Discovering molecular pathways from protein interaction and gene expression data

By Eran Segal, Haidong Wang, Daphne Koller. Intelligent Systems in Molecular Biology, 2003

345 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/0051252657f1b7095ff6081988a8683dcf602860

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Classification in Networked Data: A Toolkit and a Univariate Case Study (2007, neutral): “Segal et al. (2003a,b) apply network classiﬁcation (speciﬁcally, relational Markov networks, Taskar et al., 2002) to protein interaction and gene expression data, where protein interactions form a network over which inferences are drawn about pathways, i.e., sets of genes that coordinate to achieve…”
A probabilistic framework for semi-supervised clustering (2004, methodology): “, iterated conditional modes (ICM) [9, 40], belief propagation [34, 36], and linear programming relaxation [28].”
Finite mixture models and model-based clustering (2010, background): “This is the topic of semi-supervised clustering which arises in a number of modern fields such as bioinformatics [117] or speech recognition [57], and consequently has attracted some recent interest.”
Classes of Kernels for Machine Learning: A Statistics Perspective (2002, background): “In gene classification, our knowledge that two proteins co-occurring in processes can be viewed as a mustlink[1].”
Identification of functional modules using network topology and high-throughput data (2007, methodology): “Other methods (e.g., [21]) were not readily available for comparison.”
Integrating constraints and metric learning in semi-supervised clustering (2004, methodology): “Xing et al. (2003) utilized a combination of gradient descent and iterative projections to learn a Mahalanobis metric for K-Means clustering.”
Network-based prediction of protein function (2007, methodology): “Segal et al (2003) provided a probabilistic formulation, in which a module is a group of genes with high pairwise similarities and with a signiﬁcant portion of the possible Box 3 Detecting dense subgraphs using maximum likelihood scoring Maximum likelihood-based scoring has been used for detecting…”
Current approaches to gene regulatory network modelling (2007, background): “Segal et al . applied a learning procedure based on probabilistic graphical models to networks consisting of groups of coregulated genes [53].”