# This file is the result of combining several RDB files, specifically # T0397.t2k.str2.rdb (weight 1.54425) # T0397.t2k.str4.rdb (weight 0.924988) # T0397.t2k.pb.rdb (weight 0.789901) # T0397.t2k.bys.rdb (weight 0.748322) # T0397.t2k.alpha.rdb (weight 0.678173) # These files were combined by translating their predictions into EHL # predictions with tables generated by compare-real, and then combining # those predictions with weights proportional to their mutual information # with the EHL alphabet. The comments from the individual files follow. # # Comments from T0397.t2k.str2.rdb # ============================================ # TARGET T0397 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-str2-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 13 (1 str2 ) # The input amino acid frequencies were determined from # alignment T0397.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.30604 # # ============================================ # Comments from T0397.t2k.str4.rdb # ============================================ # TARGET T0397 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-str4-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 21 (1 str4 ) # The input amino acid frequencies were determined from # alignment T0397.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.30604 # # ============================================ # Comments from T0397.t2k.pb.rdb # ============================================ # TARGET T0397 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-pb-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 16 (1 pb ) # The input amino acid frequencies were determined from # alignment T0397.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.30604 # # ============================================ # Comments from T0397.t2k.bys.rdb # ============================================ # TARGET T0397 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-bys-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 11 (1 Bystroff ) # The input amino acid frequencies were determined from # alignment T0397.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.30604 # # ============================================ # Comments from T0397.t2k.alpha.rdb # ============================================ # TARGET T0397 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-alpha-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 11 (1 ABCDEFGHIST ) # The input amino acid frequencies were determined from # alignment T0397.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.30604 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 G 0.1553 0.0822 0.7626 2 T 0.3147 0.0576 0.6277 3 K 0.5667 0.0334 0.3999 4 L 0.7191 0.0198 0.2611 5 I 0.7701 0.0116 0.2183 6 S 0.7457 0.0085 0.2458 7 V 0.6804 0.0124 0.3071 8 P 0.5381 0.0154 0.4465 9 A 0.3746 0.1225 0.5028 10 E 0.2725 0.1108 0.6167 11 G 0.2243 0.0907 0.6850 12 Y 0.4262 0.0451 0.5287 13 K 0.6238 0.0350 0.3412 14 V 0.6479 0.0466 0.3055 15 Y 0.6506 0.0308 0.3186 16 P 0.5677 0.0533 0.3790 17 I 0.6102 0.0772 0.3126 18 M 0.5712 0.1050 0.3238 19 D 0.4622 0.1108 0.4270 20 F 0.2727 0.1973 0.5300 21 G 0.2473 0.1440 0.6087 22 F 0.3790 0.1750 0.4460 23 R 0.5216 0.1571 0.3213 24 V 0.5100 0.1779 0.3122 25 L 0.4335 0.1464 0.4200 26 K 0.2217 0.1396 0.6387 27 G 0.1135 0.0970 0.7894 28 Y 0.3033 0.0992 0.5975 29 R 0.5098 0.1349 0.3553 30 L 0.5986 0.1277 0.2738 31 A 0.6935 0.0874 0.2191 32 T 0.7295 0.0538 0.2167 33 L 0.7267 0.0504 0.2229 34 E 0.6864 0.0447 0.2689 35 S 0.5062 0.0419 0.4519 36 K 0.2659 0.1967 0.5374 37 K 0.1621 0.1290 0.7088 38 G 0.2198 0.0765 0.7037 39 D 0.4988 0.0259 0.4753 40 L 0.7092 0.0125 0.2783 41 R 0.7160 0.0158 0.2683 42 Y 0.7538 0.0124 0.2339 43 V 0.6794 0.0249 0.2957 44 N 0.5811 0.0282 0.3908 45 S 0.3796 0.0316 0.5887 46 P 0.2421 0.1012 0.6567 47 V 0.2368 0.1531 0.6101 48 S 0.2205 0.1031 0.6764 49 G 0.3461 0.0525 0.6015 50 T 0.6921 0.0108 0.2972 51 V 0.7843 0.0058 0.2099 52 I 0.8091 0.0063 0.1846 53 F 0.7639 0.0069 0.2292 54 M 0.6481 0.0413 0.3106 55 N 0.4984 0.0916 0.4099 56 E 0.4169 0.0869 0.4962 57 I 0.3230 0.0409 0.6360 58 P 0.1948 0.0965 0.7087 59 S 0.1162 0.2933 0.5904 60 E 0.1265 0.2975 0.5760 61 R 0.1822 0.2484 0.5694 62 A 0.2317 0.1758 0.5925 63 N 0.4105 0.0848 0.5047 64 Y 0.6949 0.0202 0.2849 65 V 0.7804 0.0097 0.2099 66 F 0.8092 0.0071 0.1837 67 Y 0.7969 0.0086 0.1945 68 M 0.7310 0.0137 0.2553 69 L 0.5164 0.0454 0.4382 70 E 0.3368 0.1575 0.5057 71 E 0.2625 0.2002 0.5373