Filters








1,257 Hits in 5.7 sec

KERNEL-BASED DATA FUSION AND ITS APPLICATION TO PROTEIN FUNCTION PREDICTION IN YEAST

G. R. G. LANCKRIET, M. DENG, N. CRISTIANINI, M. I. JORDAN, W. S. NOBLE
2003 Biocomputing 2004  
The method is applied to the problem of predicting yeast protein functional classifications using a support vector machine (SVM) trained on five types of data.  ...  Kernel methods provide a principled framework in which to represent many types of data, including vectors, strings, trees and graphs.  ...  MIJ and GL acknowledge support from ONR MURI N00014-00-1-0637 and NSF grant IIS-9988642.  ... 
doi:10.1142/9789812704856_0029 fatcat:r763nudm2naynjhnumotynpmiu

Kernel-based data fusion and its application to protein function prediction in yeast

G R G Lanckriet, M Deng, N Cristianini, M I Jordan, W S Noble
2004 Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing  
The method is applied to the problem of predicting yeast protein functional classifications using a support vector machine (SVM) trained on five types of data.  ...  Kernel methods provide a principled framework in which to represent many types of data, including vectors, strings, trees and graphs.  ...  statistical learning algorithms, and we have demonstrated an application of this method to the problem of predicting the function of yeast proteins.  ... 
pmid:14992512 fatcat:sm3pk53rtrdmbjsqgjaelsqami

Matrix factorization-based data fusion for gene function prediction in baker's yeast and slime mold

Marinka Zitnik, Blaž Zupan
2014 Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing  
In this manuscript, we show that this data fusion approach can be applied to gene function prediction and that it can fuse various heterogeneous data sources, such as gene expression profiles, known protein  ...  Our approach achieves predictive performance comparable to that of the state-of-the-art kernel-based data fusion, but requires fewer data preprocessing steps.  ...  Acknowledgments We thank Gad Shaulsky from Baylor College of Medicine, Houston, TX, for selecting functional terms from Table 2 .  ... 
pmid:24297565 pmcid:PMC3902649 fatcat:i5mbcklwgvblxhd2t5xivv36ze

MATRIX FACTORIZATION-BASED DATA FUSION FOR GENE FUNCTION PREDICTION IN BAKER'S YEAST AND SLIME MOLD

MARINKA ŽITNIK, BLAŽ ZUPAN
2013 Biocomputing 2014  
In this manuscript, we show that this data fusion approach can be applied to gene function prediction and that it can fuse various heterogeneous data sources, such as gene expression profiles, known protein  ...  Our approach achieves predictive performance comparable to that of the state-of-the-art kernel-based data fusion, but requires fewer data preprocessing steps.  ...  Acknowledgements We thank Gad Shaulsky from Baylor College of Medicine, Houston, TX, for selecting functional terms from Table 2 .  ... 
doi:10.1142/9789814583220_0038 fatcat:jguk2vhrpbbt3ku7djefcvl53q

Inference of protein-protein interaction networks from multiple heterogeneous data

Lei Huang, Li Liao, Cathy H. Wu
2016 EURASIP Journal on Bioinformatics and Systems Biology  
The optimal weights are obtained by ABC-DEP, and the kernel fusion built based on optimal weights serves as input to RL to infer missing or new edges in the PPI network.  ...  Protein-protein interaction (PPI) prediction is a central task in achieving a better understanding of cellular and intracellular processes.  ...  function, particle Z i is used to weight kernels in K to get kernel fusion K fusion . r G tn , r G vn represent results (AUCs) of recovering G tn and G vn based on K fusion respectively 12: r G tn ,  ... 
doi:10.1186/s13637-016-0040-2 pmid:26941784 pmcid:PMC4761017 fatcat:2mbfkfvdirfqnjczcgx42nat6a

Inference of protein-protein interaction networks from multiple heterogeneous data

Lei Huang, Li Liao, Cathy H. Wu
2015 Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics - BCB '15  
The optimal weights are obtained by ABC-DEP, and the kernel fusion built based on optimal weights serves as input to RL to infer missing or new edges in the PPI network.  ...  Protein-protein interaction (PPI) prediction is a central task in achieving a better understanding of cellular and intracellular processes.  ...  function, particle Z i is used to weight kernels in K to get kernel fusion K fusion . r G tn , r G vn represent results (AUCs) of recovering G tn and G vn based on K fusion respectively 12: r G tn ,  ... 
doi:10.1145/2808719.2814836 dblp:conf/bcb/HuangLW15 fatcat:vzthaxv3bjhytpvafadc6bym3e

A Bootstrap-based Linear Classifier Fusion System for Protein Subcellular Location Prediction

Yunfeng Wu, Yuezhu Ma, Xiaona Liu, Cong Wang
2006 2006 International Conference of the IEEE Engineering in Medicine and Biology Society  
In this paper we develop a multi-stage linear classifier fusion system based on Efron's bootstrap sampling for predicting subcellular locations of yeast proteins.  ...  The subcellular location plays a pivotal role in the functionality of proteins.  ...  In this paper, we develop a bootstrap-based multiple classifier fusion system for predicting the subcellular locations of yeast proteins.  ... 
doi:10.1109/iembs.2006.259616 pmid:17946613 fatcat:y72fi4yh7fc4dhzosdkvnva4a4

