T. Bailey and C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proc Int. Conf. Intell. Syst. Mol. Biol., pp. 28-36, 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....sequence data to the Regulates variables. Experimental biology has shown that transcription factors bind to relatively short sequences, and that there can be some variability in the binding site sequences. Thus, most standard approaches to uncovering transcription factor binding sites, e.g. [1, 26, 29], search for relatively short sequence motifs in the bound promoter sequences. A common way of representing the variability within the binding site is by using a position specific scoring matrix (PSSM) Suppose we are searching for motifs of length k (or less) A PSSM w is a k 4 matrix, ....

....recall that each gene g has a promoter sequence g:S1 ; g:Sn , where each S i 2 fA; C; G; Tg. The standard approaches to learning PSSM is by training a probabilistic model of binding sites that maximizes the likelihood of sequences (given the assignment of the regulates variables) [1, 26]. These approaches rely on a clear probabilistic semantics of PSSM scores. We denote by 0 the probability distribution over nucleotides according to the background model. For simplicity, we use a Markov process of order 0 for the background distribution. As we will see, the choice of ....

[Article contains additional citation context not shown here]

T.L. Bailey and Elkan C. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proc. Int. Conf. Intell. Syst. Mol. Biol., volume 2, pages 28--36. 1994.

....probability that O has been generated by independent tosses of a single coin or by a procession of multiple, coins selected by performing a random walk in the set of coins. More formally, we de ne an n coin model as an n state Hidden Markov Model similar to many other applications of HMMs [4]. Note that employing HMMs in the context of this paper is quite natural. Without any a priori information about which positions in the alignment sequence a coin switch is more likely, it is plausible to assume independent and identical distributions for the coin switch probabilities; this in turn ....

T. Bailey, C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers, Proceedings of ISMB 1994, AAAI Press.

....overrepresented motifs that are good candidates for being transcription factor binding sites. There are numerous motif finding programs from Current address: Box 25, The Rockefeller University, 1230 York Ave, New York, NY 10021, saurabhlonnrot.rockefeller.edu which to choose, including MEME [1], Consensus [5] AlignACE [8] Oligo Analysis [11] YMF [9, 10] AnnSpec [12] and Projection [4] and little guidance to select among them. The only previous performance comparisons that have been done for some of these programs are by Pevzner and Sze [7] and by Buhler and Tompa [4] using ....

....Sze [7] and by Buhler and Tompa [4] using simulated data generated ac cording to a motif model that may not be accurate for transcription factor binding sites. In this paper, we compare the accuracy of an enu merative motif finding algorithm YMF [9, 10] to that of two popular contenders, MEME [1] and AlignACE [8] The comparison is done on real data sets from yeast, and on synthetic data with planted motifs. See Blanchette et al. 2] for an analogous perfor mance comparison among phylogenetic footprinting algorithms. The experiments on synthetic data in dicate that each algorithm s ....

T. L. Bailey and C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, pages 28-36, Menlo Park, CA, 1994. AAAI Press.

....we would like to find patterns which are conserved in the sequences, generally preferring longer patterns which appear in most of the sequences in the set. Solving such a problem ranges from a plethora of multiple alignment methods, and numerous other methods such as Gibbs sampling [10] or MEME [1]. Another situation is when we have more information at hand, and are given a second set of sequences as an explicit negative data set that is known not to have characteristics of (or known to have di#erent characteristics from) the first set, and the problem is to find a pattern which match most ....

Bailey, T. L. and Elkan, C., Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proc. Second International Conference on Intelligent Systems for Molecular Biology, AAAI Press, 28--36, 1994.

....is examining the promoter regions of a set of genes that have common functional annotation or are co expressed. In this case, the discovered motif indicates a possibly unknown factor that regulates the set of genes. Many works in recent years have proposed different schemes to handle this task [3, 4, 24, 31, 39, 40]. Both tasks require us to describe a motif that characterizes sequences that appear at binding sites of the transcription factor. The biological literature suggests that the relevant sequences are relatively short (up to 20bp long) Moreover, although binding sites are quite conserved, they do ....

....preamble to learning motif models, we describe how we model regulated sequences. We use a generarive approach to describe the probabilistic processes that could have generated the promoter sequences. Our model is similar to the model used by probabilistic approaches for PSSM learning (such as MEME [3]) with the important difference that we allow for a general binding site model as described in section 3. The model assumes that each sequence S (SO) S ) can be generated in two ways. It is either regulated by the transcription factor T and so contains a single binding site from our model ....

[Article contains additional citation context not shown here]

TL Bailey and C Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In 1SMB'94. 1994.

....sequence data to the Regulates variables. Experimental biology has shown that transcription factors bind to relatively short sequences, and that there can be some variability in the binding site sequences. Thus, most standard approaches to uncovering transcription factor binding sites, e.g. [1, 26, 29], search for relatively short sequence motifs in the bound promoter sequences. A common way of representing the variability within the binding site is by using a position speci c scoring matrix (PSSM) Suppose we are searching for motifs of length k (or less) A PSSM w is a k 4 matrix, ....

