make -k T0126-blast.rdb T0126-double-blast.rdb make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t126' /projects/compbio/experiments/casp4/scripts/single-blast -q T0126.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0126-blast.rdb starting T0126 with E=10 /projects/compbio/experiments/casp4/scripts/double-blast -q T0126.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0126-double-blast.rdb starting T0126 with E=0.000050 T0126 T0126 blasting: T0126 gi|92567|pir||A27450_1:162 blasting: T0126 gi|627558|pir||A54261_1:163 blasting: T0126 gi|3582105|emb|CAA09446.1|_4:156 blasting: T0126 gi|3582107|emb|CAA09447.1|_3:156 blasting: make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t126' make -k T0126.t2k.a2m.gz \ T0126.t2k.pa \ T0126.t2k.pa.html \ T0126.t2k.2d \ T0126.t2k.tree \ T0126.t2k_sorted.pa \ T0126.t2k.tree.ps \ T0126.t2k.tree-unroot.ps make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t126' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0126.t2k \ -seed T0126.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-gobble-14639 @@@@ cp /projects/compbio/experiments/casp4/t126/T0126.seq m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:52 # About to count sequences in /projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 0.01, actual: 0.0001 prefilter: 1, actual: 0.0002 prefilter: 10, actual: 0.001 prefilter: 400, actual: 0.005 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.8, 0.7, 0.6, 0.5 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 541007 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: blast_max_report= 20000 /projects/compbio/experiments/models.97/scripts2k/target2k: db=/projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=1 constraints=1 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 @@@@ blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 0.01,1,10,400 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-gobble-14845 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /projects/compbio/tmp/target2k-gobble-14639/prefilter_1.fa, 0.01 For /projects/compbio/tmp/target2k-gobble-14639/prefilter_2.fa, 1 For /projects/compbio/tmp/target2k-gobble-14639/prefilter_3.fa, 10 For /projects/compbio/tmp/target2k-gobble-14639/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-gobble-14639/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /projects/compbio/tmp/target2k-gobble-14639/m0.a2m (1 sequences, 163 columns) as A2M alignment. Writing sequence output to init.a2m. No sequences have been dropped. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=400 V=20000 B=0 -gi > 1.fasta-blast.out Searched 541007 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-gobble-14845 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (1 sequences, 163 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (1 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_1-a -i tmp_1-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -26.4115278685381 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -224.906052 Database has 7 sequences with 1130 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_1-a.mult (7 sequences, 163 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=8 nll_thresh=-22.4115278685381 frac_id=0.999999999999455 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999999999999455 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_1-a.train.seq (8 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 8) duplicate sequences with differing IDs Dropping 1 (of 8) sequences with > 100.0% id 6 sequences left after dropping 2 of 8 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_1-a.train.seq (6 sequences, 163 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -464.89 -239.22 -304.53 82.54 8 0 164 @@@@ hmmscore tmp_1-b -i tmp_1-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.4115278685381 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t126/T0126.t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(18): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -306.746857 Database has 8 sequences with 1293 residues. @@@@ cp -f tmp_1-b.mult /projects/compbio/experiments/casp4/t126/T0126.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_1.a2m (8 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_2-a -i tmp_2-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -25.7183806877933 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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 /projects/compbio/experiments/casp4/t126/T0126.t2k_1.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -249.392212 Database has 7 sequences with 1130 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_2-a.mult (7 sequences, 163 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=-21.7183806877933 frac_id=0.999999999998703 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999999999998703 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_2-a.train.seq (8 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 8) duplicate sequences with differing IDs Dropping 1 (of 8) sequences with > 100.0% id 6 sequences left after dropping 2 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 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_2-a.train.seq (6 sequences, 163 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 /projects/compbio/experiments/casp4/t126/T0126.t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -463.47 -234.43 -296.25 85.18 10 0 164 @@@@ hmmscore tmp_2-b -i tmp_2-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.7183806877933 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t126/T0126.t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(18): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -297.574738 Database has 8 sequences with 1293 residues. @@@@ cp -f tmp_2-b.mult /projects/compbio/experiments/casp4/t126/T0126.