make -k T0092-blast.rdb T0092-double-blast.rdb make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t92' /projects/compbio/experiments/casp3/scripts/single-blast -q T0092.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0092-blast.rdb starting T0092 with E=10 /projects/compbio/experiments/casp3/scripts/double-blast -q T0092.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0092-double-blast.rdb starting T0092 with E=0.000050 T0092 T0092 blasting: T0092 gi|1175220|sp|P43985|YECO_HAEIN_1:241 blasting: T0092 gi|7470360|pir||S74478_56:256 blasting: T0092 gi|3025151|sp|P76290|YECO_ECOLI_4:242 blasting: T0092 gi|7449894|pir||D64568_1:242 blasting: T0092 gi|7449893|pir||F71861_1:242 blasting: T0092 gi|7518112|pir||D75063_148:300 blasting: T0092 gi|6968057|emb|CAB75226.1|_1:235 blasting: make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t92' make -k T0092.t2k.a2m.gz \ T0092.t2k.pa \ T0092.t2k.pa.html \ T0092.t2k.2d \ T0092.t2k.tree \ T0092.t2k_sorted.pa \ T0092.t2k.tree-unroot.ps make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t92' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0092.t2k \ -seed T0092.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-22501 @@@@ cp /projects/compbio/experiments/casp4/t92/T0092.seq m0.a2m @@@@ checkseq foo -alphabet protein -db m0.a2m > init.check SAM: checkseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:44 # About to count sequences in /projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 0.01, actual: 0.0001 prefilter: 1, actual: 0.0002 prefilter: 10, actual: 0.001 prefilter: 400, actual: 0.005 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.8, 0.7, 0.6, 0.5 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 503479 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: blast_max_report= 20000 /projects/compbio/experiments/models.97/scripts2k/target2k: db=/projects/compbio/data/nrp/nr /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=1 constraints=1 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 @@@@ blast-prefilter -out prefilter -seed m0.a2m -prefilter_thresholds 0.01,1,10,400 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-beta-2080 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /projects/compbio/tmp/target2k-beta-22501/prefilter_1.fa, 0.01 For /projects/compbio/tmp/target2k-beta-22501/prefilter_2.fa, 1 For /projects/compbio/tmp/target2k-beta-22501/prefilter_3.fa, 10 For /projects/compbio/tmp/target2k-beta-22501/prefilter_4.fa, 400 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: db=/projects/compbio/data/nrp/nr @@@@ uniqueseq init -alignfile /projects/compbio/tmp/target2k-beta-22501/m0.a2m -a protein -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file /projects/compbio/tmp/target2k-beta-22501/m0.a2m (1 sequences, 241 columns) as A2M alignment. Writing sequence output to init.a2m. No sequences have been droppd. @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 1.fasta E=400 V=20000 B=0 -gi > 1.fasta-blast.out Searched 503479 sequences # parsing wu-blastp output @@@@ rm -f 1.fasta < /dev/null @@@@ rm -f 1.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-beta-2080 < /dev/null @@@@ modelfromalign unused -alignfile m0.a2m \ -constraints_from_align 1 -constraints_out m0.cst SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file m0.a2m (1 sequences, 241 columns) as A2M alignment. # About to count sequences in m0.a2m # About to count sequences in prefilter_1.fa @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.regularizer \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 -constraints m0.cst -constraints_out tmp_1-a.cst Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file m0.a2m (1 sequences, 241 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 503479 \ -simple_threshold -26.3396376540048 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0829875518672199 -db prefilter_1.fa -constraints tmp_1-a.cst -constraints_out tmp_1-a-md.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(23): Reading MODEL -- Model from alignment file m0.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -93.646652 Database has 15 sequences with 4030 residues. @@@@ sortseq tmp_1-a-sort -alignfile tmp_1-a.mult \ -NLLfile tmp_1-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_1-a.mult (5 sequences, 241 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=6 nll_thresh=-22.3396376540048 frac_id=1 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 1 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (6 sequences, 241 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 6) duplicate sequences with differing IDs 5 sequences left after dropping 1 of 6 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-a.train.seq \ -aweight_bits 0.8\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_1-a.train.seq (5 sequences, 241 columns) as A2M alignment. @@@@ buildmodel tmp_1-b -insert tmp_1-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_1-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/gap1.5.regularizer -sequence_weights tmp_1-a.w -constraints tmp_1-a.train.cst Reading parameter file tmp_1-a.mod tmp_1-a.mod(23): Reading MODEL -- Model from alignment file m0.