LEADER 05664nam 2200697Ia 450 001 9910784519503321 005 20230721030449.0 010 $a1-281-86579-6 010 $a9786611865795 010 $a1-84816-109-3 035 $a(CKB)1000000000398525 035 $a(EBL)1679502 035 $a(OCoLC)879023552 035 $a(SSID)ssj0000228051 035 $a(PQKBManifestationID)11190625 035 $a(PQKBTitleCode)TC0000228051 035 $a(PQKBWorkID)10148702 035 $a(PQKB)10348909 035 $a(MiAaPQ)EBC1679502 035 $a(WSP)0000P544 035 $a(Au-PeEL)EBL1679502 035 $a(CaPaEBR)ebr10255507 035 $a(CaONFJC)MIL186579 035 $a(EXLCZ)991000000000398525 100 $a20080116d2008 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aProceedings of the 6th Asia-Pacific Bioinformatics Conference$b[electronic resource] $eKyoto, Japan, 14-17 January 2008 /$feditors, Alvis Brazma, Satoru Miyano, Tatsuya Akutsu 210 $aLondon $cImperial College Press ;$aHackensack, NJ $cDistributed by World Scientific Pub.$dc2008 215 $a1 online resource (413 p.) 225 1 $aSeries on advances in bioinformatics and computational biology,$x1751-6404 ;$vv. 6 300 $aDescription based upon print version of record. 311 $a1-84816-108-5 320 $aIncludes bibliographical references and index. 327 $aCONTENTS; Preface; APBC 2008 Organization; Program Committee; Additional Reviewers; Keynote Papers; Recent Progress in Phylogenetic Combinatorics Andreas Dress; 1. Background; 2. Discussion; References; KEGG for Medical and Pharmaceutical Applications Minoru Kanehisa; Protein Interactions Extracted from Genomes and Papers Alfonso Valencia; Contributed Papers; String Kernels with Feature Selection for SVM Protein Classification Wen-Yun Yang and Bao-Liang Lu; 1. Introduction; 2. A string kernel framework; 2.1. Notations; 2.2. Pramework definition; 2.3. Relations with existing string kernels 327 $a3. Efficient computation3.1. Tree data structure with leaf links; 3.2. Leaf traversal algorithm; 4. Selecting feature groups and weights; 4.1. Reduction of spectrum string kernel; 4.2. Statistically selecting feature groups; 5. Experiment; 6. Discussion and future work; Acknowledgments; References; Predicting Nucleolar Proteins Using Support-Vector Machines Mikael Bod&.; 1. Introduction; 2. Background; 3. Methods; 3.1. Data set; 3.2. Model; 4. Results; 5 . Conclusion; Acknowledgments; References 327 $aSupervised Ensembles of Prediction Methods for Subcellular Localization Johannes Apfalg, Jing Gong, Hans-Peter Kriegel, Alexey Pryakhin, Tiandi Wei and Arthur Zimek1. Introduction; 2. Survey on Prominent Prediction Methods for Subcellular Localization; 2.1. Amino Acid Composition; 2.2. Sorting Signals; 2.3. Homology; 2.4. Hybrid Methods; 3. Ensemble Methods; 3.1. Theory; 3.2. Selection of Base Methods for Ensembles; 3.3. Ensemble Method Based on a Voting Schema; 3.4. Ensemble Method Based on Decision Trees; 4. Evaluation; 5. Conclusions; References 327 $aChemical Compound Classification with Automatically Mined Structure Patterns Aaron M. Smalter, J. Huan and Gerald H. Lushington1. Introduction; 2. Related Work; 2.1. Marginalized and Optimal Assignment Graph Kernels; 2.2. Frequent Subgraph Mining; 3. Background; 3.1. Chemical Structure; 4. Algorithm Design; 4.1. Structure Pattern Mining; 4.2. Optimal Assignment Kernel; 4.3. Reduced Graph Representation; 4.4. Pattern-based Descriptors; 5. Experimental Study; 5.1. Data Sets; 5.2. Methods; 5.3. Results; 6. Conclusions; Acknowledgments; References 327 $aStructure-Approximating Design of Stable Proteins in 2D HP Model Fortified by Cysteine Monomers Alireza Hadj Khodabakhshi, Jdn Mariuch, Arash Rafiey and Arvind Gupta1. Introduction; 2. Definitions; 2.1. Hydropho bic-polar- c ysteine (HP C) model; 2.2. Snake structures; 2.3. The strong HPC model; 3. Proof techniques; 3.1. Saturated folds; 3.2. 2DHPSolver: a semi-automatic prover; 4. Stability of the snake structures; 5. Conclusions; References; Discrimination of Native Folds Using Network Properties of Protein Structures Alper Kiiciikural, 0. Ug'ur Sezerman and Aytiil Ercal; 1 Introduction 327 $a2 Methods 330 $a High-throughput sequencing and functional genomics technologies have given us the human genome sequence as well as those of other experimentally, medically, and agriculturally important species, thus enabling large-scale genotyping and gene expression profiling of human populations. Databases containing large numbers of sequences, polymorphisms, structures, metabolic pathways, and gene expression profiles of normal and diseased tissues are rapidly being generated for human and model organisms. Bioinformatics is therefore gaining importance in the annotation of genomic sequences; the understan 410 0$aSeries on advances in bioinformatics and computational biology ;$vv. 6. 606 $aBioinformatics$vCongresses 606 $aBiology$xData processing$vCongresses 615 0$aBioinformatics 615 0$aBiology$xData processing 676 $a572.8633 701 $aAkutsu$b Tatsuya$f1962-$01545356 701 $aBrazma$b Alvis$01545357 701 $aMiyano$b Satoru$0543473 712 12$aAsia-Pacific Bioinformatics Conference 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910784519503321 996 $aProceedings of the 6th Asia-Pacific Bioinformatics Conference$93800249 997 $aUNINA