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_2.a2m (8 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_3-a -i tmp_3-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -24.1089427738805 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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 /projects/compbio/experiments/casp4/t126/T0126.t2k_2.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -126.216782 Database has 14 sequences with 2701 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_3-a.mult (7 sequences, 163 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=8 nll_thresh=-20.1089427738805 frac_id=0.999999999990304 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.999999999990304 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_3-a.train.seq (8 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 8) duplicate sequences with differing IDs Dropping 1 (of 8) sequences with > 100.0% id 6 sequences left after dropping 2 of 8 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_3-a.train.seq (6 sequences, 163 columns) as A2M alignment. @@@@ buildmodel tmp_3-b -insert tmp_3-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_3-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_3-a.w -constraints tmp_3-a.train.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(21): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -463.24 -222.90 -286.80 89.57 10 0 164 @@@@ hmmscore tmp_3-b -i tmp_3-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.1089427738805 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t126/T0126.t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(18): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -234.610550 Database has 10 sequences with 2366 residues. @@@@ cp -f tmp_3-b.mult /projects/compbio/experiments/casp4/t126/T0126.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_3.a2m (8 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_4-a -i tmp_4-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -22.4995048540528 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -db prefilter_4.fa -constraints tmp_4-a.cst -constraints_out tmp_4-a-md.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(21): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_3.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -15.288190 Database has 301 sequences with 91167 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_4-a.mult (7 sequences, 163 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=8 nll_thresh=-18.4995048540528 frac_id=0.999999999927507 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 0.999999999927507 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_4-a.train.seq (8 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 8) duplicate sequences with differing IDs Dropping 1 (of 8) sequences with > 100.0% id 6 sequences left after dropping 2 of 8 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_4-a.train.seq \ -aweight_bits 0.5\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_4-a.train.seq (6 sequences, 163 columns) as A2M alignment. @@@@ buildmodel tmp_4-b -insert tmp_4-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_4-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/fssp-trained.regularizer -sequence_weights tmp_4-a.w -constraints tmp_4-a.train.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(21): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_3.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -463.74 -213.50 -278.17 93.69 9 0 164 @@@@ hmmscore tmp_4-b -i tmp_4-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.4995048540528 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t126/T0126.t2k_4.cst Reading parameter file tmp_4-b.mod tmp_4-b.mod(18): Reading MODEL -- Final model for run tmp_4-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -277.769958 Database has 8 sequences with 1293 residues. @@@@ cp -f tmp_4-b.mult /projects/compbio/experiments/casp4/t126/T0126.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.t2k_4.cst -constraints_out tmp_5-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_4.a2m (8 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_5-a -i tmp_5-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 541007 \ -simple_threshold -22.4995048540528 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -db prefilter_4.fa -constraints tmp_5-a.cst -constraints_out tmp_5-a-md.cst Reading parameter file tmp_5-a.mod tmp_5-a.mod(21): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k_4.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -15.323913 Database has 301 sequences with 91167 residues. @@@@ sortseq tmp_5-a-sort -alignfile tmp_5-a.mult \ -NLLfile tmp_5-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_5-a.mult (7 sequences, 163 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/t126/T0126.t2k.a2m @@@@ cp tmp_5-a.train.cst /projects/compbio/experiments/casp4/t126/T0126.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-gobble-14639 < /dev/null gzip -f T0126.t2k.a2m T0126.t2k_*.a2m prettyalign T0126.t2k.a2m.gz -m8 -i -n -L3333 > T0126.t2k.pa SAM: prettyalign v3.2 (July 31, 2000) compiled 07/31/00_16:52:38 gunzip -c T0126.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0126.t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.2 (July 31, 2000) compiled 07/31/00_16:52:38 rm tmp.a2m echo ReadNeuralNet /projects/compbio/usr/karplus/predict-2nd/testing/networks/overrep-2500-IDaa13-5-10-7-10-5-10-11-ehl2-seeded9-stride-trained.net > tmp.script echo ReadA2M T0126.t2k.a2m.gz >> tmp.script echo PrintPrediction T0126.