Titlebook: Statistical Methods in Bioinformatics; An Introduction Warren J. Ewens,Gregory R. Grant Textbook 20011st edition Springer-Verlag New York 2

挑剔为人

RAG

The Analysis of Multiple DNA or Protein Sequences,a set of prescribed values. In this section we consider the test of the hypothesis that the two sets of probabilities for the four nucleotides in two DNA sequences are equal, no specific claim being made as to what the probabilities are. The data used for this test are as given in Table 6.1.

粉笔

CRUMB

BLAST, sequence. Many of the results derived in previous chapters, especially those relating to the renewal theorem, random walks, and sequential analysis, were discussed because they are needed in the statistical theory associated with the BLAST procedure. In this chapter we describe how they are used fo

召集

SLAG

Computationally Intensive Methods, made possible by the availability of convenient and greatly increased computing power, and these methods are useful in bioinformatics and computational biology. Aspects of some computationally intensive methods used for both estimation and hypothesis testing are outlined in this chapter. Computatio

dowagers-hump

Evolutionary Models,ic process. Very simplified models of this process are often used in the literature, in particular for the construction of phylogenetic trees, and aspects of these simplified models are discussed in this chapter. The emphasis is on introductory statistical and probabilistic aspects. A probabilistic

值得尊敬

BUCK

BLAST,were discussed because they are needed in the statistical theory associated with the BLAST procedure. In this chapter we describe how they are used for this purpose. For concreteness the discussion is in terms of protein (amino acid) sequences; the analysis for DNA sequences is similar to, but simpler than, that for protein sequences.

Hot-Flash

Stochastic Processes (iii): Markov Chains, chain theory is often oversimplified, since an examination of some of the subtleties involved in the full theory is not appropriate for bioinformatics. A recent and more complete exposition of the theory can be found in Norris (1997).