PFRMAT SS TARGET T0389 AUTHOR SAM-T02-server METHOD This file is the result of combining several RDB files, specifically METHOD T0389.t2k.dssp-ebghstl.rdb (weight 1.53986) METHOD T0389.t2k.stride-ebghtl.rdb (weight 1.24869) METHOD T0389.t2k.str.rdb (weight 1.53983) METHOD These files were combined by translating their predictions into EHL METHOD predictions with tables generated by compare-real, and then combining METHOD those predictions with weights proportional to their mutual information METHOD with the EHL alphabet. The comments from the individual files follow. METHOD METHOD Comments from T0389.t2k.dssp-ebghstl.rdb METHOD ============================================ METHOD TARGET T0389 METHOD Using neural net t2k-5740-IDaaHr-5-15-7-15-9-15-13-ebghstl-seeded.net METHOD This is a 4-layer network, with METHOD window units METHOD 5 15 METHOD 7 15 METHOD 9 15 METHOD 13 7 (1 EBGHSTL ) METHOD The input amino acid frequencies were determined from METHOD alignment T0389.t2k-thin90.a2m.gz METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1) METHOD Counts were regularized to probabilities using METHOD /projects/compbio/lib/recode3.20comp METHOD Total sequence weight for alignment was 408 METHOD METHOD ============================================ METHOD Comments from T0389.t2k.stride-ebghtl.rdb METHOD ============================================ METHOD TARGET T0389 METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-ebghtl-seeded.net METHOD This is a 4-layer network, with METHOD window units METHOD 5 15 METHOD 7 15 METHOD 9 15 METHOD 13 6 (1 EBGHTL ) METHOD The input amino acid frequencies were determined from METHOD alignment T0389.t2k-thin90.a2m.gz METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1) METHOD Counts were regularized to probabilities using METHOD /projects/compbio/lib/recode3.20comp METHOD Total sequence weight for alignment was 408 METHOD METHOD ============================================ METHOD Comments from T0389.t2k.str.rdb METHOD ============================================ METHOD TARGET T0389 METHOD Using neural net t2k-5651-IDaaHr-5-15-7-15-9-15-13-str-seeded.net METHOD This is a 4-layer network, with METHOD window units METHOD 5 15 METHOD 7 15 METHOD 9 15 METHOD 13 13 (1 str ) METHOD The input amino acid frequencies were determined from METHOD alignment T0389.t2k-thin90.a2m.gz METHOD with weighted counts, using HenikoffWeight(-1 bits/column, 1) METHOD Counts were regularized to probabilities using METHOD /projects/compbio/lib/recode3.20comp METHOD Total sequence weight for alignment was 408 METHOD METHOD ============================================ MODEL 1 M C 0.95 I C 0.72 G C 0.62 T C 0.55 Q C 0.50 I H 0.46 V H 0.48 T H 0.87 E H 0.91 R H 0.92 L H 0.93 V H 0.93 A H 0.91 L H 0.90 L H 0.86 E H 0.79 S H 0.60 G C 0.77 T C 0.87 E C 0.91 K C 0.84 V E 0.74 L E 0.96 L E 0.97 I E 0.96 D E 0.89 S E 0.50 R C 0.84 P C 0.92 F H 0.59 V H 0.77 E H 0.82 Y H 0.81 N H 0.70 T H 0.52 S C 0.68 H C 0.75 I C 0.78 L C 0.74 E C 0.76 A C 0.64 I E 0.59 N E 0.62 I C 0.57 N C 0.83 C H 0.53 S H 0.74 K H 0.83 L H 0.86 M H 0.83 K H 0.77 R H 0.69 R H 0.68 L H 0.60 Q H 0.53 Q C 0.59 D C 0.67 K C 0.53 V H 0.47 L H 0.50 I H 0.55 T H 0.53 E H 0.50 L H 0.42 I C 0.46 Q C 0.61 H C 0.49 S H 0.53 A H 0.58 K H 0.57 H H 0.52 K H 0.49 V C 0.45 D C 0.56 I C 0.65 D C 0.75 C C 0.81 S C 0.88 Q C 0.75 K E 0.66 V E 0.94 V E 0.97 V E 0.96 Y E 0.92 D E 0.50 Q C 0.90 S C 0.92 S C 0.86 Q C 0.80 D C 0.68 V C 0.59 A C 0.57 S H 0.50 L H 0.51 S H 0.51 S H 0.64 D H 0.67 C H 0.78 F H 0.92 L H 0.94 T H 0.95 V H 0.96 L H 0.96 L H 0.96 G H 0.95 K H 0.94 L H 0.90 E H 0.78 K C 0.62 S C 0.91 F C 0.91 N C 0.83 S C 0.58 V E 0.84 H E 0.94 L E 0.93 L E 0.79 A C 0.55 G C 0.80 G C 0.70 F H 0.79 A H 0.94 E H 0.96 F H 0.96 S H 0.96 R H 0.91 C H 0.81 F C 0.64 P C 0.50 G H 0.53 L H 0.56 C C 0.56 E C 0.69 G C 0.84 K C 0.87 S C 0.82 T C 0.77 L C 0.81 V C 0.81 P C 0.84 T C 0.85 C C 0.84 I C 0.86 S C 0.87 Q C 0.89 P C 0.89 A C 0.88 H C 0.85 H C 0.86 H C 0.84 H C 0.84 H C 0.88 H C 0.98 END