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0126.t2k.2d.seq >> tmp.script echo PrintRDB T0126.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 T0126.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0126.t2k.a2m with 8 sequences, total weight= 2.66497 avg weight= 0.333122 19 iterations Regularizing alignment for T0126.t2k.a2m.gz # After reading T0126.t2k.a2m.gz, have 163 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 T0126.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0126.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0126.t2k.2d.rdb # command:rm tmp.script gunzip -f T0126.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0126.t2k T0126.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0126.t2k.a2m (8 sequences) as A2M alignment. Alignment T0126.t2k.a2m read. Adding sequences:0 One dot for every 10 merges: . Merges done. CPU = user 0: 0:13 system 0: 0: 0 gzip -f T0126.t2k.a2m gzip -f T0126.t2k_sorted.a2m rm T0126.t2k.phytrace T0126.t2k.tree_weight prettyalign T0126.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0126.t2k_sorted.pa SAM: prettyalign v3.2 (July 31, 2000) compiled 07/31/00_16:52:38 /projects/compbio/usr/karplus/src/phytree/dg T0126.t2k.tree /projects/compbio/usr/karplus/src/phytree/dtree T0126.t2k.tree make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t126' echo "WeightingRegularizer /projects/compbio/lib/recode3.20comp" > tmp.script echo "SequenceWeight EntropyWeight 0.5 10.0" >> tmp.script echo "ReadA2M T0126.t2k.a2m.gz" >> tmp.script echo "SavingsRegularizer /projects/compbio/lib/recode3.20comp" >> tmp.script echo "PrintSavings T0126.t2k.saves" >> tmp.script echo "exit" >> tmp.script estimate-dist < tmp.script # command:Weighting regularizer set to recode3.20comp # command:Sequence weighting on input set to EntropyWeight(0.5, 10) # command:Reading A2M format from T0126.t2k.a2m.gz % using regularizer recode3.20comp % T0126.t2k.a2m.gz with 8 sequences, total weight= 1.08148 avg weight= 0.135185 After reading T0126.t2k.a2m.gz, have 163 columns, totalling 172.051 Using SequenceWeight EntropyWeight(0.5, 10) Using regularizer recode3.20compfor sequence weight regularizer. # command:Savings regularizer set to recode3.20comp # command:% Computing savings using regularizer recode3.20comp Printed 163 columns to T0126.t2k.saves # command:rm tmp.script if test -e T0126.t2k-logo.labels ;\ then makelogo -b 60 -t T0126.t2k -o T0126.t2k-logo.eps -l T0126.t2k-logo.labels T0126.t2k.saves ;\ else makelogo -b 60 -t T0126.t2k -o T0126.t2k-logo.eps -lf T0126.t2k.2d.seq T0126.t2k.saves ;\ fi /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0126.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0126.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-14822 @@@@ mkdir /projects/compbio/tmp/score-target-14822/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-14822/for-scorescript -a2msfile /projects/compbio/tmp/score-target-14822/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-14822/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-14822/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-14822/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /projects/compbio/experiments/casp4/t126/T0126.t2k.a2m.gz /projects/compbio/tmp/score-target-14822/for-scorescript/split-tmp/gobble-15033/T0126.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048/tmp -alignfile /projects/compbio/experiments/casp4/t126/T0126.t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /projects/compbio/experiments/casp4/t126/T0126.t2k.a2m.gz (8 sequences, 163 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048/tmp.a2m. Dropping 1 (of 8) duplicate sequences with differing IDs Dropping 5 (of 8) sequences with > 80.0% id 2 sequences left after dropping 6 of 8 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048/tmp.a2m (2 sequences, 163 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048/tmp.mod /projects/compbio/tmp/score-target-14822/for-scorescript/split-tmp/gobble-15033/T0126.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-gobble-15048 m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:52 # About to count sequences in /projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 1000, actual: 0.1 prefilter: 1000, actual: 1 prefilter: 2000, actual: 10 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.8, 0.7, 0.6 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 553635 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: blast_max_report= 20000 /projects/compbio/experiments/models.97/scripts2k/target2k: db=/projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=1 constraints=1 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 @@@@ blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 1000,1000,2000 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-beta-20099 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /export/projects/compbio/tmp/target2k-beta-27178/prefilter_1.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-27178/prefilter_2.fa, 1000 For /export/projects/compbio/tmp/target2k-beta-27178/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-27178/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/tmp/target2k-beta-27178/m0.a2m (8 sequences, 163 columns) as A2M alignment. Writing sequence output to init.a2m. Dropping 1 (of 8) duplicate sequences with differing IDs Dropping 1 (of 8) sequences with > 100.0% id 6 sequences left after dropping 2 of 8 sequences. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=2000 V=20000 B=0 -gi > 1.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 2.fasta E=2000 V=20000 B=0 -gi > 2.