make -k T0094-blast.rdb T0094-double-blast.rdb make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t94' /projects/compbio/experiments/casp4/scripts/single-blast -q T0094.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0094-blast.rdb starting T0094 with E=10 /projects/compbio/experiments/casp4/scripts/double-blast -q T0094.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0094-double-blast.rdb starting T0094 with E=0.000050 T0094 T0094 blasting: T0094 gi|7484882|pir||T05030_1:181 blasting: T0094 gi|7484883|pir||T05031_18:182 blasting: make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t94' make -k T0094.t2k.a2m.gz \ T0094.t2k.pa \ T0094.t2k.pa.html \ T0094.t2k.2d \ T0094.t2k.tree \ T0094.t2k_sorted.pa \ T0094.t2k.tree.ps \ T0094.t2k.tree-unroot.ps make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t94' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0094.t2k \ -seed T0094.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-14995 @@@@ cp /projects/compbio/experiments/casp4/t94/T0094.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= 505245 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-18421 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /projects/compbio/tmp/target2k-beta-14995/prefilter_1.fa, 0.01 For /projects/compbio/tmp/target2k-beta-14995/prefilter_2.fa, 1 For /projects/compbio/tmp/target2k-beta-14995/prefilter_3.fa, 10 For /projects/compbio/tmp/target2k-beta-14995/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-beta-14995/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-beta-14995/m0.a2m (1 sequences, 181 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 505245 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-18421 < /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, 181 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, 181 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 505245 \ -simple_threshold -26.3431391109041 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -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: -228.362747 Database has 2 sequences with 377 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 (2 sequences, 181 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=3 nll_thresh=-22.3431391109041 frac_id=1 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 1 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (3 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 3) duplicate sequences with differing IDs 2 sequences left after dropping 1 of 3 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 (2 sequences, 181 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 Warning: only 2 training sequences; Buildmodel needs 5--100 sequences for best results unless the SAM-T99 method is used. -515.38 -275.87 -395.62 169.36 40 0 182 @@@@ 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 505245 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.3431391109041 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t94/T0094.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: -396.340668 Database has 3 sequences with 558 residues. @@@@ cp -f tmp_1-b.mult /projects/compbio/experiments/casp4/t94/T0094.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.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/t94/T0094.t2k_1.a2m (3 sequences, 181 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 505245 \ -simple_threshold -25.6499919301462 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -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/t94/T0094.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: -278.135681 Database has 2 sequences with 377 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 (2 sequences, 181 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=3 nll_thresh=-21.6499919301462 frac_id=1 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 1 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (3 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 3) duplicate sequences with differing IDs 2 sequences left after dropping 1 of 3 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 (2 sequences, 181 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/t94/T0094.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 Warning: only 2 training sequences; Buildmodel needs 5--100 sequences for best results unless the SAM-T99 method is used. -514.01 -276.57 -395.29 167.90 40 0 182 @@@@ 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 505245 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.6499919301462 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t94/T0094.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: -390.464966 Database has 3 sequences with 558 residues. @@@@ cp -f tmp_2-b.mult /projects/compbio/experiments/casp4/t94/T0094.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.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/t94/T0094.t2k_2.a2m (3 sequences, 181 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 505245 \ -simple_threshold -24.0405540161288 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -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/t94/T0094.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: -115.624672 Database has 5 sequences with 872 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 (2 sequences, 181 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=3 nll_thresh=-20.0405540161288 frac_id=1 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 1 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (3 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 3) duplicate sequences with differing IDs 2 sequences left after dropping 1 of 3 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 (2 sequences, 181 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/t94/T0094.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 Warning: only 2 training sequences; Buildmodel needs 5--100 sequences for best results unless the SAM-T99 method is used. -514.08 -265.88 -389.98 175.51 40 0 182 @@@@ 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 505245 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.0405540161288 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t94/T0094.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: -383.865967 Database has 3 sequences with 558 residues. @@@@ cp -f tmp_3-b.mult /projects/compbio/experiments/casp4/t94/T0094.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.