Evaluation of different biological data and computational classification methods for use in protein interaction prediction

By Yanjun Qi, Ziv Bar-Joseph, Judith Klein-Seetharaman. Proteins: Structure, Function, and Bioinformatics, 2006

417 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2c98473604b67f8cd7b4820134203473671e0705

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

Understanding Random Forests: From Theory to Practice (2014, background): “…studies [Lunetta et al., 2004; Meng et al., 2009; Botta et al., 2014], the discovery of important genes and pathways from micro-array gene-expression data [Pang et al., 2006; Chang et al., 2008] or the identification of factors for predicting protein-protein interactions [Qi et al., 2006].”
An experimentally derived confidence score for binary protein-protein interactions (2008, neutral): “We tested all pairs of the reference sets by tool-kit assays evaluating the effect of assay stringency on the detection of PRS and RRS pairs (Supplementary Fig.”
Deciphering Protein–Protein Interactions. Part II. Computational Methods to Predict Protein and Domain Interaction Partners (2007, background): “]. Each protein or protein pair can be encoded as a feature vector where features may represent a particular information source on protein interactions, domain compositions, or evidence coming from various experimental methods. As a result of a comparison of different classifiers, it has been shown ”
A human functional protein interaction network and its application to cancer data analysis (2010, background): “Creating a good negative training set is more difficult than creating a positive set due to the incompleteness of our knowledge of protein interactions [56]: just because two proteins are not known to interact does not mean that this does not in fact occur.”
Bias in random forest variable importance measures: Illustrations, sources and a solution (2007, methodology): “The random forest approach was shown to outperform six other methods in the prediction of protein interactions based on various biological features such as gene expression, gene ontology (GO) features and sequence data [12].”
Applying the Naïve Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites (2010, background): “The NBC has been so far applied to the prediction of DNA/RNA-binding residues (Yan et al., 2006; Terribilini et al., 2007) and to the prediction of protein interaction partners (Qi et al., 2006).”
Zeileis Conditional Variable Importance for Random Forests (2015, background): “Recently, the variable importance measures yielded by random forests have also been suggested for the selection of relevant predictor variables in the analysis of microarray data, DNA sequencing and other applications [2-5].”
Multitask Matrix Completion for Learning Protein Interactions Across Diseases (2016, methodology): “Hence we derived a set of ‘probable negatives’ using a heuristic often used in PPI prediction work [19, 18, 5, 13].”
A REVIEW OF STATISTICAL METHODS FOR DETERMINATION OF RELATIVE IMPORTANCE OF CORRELATED PREDICTORS AND IDENTIFICATION OF DRIVERS OF CONSUMER LIKING (2012, background): “There are many applications of variable-importance measures yielded by RFs (cf., e.g., Lunetta et al. 2004; Bureau et al. 2005; Huang et al. 2005; Berk et al. 2006; Diaz-Uriarte and de Andres 2006; Qi et al. 2006).”
Boruta – A System for Feature Selection (2010, methodology): “…it has been widely used in bioinformatical applications , for example, to predict replication capacity of HIV virus [7], HIV drug resistance [8] and protein interactions [9] as well as in modelling the quantitative structure-activity relationship (QSAR) [10] [11] and mortality process [12].”
A Survey of Link Prediction in Complex Networks (2016, methodology): “In the field of biology, link prediction techniques are being applied to find possible interactions between pairs of proteins in a protein-protein interaction network (PPI network) [Qi et al. 2006].”