make -k T0090-blast.rdb T0090-double-blast.rdb make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t90' /projects/compbio/experiments/casp3/scripts/single-blast -q T0090.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0090-blast.rdb starting T0090 with E=10 /projects/compbio/experiments/casp3/scripts/double-blast -q T0090.seq -interdb /projects/compbio/data/nrp/nr -db /projects/compbio/data/pdb/all-protein > T0090-double-blast.rdb starting T0090 with E=0.000050 T0090 T0090 blasting: T0090 gi|505331|gb|AAB46945.1|_5:155 blasting: T0090 gi|1731053|sp|P36651|YQIE_ECOLI_1:209 blasting: T0090 gi|1177043|sp|P44684|YQIE_HAEIN_14:214 blasting: T0090 gi|1731093|sp|P54570|YQKG_BACSU_9:182 blasting: T0090 gi|7429372|pir||S74496_1:184 blasting: T0090 gi|2506700|sp|P37128|YFFH_ECOLI_5:188 blasting: T0090 gi|2209125|gb|AAB95442.1|_167:361 blasting: T0090 gi|4099064|gb|AAD00531.1|_45:160 blasting: T0090 gi|7445034|pir||H72286_25:168 blasting: T0090 gi|7479996|pir||T36468_37:215 blasting: T0090 gi|7226303|gb|AAF41460.1|_11:175 blasting: T0090 gi|7301558|gb|AAF56679.1|_1233:1340 blasting: T0090 gi|7301558|gb|AAF56679.1|_1162:1206 blasting: T0090 gi|7301558|gb|AAF56679.1|_968:1003 blasting: T0090 gi|7379943|emb|CAB84518.1|_11:175 blasting: T0090 gi|7466060|pir||C58723_1:142 blasting: make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t90' make -k T0090.t2k.a2m.gz \ T0090.t2k.pa \ T0090.t2k.pa.html \ T0090.t2k.2d \ T0090.t2k.tree \ T0090.t2k_sorted.pa \ T0090.t2k.tree-unroot.ps make[1]: Entering directory `/auto/projects/compbio/experiments/casp4/t90' /projects/compbio/experiments/models.97/scripts2k/target2k -out T0090.t2k \ -seed T0090.seq \ -all @@@@ chgrp protein /projects/compbio/tmp/target2k-beta-30905 @@@@ cp /projects/compbio/experiments/casp4/t90/T0090.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= 501961 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-31703 /projects/compbio/experiments/models.97/scripts2k/blast-prefilter: E-value thresholds used are For /projects/compbio/tmp/target2k-beta-30905/prefilter_1.fa, 0.01 For /projects/compbio/tmp/target2k-beta-30905/prefilter_2.fa, 1 For /projects/compbio/tmp/target2k-beta-30905/prefilter_3.fa, 10 For /projects/compbio/tmp/target2k-beta-30905/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-30905/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-30905/m0.a2m (1 sequences, 209 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 501961 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-31703 < /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, 209 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, 209 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 501961 \ -simple_threshold -26.3366180781898 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -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: -75.280014 Database has 21 sequences with 5299 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 (10 sequences, 209 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=11 nll_thresh=-22.3366180781898 frac_id=0.999999998785775 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.999999998785775 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (11 sequences, 209 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 11) duplicate sequences with differing IDs Dropping 1 (of 11) sequences with > 100.0% id 9 sequences left after dropping 2 of 11 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 (9 sequences, 209 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 -593.67 -51.42 -220.68 151.83 12 0 210 @@@@ 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 501961 \ -db m0.a2m -db tmp_1-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -26.3366180781898 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.0001 -constraints tmp_1-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t90/T0090.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: -173.909988 Database has 20 sequences with 5150 residues. @@@@ cp -f tmp_1-b.mult /projects/compbio/experiments/casp4/t90/T0090.t2k_1.a2m # About to count sequences in prefilter_2.fa @@@@ modelfromalign tmp_2-a -alignfile /projects/compbio/experiments/casp4/t90/T0090.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/t90/T0090.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/t90/T0090.t2k_1.a2m (21 sequences, 209 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 501961 \ -simple_threshold -25.6434708974307 -Emax 0.0002 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0002\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -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/t90/T0090.