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/t94/T0094.t2k_3.a2m (3 sequences, 181 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 505245 \ -simple_threshold -22.4311160957777 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -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/t94/T0094.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: -12.037627 Database has 322 sequences with 71487 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 (2 sequences, 181 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=3 nll_thresh=-18.4311160957777 frac_id=1 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 1 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_4-a.train.seq (3 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 3) duplicate sequences with differing IDs 2 sequences left after dropping 1 of 3 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 (2 sequences, 181 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/t94/T0094.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 Warning: only 2 training sequences; Buildmodel needs 5--100 sequences for best results unless the SAM-T99 method is used. -514.66 -259.76 -387.21 180.24 40 0 182 @@@@ 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 505245 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.4311160957777 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t94/T0094.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: -378.375336 Database has 3 sequences with 558 residues. @@@@ cp -f tmp_4-b.mult /projects/compbio/experiments/casp4/t94/T0094.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.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/t94/T0094.t2k_4.a2m (3 sequences, 181 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 505245 \ -simple_threshold -22.4311160957777 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -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/t94/T0094.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: -12.037627 Database has 322 sequences with 71487 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 (2 sequences, 181 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/t94/T0094.t2k.a2m @@@@ cp tmp_5-a.train.cst /projects/compbio/experiments/casp4/t94/T0094.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-14995 < /dev/null gzip -f T0094.t2k.a2m T0094.t2k_*.a2m prettyalign T0094.t2k.a2m.gz -m8 -i -n -L3333 > T0094.t2k.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 gunzip -c T0094.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0094.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-IDaa13-5-9-7-10-5-9-11-ehl2-seeded2-stride-trained.net > tmp.script echo ReadA2M T0094.t2k.a2m.gz >> tmp.script echo PrintPrediction T0094.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0094.t2k.2d.seq >> tmp.script echo PrintRDB T0094.t2k.2d.rdb >> tmp.script predict-2nd < tmp.script # command:# Neural network set to overrep-2500-IDaa13-5-9-7-10-5-9-11-ehl2-seeded2-stride-trained.net # command:# Reading A2M format from T0094.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0094.t2k.a2m with 3 sequences, total weight= 2.55215 avg weight= 0.850716 24 iterations Regularizing alignment for T0094.t2k.a2m.gz # After reading T0094.t2k.a2m.gz, have 181 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 T0094.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0094.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0094.t2k.2d.rdb # command:rm tmp.script gunzip -f T0094.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0094.t2k T0094.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0094.t2k.a2m (3 sequences) as A2M alignment. Alignment T0094.t2k.a2m read. Adding sequences:0 One dot for every 10 merges: Merges done. CPU = user 0: 0: 1 system 0: 0: 0 gzip -f T0094.t2k.a2m gzip -f T0094.t2k_sorted.a2m rm T0094.t2k.phytrace T0094.t2k.tree_weight prettyalign T0094.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0094.t2k_sorted.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 /projects/compbio/usr/karplus/src/phytree/dg T0094.t2k.tree /projects/compbio/usr/karplus/src/phytree/dtree T0094.t2k.tree make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t94' /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0094.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0094.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-30673 @@@@ mkdir /projects/compbio/tmp/score-target-30673/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-30673/for-scorescript -a2msfile /projects/compbio/tmp/score-target-30673/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-30673/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-30673/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-30673/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /projects/compbio/experiments/casp4/t94/T0094.t2k.a2m.gz /projects/compbio/tmp/score-target-30673/for-scorescript/split-tmp/beta-18838/T0094.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-20841 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-20841/tmp -alignfile /projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.t2k.a2m.gz (3 sequences, 181 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-20841/tmp.a2m. Dropping 1 (of 3) duplicate sequences with differing IDs 2 sequences left after dropping 1 of 3 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-20841/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-20841/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-20841/tmp.a2m (2 sequences, 181 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-20841/tmp.mod /projects/compbio/tmp/score-target-30673/for-scorescript/split-tmp/beta-18838/T0094.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-20841 tmp.script echo ReadA2M T0094.t2k.a2m.gz >> tmp.script echo PrintPrediction T0094.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0094.t2k.2d.seq >> tmp.script echo PrintRDB T0094.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 T0094.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0094.t2k.a2m with 3 sequences, total weight= 2.55215 avg weight= 0.850716 24 iterations Regularizing alignment for T0094.t2k.a2m.gz # After reading T0094.t2k.a2m.gz, have 181 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 T0094.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0094.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0094.t2k.2d.rdb # command:rm tmp.script make: Nothing to be done for `T0094.t2k.2d.rdb'. make: Nothing to be done for `T0094.t2k.2d.seq'. 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 T0094.t2k.a2m.gz >> tmp.script echo PrintPrediction T0094.