# This file is the result of combining several RDB files, specifically # T0352.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0352.t2k.stride-ebghtl.rdb (weight 1.24869) # T0352.t2k.str2.rdb (weight 1.54758) # T0352.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 T0352.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0352 # 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 T0352.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 59 # # ============================================ # Comments from T0352.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0352 # 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 T0352.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 59 # # ============================================ # Comments from T0352.t2k.str2.rdb # ============================================ # TARGET T0352 # 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 T0352.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 59 # # ============================================ # Comments from T0352.t2k.alpha.rdb # ============================================ # TARGET T0352 # 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 T0352.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 59 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 M 0.0538 0.0471 0.8991 2 T 0.0797 0.0838 0.8365 3 T 0.0343 0.6477 0.3180 4 H 0.0096 0.8605 0.1298 5 D 0.0059 0.9104 0.0837 6 R 0.0056 0.9272 0.0672 7 V 0.0049 0.9365 0.0586 8 R 0.0048 0.9489 0.0463 9 L 0.0049 0.9458 0.0493 10 Q 0.0050 0.9420 0.0530 11 L 0.0049 0.9512 0.0440 12 Q 0.0049 0.9523 0.0429 13 A 0.0048 0.9536 0.0416 14 L 0.0047 0.9573 0.0380 15 E 0.0047 0.9579 0.0373 16 A 0.0047 0.9585 0.0368 17 L 0.0047 0.9575 0.0378 18 L 0.0048 0.9536 0.0416 19 R 0.0052 0.9337 0.0611 20 E 0.0065 0.8514 0.1421 21 H 0.0450 0.4828 0.4722 22 Q 0.0333 0.1559 0.8108 23 H 0.0449 0.2111 0.7440 24 W 0.0991 0.2976 0.6033 25 R 0.1059 0.3253 0.5688 26 N 0.1176 0.2275 0.6549 27 D 0.0902 0.0646 0.8452 28 E 0.0723 0.0296 0.8981 29 P 0.0732 0.0573 0.8695 30 Q 0.0597 0.1532 0.7870 31 P 0.0095 0.7754 0.2151 32 H 0.0089 0.7921 0.1990 33 Q 0.0176 0.8088 0.1736 34 F 0.0466 0.6398 0.3136 35 N 0.0437 0.3577 0.5986 36 S 0.0648 0.1907 0.7445 37 T 0.0780 0.0945 0.8275 38 Q 0.0974 0.0457 0.8570 39 P 0.1378 0.0962 0.7660 40 F 0.4156 0.0963 0.4881 41 F 0.5323 0.0657 0.4020 42 M 0.4828 0.1040 0.4132 43 D 0.3271 0.1261 0.5467 44 T 0.2798 0.0861 0.6341 45 M 0.2280 0.0289 0.7431 46 E 0.1731 0.0202 0.8067 47 P 0.0195 0.8361 0.1444 48 L 0.0098 0.9083 0.0819 49 E 0.0114 0.9214 0.0672 50 W 0.0145 0.9293 0.0562 51 L 0.0179 0.9264 0.0556 52 Q 0.0144 0.9352 0.0504 53 W 0.0198 0.9253 0.0549 54 V 0.0284 0.8900 0.0816 55 L 0.0396 0.8575 0.1028 56 I 0.0178 0.8556 0.1267 57 P 0.0053 0.9423 0.0525 58 R 0.0051 0.9426 0.0522 59 M 0.0047 0.9545 0.0407 60 H 0.0047 0.9569 0.0383 61 D 0.0050 0.9574 0.0376 62 L 0.0049 0.9561 0.0391 63 L 0.0055 0.9434 0.0511 64 D 0.0066 0.8929 0.1004 65 N 0.0328 0.4361 0.5311 66 K 0.0314 0.0809 0.8877 67 Q 0.0551 0.0209 0.9241 68 P 0.0920 0.0462 0.8619 69 L 0.0788 0.0599 0.8613 70 P 0.0619 0.1073 0.8308 71 G 0.0436 0.2549 0.7014 72 A 0.1007 0.3018 0.5975 73 F 0.1813 0.2174 0.6013 74 A 0.2201 0.2423 0.5375 75 V 0.1797 0.4092 0.4110 76 A 0.0373 0.6343 0.3284 77 P 0.0060 0.9395 0.0545 78 Y 0.0050 0.9477 0.0473 79 Y 0.0047 0.9529 0.0423 80 E 0.0048 0.9548 0.0405 81 M 0.0052 0.9486 0.0463 82 A 0.0056 0.9321 0.0623 83 L 0.0082 0.8912 0.1006 84 A 0.0098 0.7728 0.2173 85 T 0.0160 0.5314 0.4527 86 D 0.0408 0.3878 0.5714 87 H 0.0210 0.4510 0.5280 88 P 0.0150 0.5214 0.4635 89 Q 0.0161 0.6249 0.3590 90 R 0.0122 0.7734 0.2144 91 A 0.0072 0.8949 0.0980 92 L 0.0081 0.9120 0.0799 93 I 0.0053 0.9371 0.0576 94 L 0.0048 0.9492 0.0459 95 A 0.0048 0.9529 0.0423 96 E 0.0048 0.9542 0.0410 97 L 0.0048 0.9508 0.0444 98 E 0.0049 0.9373 0.0579 99 K 0.0052 0.9295 0.0653 100 L 0.0053 0.9249 0.0698 101 D 0.0064 0.8989 0.0946 102 A 0.0082 0.8993 0.0925 103 L 0.0105 0.8688 0.1207 104 F 0.0254 0.7367 0.2379 105 A 0.0393 0.4292 0.5315 106 D 0.0414 0.1626 0.7960 107 D 0.0463 0.0951 0.8586 108 A 0.0503 0.1081 0.8415 109 S 0.0390 0.0531 0.9079