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 2.fasta < /dev/null @@@@ rm -f 2.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 3.fasta E=2000 V=20000 B=0 -gi > 3.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 3.fasta < /dev/null @@@@ rm -f 3.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 4.fasta E=2000 V=20000 B=0 -gi > 4.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 4.fasta < /dev/null @@@@ rm -f 4.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 5.fasta E=2000 V=20000 B=0 -gi > 5.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 5.fasta < /dev/null @@@@ rm -f 5.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 6.fasta E=2000 V=20000 B=0 -gi > 6.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 6.fasta < /dev/null @@@@ rm -f 6.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-20099 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (8 sequences, 163 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (8 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_1-a -i tmp_1-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -19.5268458162001 -Emax 0.1 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) .... Average NLL-Simple NULL score: -10.132829 Database has 3206 sequences with 1003484 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_1-a.mult (7 sequences, 163 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=15 nll_thresh=-15.5268458162001 frac_id=0.999974438060432 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999974438060432 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_1-a.train.seq (15 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 15) duplicate sequences with differing IDs Dropping 2 (of 15) duplicate sequences with identical IDs Dropping 2 (of 15) sequences with > 100.0% id 6 sequences left after dropping 9 of 15 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_1-a.train.seq (6 sequences, 163 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -465.21 -434.07 -455.14 14.57 3 0 164 @@@@ hmmscore tmp_1-b -i tmp_1-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -19.5268458162001 -Emax 0.1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 0.1 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(18): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -180.441849 Database has 34 sequences with 8585 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.remote-t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_1.a2m (15 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_2-a -i tmp_2-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -17.2242590975847 -Emax 1 \ -adpstyle 1 \ -align_short 0 -mdEmax 1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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/t126/T0126.remote-t2k_1.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) .... Average NLL-Simple NULL score: -13.749451 Database has 3206 sequences with 1003484 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_2-a.mult (7 sequences, 163 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=15 nll_thresh=-13.2242590975847 frac_id=0.999881365662175 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999881365662175 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_2-a.train.seq (15 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 15) duplicate sequences with differing IDs Dropping 2 (of 15) duplicate sequences with identical IDs Dropping 2 (of 15) sequences with > 100.0% id 6 sequences left after dropping 9 of 15 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-a.train.seq \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_2-a.train.seq (6 sequences, 163 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/t126/T0126.remote-t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -463.86 -433.78 -454.02 14.20 3 0 164 @@@@ hmmscore tmp_2-b -i tmp_2-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -17.2242590975847 -Emax 1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 1 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(18): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -18.368172 Database has 863 sequences with 352066 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.remote-t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_2.a2m (15 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_3-a -i tmp_3-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -14.9216577482315 -Emax 10 \ -adpstyle 1 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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/t126/T0126.remote-t2k_2.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) .... Average NLL-Simple NULL score: -9.773740 Database has 3206 sequences with 1003484 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_3-a.mult (7 sequences, 163 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=15 nll_thresh=-10.9216577482315 frac_id=0.999449639425348 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.999449639425348 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_3-a.train.seq (15 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 15) duplicate sequences with differing IDs Dropping 2 (of 15) duplicate sequences with identical IDs Dropping 2 (of 15) sequences with > 99.9% id 6 sequences left after dropping 9 of 15 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_3-a.train.seq (6 sequences, 163 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/t126/T0126.remote-t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -464.15 -436.15 -454.99 13.15 3 0 164 @@@@ hmmscore tmp_3-b -i tmp_3-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -14.9216577482315 -Emax 10 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 10 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(18): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -19.985554 Database has 574 sequences with 196624 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_3.a2m @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.