Probabilistic inference of molecular networks from noisy data sources

Authors:
Ivan Iossifov;Michael Krauthammer;Carol Friedman;Vasileios Hatzivassiloglou;Joel S. Bader;Kevin P. White;Andrey Rzhetsky
Affiliations:
Department of Medical Informatics,;Department of Medical Informatics,;Department of Medical Informatics,;Department of Computer Science, Columbia University, New York, NY 10027, USA,;CuraGen Corporation, New Haven, CT 06511, USA;Department of Genetics, Yale University School of Medicine, New Haven, CT 06520, USA;Department of Medical Informatics,
Venue:
Bioinformatics
Year:
2004

Citing 0
Cited 7

Predicting Protein-Protein Interactions from Protein Domains Using a Set Cover Approach

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Prediction of yeast protein-protein interactions by neural feature association rule

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Prediction of protein interaction with neural network-based feature association rule mining

ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
Neural feature association rule mining for protein interaction prediction

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
Adaptive neural network-based clustering of yeast protein: protein interactions

CIT'04 Proceedings of the 7th international conference on Intelligent Information Technology
Towards an integrated protein-protein interaction network

RECOMB'05 Proceedings of the 9th Annual international conference on Research in Computational Molecular Biology
Using machine learning techniques and genomic/proteomic information from known databases for defining relevant features for PPI classification

Computers in Biology and Medicine

Quantified Score

Hi-index	3.84

Visualization

Abstract

Summary: Information on molecular networks, such as networks of interacting proteins, comes from diverse sources that contain remarkable differences in distribution and quantity of errors. Here, we introduce a probabilistic model useful for predicting protein interactions from heterogeneous data sources. The model describes stochastic generation of protein--protein interaction networks with real-world properties, as well as generation of two heterogeneous sources of protein-interaction information: research results automatically extracted from the literature and yeast two-hybrid experiments. Based on the domain composition of proteins, we use the model to predict protein interactions for pairs of proteins for which no experimental data are available. We further explore the prediction limits, given experimental data that cover only part of the underlying protein networks. This approach can be extended naturally to include other types of biological data sources.