Modeling SAGE tag formation and its effects on data interpretation within a Bayesian framework

BMC Bioinformatics

Table 2 Parameter Estimates

Experimental Treatment
Variables	L	S	G2/M
P	0.577 (0.545, 0.569)	0.61 (0.597,0.623)	0.748 (0.735, 0.758)
Joint Posterior Mode Estimate: $\bar{Φ}$	0.764	0.797	0.862
Simulation Based Estimate: $\bar{Φ}$	0.777 (0.773, 0.781)	0.806 (0.802,0.809)	0.861 (0.857,0.865)

Posterior mode and 95%PI values for the AE cleavage efficency p, posterior mode value for the mean tag formation probability $\hat{\bar{Φ}}$ , and simulation based estimates for $\bar{\bar{Φ}}$ for the three experiments in [9]: log growth (L), S phase-arrest, and G2/M phase-arrest. Numbers in parentheses are the lower and upper bounds of 95% PI. Parameters for the Dirichlet prior distribution on $\vec{m}$ was α_i= 1 for all genes.

ISSN: 1471-2105