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/t126/T0126.remote-t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k_3.a2m (15 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_4-a -i tmp_4-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -14.9216577482315 -Emax 10 \ -adpstyle 5 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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/t126/T0126.remote-t2k_3.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) .... Average NLL-Simple NULL score: -9.773740 Database has 3206 sequences with 1003484 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_4-a.mult (7 sequences, 163 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/t126/T0126.remote-t2k.a2m @@@@ cp tmp_4-a.train.cst /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-27178 < /dev/null gzip -9f T0126.remote-t2k.a2m gunzip -c T0126.remote-t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0126.remote-t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.2 (July 31, 2000) compiled 08/11/00_16:27:51 rm tmp.a2m echo "WeightingRegularizer /projects/compbio/lib/recode3.20comp" > tmp.script echo "SequenceWeight EntropyWeight 0.5 10.0" >> tmp.script echo "ReadA2M T0126.remote-t2k.a2m.gz" >> tmp.script echo "SavingsRegularizer /projects/compbio/lib/recode3.20comp" >> tmp.script echo "PrintSavings T0126.remote-t2k.saves" >> tmp.script echo "exit" >> tmp.script estimate-dist < tmp.script # command:Weighting regularizer set to recode3.20comp # command:Sequence weighting on input set to EntropyWeight(0.5, 10) # command:Reading A2M format from T0126.remote-t2k.a2m.gz % using regularizer recode3.20comp % T0126.remote-t2k.a2m.gz with 15 sequences, total weight= 1.08275 avg weight= 0.0721831 After reading T0126.remote-t2k.a2m.gz, have 163 columns, totalling 172.152 Using SequenceWeight EntropyWeight(0.5, 10) Using regularizer recode3.20compfor sequence weight regularizer. # command:Savings regularizer set to recode3.20comp # command:% Computing savings using regularizer recode3.20comp Printed 163 columns to T0126.remote-t2k.saves # command:rm tmp.script if test -e T0126.remote-t2k-logo.labels ;\ then makelogo -b 60 -t T0126.remote-t2k -o T0126.remote-t2k-logo.eps -ln T0126.remote-t2k-logo.labels T0126.remote-t2k.saves ;\ else makelogo -b 60 -a -t T0126.remote-t2k -o T0126.remote-t2k-logo.eps -lf T0126.remote-t2k.2d.seq -u T0126.seq T0126.remote-t2k.saves ;\ fi Invalid fasta label file : T0126.remote-t2k.2d.seq /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0126.remote-t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0126.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-10311 @@@@ mkdir /projects/compbio/tmp/score-target-10311/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-10311/for-scorescript -a2msfile /projects/compbio/tmp/score-target-10311/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-10311/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-10311/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-10311/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k.a2m.gz /projects/compbio/tmp/score-target-10311/for-scorescript/split-tmp/beta-15435/T0126.remote-t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-23300 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-23300/tmp -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remote-t2k.a2m.gz (15 sequences, 163 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-23300/tmp.a2m. Dropping 2 (of 15) duplicate sequences with differing IDs Dropping 2 (of 15) duplicate sequences with identical IDs Dropping 5 (of 15) sequences with > 80.0% id 2 sequences left after dropping 13 of 15 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-23300/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-23300/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-23300/tmp.a2m (2 sequences, 163 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-23300/tmp.mod /projects/compbio/tmp/score-target-10311/for-scorescript/split-tmp/beta-15435/T0126.remote-t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-23300 100.0% id 6 sequences left after dropping 2 of 8 sequences. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=10000 V=20000 B=0 -gi > 1.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 2.fasta E=10000 V=20000 B=0 -gi > 2.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 2.fasta < /dev/null @@@@ rm -f 2.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 3.fasta E=10000 V=20000 B=0 -gi > 3.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 3.fasta < /dev/null @@@@ rm -f 3.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 4.fasta E=10000 V=20000 B=0 -gi > 4.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 4.fasta < /dev/null @@@@ rm -f 4.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 5.fasta E=10000 V=20000 B=0 -gi > 5.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 5.fasta < /dev/null @@@@ rm -f 5.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 6.fasta E=10000 V=20000 B=0 -gi > 6.fasta-blast.out Searched 553635 sequences # parsing wu-blastp output @@@@ rm -f 6.fasta < /dev/null @@@@ rm -f 6.