# This file is the result of combining several RDB files, specifically # TR462.t2k.str2.rdb (weight 1.54425) # TR462.t2k.str4.rdb (weight 0.924988) # TR462.t2k.pb.rdb (weight 0.789901) # TR462.t2k.bys.rdb (weight 0.748322) # TR462.t2k.alpha.rdb (weight 0.678173) # 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 TR462.t2k.str2.rdb # ============================================ # TARGET TR462 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-str2-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 13 (1 str2 ) # The input amino acid frequencies were determined from # alignment TR462.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.77549 # # ============================================ # Comments from TR462.t2k.str4.rdb # ============================================ # TARGET TR462 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-str4-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 21 (1 str4 ) # The input amino acid frequencies were determined from # alignment TR462.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.77549 # # ============================================ # Comments from TR462.t2k.pb.rdb # ============================================ # TARGET TR462 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-pb-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 16 (1 pb ) # The input amino acid frequencies were determined from # alignment TR462.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.77549 # # ============================================ # Comments from TR462.t2k.bys.rdb # ============================================ # TARGET TR462 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-bys-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 11 (1 Bystroff ) # The input amino acid frequencies were determined from # alignment TR462.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.77549 # # ============================================ # Comments from TR462.t2k.alpha.rdb # ============================================ # TARGET TR462 # Using neural net dunbrack-40pc-3157-t2k-IDGaaH13-3-13-7-13-9-13-11-alpha-seeded.net # This is a 4-layer network, with # window units # 3 13 # 7 13 # 9 13 # 11 11 (1 ABCDEFGHIST ) # The input amino acid frequencies were determined from # alignment TR462.t2k-thin90.a2m.gz # with weighted counts, using HenikoffWeight(1.3 bits/column, 1) # The weighting was determined by the posterior distribution # after regularizing with /projects/compbio/lib/recode3.20comp. # Counts were regularized to probabilities using # /projects/compbio/lib/recode3.20comp # Total sequence weight for alignment was 4.77549 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 E 0.2956 0.0872 0.6172 2 L 0.3955 0.0252 0.5793 3 P 0.4364 0.0259 0.5377 4 L 0.6470 0.0292 0.3237 5 I 0.7024 0.0238 0.2738 6 L 0.6743 0.0240 0.3017 7 A 0.4784 0.0456 0.4760 8 D 0.3036 0.1354 0.5610 9 D 0.1716 0.0999 0.7285 10 G 0.1949 0.0706 0.7345 11 T 0.5837 0.0205 0.3958 12 Y 0.7210 0.0094 0.2696 13 E 0.7880 0.0080 0.2040 14 I 0.7749 0.0070 0.2181 15 T 0.7742 0.0126 0.2132 16 K 0.7596 0.0142 0.2262 17 L 0.5856 0.0585 0.3558 18 N 0.3018 0.1093 0.5889 19 G 0.1470 0.1707 0.6824 20 G 0.1090 0.3695 0.5215 21 R 0.0647 0.6649 0.2704 22 R 0.0447 0.7849 0.1704 23 F 0.0380 0.8478 0.1142 24 L 0.0183 0.8962 0.0855 25 F 0.0147 0.9044 0.0809 26 R 0.0175 0.8909 0.0916 27 M 0.0253 0.8682 0.1065 28 K 0.0241 0.8507 0.1252 29 N 0.0696 0.6804 0.2501 30 L 0.1000 0.3342 0.5658 31 G 0.1715 0.1198 0.7087 32 I 0.3430 0.0882 0.5688 33 E 0.4166 0.1059 0.4775 34 S 0.3111 0.0887 0.6003 35 G 0.1958 0.0632 0.7411 36 K 0.4534 0.0295 0.5170 37 K 0.7076 0.0129 0.2795 38 I 0.7730 0.0080 0.2190 39 Q 0.7437 0.0068 0.2496 40 V 0.6953 0.0119 0.2928 41 S 0.5109 0.0380 0.4511 42 G 0.3316 0.0453 0.6230 43 R 0.3885 0.0531 0.5584 44 R 0.6088 0.0240 0.3672 45 Y 0.7214 0.0106 0.2680 46 Y 0.7351 0.0092 0.2557 47 I 0.6441 0.0230 0.3330 48 E 0.3800 0.0476 0.5724 49 G 0.2272 0.0658 0.7070 50 R 0.3592 0.0837 0.5571 51 E 0.6009 0.0455 0.3536 52 I 0.6717 0.0343 0.2940 53 D 0.6232 0.0365 0.3403 54 L 0.4969 0.0867 0.4165 55 G 0.2924 0.0857 0.6219 56 Y 0.2326 0.1366 0.6308 57 G 0.1740 0.1300 0.6960 58 E 0.2840 0.1988 0.5173 59 A 0.3677 0.2007 0.4316 60 T 0.4508 0.1497 0.3995 61 K 0.6516 0.0578 0.2905 62 I 0.7290 0.0262 0.2448 63 W 0.7533 0.0251 0.2217 64 V 0.7274 0.0401 0.2325 65 R 0.6635 0.0533 0.2832 66 R 0.5658 0.0454 0.3888 67 V 0.3811 0.0786 0.5403