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: -104.960182 Database has 40 sequences with 9083 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 (36 sequences, 209 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=37 nll_thresh=-21.6434708974307 frac_id=0.997701749798507 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.997701749798507 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (37 sequences, 209 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 1 (of 37) duplicate sequences with differing IDs Dropping 2 (of 37) sequences with > 99.8% id 34 sequences left after dropping 3 of 37 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 (34 sequences, 209 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/t90/T0090.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 -591.78 -0.21 -117.36 96.24 4 0 210 @@@@ 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 501961 \ -db m0.a2m -db tmp_2-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -25.6434708974307 -Emax 0.0002 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.0002 -constraints tmp_2-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t90/T0090.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: -135.096649 Database has 38 sequences with 8408 residues. @@@@ cp -f tmp_2-b.mult /projects/compbio/experiments/casp4/t90/T0090.t2k_2.a2m # About to count sequences in prefilter_3.fa @@@@ modelfromalign tmp_3-a -alignfile /projects/compbio/experiments/casp4/t90/T0090.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/t90/T0090.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/t90/T0090.t2k_2.a2m (39 sequences, 209 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 501961 \ -simple_threshold -24.0340329834028 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -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/t90/T0090.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: -84.150047 Database has 71 sequences with 16541 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 (62 sequences, 209 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=63 nll_thresh=-20.0340329834028 frac_id=0.968059893382983 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.968059893382983 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (63 sequences, 209 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 2 (of 63) duplicate sequences with differing IDs Dropping 7 (of 63) sequences with > 96.8% id 54 sequences left after dropping 9 of 63 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 (54 sequences, 209 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/t90/T0090.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 -591.13 -17.73 -90.97 78.63 6 0 210 @@@@ 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 501961 \ -db m0.a2m -db tmp_3-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -24.0340329834028 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.001 -constraints tmp_3-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t90/T0090.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: -110.369827 Database has 60 sequences with 13943 residues. @@@@ cp -f tmp_3-b.mult /projects/compbio/experiments/casp4/t90/T0090.t2k_3.a2m # About to count sequences in prefilter_4.fa @@@@ modelfromalign tmp_4-a -alignfile /projects/compbio/experiments/casp4/t90/T0090.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/t90/T0090.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/t90/T0090.t2k_3.a2m (63 sequences, 209 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 501961 \ -simple_threshold -22.424595063 -Emax 0.005 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -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/t90/T0090.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: -29.534657 Database has 391 sequences with 100816 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 (135 sequences, 209 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=136 nll_thresh=-18.424595063 frac_id=0.835924040791116 @@@@ uniqueseq thinned_tmp -alignfile tmp_4-a.train.seq -a protein \ -percent_id 0.835924040791116 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_4-a.train.seq (136 sequences, 209 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 7 (of 136) duplicate sequences with differing IDs Dropping 26 (of 136) sequences with > 83.6% id 103 sequences left after dropping 33 of 136 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 (103 sequences, 209 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/t90/T0090.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 -591.78 -1.52 -72.91 58.40 4 0 210 @@@@ 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 501961 \ -db m0.a2m -db tmp_4-a.sel \ -select_score 4 \ -select_seq 4 \ -simple_threshold -22.424595063 -Emax 0.005 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.005 -constraints tmp_4-a.train.cst -constraints_out /projects/compbio/experiments/casp4/t90/T0090.