# This file is the result of combining several RDB files, specifically # T0151.t2k.dssp-ebghstl.rdb (weight 1.53986) # T0151.t2k.stride-ebghtl.rdb (weight 1.24869) # T0151.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 T0151.t2k.dssp-ebghstl.rdb # ============================================ # TARGET T0151 # 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 T0151.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 4 # # ============================================ # Comments from T0151.t2k.stride-ebghtl.rdb # ============================================ # TARGET T0151 # 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 T0151.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 4 # # ============================================ # Comments from T0151.t2k.str.rdb # ============================================ # TARGET T0151 # 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 T0151.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 4 # # ============================================ Pos AA E H C 10N 1S 5N 5N 5N 1 L 0.0523 0.0191 0.9285 2 R 0.3628 0.0403 0.5969 3 Y 0.5664 0.1466 0.2870 4 A 0.5916 0.1436 0.2648 5 T 0.6947 0.1303 0.1750 6 A 0.7518 0.0601 0.1881 7 K 0.7600 0.0555 0.1845 8 V 0.6816 0.1112 0.2072 9 N 0.4404 0.1091 0.4505 10 K 0.2923 0.1801 0.5277 11 A 0.2325 0.1906 0.5769 12 S 0.1975 0.1680 0.6345 13 R 0.1024 0.1240 0.7736 14 S 0.0744 0.0865 0.8391 15 G 0.0416 0.0709 0.8875 16 G 0.0551 0.0715 0.8734 17 F 0.1056 0.0790 0.8154 18 G 0.0864 0.0778 0.8359 19 S 0.1035 0.0807 0.8158 20 G 0.1211 0.0911 0.7879 21 S 0.1263 0.1258 0.7478 22 R 0.0988 0.1188 0.7825 23 P 0.0975 0.1311 0.7714 24 A 0.0831 0.1496 0.7673 25 P 0.0782 0.2088 0.7130 26 A 0.0896 0.2221 0.6883 27 Q 0.1157 0.2212 0.6631 28 T 0.1515 0.2325 0.6160 29 S 0.1433 0.1755 0.6812 30 S 0.1194 0.1385 0.7421 31 A 0.1010 0.1087 0.7903 32 S 0.0613 0.1782 0.7606 33 G 0.0459 0.1433 0.8108 34 D 0.0902 0.1065 0.8033 35 D 0.0498 0.0524 0.8977 36 P 0.0364 0.1435 0.8201 37 W 0.0306 0.1562 0.8132 38 G 0.0625 0.1274 0.8100 39 S 0.1705 0.0719 0.7576 40 A 0.1477 0.0753 0.7770 41 P 0.1211 0.1176 0.7613 42 A 0.1302 0.1322 0.7376 43 S 0.1101 0.1089 0.7810 44 G 0.0714 0.0792 0.8494 45 S 0.1054 0.0863 0.8083 46 F 0.0986 0.0669 0.8345 47 G 0.0721 0.0656 0.8623 48 G 0.0949 0.0526 0.8525 49 G 0.0491 0.0697 0.8812 50 D 0.0328 0.1002 0.8670 51 D 0.0344 0.1188 0.8469 52 E 0.0456 0.0623 0.8920 53 P 0.0421 0.0422 0.9157 54 P 0.0452 0.0256 0.9293 55 F 0.0107 0.0066 0.9827