Completing sparse and disconnected protein-protein network by deep learning

Lei Huang, Li Liao, Cathy H. Wu
2018 BMC Bioinformatics  
The results from cross-validation experiments show that the PPI prediction accuracies for yeast data and human data measured as AUC are increased by up to 8.4 and 14.9% respectively, as compared to the  ...  Protein-protein interaction (PPI) prediction remains a central task in systems biology to achieve a better and holistic understanding of cellular and intracellular processes.  ...  Acknowledgements The authors are grateful to the anonymous reviewers for their valuable comments and suggestions.  ... 
doi:10.1186/s12859-018-2112-7 pmid:29566671 pmcid:PMC5863833 fatcat:apd3arad7zckfbvjwalznd6abe

A statistical framework for genomic data fusion

G. R. G. Lanckriet, T. De Bie, N. Cristianini, M. I. Jordan, W. S. Noble
2004 Bioinformatics  
Furthermore, kernel functions derived from different types of data can be combined in a straightforward fashion.  ...  The kernel representation is both flexible and efficient, and can be applied to many different types of data.  ...  KERNEL METHODS FOR DATA FUSION Each of the kernel functions described above produces, for the yeast genome, a square matrix in which each entry encodes a particular notion of similarity of one yeast protein  ... 
doi:10.1093/bioinformatics/bth294 pmid:15130933 fatcat:5si35euhezfo7h4pbudpq7d73u

Computational Methods For Predicting Protein–Protein Interactions [chapter]

Sylvain Pitre, Md Alamgir, James R. Green, Michel Dumontier, Frank Dehne, Ashkan Golshani
2008 Advances in Biochemical Engineering/Biotechnology  
Protein-protein interactions (PPIs) play a critical role in many cellular functions.  ...  There are also large discrepancies between the PPI data collected by the same or different techniques in the same organism. We therefore turn to computational techniques for the prediction of PPIs.  ...  PIPE analysis also has other applications in that it can be used to study the internal architecture of yeast protein complexes [52] .  ... 
doi:10.1007/10_2007_089 pmid:18202838 fatcat:pnmk2suq55bxhgvlpylewr4s3m

Synergy of multi-label hierarchical ensembles, data fusion, and cost-sensitive methods for gene functional inference

Nicolò Cesa-Bianchi, Matteo Re, Giorgio Valentini
2011 Machine Learning  
with respect to the hierarchical loss, and one based on a heuristic approach inspired by the true path rule for the biological functional ontologies.  ...  approaches on whole-ontology and genome-wide gene function prediction.  ...  Acknowledgements We would like to thank the anonymous reviewers for their comments and suggestions.  ... 
doi:10.1007/s10994-011-5271-6 fatcat:5uvavmu6zjft3g7xvtc6sghsya

Protein Interaction Networks: Protein Domain Interaction and Protein Function Prediction [chapter]

Yanjun Qi, William Stafford Noble
2011 Handbook of Statistical Bioinformatics  
In this chapter, we describe recent efforts to predict interactions between proteins and between protein domains.  ...  We also describe methods that attempt to use protein interaction data to infer protein function.  ...  In this paper, an MRF was used to assign functions to unknown yeast proteins, with a probability representing the confidence in the prediction.  ... 
doi:10.1007/978-3-642-16345-6_21 fatcat:whl2kgd3rbfcjm3ljkd56tj7vq

Prediction of Gene Function Using Ensembles of SVMs and Heterogeneous Data Sources [chapter]

Matteo Re, Giorgio Valentini
2009 Studies in Computational Intelligence  
The results show that heterogeneous data integration through ensemble methods represents a valuable research line in gene function prediction.  ...  computational approaches on gene function prediction.  ...  Kernel methods and techniques based on kernel fusion methods represent another important research area with significant applications in the integration of different bio-molecular data sources for gene  ... 
doi:10.1007/978-3-642-03999-7_5 fatcat:aebv6vs5ifg5lkxnimufypl5bq

Predicting gene functions from multiple biological sources using novel ensemble methods

Chandan K. Reddy, Mohammad S. Aziz
2015 International Journal of Data Mining and Bioinformatics  
In this work, information from several biological sources such as comparative genome sequences, gene expression, and protein interactions are combined to obtain robust results on predicting gene functions  ...  In the context of gene function prediction, most of the recent research on data integration has been primarily focused on the cases where the information is available across all the different sources.  ...  Acknowledgements This work was supported in part by the U.S. National Science Foundation grants IIS-1231742 and IIS-1242304.  ... 
doi:10.1504/ijdmb.2015.069418 pmid:26510302 fatcat:udvhfke32ndf3j43td7uqatvhu

deepNF: deep network fusion for protein function prediction

Vladimir Gligorijević, Meet Barot, Richard Bonneau, Jonathan Wren
2018 Bioinformatics  
Thus, we propose deepNF, a network fusion method based on Multimodal Deep Autoencoders to extract high-level features of proteins from multiple heterogeneous interaction networks.  ...  An important challenge has been to develop methods for combining these heterogeneous networks to extract useful protein feature representations for function prediction.  ...  Acknowledgements The authors would like to thank Da Chen Emily Koo for enlightening discussions and help with construction of the temporal holdout validation sets.  ... 
doi:10.1093/bioinformatics/bty440 pmid:29868758 fatcat:ojvpkefxnvhijhw3kiaexnxv7a
« Previous Showing results 1 — 15 out of 1,257 results