# This file is the result of combining several RDB files, specifically # T0498.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0498.t2k.stride-ebghtl.rdb (weight 1.24869) # T0498.t2k.str.rdb (weight 1.53983) # 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 T0498.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0498 # 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 T0498.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 14 # # ============================================ # Comments from T0498.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0498 # 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 T0498.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 14 # # ============================================ # Comments from T0498.t2k.str.rdb # ============================================ # TARGET T0498 # Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str-seeded.net # This is a 4-layer network, with # window units # 5 15 # 7 15 # 9 15 # 13 13 (1 str ) # The input amino acid frequencies were determined from # alignment T0498.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 14 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 T 0.0519 0.0055 0.9427 2 T 0.4687 0.0085 0.5227 3 Y 0.8110 0.0123 0.1767 4 K 0.9161 0.0107 0.0732 5 L 0.9551 0.0088 0.0361 6 I 0.9506 0.0074 0.0420 7 L 0.9072 0.0104 0.0824 8 N 0.6546 0.0220 0.3234 9 L 0.2445 0.0484 0.7072 10 K 0.2337 0.0707 0.6955 11 Q 0.2934 0.0715 0.6351 12 A 0.3701 0.0703 0.5596 13 K 0.4331 0.0948 0.4721 14 E 0.5741 0.1191 0.3067 15 E 0.6283 0.1387 0.2331 16 A 0.5997 0.1904 0.2099 17 I 0.5515 0.2201 0.2284 18 K 0.4416 0.2928 0.2656 19 E 0.3185 0.4566 0.2249 20 L 0.3118 0.3853 0.3029 21 V 0.3225 0.3428 0.3348 22 D 0.1177 0.2838 0.5985 23 A 0.0052 0.8849 0.1099 24 G 0.0038 0.9423 0.0539 25 T 0.0037 0.9561 0.0401 26 A 0.0037 0.9675 0.0287 27 E 0.0038 0.9702 0.0260 28 K 0.0038 0.9701 0.0261 29 Y 0.0038 0.9723 0.0240 30 I 0.0038 0.9731 0.0231 31 K 0.0037 0.9725 0.0238 32 L 0.0038 0.9673 0.0289 33 I 0.0038 0.9524 0.0438 34 A 0.0053 0.9197 0.0750 35 N 0.0081 0.7569 0.2349 36 A 0.0127 0.4436 0.5437 37 K 0.0146 0.2223 0.7631 38 T 0.0278 0.0262 0.9460 39 V 0.1527 0.0177 0.8297 40 E 0.2731 0.0157 0.7112 41 G 0.4265 0.0239 0.5496 42 V 0.7368 0.0141 0.2491 43 W 0.8618 0.0063 0.1319 44 T 0.8233 0.0070 0.1697 45 L 0.6931 0.0434 0.2635 46 K 0.3293 0.1479 0.5228 47 D 0.1585 0.2407 0.6008 48 E 0.2523 0.1981 0.5496 49 I 0.4382 0.0609 0.5009 50 K 0.5019 0.0402 0.4579 51 T 0.5880 0.0326 0.3794 52 F 0.7462 0.0229 0.2309 53 T 0.7423 0.0255 0.2322 54 V 0.5687 0.0304 0.4009 55 T 0.2993 0.0320 0.6687 56 E 0.0523 0.0554 0.8923