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: -81.026566 Database has 133 sequences with 27651 residues. @@@@ cp -f tmp_4-b.mult /projects/compbio/experiments/casp4/t90/T0090.t2k_4.a2m @@@@ modelfromalign tmp_5-a -alignfile /projects/compbio/experiments/casp4/t90/T0090.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/t90/T0090.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/t90/T0090.t2k_4.a2m (132 sequences, 209 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 501961 \ -simple_threshold -22.424595063 -Emax 0.005 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.005\ -select_score 4 \ -select_seq 4 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -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/t90/T0090.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: -33.119770 Database has 391 sequences with 100816 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 (125 sequences, 209 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/t90/T0090.t2k.a2m @@@@ cp tmp_5-a.train.cst /projects/compbio/experiments/casp4/t90/T0090.t2k.cst @@@@ rm -rf /projects/compbio/tmp/target2k-beta-30905 < /dev/null gzip -f T0090.t2k*.a2m prettyalign T0090.t2k.a2m.gz -m8 -i -n -L3333 > T0090.t2k.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 gunzip -c T0090.t2k.a2m.gz > tmp.a2m a2m2html -a2m_in tmp.a2m -retrieve > T0090.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 T0090.t2k.a2m.gz >> tmp.script echo PrintPrediction T0090.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0090.t2k.2d.seq >> tmp.script echo PrintRDB T0090.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 T0090.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0090.t2k.a2m with 126 sequences, total weight= 77.6843 avg weight= 0.616542 clipped 46 iterations # AdjustWeights couldn't save exactly 1.4 bits/position, saving 0.823325 bits. Regularizing alignment for T0090.t2k.a2m.gz # After reading T0090.t2k.a2m.gz, have 209 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 T0090.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0090.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0090.t2k.2d.rdb # command:rm tmp.script gunzip -f T0090.t2k.a2m.gz /projects/compbio/usr/karplus/src/phytree/phytree -o -i -r flat T0090.t2k T0090.t2k.a2m /projects/compbio/lib/recode2.20comp Prior library /projects/compbio/lib/recode2.20comp read. Reading alignment file T0090.t2k.a2m (126 sequences) as A2M alignment. Alignment T0090.t2k.a2m read. Adding sequences:0 10 20 30 40 50 60 70 80 90 100 110 120 One dot for every 10 merges: ............. Merges done. CPU = user 0: 1:53 system 0: 0: 0 gzip -f T0090.t2k.a2m gzip -f T0090.t2k_sorted.a2m rm T0090.t2k.phytrace T0090.t2k.tree_weight prettyalign T0090.t2k_sorted.a2m.gz -m8 -i -n -L3333 > T0090.t2k_sorted.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 /projects/compbio/usr/karplus/src/phytree/dtree T0090.t2k.tree make[1]: Leaving directory `/auto/projects/compbio/experiments/casp4/t90' /projects/compbio/experiments/models.97/scripts99/score-target -alignment T0090.t2k.a2m.gz -build w0.5 \ -db /projects/compbio/data/pdb/all-protein \ -Emax 40.0 \ -viterbi 0 -sw_score 2 \ -output T0090.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-5387 @@@@ mkdir /projects/compbio/tmp/score-target-5387/for-scorescript @@@@ /projects/compbio/experiments/models.97/scripts99/score-mods-vs-seqs.pl -root_tmp /projects/compbio/tmp/score-target-5387/for-scorescript -a2msfile /projects/compbio/tmp/score-target-5387/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-5387/score-target.op @@@@ chgrp protein /projects/compbio/tmp/score-target-5387/for-scorescript/split-tmp @@@@ chgrp protein /projects/compbio/tmp/score-target-5387/for-scorescript/split-tmp @@@@ /projects/compbio/bin/scripts/w0.5 /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz /projects/compbio/tmp/score-target-5387/for-scorescript/split-tmp/beta-3859/T0090.t2k.mod Reading /projects/compbio/bin/scripts/sam-t99.conf @@@@ chgrp protein /projects/compbio/tmp/tmp-build-weighted-model-beta-5301 @@@@ uniqueseq /projects/compbio/tmp/tmp-build-weighted-model-beta-5301/tmp -alignfile /projects/compbio/experiments/casp4/t90/T0090.