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-10154 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (8 sequences, 163 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file m0.a2m (8 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_1-a -i tmp_1-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -17.2242590975847 -Emax 1 \ -adpstyle 1 \ -align_short 0 -mdEmax 1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ............. Average NLL-Simple NULL score: -9.113834 Database has 12437 sequences with 4493267 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_1-a.mult (7 sequences, 163 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=15 nll_thresh=-13.2242590975847 frac_id=0.999881365662175 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999881365662175 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_1-a.train.seq (15 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 15) duplicate sequences with differing IDs Dropping 2 (of 15) duplicate sequences with identical IDs Dropping 2 (of 15) sequences with > 100.0% id 6 sequences left after dropping 9 of 15 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_1-a.train.seq (6 sequences, 163 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(21): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -465.21 -434.07 -455.14 14.57 3 0 164 @@@@ hmmscore tmp_1-b -i tmp_1-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -17.2242590975847 -Emax 1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 1 -constraints tmp_1-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(18): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -52.833046 Database has 140 sequences with 59388 residues. @@@@ cp -f tmp_1-b.mult /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.remoter-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/t126/T0126.remoter-t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_1.a2m (15 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_2-a -i tmp_2-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -14.9216577482315 -Emax 10 \ -adpstyle 1 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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/t126/T0126.remoter-t2k_1.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ............. Average NLL-Simple NULL score: -13.190492 Database has 12437 sequences with 4493267 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_2-a.mult (7 sequences, 163 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=15 nll_thresh=-10.9216577482315 frac_id=0.999449639425348 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999449639425348 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_2-a.train.seq (15 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 15) duplicate sequences with differing IDs Dropping 2 (of 15) duplicate sequences with identical IDs Dropping 2 (of 15) sequences with > 99.9% id 6 sequences left after dropping 9 of 15 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-a.train.seq \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_2-a.train.seq (6 sequences, 163 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/t126/T0126.remoter-t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -463.86 -433.78 -454.02 14.20 3 0 164 @@@@ hmmscore tmp_2-b -i tmp_2-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -14.9216577482315 -Emax 10 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 10 -constraints tmp_2-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(18): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ...... Average NLL-Simple NULL score: -11.027126 Database has 5901 sequences with 2364661 residues. @@@@ cp -f tmp_2-b.mult /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.remoter-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/t126/T0126.remoter-t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_2.a2m (16 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_3-a -i tmp_3-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -12.6189100771092 -Emax 100 \ -adpstyle 1 \ -align_short 0 -mdEmax 100\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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/t126/T0126.remoter-t2k_2.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ............. Average NLL-Simple NULL score: -8.946619 Database has 12437 sequences with 4493267 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_3-a.mult (11 sequences, 163 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=19 nll_thresh=-8.61891007710923 frac_id=0.991520199379974 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.991520199379974 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_3-a.train.seq (19 sequences, 163 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 19) duplicate sequences with differing IDs Dropping 2 (of 19) duplicate sequences with identical IDs Dropping 2 (of 19) sequences with > 99.2% id 10 sequences left after dropping 9 of 19 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file tmp_3-a.train.seq (10 sequences, 163 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/t126/T0126.remoter-t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.2 (July 31, 2000) compiled 07/31/00_14:08:12 -464.79 -9.17 -286.44 219.00 40 0 164 @@@@ hmmscore tmp_3-b -i tmp_3-b.