Gene functional classification from heterogeneous data

By Paul Pavlidis, Jason Aaron Edward Weston, Jinsong Cai, William Noble Grundy. 2001

333 citations recorded by the source corpus.

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

Learning kernel logistic regression in the presence of class label noise (2014, background): “In contrast to the majority of MKL literature where the aim is centred around combining heterogeneous data sources [34,23], our adoption of MKL focuses on the combination of multiple kernels that correspond to different notions of similarity, as defined by different kernel widths.”
Bioinformatics Original Paper Integrating Multi-attribute Similarity Networks for Robust Representation of the Protein Space (neutral): “The advantages of integrating multiple data sources for predicting protein function has been demonstrated by a number of recent studies (Deng et al., 2004; Lanckriet et al., 2004; Pavlidis et al., 2001; Yamanishi et al., 2004).”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, background): “On the other hand, integration of data or of the models for that matter for the heterogeneous data generated or gathered from different instruments and data-generation processes is a significant research problem [344,345].”
Feature selection for support vector machines by means of genetic algorithm (2003, background): “[13]) consists of 208 genes that have to be discriminated into 5 classes based on 79 gene expres-”
Support Vector Machines with Applications (2006, methodology): “The SVMs have been applied recently to tissue classification [26], gene function prediction [59], protein subcellular location prediction [31], protein secondary structure prediction [32] and protein fold prediction [23], among other tasks.”
Protein network inference from multiple genomic data: a supervised approach (2004, background): “While more complex approaches can be imagined to combine heterogeneous data through kernel operation, this simple operation has proved to be useful in (Pavlidis et al., 2001; Yamanishi et al., 2003) and is used below.”
Prediction of Protein Function Using Protein–Protein Interaction Data (2002, methodology): “Clustering analysis of gene expression data can be used to predict functions of unannotated proteins based on the idea that genes with similar functions are likely to be co-expressed [3] [7] [23].”
Localized multiple kernel learning (2008, methodology): “For classi.cation tasks, the basic idea is to map the training instances from the input space to a feature space (generally a higher dimensional space than the input space) where they are linearly separable.”
Multiple Kernel Learning Algorithms (2011, positive): “…of N independent and identically distributed training instances { ( x i , y i ) } Ni =1 where x i is the D -dimensional input vector and y i ∈ {− 1 , +1 } is its class label, SVM basically ﬁnds the linear discriminant with the maximum margin in the feature space induced by the mapping function Φ.”
Kernel Methods in Computational Biology (2005, background): “Examples: SVM in bioinformatics • Gene functional classification from microarry: Brown et al. (2000), Pavlidis et al. (2001) • Tissue classification from microarray: Mukherje et al. (1999), Furey et al. (2000), Guyon et al. (2001) • Protein family prediction from sequence: Jaakkoola et al. (1998) •…”
Network-based prediction of protein function (2007, positive): “Classical computational approaches to gene annotation collect for each protein a set of features characterizing it, and apply machine-learning algorithms to infer annotation rules based on those features ( Pavlidis et al, 2001 ).”
Kernel Methods and Machine Learning (2014, methodology): “The accuracy and testing time for different numbers of features selected by a Fisher-based method [202], for the eukaryotic protein dataset published by Reinhardt and Hubbard [218].”
Functional Knowledge Transfer for High-accuracy Prediction of Under-studied Biological Processes (2013, background): “at least some genes in the organism already annotated to the pathway) [7–11].”
Kernel-Based Data Fusion and Its Application to Protein Function Prediction in Yeast (2003, methodology): “improved gene classification performance in yeast, relative to learning from a single kernel matrix.(16) The current work takes this methodology further—we use a weighted linear combination of kernels, and demonstrate how to estimate the kernel weights from the data.”