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0094.t2k.2d.seq >> tmp.script echo PrintRDB T0094.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 T0094.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0094.t2k.a2m with 3 sequences, total weight= 2.55215 avg weight= 0.850716 24 iterations Regularizing alignment for T0094.t2k.a2m.gz # After reading T0094.t2k.a2m.gz, have 181 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 T0094.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0094.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0094.t2k.2d.rdb # command:rm tmp.script /projects/compbio/experiments/models.97/scripts2k/target2k -out T0094.remote-t2k \ -seed T0094.t2k.a2m.gz -all \ -iter 3 \ -thresholds 0.1,1,10 \ -prefilter_thresholds 1000,1000,2000 @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-31001 @@@@ gunzip -c /export/projects/compbio/experiments/casp4/t94/T0094.t2k.a2m.gz > m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.2 (June, 2000) compiled 07/06/00_15:43:49 # 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= 521662 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-11596 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-31001/prefilter_1.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-31001/prefilter_2.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-31001/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-31001/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.2 (June, 2000) compiled 07/06/00_15:43:59 Reading alignment file /export/projects/compbio/tmp/target2k-beta-31001/m0.a2m (3 sequences, 181 columns) as A2M alignment. Writing sequence output to init.a2m. Dropping 1 (of 3) duplicate sequences with differing IDs 2 sequences left after dropping 1 of 3 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 521662 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 521662 sequences # parsing wu-blastp output @@@@ rm -f 2.fasta < /dev/null @@@@ rm -f 2.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-11596 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file m0.a2m (3 sequences, 181 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file m0.a2m (3 sequences, 181 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 521662 \ -simple_threshold -19.4673600488604 -Emax 0.1 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) ... Average NLL-Simple NULL score: -10.554305 Database has 2306 sequences with 682352 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.2 (June, 2000) compiled 07/06/00_15:43:43 Reading alignment file tmp_1-a.mult (2 sequences, 181 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=5 nll_thresh=-15.4673600488604 frac_id=0.999999999999971 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999999999999971 -a2mdots 0 SAM: uniqueseq v3.2 (June, 2000) compiled 07/06/00_15:43:59 Reading alignment file tmp_1-a.train.seq (5 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 5) duplicate sequences with differing IDs Dropping 2 (of 5) duplicate sequences with identical IDs 2 sequences left after dropping 3 of 5 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file tmp_1-a.train.seq (2 sequences, 181 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.2 (June, 2000) compiled 07/07/00_22:42:24 Warning: only 2 training sequences; Buildmodel needs 5--100 sequences for best results unless -sequence_models is used. -515.79 -482.43 -499.11 23.59 3 0 182 @@@@ 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 521662 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -19.4673600488604 -Emax 0.1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 0.1 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(18): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -443.311432 Database has 5 sequences with 912 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.remote-t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_1.a2m (5 sequences, 181 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 521662 \ -simple_threshold -17.1647732306095 -Emax 1 \ -adpstyle 1 \ -align_short 0 -mdEmax 1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -db prefilter_2.fa -constraints tmp_2-a.cst -constraints_out tmp_2-a-md.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_1.a2m SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) ... Average NLL-Simple NULL score: -14.693015 Database has 2306 sequences with 682352 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.2 (June, 2000) compiled 07/06/00_15:43:43 Reading alignment file tmp_2-a.mult (5 sequences, 181 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=8 nll_thresh=-13.1647732306095 frac_id=0.999999942937014 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999999942937014 -a2mdots 0 SAM: uniqueseq v3.2 (June, 2000) compiled 07/06/00_15:43:59 Reading alignment file tmp_2-a.train.seq (8 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 3 (of 8) duplicate sequences with differing IDs Dropping 3 (of 8) duplicate sequences with identical IDs 4 sequences left after dropping 4 of 8 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-a.train.seq \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file tmp_2-a.train.seq (4 sequences, 181 columns) as A2M alignment. @@@@ buildmodel tmp_2-b -insert tmp_2-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_2-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_2-a.w -constraints tmp_2-a.train.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (June, 2000) compiled 07/07/00_22:42:24 Warning: only 4 training sequences; Buildmodel needs 5--100 sequences for best results unless -sequence_models is used. -514.24 -17.69 -262.00 271.36 40 0 182 @@@@ 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 521662 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -17.1647732306095 -Emax 1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 1 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(18): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -166.262039 Database has 15 sequences with 3605 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.remote-t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_2.a2m (8 sequences, 181 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 521662 \ -simple_threshold -14.862170884883 -Emax 10 \ -adpstyle 1 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -db prefilter_3.fa -constraints tmp_3-a.cst -constraints_out tmp_3-a-md.