Protein Function Prediction Using Multilabel Ensemble Classification

Yu, Guoxian; Rangwala, Huzefa; Domeniconi, Carlotta; Zhang, Guoji; Yu, Zhiwen

doi:10.1109/tcbb.2013.111

Cited by 49 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These predictors have been immensely successful in producing accurate predictions for many biomedical prediction tasks (Yang et al (2010); Altmann et al (2008); Liu et al (2012); Khan et al (2010); Pandey et al (2010)), including protein function prediction (Valentini (2014); Yu et al (2013); Guan et al (2008)). The success of these methods is attributed to their ability to reinforce accurate predictions as well as correct errors across many diverse base predictors (Tumer and Ghosh (1996)).…”

Section: Introductionmentioning

confidence: 99%

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Whalen

Pandey

2016

Methods

View full text Add to dashboard Cite

Prediction problems in biomedical sciences, including protein function prediction (PFP), are generally quite difficult. This is due in part to incomplete knowledge of the cellular phenomenon of interest, the appropriateness and data quality of the variables and measurements used for prediction, as well as a lack of consensus regarding the ideal predictor for specific problems. In such scenarios, a powerful approach to improving prediction performance is to construct heterogeneous ensemble predictors that combine the output of diverse individual predictors that capture complementary aspects of the problems and/or datasets. In this paper, we demonstrate the potential of such heterogeneous ensembles, derived from stacking and ensemble selection methods, for addressing PFP and other similar biomedical prediction problems. Deeper analysis of these results shows that the superior predictive ability of these methods, especially stacking, can be attributed to their attention to the following aspects of the ensemble learning process: (i) better balance of diversity and performance, (ii) more effective calibration of outputs and (iii) more robust incorporation of additional base predictors. Finally, to make the effective application of heterogeneous ensembles to large complex datasets (big data) feasible, we present DataSink, a distributed ensemble learning framework, and demonstrate its sound scalability using the examined datasets. DataSink is publicly available from https://github.com/shwhalen/datasink.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Whalen

Pandey

2016

Methods

View full text Add to dashboard Cite

show abstract

“…Moreover, they are not robust to noisy links and dense structures often present in certain network types (e.g., large blocks in gene co-expression networks or large hubs in protein-protein interaction networks); in this case, the resulting network is obscured by links from the noisy network types and can significantly impair the classification performance. To overcome these problems, some approaches train individual classifiers on these networks and then use ensemble learning methods to combine their predictions [35,26,32]. Lastly, such methods do not typically take into account correlations between different data sources, and often suffer from learning time and memory constraints.…”

Section: Introductionmentioning

confidence: 99%

deepNF: Deep network fusion for protein function prediction

Gligorijević

Barot

Bonneau

2017

Preprint

View full text Add to dashboard Cite

The prevalence of high-throughput experimental methods has resulted in an abundance of large-scale molecular and functional interaction networks. The connectivity of these networks provide a rich source of information for inferring functional annotations for genes and proteins. An important challenge has been to develop methods for combining these heterogeneous networks to extract useful protein feature representations for function prediction. Most of the existing approaches for network integration use shallow models that cannot capture complex and highly-nonlinear network structures. 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. We apply this method to combine STRING networks to construct a common low-dimensional representation containing high-level protein features. We use separate layers for different network types in the early stages of the multimodal autoencoder, later connecting all the layers into a single bottleneck layer from which we extract features to predict protein function. We compare the cross-validation and temporal holdout predictive performance of our method with state-of-the-art methods, including the recently proposed method Mashup. Our results show that our method outperforms previous methods for both human and yeast STRING networks. We also show substantial improvement in the performance of our method in predicting GO terms of varying type and specificity.

show abstract

“…In this way, each data source can be transformed into a network (or kernel). To leverage the networks derived from heterogeneous data sources to predict protein functions, some approaches first train individual classifiers on these networks and then use ensemble learning techniques to combine these classifiers [ 7 , 9 , 11 , 18 ]. Another set of algorithms first integrate these networks into a composite network and then train network-based learning methods [ 5 , 14 - 16 ].…”

Section: Introductionmentioning

confidence: 99%

Integrating multiple networks for protein function prediction

Zhu

Domeniconi

et al. 2015

BMC Systems Biology

Self Cite

View full text Add to dashboard Cite

BackgroundHigh throughput techniques produce multiple functional association networks. Integrating these networks can enhance the accuracy of protein function prediction. Many algorithms have been introduced to generate a composite network, which is obtained as a weighted sum of individual networks. The weight assigned to an individual network reflects its benefit towards the protein functional annotation inference. A classifier is then trained on the composite network for predicting protein functions. However, since these techniques model the optimization of the composite network and the prediction tasks as separate objectives, the resulting composite network is not necessarily optimal for the follow-up protein function prediction.ResultsWe address this issue by modeling the optimization of the composite network and the prediction problems within a unified objective function. In particular, we use a kernel target alignment technique and the loss function of a network based classifier to jointly adjust the weights assigned to the individual networks. We show that the proposed method, called MNet, can achieve a performance that is superior (with respect to different evaluation criteria) to related techniques using the multiple networks of four example species (yeast, human, mouse, and fly) annotated with thousands (or hundreds) of GO terms.ConclusionMNet can effectively integrate multiple networks for protein function prediction and is robust to the input parameters. Supplementary data is available at https://sites.google.com/site/guoxian85/home/mnet. The Matlab code of MNet is available upon request.

show abstract

Protein Function Prediction Using Multilabel Ensemble Classification

Cited by 49 publications

References 34 publications

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

deepNF: Deep network fusion for protein function prediction

Integrating multiple networks for protein function prediction

Contact Info

Product

Resources

About