# This file is the result of combining several RDB files, specifically # T0254.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0254.t2k.stride-ebghtl.rdb (weight 1.24869) # T0254.t2k.str2.rdb (weight 1.54758) # T0254.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 T0254.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0254 # 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 T0254.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 9 # # ============================================ # Comments from T0254.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0254 # 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 T0254.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 9 # # ============================================ # Comments from T0254.t2k.str2.rdb # ============================================ # TARGET T0254 # 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 T0254.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 9 # # ============================================ # Comments from T0254.t2k.alpha.rdb # ============================================ # TARGET T0254 # 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 T0254.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 9 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 M 0.0960 0.0284 0.8756 2 P 0.1879 0.0210 0.7912 3 H 0.5919 0.0203 0.3879 4 L 0.7411 0.0255 0.2334 5 R 0.8406 0.0177 0.1418 6 F 0.7959 0.0263 0.1779 7 R 0.6351 0.0496 0.3153 8 A 0.4248 0.0523 0.5229 9 V 0.2606 0.0523 0.6871 10 E 0.1478 0.0913 0.7609 11 A 0.0155 0.8058 0.1787 12 H 0.0128 0.8552 0.1319 13 I 0.0084 0.9025 0.0891 14 V 0.0087 0.9051 0.0862 15 E 0.0088 0.9122 0.0790 16 S 0.0083 0.8795 0.1122 17 L 0.0102 0.8216 0.1681 18 V 0.0201 0.8187 0.1613 19 P 0.0052 0.9281 0.0667 20 T 0.0051 0.9370 0.0579 21 L 0.0052 0.9416 0.0532 22 L 0.0050 0.9509 0.0440 23 N 0.0049 0.9494 0.0457 24 E 0.0057 0.9295 0.0649 25 L 0.0055 0.9285 0.0660 26 S 0.0051 0.9390 0.0559 27 S 0.0055 0.9088 0.0857 28 L 0.0090 0.8649 0.1261 29 L 0.0445 0.6734 0.2821 30 S 0.0643 0.2232 0.7125 31 T 0.0878 0.0470 0.8651 32 A 0.0745 0.0446 0.8810 33 R 0.0458 0.2031 0.7511 34 N 0.0925 0.1839 0.7236 35 A 0.4050 0.0976 0.4974 36 F 0.7513 0.0169 0.2318 37 T 0.8710 0.0085 0.1205 38 F 0.8666 0.0103 0.1231 39 E 0.8335 0.0119 0.1546 40 L 0.7217 0.0176 0.2607 41 I 0.5270 0.0372 0.4359 42 N 0.4417 0.0400 0.5183 43 T 0.6070 0.0320 0.3610 44 Q 0.7860 0.0221 0.1919 45 Y 0.8565 0.0152 0.1283 46 F 0.8143 0.0206 0.1652 47 A 0.6478 0.0415 0.3106 48 E 0.2510 0.0473 0.7017 49 G 0.1111 0.0383 0.8505 50 G 0.2122 0.0293 0.7585 51 V 0.4427 0.0185 0.5388 52 Y 0.6201 0.0088 0.3711 53 P 0.6784 0.0080 0.3136 54 M 0.8766 0.0046 0.1188 55 V 0.9117 0.0037 0.0846 56 E 0.9204 0.0034 0.0762 57 V 0.9147 0.0033 0.0820 58 L 0.8861 0.0063 0.1076 59 W 0.7429 0.0131 0.2441 60 F 0.3887 0.0239 0.5874 61 G 0.2115 0.0524 0.7361 62 R 0.0619 0.1040 0.8341 63 E 0.0536 0.1451 0.8013 64 Q 0.0139 0.7850 0.2011 65 Q 0.0089 0.8849 0.1062 66 T 0.0088 0.9095 0.0817 67 Q 0.0051 0.9403 0.0547 68 D 0.0050 0.9514 0.0437 69 Q 0.0048 0.9556 0.0396 70 I 0.0047 0.9566 0.0387 71 A 0.0047 0.9592 0.0361 72 Q 0.0047 0.9582 0.0371 73 V 0.0047 0.9560 0.0393 74 I 0.0048 0.9533 0.0419 75 T 0.0048 0.9522 0.0431 76 D 0.0050 0.9444 0.0506 77 Q 0.0053 0.9348 0.0599 78 I 0.0063 0.9186 0.0751 79 R 0.0076 0.8949 0.0975 80 Q 0.0116 0.8498 0.1386 81 L 0.0178 0.7706 0.2116 82 L 0.0542 0.4606 0.4852 83 G 0.0329 0.2370 0.7301 84 A 0.0354 0.1505 0.8141 85 D 0.0845 0.0830 0.8325 86 S 0.1827 0.0582 0.7591 87 H 0.5250 0.0164 0.4586 88 L 0.8499 0.0046 0.1455 89 A 0.9179 0.0036 0.0785 90 V 0.9289 0.0031 0.0680 91 V 0.9234 0.0037 0.0729 92 F 0.8948 0.0050 0.1002 93 I 0.8222 0.0151 0.1627 94 P 0.7758 0.0151 0.2091 95 L 0.5439 0.0420 0.4141 96 Q 0.2949 0.0365 0.6686 97 R 0.0780 0.3220 0.6000 98 T 0.1034 0.3510 0.5456 99 A 0.2198 0.3447 0.4354 100 Y 0.3536 0.2256 0.4208 101 Y 0.3116 0.1914 0.4970 102 L 0.1568 0.1726 0.6706 103 D 0.0699 0.0758 0.8543 104 G 0.0813 0.0589 0.8598 105 Q 0.2607 0.0460 0.6934 106 H 0.2571 0.0346 0.7083 107 F 0.0568 0.0244 0.9188