/projects/compbio/experiments/models.97/scripts2k/target2k -out T0088.remote-t2k \ -seed T0088.t2k.a2m.gz -all \ -iter 3 \ -thresholds 1,10,100 \ -prefilter_thresholds 1000,2000,10000 @@@@ chgrp protein /projects/compbio/tmp/target2k-eclipse-1823 @@@@ gunzip -c /projects/compbio/experiments/casp4/t88/T0088.t2k.a2m.gz > 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: 1 prefilter: 2000, actual: 10 prefilter: 10000, actual: 100 /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= 551100 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 1000,2000,10000 -db /projects/compbio/data/nrp/nr -blast_max_report 20000 @@@@ chgrp protein /projects/compbio/tmp/blast-prefilter-eclipse-223 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /projects/compbio/tmp/target2k-eclipse-1823/prefilter_1.fa, 1000 For /projects/compbio/tmp/target2k-eclipse-1823/prefilter_2.fa, 2000 For /projects/compbio/tmp/target2k-eclipse-1823/prefilter_3.fa, 10000 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: db=/projects/compbio/data/nrp/nr @@@@ uniqueseq init -alignfile /projects/compbio/tmp/target2k-eclipse-1823/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-eclipse-1823/m0.a2m (10 sequences, 156 columns) as A2M alignment. Writing sequence output to init.a2m. Dropping 2 (of 10) duplicate sequences with differing IDs 8 sequences left after dropping 2 of 10 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 551100 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 551100 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 551100 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 551100 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 551100 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 551100 sequences # parsing wu-blastp output @@@@ rm -f 6.fasta < /dev/null @@@@ rm -f 6.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 7.fasta E=10000 V=20000 B=0 -gi > 7.fasta-blast.out Searched 551100 sequences # parsing wu-blastp output @@@@ rm -f 7.fasta < /dev/null @@@@ rm -f 7.fasta-blast.out < /dev/null @@@@ /projects/compbio/bin/wu-blastp /projects/compbio/data/nrp/nr 8.fasta E=10000 V=20000 B=0 -gi > 8.fasta-blast.out Searched 551100 sequences # parsing wu-blastp output @@@@ rm -f 8.fasta < /dev/null @@@@ rm -f 8.fasta-blast.out < /dev/null # Extracting hits in FASTA format from /projects/compbio/data/nrp/nr @@@@ rm -rf /projects/compbio/tmp/blast-prefilter-eclipse-223 < /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 (10 sequences, 156 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 (10 sequences, 156 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 551100 \ -simple_threshold -17.219669745317 -Emax 1 \ -adpstyle 1 \ -align_short 0 -mdEmax 1\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.128205128205128 -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: -10.044186 Database has 9367 sequences with 3394734 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 (9 sequences, 156 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=19 nll_thresh=-13.219669745317 frac_id=0.999239713543954 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999239713543954 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_1-a.train.seq (19 sequences, 156 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 4 (of 19) duplicate sequences with differing IDs Dropping 4 (of 19) duplicate sequences with identical IDs 8 sequences left after dropping 11 of 19 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 (8 sequences, 156 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 -446.50 -442.36 -444.55 1.82 3 0 157 @@@@ 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 551100 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -17.219669745317 -Emax 1 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.128205128205128 \ -align_short 5 -mdEmax 1 -constraints tmp_1-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t88/T0088.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: -47.609985 Database has 202 sequences with 76860 residues. @@@@ cp -f tmp_1-b.mult /projects/compbio/experiments/casp4/t88/T0088.remote-t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /projects/compbio/experiments/casp4/t88/T0088.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 /projects/compbio/experiments/casp4/t88/T0088.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 /projects/compbio/experiments/casp4/t88/T0088.remote-t2k_1.a2m (19 sequences, 156 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 551100 \ -simple_threshold -14.9170683211855 -Emax 10 \ -adpstyle 1 \ -align_short 0 -mdEmax 10\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.128205128205128 -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/t88/T0088.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: -14.365654 Database has 9367 sequences with 3394734 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 (9 sequences, 156 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=19 nll_thresh=-10.9170683211855 frac_id=0.997451269742766 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.997451269742766 -a2mdots 0 SAM: uniqueseq v3.2 (July 31, 2000) compiled 07/31/00_14:08:59 Reading alignment file tmp_2-a.train.seq (19 sequences, 156 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 4 (of 19) duplicate sequences with differing IDs Dropping 4 (of 19) duplicate sequences with identical IDs 8 sequences left after dropping 11 of 19 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 (8 sequences, 156 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/t88/T0088.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 -445.59 -439.08 -442.76 3.00 3 0 157 @@@@ 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 551100 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -14.9170683211855 -Emax 10 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.128205128205128 \ -align_short 5 -mdEmax 10 -constraints tmp_2-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t88/T0088.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: -12.735905 Database has 4051 sequences with 1443082 residues. @@@@ cp -f tmp_2-b.mult /projects/compbio/experiments/casp4/t88/T0088.remote-t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /projects/compbio/experiments/casp4/t88/T0088.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 /projects/compbio/experiments/casp4/t88/T0088.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 /projects/compbio/experiments/casp4/t88/T0088.remote-t2k_2.a2m (19 sequences, 156 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 551100 \ -simple_threshold -12.614319902147 -Emax 100 \ -adpstyle 1 \ -align_short 0 -mdEmax 100\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.128205128205128 -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/t88/T0088.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: -9.652761 Database has 9367 sequences with 3394734 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 (9 sequences, 156 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=-8.61431990214696 frac_id=0.991499906351333 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.991499906351333 -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, 156 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 4 (of 19) duplicate sequences with differing IDs Dropping 4 (of 19) duplicate sequences with identical IDs Dropping 2 (of 19) sequences with > 99.1% id 6 sequences left after dropping 13 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 (6 sequences, 156 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 /projects/compbio/experiments/casp4/t88/T0088.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 -446.56 -440.76 -444.14 2.66 3 0 157 @@@@ 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 551100 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -12.614319902147 -Emax 100 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.128205128205128 \ -align_short 5 -mdEmax 100 -constraints tmp_3-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t88/T0088.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: -10.911118 Database has 4584 sequences with 1716825 residues. @@@@ cp -f tmp_3-b.mult /projects/compbio/experiments/casp4/t88/T0088.remote-t2k_3.a2m @@@@ modelfromalign tmp_4-a -alignfile /projects/compbio/experiments/casp4/t88/T0088.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 /projects/compbio/experiments/casp4/t88/T0088.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 /projects/compbio/experiments/casp4/t88/T0088.remote-t2k_3.a2m (19 sequences, 156 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 551100 \ -simple_threshold -12.614319902147 -Emax 100 \ -adpstyle 5 \ -align_short 0 -mdEmax 100\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.128205128205128 -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 /projects/compbio/experiments/casp4/t88/T0088.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: -9.652761 Database has 9367 sequences with 3394734 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 (9 sequences, 156 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 /projects/compbio/experiments/casp4/t88/T0088.remote-t2k.a2m @@@@ cp tmp_4-a.train.cst /projects/compbio/experiments/casp4/t88/T0088.remote-t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-eclipse-1823 < /dev/null gzip -9f T0088.remoter-t2k.a2m T0088.remoter-t2k.a2m: No such file or directory make: *** [T0088.remoter-t2k.a2m.gz] Error 1