Pattern recognition in bioinformatics

Więcej o książce

The book covers a range of advanced topics in computational biology and bioinformatics. It begins with evolutionary parameters in sequence families and introduces MProfiler, a method for DNA motif discovery. The text explores optimal syntactic modeling for peptide classification and joint tracking of cell morphology and motion. It discusses multiclass microarray gene expression analysis using mutual dependency models and presents an efficient convex nonnegative network component analysis for gene regulatory network reconstruction. Higher-order dynamic Bayesian networks are utilized to model periodic data from Arabidopsis Thaliana, while sequential hierarchical pattern clustering and syntactic pattern recognition using finite inductive strings are also examined. The book addresses evidence-based clustering of reads and taxonomic analysis of metagenomic data, as well as avoiding spurious feedback loops in gene regulatory network reconstruction. Additional topics include ligand electron density shape recognition, defining valid proteomic biomarkers through a Bayesian approach, and inferring meta-covariates in classification. It presents a multiobjective evolutionary algorithm for reaction diffusion systems and knowledge-guided docking of WW domain proteins. The text also covers distinguishing regional rate heterogeneity in DNA sequence alignments, a hybrid metaheuristic for biclustering, and modeling stem cell lineages with M