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/gap1.5.regularizer /projects/compbio/lib/gap1.5.regularizer(1): Reading REGULARIZER: gap1.5. Weak regularizer, gaps average 1.5, matches average 10 SAM: buildmodel v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 Warning: only 5 training sequences; Buildmodel needs 5--100 sequences for best results unless the SAM-T99 method is used. -695.83 -310.05 -406.99 164.03 9 0 242 @@@@ 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 503479 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.3396376540048 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0829875518672199 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t92/T0092.t2k_1.cst Reading parameter file tmp_1-b.mod tmp_1-b.mod(20): Reading MODEL -- Final model for run tmp_1-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -191.270325 Database has 15 sequences with 4064 residues. @@@@ cp -f tmp_1-b.mult /projects/compbio/experiments/casp4/t92/T0092.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /projects/compbio/experiments/casp4/t92/T0092.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/t92/T0092.t2k_1.cst -constraints_out tmp_2-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_1.a2m (14 sequences, 241 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 503479 \ -simple_threshold -25.6464904732463 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0829875518672199 -db prefilter_2.fa -constraints tmp_2-a.cst -constraints_out tmp_2-a-md.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_1.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -107.395058 Database has 33 sequences with 10893 residues. @@@@ sortseq tmp_2-a-sort -alignfile tmp_2-a.mult \ -NLLfile tmp_2-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_2-a.mult (29 sequences, 241 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=30 nll_thresh=-21.6464904732463 frac_id=0.999412347758447 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.999412347758447 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (30 sequences, 241 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 30) duplicate sequences with differing IDs 28 sequences left after dropping 2 of 30 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-a.train.seq \ -aweight_bits 0.7\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_2-a.train.seq (28 sequences, 241 columns) as A2M alignment. @@@@ buildmodel tmp_2-b -insert tmp_2-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_2-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_2-a.w -constraints tmp_2-a.train.cst Reading parameter file tmp_2-a.mod tmp_2-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_1.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -697.33 -40.23 -128.35 125.74 10 0 242 @@@@ 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 503479 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.6464904732463 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0829875518672199 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t92/T0092.t2k_2.cst Reading parameter file tmp_2-b.mod tmp_2-b.mod(20): Reading MODEL -- Final model for run tmp_2-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -144.947479 Database has 33 sequences with 10891 residues. @@@@ cp -f tmp_2-b.mult /projects/compbio/experiments/casp4/t92/T0092.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /projects/compbio/experiments/casp4/t92/T0092.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/t92/T0092.t2k_2.cst -constraints_out tmp_3-a.cst Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_2.a2m (33 sequences, 241 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 503479 \ -simple_threshold -24.0370525592232 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0829875518672199 -db prefilter_3.fa -constraints tmp_3-a.cst -constraints_out tmp_3-a-md.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_2.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -94.595390 Database has 61 sequences with 23052 residues. @@@@ sortseq tmp_3-a-sort -alignfile tmp_3-a.mult \ -NLLfile tmp_3-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_3-a.mult (53 sequences, 241 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=54 nll_thresh=-20.0370525592232 frac_id=0.980896392487326 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.980896392487326 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (54 sequences, 241 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 6 (of 54) duplicate sequences with differing IDs 48 sequences left after dropping 6 of 54 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-a.train.seq \ -aweight_bits 0.6\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_3-a.train.seq (48 sequences, 241 columns) as A2M alignment. @@@@ buildmodel tmp_3-b -insert tmp_3-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_3-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/stiff-gap5.regularizer -sequence_weights tmp_3-a.w -constraints tmp_3-a.train.cst Reading parameter file tmp_3-a.mod tmp_3-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/stiff-gap5.regularizer /projects/compbio/lib/stiff-gap5.regularizer(1): Reading REGULARIZER: gap5. stiff regularizer, gaps averge 5, matches average 10 SAM: buildmodel v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -697.08 -29.81 -104.50 96.89 6 0 242 @@@@ 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 503479 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.0370525592232 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0829875518672199 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t92/T0092.t2k_3.cst Reading parameter file tmp_3-b.mod tmp_3-b.mod(20): Reading MODEL -- Final model for run tmp_3-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -124.063828 Database has 54 sequences with 19839 residues. @@@@ cp -f tmp_3-b.mult /projects/compbio/experiments/casp4/t92/T0092.