Alignment T0097.t2k.a2m read. Adding sequences:0 10 One dot for every 10 merges: . Merges done. CPU = user 0: 0: 3 system 0: 0: 0 gzip -f T0097.t2k.a2m gzip -f T0097.t2k_sorted.a2m rm T0097.t2k.phytrace T0097.t2k.tree_weight prettyalign T0097.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0097.t2k_sorted.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 /projects/compbio/usr/karplus/src/phytree/dg T0097.t2k.tree /projects/compbio/usr/karplus/src/phytree/dtree T0097.t2k.tree make[1]: Leaving directory `/export/projects/compbio/experiments/casp4/t97' /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0097.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0097.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-26775 @@@@ mkdir /projects/compbio/tmp/score-target-26775/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-26775/for-scorescript -a2msfile /projects/compbio/tmp/score-target-26775/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-26775/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-26775/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-26775/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /export/projects/compbio/experiments/casp4/t97/T0097.t2k.a2m.gz /projects/compbio/tmp/score-target-26775/for-scorescript/split-tmp/beta-14153/T0097.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-16483 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-16483/tmp -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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 /export/projects/compbio/experiments/casp4/t97/T0097.t2k.a2m.gz (13 sequences, 105 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-16483/tmp.a2m. Dropping 1 (of 13) duplicate sequences with differing IDs Dropping 2 (of 13) sequences with > 80.0% id 10 sequences left after dropping 3 of 13 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-16483/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-16483/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-beta-16483/tmp.a2m (10 sequences, 105 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-16483/tmp.mod /projects/compbio/tmp/score-target-26775/for-scorescript/split-tmp/beta-14153/T0097.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-16483 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: 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= 507064 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-7840 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-25697/prefilter_1.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-25697/prefilter_2.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-25697/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-25697/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file /export/projects/compbio/tmp/target2k-beta-25697/m0.a2m (13 sequences, 105 columns) as A2M alignment. Writing sequence output to init.a2m. Dropping 1 (of 13) duplicate sequences with differing IDs 12 sequences left after dropping 1 of 13 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 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 507064 sequences # parsing wu-blastp output @@@@ rm -f 12.fasta < /dev/null @@@@ rm -f 12.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-7840 < /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 (13 sequences, 105 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 (13 sequences, 105 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 507064 \ -simple_threshold -19.4389774031285 -Emax 0.1 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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: -8.647607 Database has 31393 sequences with 11267630 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 (12 sequences, 105 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=25 nll_thresh=-15.4389774031285 frac_id=0.998339791247238 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.998339791247238 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (25 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 25) duplicate sequences with differing IDs Dropping 2 (of 25) duplicate sequences with identical IDs Dropping 2 (of 25) sequences with > 99.8% id 12 sequences left after dropping 13 of 25 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 (12 sequences, 105 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 -289.45 -51.99 -210.90 83.07 40 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -19.4389774031285 -Emax 0.1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 0.1 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.remote-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: -183.323547 Database has 25 sequences with 4805 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k_1.a2m (25 sequences, 105 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 507064 \ -simple_threshold -17.1363905352087 -Emax 1 \ -adpstyle 1 \ -align_short 0 -mdEmax 1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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 /export/projects/compbio/experiments/casp4/t97/T0097.remote-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: -11.671954 Database has 31393 sequences with 11267630 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 (12 sequences, 105 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=25 nll_thresh=-13.1363905352087 frac_id=0.995842784722711 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.995842784722711 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (25 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 25) duplicate sequences with differing IDs Dropping 2 (of 25) duplicate sequences with identical IDs Dropping 3 (of 25) sequences with > 99.6% id 13 sequences left after dropping 12 of 25 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 (13 sequences, 105 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 /export/projects/compbio/experiments/casp4/t97/T0097.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 v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -286.68 -81.92 -189.99 85.28 40 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -17.1363905352087 -Emax 1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 1 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.remote-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: -171.848602 Database has 26 sequences with 4999 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k_2.a2m (25 sequences, 105 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 507064 \ -simple_threshold -14.8337876927833 -Emax 10 \ -adpstyle 1 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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 /export/projects/compbio/experiments/casp4/t97/T0097.remote-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: -8.701568 Database has 31393 sequences with 11267630 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 (13 sequences, 105 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=26 nll_thresh=-10.8337876927833 frac_id=0.987788378524075 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.987788378524075 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (26 sequences, 105 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 26) duplicate sequences with differing IDs Dropping 2 (of 26) duplicate sequences with identical IDs Dropping 2 (of 26) sequences with > 98.8% id 13 sequences left after dropping 13 of 26 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 (13 sequences, 105 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(23): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t97/T0097.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 v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -286.85 -32.90 -200.06 88.40 40 0 106 @@@@ 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 507064 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -14.8337876927833 -Emax 10 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.19047619047619 \ -align_short 5 -mdEmax 10 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t97/T0097.remote-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: -167.604599 Database has 27 sequences with 5805 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k_3.a2m @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.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/t97/T0097.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 v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k_3.a2m (26 sequences, 105 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 507064 \ -simple_threshold -14.8337876927833 -Emax 10 \ -adpstyle 5 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.19047619047619 -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(23): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t97/T0097.remote-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: -8.703986 Database has 31393 sequences with 11267630 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 (13 sequences, 105 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 @@@@ cp tmp_4-a.train.seq /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k.a2m @@@@ cp tmp_4-a.train.cst /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-25697 < /dev/null gzip -9f T0097.remote-t2k.a2m /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0097.remote-t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0097.remote-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-799 @@@@ mkdir /projects/compbio/tmp/score-target-799/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-799/for-scorescript -a2msfile /projects/compbio/tmp/score-target-799/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-799/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-799/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-799/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k.a2m.gz /projects/compbio/tmp/score-target-799/for-scorescript/split-tmp/beta-8200/T0097.remote-t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-16933 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-16933/tmp -alignfile /export/projects/compbio/experiments/casp4/t97/T0097.remote-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 /export/projects/compbio/experiments/casp4/t97/T0097.remote-t2k.a2m.gz (26 sequences, 105 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-16933/tmp.a2m. Dropping 2 (of 26) duplicate sequences with differing IDs Dropping 2 (of 26) duplicate sequences with identical IDs Dropping 4 (of 26) sequences with > 80.0% id 11 sequences left after dropping 15 of 26 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-16933/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-16933/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-beta-16933/tmp.a2m (11 sequences, 105 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-16933/tmp.mod /projects/compbio/tmp/score-target-799/for-scorescript/split-tmp/beta-8200/T0097.remote-t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-16933 tmp.script echo ReadA2M T0097.t2k.a2m.gz >> tmp.script echo PrintPrediction T0097.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0097.t2k.2d.seq >> tmp.script echo PrintRDB T0097.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 T0097.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0097.t2k.a2m with 13 sequences, total weight= 9.69344 avg weight= 0.745649 37 iterations Regularizing alignment for T0097.t2k.a2m.gz # After reading T0097.t2k.a2m.gz, have 105 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 T0097.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0097.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0097.t2k.2d.rdb # command:rm tmp.script