# This file is the result of combining several RDB files, specifically # T0347.t06.dssp-ebghstl.rdb (weight 1.53986) # T0347.t06.stride-ebghtl.rdb (weight 1.24869) # T0347.t06.str2.rdb (weight 1.54758) # T0347.t06.alpha.rdb (weight 0.659012) # T0347.t04.dssp-ebghstl.rdb (weight 1.53986) # T0347.t04.stride-ebghtl.rdb (weight 1.24869) # T0347.t04.str2.rdb (weight 1.54758) # T0347.t04.alpha.rdb (weight 0.659012) # T0347.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0347.t2k.stride-ebghtl.rdb (weight 1.24869) # T0347.t2k.str2.rdb (weight 1.54758) # T0347.t2k.alpha.rdb (weight 0.659012) # 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 T0347.t06.dssp-ebghstl.rdb # ============================================ # TARGET T0347 # Using neural net t06-IDGaaH13-3-13-7-13-9-13-11-ebghstl-dssp-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 7 (1 EBGHSTL ) # The input amino acid frequencies were determined from # alignment T0347.t06-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 13.3407 # # ============================================ # Comments from T0347.t06.stride-ebghtl.rdb # ============================================ # TARGET T0347 # Using neural net t06-IDGaaH13-3-13-7-13-9-13-11-ebghtl-stride-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 6 (1 EBGHTL ) # The input amino acid frequencies were determined from # alignment T0347.t06-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 13.3407 # # ============================================ # Comments from T0347.t06.str2.rdb # ============================================ # TARGET T0347 # Using neural net t06-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 T0347.t06-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 13.3407 # # ============================================ # Comments from T0347.t06.alpha.rdb # ============================================ # TARGET T0347 # Using neural net t06-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 T0347.t06-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 13.3407 # # ============================================ # Comments from T0347.t04.dssp-ebghstl.rdb # ============================================ # TARGET T0347 # Using neural net t06-IDGaaH13-3-13-7-13-9-13-11-ebghstl-dssp-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 7 (1 EBGHSTL ) # The input amino acid frequencies were determined from # alignment T0347.t04-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 13.05 # # ============================================ # Comments from T0347.t04.stride-ebghtl.rdb # ============================================ # TARGET T0347 # Using neural net t04-2621-IDGaaH13-3-13-7-13-9-13-11-ebghtl-stride-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 6 (1 EBGHTL ) # The input amino acid frequencies were determined from # alignment T0347.t04-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 13.05 # # ============================================ # Comments from T0347.t04.str2.rdb # ============================================ # TARGET T0347 # Using neural net t04-2621-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 T0347.t04-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 13.05 # # ============================================ # Comments from T0347.t04.alpha.rdb # ============================================ # TARGET T0347 # Using neural net t04-2621-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 T0347.t04-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 13.05 # # ============================================ # Comments from T0347.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0347 # Using neural net t2k-5740-IDaaHr-5-15-7-15-9-15-13-ebghstl-seeded.net # This is a 4-layer network, with # window units # 5 15 # 7 15 # 9 15 # 13 7 (1 EBGHSTL ) # The input amino acid frequencies were determined from # alignment T0347.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(-1 bits/column, 1) # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 27 # # ============================================ # Comments from T0347.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0347 # Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-ebghtl-seeded.net # This is a 4-layer network, with # window units # 5 15 # 7 15 # 9 15 # 13 6 (1 EBGHTL ) # The input amino acid frequencies were determined from # alignment T0347.