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /projects/compbio/experiments/casp4/t92/T0092.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/t92/T0092.t2k_3.cst -constraints_out tmp_4-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_3.a2m (54 sequences, 241 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 503479 \ -simple_threshold -22.4276146388444 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0829875518672199 -db prefilter_4.fa -constraints tmp_4-a.cst -constraints_out tmp_4-a-md.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_3.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -32.231735 Database has 399 sequences with 142544 residues. @@@@ sortseq tmp_4-a-sort -alignfile tmp_4-a.mult \ -NLLfile tmp_4-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_4-a.mult (132 sequences, 241 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=133 nll_thresh=-18.4276146388444 frac_id=0.839902771342126 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 0.839902771342126 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_4-a.train.seq (133 sequences, 241 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 11 (of 133) duplicate sequences with differing IDs Dropping 10 (of 133) sequences with > 84.0% id 112 sequences left after dropping 21 of 133 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_4-a.train.seq \ -aweight_bits 0.5\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1 \ -aweight_method 1\ -aweight_exponent 10 SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file tmp_4-a.train.seq (112 sequences, 241 columns) as A2M alignment. @@@@ buildmodel tmp_4-b -insert tmp_4-a.mod\ -fimtrans -1\ -fimstrength 1\ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -binary_output 1\ -prior_library /projects/compbio/lib/recode3.20comp \ -a2mdots 0 \ -a protein \ -sw 2 -jump_in_prob 0.2 -jump_out_prob 1\ -modellength 0 \ -internal_weight 0 \ -anneal_length 2 \ -many_files 1 \ -Nseq 20000\ -nsurgery 0 \ -fracinsert 0.2 \ -cutinsert 0.25 -cutmatch 0.2 -initial_noise 0.0001 -anneal_noise 0.000001 \ -internal_weight 0 \ -train tmp_4-a.train.seq \ -nmodels 1\ -insert /projects/compbio/lib/fssp-trained.regularizer -sequence_weights tmp_4-a.w -constraints tmp_4-a.train.cst Reading parameter file tmp_4-a.mod tmp_4-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_3.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -697.72 -16.98 -85.06 65.37 8 0 242 @@@@ 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 503479 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.4276146388444 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0829875518672199 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t92/T0092.t2k_4.cst Reading parameter file tmp_4-b.mod tmp_4-b.mod(20): Reading MODEL -- Final model for run tmp_4-b SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -93.387787 Database has 134 sequences with 45183 residues. @@@@ cp -f tmp_4-b.mult /projects/compbio/experiments/casp4/t92/T0092.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /projects/compbio/experiments/casp4/t92/T0092.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/t92/T0092.t2k_4.cst -constraints_out tmp_5-a.cst Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_4.a2m (134 sequences, 241 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 503479 \ -simple_threshold -22.4276146388444 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0829875518672199 -db prefilter_4.fa -constraints tmp_5-a.cst -constraints_out tmp_5-a-md.cst Reading parameter file tmp_5-a.mod tmp_5-a.mod(23): Reading MODEL -- Model from alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k_4.a2m SAM: hmmscore v3.1b (February 24, 1999) compiled 05/16/00_17:09:35 Calculating Distances (. = 1000 sequences) . Average NLL-Simple NULL score: -36.188789 Database has 399 sequences with 142544 residues. @@@@ sortseq tmp_5-a-sort -alignfile tmp_5-a.mult \ -NLLfile tmp_5-a.mstat -a2mdots 0 SAM: sortseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:38 Reading alignment file tmp_5-a.mult (130 sequences, 241 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/t92/T0092.t2k.a2m @@@@ cp tmp_5-a.train.cst /projects/compbio/experiments/casp4/t92/T0092.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-22501 < /dev/null gzip -f T0092.t2k.a2m T0092.t2k_*.a2m prettyalign T0092.t2k.a2m.gz -m8 -i -n -L3333 > T0092.t2k.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 gunzip -c T0092.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0092.t2k.pa.html SAM: /projects/compbio/bin/alpha/prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 rm tmp.a2m echo ReadNeuralNet /projects/compbio/usr/karplus/predict-2nd/testing/networks/overrep-2500-IDaa13-5-9-7-10-5-9-11-ehl2-seeded2-stride-trained.net > tmp.script echo ReadA2M T0092.t2k.a2m.gz >> tmp.script echo PrintPrediction T0092.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0092.t2k.2d.seq >> tmp.script echo PrintRDB T0092.t2k.2d.rdb >> tmp.script predict-2nd < tmp.script # command:# Neural network set to overrep-2500-IDaa13-5-9-7-10-5-9-11-ehl2-seeded2-stride-trained.net # command:# Reading A2M format from T0092.