# This file is the result of combining several RDB files, specifically # T0236.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0236.t2k.stride-ebghtl.rdb (weight 1.24869) # T0236.t2k.str2.rdb (weight 1.54758) # T0236.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 T0236.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0236 # 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 T0236.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 7 # # ============================================ # Comments from T0236.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0236 # 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 T0236.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 7 # # ============================================ # Comments from T0236.t2k.str2.rdb # ============================================ # TARGET T0236 # 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 T0236.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 7 # # ============================================ # Comments from T0236.t2k.alpha.rdb # ============================================ # TARGET T0236 # 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 T0236.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 7 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 M 0.0459 0.1310 0.8231 2 D 0.0721 0.3524 0.5755 3 F 0.0179 0.7608 0.2214 4 R 0.0099 0.8569 0.1332 5 E 0.0077 0.8795 0.1128 6 V 0.0082 0.8911 0.1008 7 I 0.0080 0.8743 0.1177 8 E 0.0077 0.8760 0.1163 9 Q 0.0081 0.8890 0.1030 10 R 0.0081 0.8873 0.1046 11 Y 0.0056 0.9347 0.0596 12 H 0.0048 0.9520 0.0432 13 Q 0.0048 0.9545 0.0408 14 L 0.0048 0.9543 0.0408 15 L 0.0048 0.9517 0.0435 16 S 0.0048 0.9481 0.0471 17 R 0.0055 0.9371 0.0574 18 Y 0.0059 0.9159 0.0782 19 I 0.0100 0.8148 0.1752 20 A 0.0133 0.7198 0.2670 21 E 0.0279 0.5177 0.4545 22 L 0.0394 0.3368 0.6239 23 T 0.0559 0.2395 0.7045 24 E 0.0168 0.8110 0.1721 25 T 0.0262 0.8469 0.1269 26 S 0.0246 0.8730 0.1024 27 L 0.0530 0.8548 0.0922 28 Y 0.0766 0.8155 0.1080 29 Q 0.0756 0.7890 0.1353 30 A 0.0305 0.8389 0.1306 31 Q 0.0255 0.8519 0.1225 32 K 0.0252 0.8181 0.1567 33 F 0.0281 0.7429 0.2290 34 S 0.0378 0.7019 0.2603 35 R 0.0056 0.9246 0.0698 36 K 0.0058 0.9335 0.0608 37 T 0.0062 0.9273 0.0664 38 I 0.0081 0.9001 0.0918 39 E 0.0099 0.7985 0.1917 40 H 0.0210 0.5005 0.4785 41 Q 0.0339 0.2070 0.7591 42 I 0.0848 0.0497 0.8656 43 P 0.0619 0.0352 0.9028 44 P 0.0064 0.8858 0.1078 45 E 0.0049 0.9367 0.0584 46 E 0.0049 0.9447 0.0505 47 I 0.0048 0.9492 0.0460 48 I 0.0048 0.9489 0.0463 49 S 0.0049 0.9507 0.0444 50 I 0.0049 0.9480 0.0471 51 H 0.0056 0.9478 0.0466 52 R 0.0048 0.9537 0.0416 53 K 0.0049 0.9539 0.0411 54 V 0.0048 0.9512 0.0440 55 L 0.0049 0.9418 0.0533 56 K 0.0052 0.9122 0.0827 57 E 0.0065 0.8149 0.1787 58 L 0.0270 0.5792 0.3938 59 Y 0.0542 0.2699 0.6759 60 P 0.0108 0.4486 0.5406 61 S 0.0208 0.3512 0.6280 62 L 0.0446 0.3229 0.6325 63 P 0.0167 0.6791 0.3043 64 E 0.0087 0.7914 0.1999 65 D 0.0084 0.8507 0.1409 66 V 0.0084 0.9199 0.0717 67 F 0.0080 0.9338 0.0582 68 H 0.0081 0.9300 0.0620 69 S 0.0062 0.9380 0.0557 70 L 0.0049 0.9521 0.0430 71 D 0.0047 0.9555 0.0397 72 F 0.0047 0.9562 0.0390 73 L 0.0047 0.9580 0.0373 74 I 0.0047 0.9561 0.0391 75 E 0.0051 0.9529 0.0420 76 V 0.0052 0.9513 0.0436 77 M 0.0067 0.9480 0.0453 78 I 0.0074 0.9335 0.0592 79 G 0.0093 0.9104 0.0803 80 Y 0.0168 0.8618 0.1215 81 G 0.0160 0.8015 0.1825 82 M 0.0242 0.8001 0.1757 83 A 0.0363 0.7770 0.1866 84 Y 0.0249 0.8584 0.1166 85 Q 0.0340 0.8392 0.1268 86 E 0.0341 0.8358 0.1301 87 H 0.0343 0.8389 0.1268 88 Q 0.0314 0.8084 0.1602 89 T 0.0339 0.7828 0.1833 90 L 0.0240 0.8095 0.1665 91 R 0.0183 0.8389 0.1428 92 G 0.0154 0.8199 0.1647 93 I 0.0096 0.8636 0.1269 94 Q 0.0090 0.8889 0.1021 95 Q 0.0094 0.8796 0.1110 96 E 0.0069 0.8967 0.0964 97 I 0.0078 0.8876 0.1046 98 K 0.0064 0.9196 0.0739 99 S 0.0067 0.9275 0.0658 100 E 0.0055 0.9521 0.0424 101 I 0.0053 0.9568 0.0379 102 E 0.0055 0.9560 0.0386 103 I 0.0055 0.9495 0.0450 104 A 0.0065 0.9402 0.0533 105 A 0.0078 0.9055 0.0867 106 N 0.0118 0.8091 0.1791 107 V 0.0348 0.7038 0.2614 108 Q 0.0460 0.4332 0.5208 109 Q 0.0494 0.2315 0.7191 110 T 0.0438 0.0409 0.9153