# This file is the result of combining several RDB files, specifically # T0251.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0251.t2k.stride-ebghtl.rdb (weight 1.24869) # T0251.t2k.str2.rdb (weight 1.54758) # T0251.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 T0251.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0251 # 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 T0251.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 8 # # ============================================ # Comments from T0251.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0251 # 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 T0251.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 8 # # ============================================ # Comments from T0251.t2k.str2.rdb # ============================================ # TARGET T0251 # 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 T0251.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 8 # # ============================================ # Comments from T0251.t2k.alpha.rdb # ============================================ # TARGET T0251 # 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 T0251.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 8 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 M 0.2553 0.0109 0.7337 2 V 0.7779 0.0082 0.2138 3 V 0.8397 0.0139 0.1464 4 Y 0.7045 0.0306 0.2649 5 G 0.4112 0.0421 0.5467 6 A 0.2939 0.1108 0.5952 7 D 0.3335 0.1248 0.5417 8 V 0.4254 0.1564 0.4182 9 I 0.4886 0.1113 0.4000 10 C 0.3565 0.0881 0.5554 11 A 0.2630 0.2003 0.5366 12 S 0.2451 0.2426 0.5123 13 C 0.2493 0.2234 0.5273 14 V 0.1815 0.1421 0.6764 15 N 0.1258 0.0653 0.8089 16 A 0.1040 0.0439 0.8521 17 P 0.1015 0.0673 0.8312 18 T 0.0837 0.0982 0.8181 19 S 0.0429 0.3476 0.6096 20 K 0.0159 0.7076 0.2766 21 D 0.0196 0.7595 0.2210 22 I 0.0147 0.8389 0.1464 23 Y 0.0047 0.9448 0.0504 24 D 0.0047 0.9504 0.0448 25 W 0.0047 0.9568 0.0385 26 L 0.0047 0.9576 0.0377 27 Q 0.0047 0.9545 0.0408 28 P 0.0049 0.9511 0.0441 29 L 0.0053 0.9351 0.0595 30 L 0.0176 0.8062 0.1763 31 K 0.0197 0.5622 0.4181 32 R 0.0523 0.4426 0.5051 33 K 0.1062 0.3064 0.5874 34 Y 0.0901 0.1044 0.8055 35 P 0.0309 0.1362 0.8330 36 N 0.0323 0.0781 0.8896 37 I 0.1157 0.0462 0.8381 38 S 0.2325 0.0221 0.7454 39 F 0.5498 0.0073 0.4429 40 K 0.8008 0.0050 0.1942 41 Y 0.8857 0.0039 0.1104 42 T 0.8986 0.0048 0.0966 43 Y 0.9149 0.0035 0.0816 44 I 0.8794 0.0052 0.1154 45 D 0.7654 0.0051 0.2295 46 I 0.3020 0.0855 0.6125 47 T 0.0995 0.0845 0.8160 48 K 0.0669 0.0668 0.8663 49 D 0.0587 0.1087 0.8326 50 N 0.0410 0.3273 0.6317 51 D 0.0281 0.4023 0.5696 52 N 0.0337 0.4343 0.5321 53 L 0.0309 0.4665 0.5026 54 T 0.0335 0.4676 0.4989 55 D 0.0186 0.6663 0.3152 56 H 0.0144 0.7436 0.2420 57 D 0.0087 0.8150 0.1762 58 L 0.0068 0.9005 0.0927 59 Q 0.0068 0.9107 0.0825 60 F 0.0060 0.9259 0.0681 61 I 0.0050 0.9421 0.0529 62 E 0.0058 0.9283 0.0659 63 R 0.0071 0.9002 0.0927 64 I 0.0171 0.8506 0.1323 65 E 0.0230 0.7468 0.2302 66 Q 0.0242 0.6198 0.3560 67 D 0.0350 0.4434 0.5216 68 E 0.0821 0.3327 0.5852 69 L 0.2022 0.2001 0.5977 70 F 0.3610 0.0824 0.5566 71 Y 0.4784 0.0363 0.4853 72 P 0.6179 0.0259 0.3563 73 L 0.8581 0.0123 0.1296 74 I 0.9147 0.0054 0.0799 75 T 0.9047 0.0054 0.0899 76 M 0.8250 0.0170 0.1580 77 N 0.2057 0.0236 0.7708 78 D 0.0450 0.0879 0.8671 79 E 0.5940 0.1002 0.3058 80 Y 0.7197 0.1278 0.1525 81 V 0.6368 0.1804 0.1828 82 A 0.5127 0.2166 0.2707 83 D 0.2393 0.2031 0.5576 84 G 0.1322 0.0904 0.7774 85 Y 0.1614 0.1765 0.6620 86 I 0.1568 0.3313 0.5119 87 Q 0.1524 0.4244 0.4233 88 T 0.0909 0.6406 0.2685 89 K 0.0354 0.7921 0.1725 90 Q 0.0189 0.8928 0.0884 91 I 0.0092 0.9287 0.0621 92 T 0.0101 0.9346 0.0553 93 R 0.0100 0.9344 0.0555 94 F 0.0085 0.9297 0.0618 95 I 0.0115 0.9133 0.0752 96 D 0.0109 0.8984 0.0907 97 Q 0.0123 0.8583 0.1294 98 K 0.0166 0.8069 0.1765 99 L 0.0396 0.6704 0.2899 100 V 0.0450 0.4561 0.4989 101 N 0.0488 0.2169 0.7343 102 E 0.0323 0.0546 0.9131