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/t90/T0090.t2k.a2m.gz (126 sequences, 209 columns) as A2M alignment. Writing sequence output to /projects/compbio/tmp/tmp-build-weighted-model-beta-5301/tmp.a2m. Dropping 2 (of 126) duplicate sequences with differing IDs Dropping 26 (of 126) sequences with > 80.0% id 98 sequences left after dropping 28 of 126 sequences. @@@@ modelfromalign /projects/compbio/tmp/tmp-build-weighted-model-beta-5301/tmp -alignfile /projects/compbio/tmp/tmp-build-weighted-model-beta-5301/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-5301/tmp.a2m (98 sequences, 209 columns) as A2M alignment. @@@@ cp -f /projects/compbio/tmp/tmp-build-weighted-model-beta-5301/tmp.mod /projects/compbio/tmp/score-target-5387/for-scorescript/split-tmp/beta-3859/T0090.t2k.mod @@@@ rm -rf /projects/compbio/tmp/tmp-build-weighted-model-beta-5301 init.check SAM: checkseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:44 /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 0.01, actual: 0.0001 prefilter: 1, actual: 0.001 prefilter: 10, actual: 0.01 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.5, 0.5, 0.5 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 10 reverse_diff= 4 /projects/compbio/experiments/models.97/scripts2k/target2k: homologs=/projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz close=/projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_method=1 aweight_exponent=10 /projects/compbio/experiments/models.97/scripts2k/target2k: force_seed=0 constraints=0 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 /projects/compbio/experiments/models.97/scripts2k/target2k: nsurgery=10 cutinsert=0.3 cutmatch=0.2 fracinsert=0.3 # About to count sequences in m0.a2m # About to count sequences in /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.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 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 (126 sequences, 141 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 10 \ -simple_threshold -15.5129154649202 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 8 \ -select_seq 8 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.141843971631206 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz 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: -74.069443 Database has 126 sequences with 16817 residues. @@@@ cp tmp_1-a.mult tmp_1-a-sort.a2m # About to count sequences in tmp_1-a.train.seq # num_seqs=126 nll_thresh=-11.5129154649202 frac_id=0.771009192818446 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.771009192818446 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (126 sequences, 141 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 4 (of 126) duplicate sequences with differing IDs Dropping 25 (of 126) sequences with > 77.1% id 97 sequences left after dropping 29 of 126 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-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_1-a.train.seq (97 sequences, 141 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 10 \ -fracinsert 0.3 \ -cutinsert 0.3 -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 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 -95.54 23.47 -59.43 18.65 8 1 138 @@@@ 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 10 \ -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz \ -select_score 8 \ -select_seq 8 \ -simple_threshold -15.5129154649202 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.141843971631206 \ -align_short 5 -mdEmax 0.0001 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: -68.593971 Database has 126 sequences with 16817 residues. @@@@ cp -f tmp_1-b.mult m_1.a2m # About to count sequences in /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz @@@@ modelfromalign tmp_2-a -alignfile m_1.a2m \ -insert /projects/compbio/lib/stiff-gap5.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 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 m_1.a2m (126 sequences, 137 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 10 \ -simple_threshold -13.2102403669758 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 8 \ -select_seq 8 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.141843971631206 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz Reading parameter file tmp_2-a.mod tmp_2-a.mod(23): Reading MODEL -- Model from alignment file m_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: -69.877434 Database has 126 sequences with 16817 residues. @@@@ cp tmp_2-a.mult tmp_2-a-sort.a2m # About to count sequences in tmp_2-a.train.seq # num_seqs=126 nll_thresh=-9.21024036697585 frac_id=0.740014732860024 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.740014732860024 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (126 sequences, 137 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 6 (of 126) duplicate sequences with differing IDs Dropping 23 (of 126) sequences with > 74.0% id 97 sequences left after dropping 29 of 126 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-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_2-a.train.seq (97 sequences, 137 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 10 \ -fracinsert 0.3 \ -cutinsert 0.3 -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 Reading parameter file tmp_2-a.mod tmp_2-a.mod(23): Reading MODEL -- Model from alignment file m_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 -91.61 -16.12 -57.66 12.37 8 1 137 @@@@ 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 10 \ -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz \ -select_score 8 \ -select_seq 8 \ -simple_threshold -13.2102403669758 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.141843971631206 \ -align_short 5 -mdEmax 0.001 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: -63.580910 Database has 126 sequences with 16817 residues. @@@@ cp -f tmp_2-b.mult m_2.a2m # About to count sequences in /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz @@@@ modelfromalign tmp_3-a -alignfile m_2.