# This file is the result of combining several RDB files, specifically # T0300.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0300.t2k.stride-ebghtl.rdb (weight 1.24869) # T0300.t2k.str2.rdb (weight 1.54758) # T0300.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 T0300.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0300 # 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 T0300.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 13 # # ============================================ # Comments from T0300.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0300 # 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 T0300.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 13 # # ============================================ # Comments from T0300.t2k.str2.rdb # ============================================ # TARGET T0300 # Using neural net dunbrack-30pc-1763-t2k-thin90-IDGaaH13-3-13-7-13-9-13-11-t1c2-str2-from-empty.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 T0300.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 8.03554 # # ============================================ # Comments from T0300.t2k.alpha.rdb # ============================================ # TARGET T0300 # 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 T0300.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 13 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 M 0.0588 0.1013 0.8399 2 A 0.1023 0.0809 0.8168 3 S 0.0960 0.0656 0.8384 4 K 0.0664 0.1208 0.8129 5 K 0.0744 0.0946 0.8310 6 P 0.0522 0.1200 0.8278 7 D 0.0821 0.0776 0.8402 8 K 0.1075 0.0452 0.8473 9 T 0.0972 0.0458 0.8570 10 Y 0.0055 0.9331 0.0615 11 E 0.0048 0.9523 0.0429 12 E 0.0047 0.9557 0.0396 13 M 0.0047 0.9572 0.0381 14 V 0.0047 0.9557 0.0396 15 K 0.0048 0.9546 0.0406 16 E 0.0049 0.9528 0.0424 17 V 0.0048 0.9528 0.0423 18 E 0.0049 0.9463 0.0489 19 R 0.0050 0.9279 0.0672 20 L 0.0063 0.9244 0.0692 21 K 0.0058 0.9019 0.0923 22 L 0.0081 0.8725 0.1194 23 E 0.0117 0.8630 0.1252 24 N 0.0122 0.8865 0.1013 25 K 0.0053 0.9172 0.0776 26 T 0.0054 0.9290 0.0656 27 L 0.0054 0.9290 0.0656 28 K 0.0055 0.9441 0.0503 29 Q 0.0063 0.9469 0.0468 30 K 0.0056 0.9439 0.0504 31 V 0.0090 0.9248 0.0662 32 K 0.0125 0.8676 0.1199 33 S 0.0416 0.5895 0.3688 34 S 0.0525 0.1929 0.7545 35 G 0.0561 0.0822 0.8617 36 A 0.0709 0.0744 0.8547 37 V 0.0881 0.0575 0.8543 38 S 0.0661 0.0474 0.8865 39 S 0.0761 0.0754 0.8485 40 D 0.0715 0.0959 0.8325 41 D 0.0834 0.1884 0.7282 42 S 0.1095 0.1802 0.7102 43 I 0.1547 0.1260 0.7193 44 L 0.1355 0.0611 0.8034 45 T 0.0629 0.0310 0.9061 46 A 0.0109 0.7980 0.1911 47 A 0.0084 0.8844 0.1072 48 K 0.0102 0.9252 0.0646 49 R 0.0068 0.9482 0.0449 50 E 0.0079 0.9467 0.0453 51 S 0.0091 0.9474 0.0435 52 I 0.0061 0.9523 0.0416 53 I 0.0057 0.9531 0.0412 54 V 0.0055 0.9485 0.0460 55 S 0.0060 0.9398 0.0542 56 S 0.0049 0.9446 0.0505 57 S 0.0050 0.9483 0.0466 58 R 0.0052 0.9460 0.0488 59 A 0.0054 0.9338 0.0608 60 L 0.0056 0.9295 0.0650 61 G 0.0070 0.9304 0.0626 62 A 0.0060 0.9412 0.0529 63 V 0.0063 0.9404 0.0533 64 A 0.0052 0.9444 0.0503 65 M 0.0051 0.9522 0.0427 66 R 0.0051 0.9550 0.0399 67 K 0.0051 0.9543 0.0407 68 I 0.0049 0.9567 0.0384 69 E 0.0047 0.9585 0.0367 70 A 0.0049 0.9555 0.0396 71 K 0.0052 0.9493 0.0455 72 V 0.0055 0.9405 0.0541 73 R 0.0076 0.9195 0.0729 74 S 0.0090 0.8735 0.1175 75 R 0.0130 0.7882 0.1989 76 A 0.0251 0.6595 0.3154 77 A 0.0272 0.5266 0.4462 78 K 0.0272 0.4322 0.5406 79 A 0.1546 0.2874 0.5581 80 V 0.2493 0.1103 0.6405 81 T 0.1193 0.0793 0.8013 82 E 0.0073 0.8583 0.1344 83 Q 0.0051 0.9242 0.0707 84 E 0.0053 0.9404 0.0544 85 L 0.0048 0.9506 0.0446 86 T 0.0047 0.9521 0.0432 87 S 0.0051 0.9400 0.0548 88 L 0.0050 0.9225 0.0724 89 L 0.0094 0.8838 0.1068 90 Q 0.0107 0.7193 0.2701 91 S 0.0376 0.2411 0.7213 92 L 0.1585 0.0583 0.7832 93 T 0.3718 0.0298 0.5984 94 L 0.7883 0.0093 0.2024 95 R 0.8645 0.0053 0.1301 96 V 0.8870 0.0040 0.1090 97 D 0.8393 0.0045 0.1562 98 V 0.5538 0.0100 0.4363 99 S 0.2650 0.0115 0.7235 100 M 0.0839 0.1384 0.7777 101 E 0.0429 0.1315 0.8256 102 E 0.0302 0.0834 0.8863