....recall that each gene g has a promoter sequence g:S1 ; g:Sn , where each S i 2 fA; C; G; Tg. The standard approaches to learning PSSM is by training a probabilistic model of binding sites that maximizes the likelihood of sequences (given the assignment of the regulates variables) [1, 26]. These approaches rely on a clear probabilistic semantics of PSSM scores. We denote by 0 the probability distribution over nucleotides according to the background model. For simplicity, we use a Markov process of order 0 for the background distribution. As we will see, the choice of ....

[Article contains additional citation context not shown here]

T.L. Bailey and Elkan C. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proc. Int. Conf. Intell. Syst. Mol. Biol., volume 2, pages 2836. 1994.

....sequence data to the Regulates variables. Experimental biology has shown that transcription factors bind to relatively short sequences, and that there can be some variability in the binding site sequences. Thus, most standard approaches to uncovering transcription factor binding sites, e.g. [1, 26, 29], search for relatively short sequence motifs in the bound promoter sequences. A common way of representing the variability within the binding site is by using aposition specific scoring matrix (PSSM) Suppose we are searching for motifs of length k (or less) A PSSM t is a k x 4 matrix, ....

....t from o notation. Furthermore, recl that each gene 9 has a promoter sequence 9.S, 9.S, where each Si A, C, G, T . The standd approaches to leaning PSSM is by ning a probabilistic model of binding sites that maximizes the likelihood of sequences (given the assignment of the regulates viables) [1, 26]. These approaches rely on a cle probabilistic semantics of PSSM scores. We denote by 0o the probability distribution over nucleotides according to the background model. For simplicity, we use a Mkov process of order 0 for the backound distribution. As we will see, the choice of background model ....

[Article contains additional citation context not shown here]

T.L. Bailey and Elkan C. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proc. Int. Conf Intell. Syst. Mol. Biol., volume 2, pages 28-36. 1994.

No context found.

T. Bailey and C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proc Int. Conf. Intell. Syst. Mol. Biol., pp. 28-36, 1994.

No context found.

T.L. Bailey and C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Second International Conference on Intelligent Systems for Molecular Biology, pages 28--36. AAAI Press, 1994.

No context found.

T. Bailey and C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Second International Conference on Intelligent Systems for Molecular Biology, pages 28--36. AAAI Press, 1994.

No context found.

Bailey, T. L., & Elkan, C. (1994). Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proc. of ISMB'94.

No context found.

Bailey, T.L. and Elkan, C. (1994) Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proc. Int. Conf. Intell. Syst. Mol. Biol., 2, 28-36.

No context found.

T. L. Bailey and C. Elkan, "Fitting a mixture model by expectation maximization to discover motifs in biopolymers," Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, 28-36, AAAI Press, 1994.

No context found.

Bailey, T.L. and Elkan, C., Fitting a mixture model by expectation maximization to discover motifs in biopolymers, Proc.Int.Conf.Intell.Syst.Mol.Biol., 2:28--36, 1994.

No context found.

Bailey, T.L. & Elkan, C. (1994) Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology: 28-36, AAAI Press.

No context found.

Bailey, T.L. and Elkan, C., Fitting a mixture model by expectation maximization to discover motifs in biopolymers, 2nd ISMB., 28--36, 1994.

No context found.

T. L. Bailey and C. Elkan, "Fitting a mixture model by expectation maximization to discover motifs in biopolymers," Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, 28-36, AAAI Press, 1994.

No context found.

Bailey, T. L. and Elkan, C. (1994). Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Second International Conference on Intelligent Systems for Molecular Biology, pages 28--36, Menlo Park, California. AAAI Press.

No context found.

Bailey TL, Elkan C. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proc Int Conf Intell Syst Mol Biol. 1994;2:28-36.

No context found.

Bailey,T.L. and Elkan,C. (1994) Fitting a mixture model by expectation maximization to discover motifs in biopolymers. ISMB, 2, 28--36.

No context found.

TL Bailey and C Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In ISMB'94. 1994.

No context found.

Timothy L. Bailey and Charles Elkan, Fitting a mixture model by expectation maximization to discover motifs in biopolymers, Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, pp. 28-36, AAAI Press, Menlo Park, California, 1994.

No context found.

T. Bailey and C. Elkan, Fitting a mixture model by expectation maximization to discover motifs in biopolymers, Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, pp. 28-36, AAAI Press, Menlo Park, California, 1994.

No context found.

T. L. Bailey and C. Elkan, Fitting a mixture model by expectation maximization to discover motifs in biopolymers. Proceedings of the International Conference of Intelligent Systems in Moleclular Biology, 2:28-36, 1994.

No context found.

T.L. Bailey and C. Elkan. Fitting a mixture model by expectation maximization to discover motifs in biopolymers. In Proceedings of the 2nd International Conference on Intelligent Systems for Molecular Biology, volume 2, pages 28-- 36. AAAI Press, 1994.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC