The paper reports a novel approach for the problem of automatic gridding in Microarray images. The solution is modeled as a Bayesian Random Field with a Gibbs prior possibly containing first order cliques (1-clique). On the contrary of previously published contributions, this paper does not assume second order cliques, instead it relies on a two step procedure to locate microarray spots. First a set of guide spots are used to interpolate a reference grid. The final grid is then produced by an a-posteriori maximization which takes into account the reference rectangular grid and local deformations. The algorithm is completely automatic and no human intervention is required, the only critical parameter being the range of the radius of the guide spots.
A Markov random field approach to microarray image gridding
CECCARELLI M.
2004-01-01
Abstract
The paper reports a novel approach for the problem of automatic gridding in Microarray images. The solution is modeled as a Bayesian Random Field with a Gibbs prior possibly containing first order cliques (1-clique). On the contrary of previously published contributions, this paper does not assume second order cliques, instead it relies on a two step procedure to locate microarray spots. First a set of guide spots are used to interpolate a reference grid. The final grid is then produced by an a-posteriori maximization which takes into account the reference rectangular grid and local deformations. The algorithm is completely automatic and no human intervention is required, the only critical parameter being the range of the radius of the guide spots.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