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0092.t2k.a2m with 131 sequences, total weight= 80.4533 avg weight= 0.614148 clipped 46 iterations # AdjustWeights couldn't save exactly 1.4 bits/position, saving 0.802916 bits. Regularizing alignment for T0092.t2k.a2m.gz # After reading T0092.t2k.a2m.gz, have 241 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 T0092.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0092.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0092.t2k.2d.rdb # command:rm tmp.script gunzip -f T0092.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0092.t2k T0092.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0092.t2k.a2m (131 sequences) as A2M alignment. Alignment T0092.t2k.a2m read. Adding sequences:0 10 20 30 40 50 60 70 80 90 100 110 120 130 One dot for every 10 merges: ............. Merges done. CPU = user 0: 2:22 system 0: 0: 0 gzip -f T0092.t2k.a2m gzip -f T0092.t2k_sorted.a2m rm T0092.t2k.phytrace T0092.t2k.tree_weight prettyalign T0092.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0092.t2k_sorted.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 /projects/compbio/usr/karplus/src/phytree/dtree T0092.t2k.tree make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t92' /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0092.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0092.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-90 @@@@ mkdir /projects/compbio/tmp/score-target-90/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-90/for-scorescript -a2msfile /projects/compbio/tmp/score-target-90/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-90/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-90/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-90/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /projects/compbio/experiments/casp4/t92/T0092.t2k.a2m.gz /projects/compbio/tmp/score-target-90/for-scorescript/split-tmp/beta-29832/T0092.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-277 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-277/tmp -alignfile /projects/compbio/experiments/casp4/t92/T0092.t2k.a2m.gz \ -a protein -percent_id 0.8 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file /projects/compbio/experiments/casp4/t92/T0092.t2k.a2m.gz (131 sequences, 241 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-277/tmp.a2m. Dropping 8 (of 131) duplicate sequences with differing IDs Dropping 17 (of 131) sequences with > 80.0% id 106 sequences left after dropping 25 of 131 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-277/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-277/tmp.a2m \ -insert /projects/compbio/lib/fssp-trained.regularizer \ -ins_jump_conf 1 \ -match_jump_conf 1 \ -del_jump_conf 1 \ -prior_library /projects/compbio/lib/recode3.20comp \ -binary_output 1 -a protein -aweight_method 1 -aweight_bits 0.5 -aweight_exponent 10 Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: modelfromalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:13 Reading alignment file /projects/compbio/tmp/tmp-build-weighted-model-beta-277/tmp.a2m (106 sequences, 241 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-277/tmp.mod /projects/compbio/tmp/score-target-90/for-scorescript/split-tmp/beta-29832/T0092.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-277 tmp.script echo ReadA2M T0092.t2k.a2m.gz >> tmp.script echo PrintPrediction T0092.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0092.t2k.2d.seq >> tmp.script echo PrintRDB T0092.t2k.2d.rdb >> tmp.script predict-2nd < tmp.script # command:# Neural network set to overrep-2500-IDaa13-5-9-7-10-5-10-11-ehl2-seeded4-stride-trained.net # command:# Reading A2M format from T0092.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0092.t2k.a2m with 131 sequences, total weight= 80.4533 avg weight= 0.614148 clipped 46 iterations # AdjustWeights couldn't save exactly 1.4 bits/position, saving 0.802916 bits. Regularizing alignment for T0092.t2k.a2m.gz # After reading T0092.t2k.a2m.gz, have 241 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 T0092.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0092.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0092.t2k.2d.rdb # command:rm tmp.script make: Nothing to be done for `T0092.t2k.2d.rdb'. make: Nothing to be done for `T0092.t2k.2d.seq'. echo ReadNeuralNet /projects/compbio/usr/karplus/predict-2nd/testing/networks/overrep-2500-IDaa13-5-10-7-10-5-10-11-ehl2-seeded9-stride-trained.net > tmp.script echo ReadA2M T0092.t2k.a2m.gz >> tmp.script echo PrintPrediction T0092.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0092.t2k.2d.seq >> tmp.script echo PrintRDB T0092.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 T0092.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0092.t2k.a2m with 131 sequences, total weight= 80.4533 avg weight= 0.614148 clipped 46 iterations # AdjustWeights couldn't save exactly 1.4 bits/position, saving 0.802916 bits. Regularizing alignment for T0092.t2k.a2m.gz # After reading T0092.t2k.a2m.gz, have 241 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 T0092.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0092.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0092.t2k.2d.rdb # command:rm tmp.script