Нашли опечатку? Выделите ее мышкой и нажмите Ctrl+Enter
Название: Computational Text Analysis: For Functional Genomics and Bioinformatics
Автор: Raychaudhuri S.
This book is an introduction to the newly emerging field of textual analysis
in genomics. It presents some of the newest methods, and demonstrates
applications to proteomics, sequence analysis, and gene expression data.
My personal interest in this field began early during my graduate school
years as these methods were rapidly emerging. My colleagues were excitedly
utilizing new high throughput technologies in biology with which they could
collect data at unprecedented rates. Gene expression arrays, for example,
offered the opportunity to simultaneously explore expression of all genes in
a cell. However, many were hitting the same roadblocks; making sense of all
of that data was tedious and frustrating. Even differentiating signal from
noise was a challenge; certainly finding subtle patterns in the data proved to
be much more difficult than anyone expected. A host of statistical methods
were emerging to analyze the numerical data, but yet they lacked the
necessary context to fully harness the power of these complex experimental
results. The difficulty is that complete interpretation requires understanding
all of the large number of genes, their complex functions, and interactions.
But, just keeping up with the literature on a single gene can be a challenge
itself, and for thousands of genes it is simply impossible! At that time I
became interested in the promise of statistical natural language processing
algorithms, and their potential in biology. These methods often are the only
reasonable way to include the literature on thousands of genes in genomics
data analysis and to give context to the data.