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 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 m_2.a2m (126 sequences, 136 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 10 \ -simple_threshold -10.9067547786486 -Emax 0.01 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.01\ -select_score 8 \ -select_seq 8 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.141843971631206 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz Reading parameter file tmp_3-a.mod tmp_3-a.mod(23): Reading MODEL -- Model from alignment file m_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: -67.131447 Database has 126 sequences with 16817 residues. @@@@ cp tmp_3-a.mult tmp_3-a-sort.a2m # About to count sequences in tmp_3-a.train.seq # num_seqs=126 nll_thresh=-6.90675477864855 frac_id=0.706965971069121 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.706965971069121 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (126 sequences, 136 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 6 (of 126) duplicate sequences with differing IDs Dropping 24 (of 126) sequences with > 70.7% id 96 sequences left after dropping 30 of 126 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-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_3-a.train.seq (96 sequences, 136 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 10 \ -fracinsert 0.3 \ -cutinsert 0.3 -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 Reading parameter file tmp_3-a.mod tmp_3-a.mod(23): Reading MODEL -- Model from alignment file m_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -90.43 -12.84 -58.59 11.98 2 0 137 @@@@ 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 10 \ -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz \ -select_score 8 \ -select_seq 8 \ -simple_threshold -10.9067547786486 -Emax 0.01 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.141843971631206 \ -align_short 5 -mdEmax 0.01 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: -62.944031 Database has 126 sequences with 16817 residues. @@@@ cp -f tmp_3-b.mult m_3.a2m @@@@ modelfromalign tmp_4-a -alignfile m_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 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 m_3.a2m (126 sequences, 136 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 10 \ -simple_threshold -10.9067547786486 -Emax 0.01 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.01\ -select_score 8 \ -select_seq 8 \ -select_align 8 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz Reading parameter file tmp_4-a.mod tmp_4-a.mod(23): Reading MODEL -- Model from alignment file m_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: -67.589272 Database has 126 sequences with 16817 residues. @@@@ cp tmp_4-a.a2m tmp_4-a-sort.a2m @@@@ cp tmp_4-a.train.seq /projects/compbio/experiments/casp4/t90/T0090.t2k.noseed.a2m @@@@ rm -rf /projects/compbio/tmp/target2k-eclipse-10188 < /dev/null gzip -f T0090.t2k.noseed.a2m prettyalign T0090.t2k.noseed.a2m.gz -m8 -i -n -L3333 > T0090.t2k.noseed.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 /projects/compbio/experiments/models.97/scripts2k/target2k \ -seed T0090.t2k.a2m.gz -out T0090.t2k.tuneup -tuneup @@@@ chgrp protein /projects/compbio/tmp/target2k-eclipse-9543 @@@@ gunzip -c /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz > 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 /projects/compbio/experiments/models.97/scripts2k/target2k: E-value thresholds used are prefilter: 0.01, actual: 0.0001 prefilter: 1, actual: 0.001 prefilter: 10, actual: 0.01 /projects/compbio/experiments/models.97/scripts2k/target2k: aweight_bits are 0.5, 0.5, 0.5 /projects/compbio/experiments/models.97/scripts2k/target2k: db_size= 10 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=0 constraints=0 /projects/compbio/experiments/models.97/scripts2k/target2k: jump_in=0.2 jump_out=1 fimstrength=1 fimtrans=-1 /projects/compbio/experiments/models.97/scripts2k/target2k: nsurgery=10 cutinsert=0.3 cutmatch=0.2 fracinsert=0.3 # About to count sequences in m0.a2m # About to count sequences in m0.a2m @@@@ modelfromalign tmp_1-a -alignfile m0.a2m \ -insert /projects/compbio/lib/gap1.5.