AuthorDua, Sumeet
TitleData mining for bioinformatics / Sumeet Dua, Pradeep Chowriappa
Imprint Boca Raton, FL : CRC, 2013
Descript xix, 328 p. : ill. ; 24 cm

SUMMARY

"Data Mining for Bioinformatics enables researchers to meet the challenge of mining vast amounts of biomolecular data to discover real knowledge. Covering theory, algorithms, and methodologies, as well as data mining technologies, the book presents a thorough discussion of data-intensive computations used in data mining applied to bioinformatics. The book explains data mining design concepts to build applications and systems. It shows how to prepare raw data for the mining process and is filled with heuristics that speed the data mining process"-- Provided by publisher


CONTENT

Transcription and translation -- The human genome project -- Beyond the human genome project -- Biological data storage and analysis -- The curse of dimensionality -- Data cleaning -- Analysis of data using large databases -- Challenges in data cleaning -- Data integration -- Data warehousing -- Data transformation -- Features and relevance -- Overview of feature selection -- Filter approaches for feature selection -- Feature subset selection using forward selection -- Other nested subset selection methods -- Feature construction and extraction -- Normalization techniques for gene expression analysis -- Data preprocessing of mass spectrometry data -- Data preprocessing for genomic sequence data -- Ontologies in bioinformatics -- Clustering in bioinformatics -- Clustering techniques -- Applications of distance-based clustering in bioinformatics -- Implementation of k-means in WEKA -- Herarchical clustering -- Implementation of hierarchical clustering -- Self-organizing maps clustering -- Fuzzy clustering -- Implementation of expectation maximization algorithm -- Graph-based clustering -- Measures for identifying clusters -- Determining a split in the graph -- Graph-based algorithms -- Application of graph-based clustering in bioinformatics -- Kernel-based clustering Application of kernel clustering in bioinformatics -- Model-base clustering for gene expression data -- Relevant number of genes -- Higher-order mining -- Supervised learning in bioinformatics -- Support vector machines (SVMs) -- Bayesian approaches -- Decision trees -- Ensemble approaches -- Classifier validation -- Performance measures -- Cluster validation techniques


SUBJECT

  1. Bioinformatics
  2. Data mining
  3. Computational biology

LOCATIONCALL#STATUS
Central Library (4th Floor)572.80285 D812D CHECK SHELVES