# This file is the result of combining several RDB files, specifically # T0484.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0484.t2k.stride-ebghtl.rdb (weight 1.24869) # T0484.t2k.str.rdb (weight 1.53983) # 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 T0484.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0484 # 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 T0484.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 75 # # ============================================ # Comments from T0484.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0484 # 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 T0484.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 75 # # ============================================ # Comments from T0484.t2k.str.rdb # ============================================ # TARGET T0484 # Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str-seeded.net # This is a 4-layer network, with # window units # 5 15 # 7 15 # 9 15 # 13 13 (1 str ) # The input amino acid frequencies were determined from # alignment T0484.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 75 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 M 0.0261 0.0205 0.9534 2 R 0.1148 0.0393 0.8458 3 D 0.0876 0.0436 0.8688 4 M 0.0352 0.0662 0.8986 5 T 0.0333 0.0716 0.8951 6 E 0.0364 0.0937 0.8699 7 E 0.0508 0.0635 0.8857 8 T 0.0487 0.0658 0.8855 9 R 0.0567 0.1068 0.8365 10 K 0.0407 0.1052 0.8540 11 D 0.0426 0.0721 0.8853 12 L 0.0240 0.0284 0.9476 13 P 0.0104 0.0435 0.9461 14 P 0.0039 0.9358 0.0603 15 E 0.0038 0.9561 0.0402 16 A 0.0037 0.9668 0.0294 17 L 0.0037 0.9662 0.0300 18 R 0.0037 0.9623 0.0339 19 A 0.0037 0.9517 0.0445 20 L 0.0038 0.9539 0.0423 21 A 0.0038 0.9506 0.0456 22 E 0.0040 0.9338 0.0622 23 A 0.0039 0.9438 0.0523 24 E 0.0040 0.9325 0.0635 25 E 0.0040 0.9190 0.0770 26 R 0.0042 0.9020 0.0938 27 R 0.0052 0.8659 0.1290 28 R 0.0045 0.8689 0.1266 29 R 0.0048 0.8350 0.1602 30 A 0.0048 0.8144 0.1808 31 K 0.0050 0.7903 0.2046 32 A 0.0056 0.7154 0.2790 33 L 0.0059 0.5326 0.4615 34 D 0.0087 0.3388 0.6524 35 L 0.0146 0.1067 0.8787 36 P 0.0131 0.0888 0.8981 37 K 0.0322 0.3054 0.6624 38 E 0.0721 0.3802 0.5477 39 I 0.0979 0.2393 0.6627 40 G 0.0791 0.1260 0.7949 41 G 0.0495 0.0515 0.8990 42 R 0.0402 0.0663 0.8936 43 N 0.0390 0.0416 0.9193 44 G 0.0433 0.0224 0.9343 45 P 0.0837 0.0257 0.8906 46 E 0.0802 0.0204 0.8995 47 P 0.1565 0.0310 0.8125 48 V 0.4669 0.0318 0.5012 49 R 0.4503 0.0343 0.5154 50 F 0.2387 0.0566 0.7047 51 G 0.1042 0.0583 0.8375 52 D 0.1146 0.0987 0.7867 53 W 0.2012 0.2509 0.5479 54 E 0.3656 0.2072 0.4272 55 K 0.4129 0.1544 0.4327 56 K 0.2698 0.1074 0.6228 57 G 0.3491 0.0544 0.5965 58 I 0.6157 0.0376 0.3467 59 A 0.6683 0.0336 0.2981 60 I 0.5421 0.0471 0.4108 61 D 0.2917 0.0275 0.6808 62 F 0.0366 0.0159 0.9476