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(-1 bits/column, 1) # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 27 # # ============================================ # Comments from T0347.t2k.str2.rdb # ============================================ # TARGET T0347 # Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str2-from-empty.net # This is a 4-layer network, with # window units # 5 15 # 7 15 # 9 15 # 13 13 (1 str2 ) # The input amino acid frequencies were determined from # alignment T0347.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(-1 bits/column, 1) # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 27 # # ============================================ # Comments from T0347.t2k.alpha.rdb # ============================================ # TARGET T0347 # Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-alpha-seeded.net # This is a 4-layer network, with # window units # 5 15 # 7 15 # 9 15 # 13 11 (1 ABCDEFGHIST ) # The input amino acid frequencies were determined from # alignment T0347.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(-1 bits/column, 1) # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 27 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 G 0.0649 0.0452 0.8900 2 K 0.0256 0.6559 0.3185 3 D 0.0106 0.8768 0.1126 4 E 0.0067 0.9292 0.0641 5 F 0.0051 0.9502 0.0447 6 W 0.0051 0.9563 0.0386 7 S 0.0050 0.9580 0.0370 8 V 0.0049 0.9567 0.0383 9 M 0.0057 0.9473 0.0470 10 D 0.0058 0.9143 0.0800 11 H 0.0090 0.7497 0.2414 12 R 0.0446 0.3200 0.6354 13 N 0.0464 0.0417 0.9119 14 L 0.2125 0.0358 0.7517 15 I 0.5135 0.0254 0.4611 16 Y 0.5559 0.0193 0.4248 17 P 0.4649 0.0469 0.4882 18 F 0.3793 0.0552 0.5655 19 D 0.1214 0.0401 0.8385 20 A 0.0183 0.1516 0.8301 21 Q 0.0472 0.0623 0.8905 22 G 0.0433 0.0667 0.8900 23 L 0.1020 0.0626 0.8353 24 R 0.2774 0.0476 0.6750 25 R 0.1501 0.0356 0.8142 26 Q 0.1299 0.0459 0.8242 27 S 0.0169 0.7712 0.2119 28 G 0.0109 0.7513 0.2378 29 D 0.0225 0.7040 0.2735 30 I 0.0649 0.2569 0.6782 31 P 0.0553 0.4269 0.5179 32 K 0.0251 0.6607 0.3142 33 N 0.0396 0.7110 0.2494 34 I 0.0271 0.7481 0.2248 35 H 0.0397 0.6391 0.3211 36 D 0.0401 0.4569 0.5031 37 L 0.0807 0.3121 0.6072 38 E 0.0496 0.3274 0.6230 39 D 0.0527 0.2829 0.6644 40 D 0.0990 0.1684 0.7326 41 P 0.0089 0.5870 0.4042 42 F 0.0100 0.6781 0.3119 43 R 0.0128 0.8161 0.1711 44 S 0.0207 0.8806 0.0987 45 L 0.0080 0.9409 0.0511 46 A 0.0053 0.9524 0.0423 47 G 0.0062 0.9520 0.0418 48 A 0.0075 0.9532 0.0393 49 L 0.0105 0.9437 0.0458 50 R 0.0093 0.9304 0.0602 51 M 0.0089 0.8804 0.1107 52 A 0.0400 0.4331 0.5269 53 G 0.0405 0.1233 0.8362 54 G 0.0684 0.1727 0.7589 55 Y 0.1955 0.1860 0.6184 56 A 0.1856 0.1636 0.6508 57 K 0.1470 0.0726 0.7804 58 V 0.1124 0.0473 0.8403 59 I 0.1156 0.0605 0.8240 60 I 0.1111 0.0539 0.8350 61 P 0.0940 0.1603 0.7458 62 F 0.0606 0.3825 0.5569 63 S 0.0417 0.5986 0.3597 64 E 0.0512 0.6843 0.2645 65 F 0.0707 0.7175 0.2118 66 G 0.0704 0.7166 0.2130 67 W 0.0303 0.8236 0.1461 68 A 0.0096 0.8988 0.0916 69 D 0.0064 0.9226 0.0710 70 F 0.0058 0.9171 0.0771 71 L 0.0103 0.8923 0.0974 72 R 0.0153 0.8014 0.1833 73 R 0.0203 0.6443 0.3354 74 R 0.0477 0.4181 0.5342 75 I 0.0690 0.2493 0.6816 76 D 0.0556 0.1702 0.7741 77 R 0.0338 0.4794 0.4867 78 D 0.0173 0.5942 0.3884 79 L 0.0244 0.6021 0.3735 80 L 0.0410 0.5216 0.4375 81 S 0.0299 0.5713 0.3988 82 D 0.0213 0.5193 0.4595 83 S 0.0406 0.3802 0.5792 84 F 0.0147 0.7196 0.2657 85 D 0.0106 0.8898 0.0996 86 D 0.0059 0.9189 0.0752 87 A 0.0072 0.9196 0.0732 88 L 0.0072 0.9406 0.0522 89 A 0.0056 0.9502 0.0442 90 E 0.0059 0.9499 0.0442 91 A 0.0050 0.9491 0.0458 92 M 0.0050 0.9427 0.0523 93 K 0.0050 0.9058 0.0892 94 L 0.0059 0.8169 0.1772 95 A 0.0235 0.6383 0.3382 96 K 0.0276 0.4709 0.5015 97 S 0.0513 0.2744 0.6743 98 R 0.0093 0.7522 0.2385 99 E 0.0108 0.7911 0.1981 100 A 0.0190 0.8103 0.1706 101 R 0.0171 0.6607 0.3222 102 H 0.0289 0.3783 0.5928 103 L 0.0740 0.1101 0.8159 104 P 0.0523 0.1335 0.8143 105 G 0.0766 0.1546 0.7688 106 W 0.1976 0.2032 0.5992 107 C 0.2492 0.1167 0.6341 108 G 0.1771 0.0819 0.7410 109 V 0.1336 0.0944 0.7719 110 E 0.0816 0.0852 0.8332 111 E 0.0401 0.0422 0.9177