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 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 (126 sequences, 209 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 10 \ -simple_threshold -15.5129154649202 -Emax 0.0001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.0001\ -select_score 8 \ -select_seq 8 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz -db m0.a2m 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: -86.199043 Database has 252 sequences with 33634 residues. @@@@ cp tmp_1-a.mult tmp_1-a-sort.a2m # About to count sequences in tmp_1-a.train.seq # num_seqs=252 nll_thresh=-11.5129154649202 frac_id=0.689815541200994 @@@@ uniqueseq thinned_tmp -alignfile tmp_1-a.train.seq -a protein \ -percent_id 0.689815541200994 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_1-a.train.seq (252 sequences, 209 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 6 (of 252) duplicate sequences with differing IDs Dropping 6 (of 252) duplicate sequences with identical IDs Dropping 28 (of 252) sequences with > 69.0% id 95 sequences left after dropping 157 of 252 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_1-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_1-a.train.seq (95 sequences, 209 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 10 \ -fracinsert 0.3 \ -cutinsert 0.3 -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 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 -123.16 4.99 -73.06 23.93 17 3 175 @@@@ 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 10 \ -db m0.a2m \ -select_score 8 \ -select_seq 8 \ -simple_threshold -15.5129154649202 -Emax 0.0001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.0001 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: -82.021957 Database has 126 sequences with 16817 residues. @@@@ cp -f tmp_1-b.mult m_1.a2m # About to count sequences in m0.a2m @@@@ modelfromalign tmp_2-a -alignfile m_1.a2m \ -insert /projects/compbio/lib/stiff-gap5.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 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 m_1.a2m (126 sequences, 174 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 10 \ -simple_threshold -13.2102403669758 -Emax 0.001 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.001\ -select_score 8 \ -select_seq 8 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz -db m0.a2m Reading parameter file tmp_2-a.mod tmp_2-a.mod(23): Reading MODEL -- Model from alignment file m_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: -79.271538 Database has 252 sequences with 33634 residues. @@@@ cp tmp_2-a.mult tmp_2-a-sort.a2m # About to count sequences in tmp_2-a.train.seq # num_seqs=252 nll_thresh=-9.21024036697585 frac_id=0.67229417814115 @@@@ uniqueseq thinned_tmp -alignfile tmp_2-a.train.seq -a protein \ -percent_id 0.67229417814115 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_2-a.train.seq (252 sequences, 174 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 8 (of 252) duplicate sequences with differing IDs Dropping 8 (of 252) duplicate sequences with identical IDs Dropping 28 (of 252) sequences with > 67.2% id 94 sequences left after dropping 158 of 252 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_2-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_2-a.train.seq (94 sequences, 174 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 10 \ -fracinsert 0.3 \ -cutinsert 0.3 -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 Reading parameter file tmp_2-a.mod tmp_2-a.mod(23): Reading MODEL -- Model from alignment file m_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 -96.56 -23.28 -64.69 15.56 30 8 166 @@@@ 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 10 \ -db m0.a2m \ -select_score 8 \ -select_seq 8 \ -simple_threshold -13.2102403669758 -Emax 0.001 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.001 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: -71.737495 Database has 126 sequences with 16817 residues. @@@@ cp -f tmp_2-b.mult m_2.a2m # About to count sequences in m0.a2m @@@@ modelfromalign tmp_3-a -alignfile m_2.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 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 m_2.a2m (126 sequences, 165 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 10 \ -simple_threshold -10.9067547786486 -Emax 0.01 \ -adpstyle 1 \ -align_short 0 -mdEmax 0.01\ -select_score 8 \ -select_seq 8 \ -select_mdalign 4 -select_md 4 -Motifcutoff 0.0956937799043062 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz -db m0.a2m Reading parameter file tmp_3-a.mod tmp_3-a.mod(23): Reading MODEL -- Model from alignment file m_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: -75.068108 Database has 252 sequences with 33634 residues. @@@@ cp tmp_3-a.mult tmp_3-a-sort.a2m # About to count sequences in tmp_3-a.train.seq # num_seqs=252 