000 03147nam a22004215i 4500
001 978-1-59745-290-8
003 DE-He213
005 20140220083250.0
007 cr nn 008mamaa
008 120106s2012 xxu| s |||| 0|eng d
020 _a9781597452908
_9978-1-59745-290-8
024 7 _a10.1007/978-1-59745-290-8
_2doi
050 4 _aQH324.2-324.25
072 7 _aPSD
_2bicssc
072 7 _aUB
_2bicssc
072 7 _aSCI056000
_2bisacsh
082 0 4 _a570.285
_223
100 1 _aSullivan, Rob.
_eauthor.
245 1 0 _aIntroduction to Data Mining for the Life Sciences
_h[electronic resource] /
_cby Rob Sullivan.
264 1 _aTotowa, NJ :
_bHumana Press,
_c2012.
300 _aXVII, 631p. 339 illus., 97 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
505 0 _aIntroduction -- Fundamental Concepts -- Data Architecture and Data Modeling -- Representing Data Mining Results -- The Input Side of the Equation -- Statistical Methods -- Bayesian Statistics -- Machine Learning Techniques -- Classification and Prediction -- Informatics -- Systems Biology -- Let’s Call it a Day -- Appendix A -- Appendix B -- Appendix C. Appendix D -- Index.
520 _aOne of the major challenges for the scientific community, a challenge that has been seen in many business disciplines, is the exponential increase in data being generated by new experimental techniques and research. A single microarray experiment, for example, can generate thousands of data points that need to be analyzed, and this problem is predicted to increase. As new techniques in areas such as genomics and proteomics continue to be adopted into the mainstream as the costs fall, the need for effective mechanisms for synthesizing these disparate forms of data together for analysis is of paramount importance. But the sheer volume of data means that traditional techniques need to be augmented by approaches that elicit knowledge from the data, using automated procedures. Data mining provides a set of such techniques, new techniques to integrate, synthesize, and analyze the data, uncovering the hidden patterns that exist within. Traditionally, techniques such as kernel learning methods, pattern recognition, and data mining, have been the domain of researchers in areas such as artificial intelligence, but leveraging these tools, techniques, and concepts against your data asset to identify problems early, understand interactions that exist and highlight previously unrealized relationships through the combination of these different disciplines can provide significant value for the investigator and her organization.
650 0 _aLife sciences.
650 0 _aBioinformatics.
650 1 4 _aLife Sciences.
650 2 4 _aBioinformatics.
710 2 _aSpringerLink (Online service)
773 0 _tSpringer eBooks
776 0 8 _iPrinted edition:
_z9781588299420
856 4 0 _uhttp://dx.doi.org/10.1007/978-1-59745-290-8
912 _aZDB-2-SBL
999 _c101551
_d101551