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -12.6189100771092 -Emax 100 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.122699386503067 \ -align_short 5 -mdEmax 100 -constraints tmp_3-a.train.cst -constraints_out /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(18): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ..... Average NLL-Simple NULL score: -9.335401 Database has 4293 sequences with 1425033 residues. @@@@ cp -f tmp_3-b.mult /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_3.a2m @@@@ modelfromalign tmp_4-a -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.remoter-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/t126/T0126.remoter-t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k_3.a2m (25 sequences, 163 columns) as A2M alignment. @@@@ hmmscore tmp_4-a -i tmp_4-a.mod -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -dpstyle 0 \ -subtract_null 4 -sort 2 \ -db_size 553635 \ -simple_threshold -12.6189100771092 -Emax 100 \ -adpstyle 5 \ -align_short 0 -mdEmax 100\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.122699386503067 -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/t126/T0126.remoter-t2k_3.a2m SAM: hmmscore v3.2 (July 31, 2000) compiled 08/04/00_11:31:33 Calculating Distances (. = 1000 sequences) ............. Average NLL-Simple NULL score: -8.553579 Database has 12437 sequences with 4493267 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:48 Reading alignment file tmp_4-a.mult (16 sequences, 163 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/t126/T0126.remoter-t2k.a2m @@@@ cp tmp_4-a.train.cst /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-21633 < /dev/null gzip -9f T0126.remoter-t2k.a2m echo "WeightingRegularizer /projects/compbio/lib/recode3.20comp" > tmp.script echo "SequenceWeight EntropyWeight 0.5 10.0" >> tmp.script echo "ReadA2M T0126.remoter-t2k.a2m.gz" >> tmp.script echo "SavingsRegularizer /projects/compbio/lib/recode3.20comp" >> tmp.script echo "PrintSavings T0126.remoter-t2k.saves" >> tmp.script echo "exit" >> tmp.script estimate-dist < tmp.script # command:Weighting regularizer set to recode3.20comp # command:Sequence weighting on input set to EntropyWeight(0.5, 10) # command:Reading A2M format from T0126.remoter-t2k.a2m.gz % using regularizer recode3.20comp % T0126.remoter-t2k.a2m.gz with 24 sequences, total weight= 3.03556 avg weight= 0.126482 After reading T0126.remoter-t2k.a2m.gz, have 163 columns, totalling 286.312 Using SequenceWeight EntropyWeight(0.5, 10) Using regularizer recode3.20compfor sequence weight regularizer. # command:Savings regularizer set to recode3.20comp # command:% Computing savings using regularizer recode3.20comp Printed 163 columns to T0126.remoter-t2k.saves # command:rm tmp.script 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 T0126.remoter-t2k.a2m.gz >> tmp.script echo PrintPrediction T0126.remoter-t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0126.remoter-t2k.2d.seq >> tmp.script echo PrintRDB T0126.remoter-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 T0126.remoter-t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0126.remoter-t2k.a2m with 24 sequences, total weight= 9.87474 avg weight= 0.411447 38 iterations Regularizing alignment for T0126.remoter-t2k.a2m.gz # After reading T0126.remoter-t2k.a2m.gz, have 163 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 T0126.remoter-t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0126.remoter-t2k.2d.seq # command:# Network initialization done # Printing prediction to T0126.remoter-t2k.2d.rdb # command:rm tmp.script if test -e T0126.remoter-t2k-logo.labels ;\ then makelogo -b 60 -t T0126.remoter-t2k -o T0126.remoter-t2k-logo.eps -ln T0126.remoter-t2k-logo.labels T0126.remoter-t2k.saves ;\ else makelogo -b 60 -a -t T0126.remoter-t2k -o T0126.remoter-t2k-logo.eps -lf T0126.remoter-t2k.2d.seq -u T0126.seq T0126.remoter-t2k.saves ;\ fi gunzip -c T0126.remoter-t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0126.remoter-t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.2 (July 31, 2000) compiled 08/11/00_16:27:51 rm tmp.a2m /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0126.remoter-t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0126.remoter-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-16942 @@@@ mkdir /projects/compbio/tmp/score-target-16942/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-16942/for-scorescript -a2msfile /projects/compbio/tmp/score-target-16942/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-16942/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-16942/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-16942/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k.a2m.gz /projects/compbio/tmp/score-target-16942/for-scorescript/split-tmp/beta-13124/T0126.remoter-t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-18288 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-18288/tmp -alignfile /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file /export/projects/compbio/experiments/casp4/t126/T0126.remoter-t2k.a2m.gz (24 sequences, 163 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-18288/tmp.a2m. Dropping 2 (of 24) duplicate sequences with differing IDs Dropping 2 (of 24) duplicate sequences with identical IDs Dropping 6 (of 24) sequences with > 80.0% id 10 sequences left after dropping 14 of 24 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-18288/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-18288/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-18288/tmp.a2m (10 sequences, 163 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-18288/tmp.mod /projects/compbio/tmp/score-target-16942/for-scorescript/split-tmp/beta-13124/T0126.remoter-t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-18288 80.0% id 10 sequences left after dropping 14 of 24 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-22776/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-22776/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.2 (July 31, 2000) compiled 07/31/00_14:08:27 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-22776/tmp.a2m (10 sequences, 163 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-22776/tmp.mod T0126.remoter-t2k-w0.5.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-22776