nll_thresh=-6.90675477864855 frac_id=0.654474933941787 @@@@ uniqueseq thinned_tmp -alignfile tmp_3-a.train.seq -a protein \ -percent_id 0.654474933941787 -a2mdots 0 SAM: uniqueseq v3.1b (February 24, 1999) compiled 04/18/00_11:44:50 Reading alignment file tmp_3-a.train.seq (252 sequences, 165 columns) as A2M alignment. Writing sequence output to thinned_tmp.a2m. Dropping 8 (of 252) duplicate sequences with differing IDs Dropping 8 (of 252) duplicate sequences with identical IDs Dropping 26 (of 252) sequences with > 65.4% id 96 sequences left after dropping 156 of 252 sequences. @@@@ modelfromalign junk_for_weights \ -alignfile tmp_3-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_3-a.train.seq (96 sequences, 165 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 10 \ -fracinsert 0.3 \ -cutinsert 0.3 -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 Reading parameter file tmp_3-a.mod tmp_3-a.mod(23): Reading MODEL -- Model from alignment file m_2.a2m Command line option(48): internal_weight has already been set. Using 0. Reading parameter file /projects/compbio/lib/fssp-trained.regularizer /projects/compbio/lib/fssp-trained.regularizer(1): Reading REGULARIZER: transitions from FSSP and pseudocounts for diverse weighted HSSP SAM: buildmodel v3.1b (February 24, 1999) compiled 04/18/00_11:43:59 -98.45 -26.51 -66.49 14.61 2 0 166 @@@@ 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 10 \ -db m0.a2m \ -select_score 8 \ -select_seq 8 \ -simple_threshold -10.9067547786486 -Emax 0.01 \ -select_mdalign 4 -select_md 4 \ -adpstyle 1 \ -Motifcutoff 0.0956937799043062 \ -align_short 5 -mdEmax 0.01 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: -71.371956 Database has 126 sequences with 16817 residues. @@@@ cp -f tmp_3-b.mult m_3.a2m @@@@ modelfromalign tmp_4-a -alignfile m_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 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 m_3.a2m (126 sequences, 165 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 10 \ -simple_threshold -10.9067547786486 -Emax 0.01 \ -adpstyle 5 \ -align_short 0 -mdEmax 0.01\ -select_score 8 \ -select_seq 8 \ -select_align 8 -db /projects/compbio/experiments/casp4/t90/T0090.t2k.a2m.gz -db m0.a2m Reading parameter file tmp_4-a.mod tmp_4-a.mod(23): Reading MODEL -- Model from alignment file m_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: -76.090019 Database has 252 sequences with 33634 residues. @@@@ cp tmp_4-a.a2m tmp_4-a-sort.a2m @@@@ cp tmp_4-a.train.seq /projects/compbio/experiments/casp4/t90/T0090.t2k.tuneup.a2m @@@@ rm -rf /projects/compbio/tmp/target2k-eclipse-9543 < /dev/null gzip -f T0090.t2k.tuneup.a2m prettyalign T0090.t2k.tuneup.a2m.gz -m8 -i -n -L3333 > T0090.t2k.tuneup.pa SAM: prettyalign v3.1b (February 24, 1999) compiled 04/18/00_11:44:15 echo ReadNeuralNet /projects/compbio/usr/karplus/predict-2nd/testing/networks/overrep-2500-IDaa13-5-9-7-10-5-10-11-ehl2-seeded4-stride-trained.net > tmp.script echo ReadA2M T0090.t2k.a2m.gz >> tmp.script echo PrintPrediction T0090.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0090.t2k.2d.seq >> tmp.script echo PrintRDB T0090.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 T0090.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0090.t2k.a2m with 126 sequences, total weight= 77.6843 avg weight= 0.616542 clipped 46 iterations # AdjustWeights couldn't save exactly 1.4 bits/position, saving 0.823325 bits. Regularizing alignment for T0090.t2k.a2m.gz # After reading T0090.t2k.a2m.gz, have 209 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 T0090.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0090.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0090.t2k.2d.rdb # command:rm tmp.script make: Nothing to be done for `T0090.t2k.2d.rdb'. make: Nothing to be done for `T0090.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 T0090.t2k.a2m.gz >> tmp.script echo PrintPrediction T0090.t2k.2d 3670-4530-6947 >> tmp.script echo PrintPredictionFasta T0090.t2k.2d.seq >> tmp.script echo PrintRDB T0090.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 T0090.t2k.a2m.gz # Using SequenceWeight EntropyWeight(1.4, 10) # Using regularizer /projects/compbio/lib/recode3.20comp for sequence weight regularizer. # T0090.t2k.a2m with 126 sequences, total weight= 77.6843 avg weight= 0.616542 clipped 46 iterations # AdjustWeights couldn't save exactly 1.4 bits/position, saving 0.823325 bits. Regularizing alignment for T0090.t2k.a2m.gz # After reading T0090.t2k.a2m.gz, have 209 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 T0090.t2k.2d # command:# Network initialization done # Printing prediction in FASTA format to T0090.t2k.2d.seq # command:# Network initialization done # Printing prediction to T0090.t2k.2d.rdb # command:rm tmp.script make: `T0090.t2k.2d' is up to date.