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_2.a2m SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) ... Average NLL-Simple NULL score: -9.965983 Database has 2306 sequences with 682352 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.2 (June, 2000) compiled 07/06/00_15:43:43 Reading alignment file tmp_3-a.mult (6 sequences, 181 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=9 nll_thresh=-10.862170884883 frac_id=0.999995412741763 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.999995412741763 -a2mdots 0 SAM: uniqueseq v3.2 (June, 2000) compiled 07/06/00_15:43:59 Reading alignment file tmp_3-a.train.seq (9 sequences, 181 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 3 (of 9) duplicate sequences with differing IDs Dropping 3 (of 9) duplicate sequences with identical IDs 5 sequences left after dropping 4 of 9 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file tmp_3-a.train.seq (5 sequences, 181 columns) as A2M alignment. @@@@ buildmodel tmp_3-b -insert tmp_3-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_3-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/fssp-trained.regularizer -sequence_weights tmp_3-a.w -constraints tmp_3-a.train.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.2 (June, 2000) compiled 07/07/00_22:42:24 Warning: only 5 training sequences; Buildmodel needs 5--100 sequences for best results unless -sequence_models is used. -514.78 -30.50 -222.43 252.56 40 0 182 @@@@ 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 521662 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -14.862170884883 -Emax 10 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.110497237569061 \ -align_short 5 -mdEmax 10 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(18): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -204.234741 Database has 12 sequences with 2885 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_3.a2m @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t94/T0094.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/t94/T0094.remote-t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_3.a2m (9 sequences, 181 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 521662 \ -simple_threshold -14.862170884883 -Emax 10 \ -adpstyle 5 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.110497237569061 -db prefilter_3.fa -constraints tmp_4-a.cst -constraints_out tmp_4-a-md.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(21): Reading MODEL -- Model from alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k_3.a2m SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) ... Average NLL-Simple NULL score: -9.691990 Database has 2306 sequences with 682352 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.2 (June, 2000) compiled 07/06/00_15:43:43 Reading alignment file tmp_4-a.mult (6 sequences, 181 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/t94/T0094.remote-t2k.a2m @@@@ cp tmp_4-a.train.cst /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-31001 < /dev/null gzip -9f T0094.remote-t2k.a2m gunzip -c T0094.remote-t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0094.remote-t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.2 (June, 2000) compiled 07/10/00_09:40:44 rm tmp.a2m /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0094.remote-t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0094.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-858 @@@@ mkdir /projects/compbio/tmp/score-target-858/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-858/for-scorescript -a2msfile /projects/compbio/tmp/score-target-858/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-858/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k.a2m.gz /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/T0094.remote-t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-24656 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp -alignfile /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.2 (June, 2000) compiled 07/06/00_15:43:59 Reading alignment file /export/projects/compbio/experiments/casp4/t94/T0094.remote-t2k.a2m.gz (9 sequences, 181 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp.a2m. Dropping 3 (of 9) duplicate sequences with differing IDs Dropping 3 (of 9) duplicate sequences with identical IDs 5 sequences left after dropping 4 of 9 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (June, 2000) compiled 07/06/00_15:43:15 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp.a2m (5 sequences, 181 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp.mod /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/T0094.remote-t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ hmmscore /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/tmp13994 -i /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/T0094.remote-t2k.mod -db /projects/compbio/data/pdb/all-protein -SW_score 2 -viterbi 0 -select_score 4 -Emax 40.0 Reading parameter file /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/T0094.remote-t2k.mod /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/T0094.remote-t2k.mod(21): Reading MODEL -- Model from alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-24656/tmp.a2m SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 Calculating Distances (. = 1000 sequences) ....................... Average NLL-Simple NULL score: -9.446185 Database has 22453 sequences with 4882309 residues. @@@@ mv /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994/op_temp13994 /projects/compbio/tmp/score-target-858/score-target.op @@@@ rm -rf /projects/compbio/tmp/score-target-858/for-scorescript/split-tmp/beta-13994 < /dev/null @@@@ rm -rf /projects/compbio/tmp/score-target-858 /projects/compbio/experiments/models.97/scripts/2nd-rdb-to-sam-model T0094.t2k.2d.rdb T0094-t2k-2d.mod hmmscore T0094-t2k-2track \ -trackmod T0094.t2k-w0.5.mod,T0094-t2k-2d.mod \ -db /projects/compbio/experiments/test-set/fold-recognition-test/fssp-test-00/fssp-in-scop.seqs,/projects/compbio/experiments/test-set/fold-recognition-test/fssp-test-00/fssp-in-scop.2ds \ -alphabet protein,EHL2 \ -trackcoeff 0.5,0.5 \ -sw 2 -dpstyle 0 \ -select_score 4 -Emax 40. SAM: hmmscore v3.2 (June, 2000) compiled 07/18/00_10:49:49 T0094.t2k-w0.5.mod(23): Reading track 0 model from MODEL -- Model from alignment file /projects/compbio/tmp/tmp-build-weighted-model-eclipse-188/tmp.a2m T0094-t2k-2d.mod(1109): Reading track 1 model from MODEL -- Model from 2nd structure file T0094.t2k.2d.rdb Calculating Distances (. = 1000 sequences) .. Average NLL-Simple NULL score: -11.213199 Database has 1997 sequences with 465801 residues. rm T0094-t2k-2d.mod