# This file is the result of combining several RDB files, specifically # T0320.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0320.t2k.stride-ebghtl.rdb (weight 1.24869) # T0320.t2k.str2.rdb (weight 1.54758) # T0320.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 T0320.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0320 # 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 T0320.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 22 # # ============================================ # Comments from T0320.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0320 # 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 T0320.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 22 # # ============================================ # Comments from T0320.t2k.str2.rdb # ============================================ # TARGET T0320 # 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 T0320.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 13.8556 # # ============================================ # Comments from T0320.t2k.alpha.rdb # ============================================ # TARGET T0320 # 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 T0320.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 22 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 N 0.0696 0.0433 0.8872 2 E 0.2013 0.0297 0.7690 3 P 0.3928 0.0452 0.5620 4 I 0.5630 0.0856 0.3515 5 C 0.5644 0.1468 0.2888 6 G 0.5482 0.2143 0.2375 7 L 0.4592 0.2720 0.2688 8 Y 0.3957 0.2419 0.3625 9 G 0.2695 0.2477 0.4828 10 K 0.1305 0.1928 0.6767 11 G 0.1602 0.0667 0.7731 12 F 0.3661 0.0637 0.5702 13 T 0.5083 0.0578 0.4339 14 S 0.4375 0.0753 0.4872 15 I 0.2352 0.1242 0.6406 16 G 0.1536 0.1004 0.7460 17 G 0.1665 0.0913 0.7422 18 I 0.1516 0.1132 0.7352 19 N 0.1264 0.1312 0.7424 20 N 0.1104 0.1258 0.7638 21 S 0.1564 0.0991 0.7446 22 L 0.1275 0.0555 0.8169 23 P 0.1298 0.0560 0.8142 24 N 0.1388 0.0836 0.7775 25 P 0.0661 0.3471 0.5868 26 H 0.1519 0.3547 0.4934 27 L 0.3011 0.2823 0.4165 28 R 0.3362 0.1302 0.5336 29 K 0.2431 0.0863 0.6706 30 D 0.0896 0.0806 0.8298 31 S 0.0643 0.1202 0.8156 32 N 0.0461 0.1389 0.8150 33 N 0.0641 0.1509 0.7850 34 P 0.0668 0.1681 0.7651 35 A 0.1239 0.2529 0.6232 36 L 0.1503 0.2441 0.6056 37 H 0.1251 0.2318 0.6431 38 F 0.0879 0.4046 0.5075 39 E 0.0808 0.4523 0.4669 40 W 0.1110 0.5239 0.3652 41 E 0.1722 0.5860 0.2418 42 I 0.1684 0.6272 0.2043 43 I 0.1329 0.6810 0.1861 44 H 0.1422 0.6613 0.1966 45 A 0.1102 0.6671 0.2227 46 F 0.0755 0.6077 0.3168 47 G 0.0751 0.4992 0.4257 48 K 0.0874 0.4601 0.4525 49 D 0.0919 0.4489 0.4592 50 A 0.1023 0.4720 0.4257 51 E 0.1130 0.4303 0.4567 52 G 0.0958 0.3085 0.5957 53 E 0.0913 0.2494 0.6593 54 R 0.1193 0.1864 0.6943 55 S 0.1098 0.1788 0.7114 56 S 0.0870 0.1771 0.7358 57 A 0.0934 0.2430 0.6636 58 I 0.1339 0.2384 0.6277 59 N 0.1437 0.1574 0.6988 60 T 0.1458 0.1449 0.7093 61 S 0.1653 0.1027 0.7319 62 P 0.1809 0.1286 0.6905 63 I 0.1472 0.2119 0.6409 64 S 0.1801 0.2590 0.5609 65 V 0.1111 0.3651 0.5238 66 V 0.0890 0.3596 0.5515 67 D 0.0821 0.4602 0.4577 68 K 0.1096 0.4525 0.4379 69 E 0.1812 0.4051 0.4136 70 R 0.2314 0.3487 0.4199 71 F 0.1975 0.3573 0.4452 72 S 0.1441 0.3001 0.5558 73 K 0.1242 0.2249 0.6510 74 Y 0.1303 0.1870 0.6827 75 H 0.0930 0.1662 0.7408 76 D 0.0586 0.1976 0.7438 77 N 0.1051 0.1600 0.7349 78 Y 0.3243 0.0680 0.6077 79 Y 0.4108 0.0233 0.5659 80 P 0.5277 0.0602 0.4122 81 G 0.5522 0.1196 0.3282 82 W 0.6126 0.1447 0.2427 83 Y 0.7171 0.0944 0.1885 84 L 0.5962 0.1033 0.3005 85 V 0.2798 0.0963 0.6239 86 D 0.1150 0.1040 0.7810 87 D 0.0490 0.4715 0.4795 88 T 0.0317 0.7149 0.2534 89 L 0.0579 0.7287 0.2134 90 E 0.0612 0.7225 0.2162 91 R 0.0801 0.6498 0.2700 92 A 0.0813 0.5013 0.4173 93 G 0.0879 0.2588 0.6533 94 R 0.1541 0.1323 0.7137 95 I 0.2141 0.1263 0.6596 96 K 0.1291 0.1156 0.7553 97 N 0.0592 0.0400 0.9008