Next Article in Journal
The Gene Structure and Expression Level Changes of the GH3 Gene Family in Brassica napus Relative to Its Diploid Ancestors
Next Article in Special Issue
A Random Walk Based Cluster Ensemble Approach for Data Integration and Cancer Subtyping
Previous Article in Journal
Overexpression of Rice Rab7 Gene Improves Drought and Heat Tolerance and Increases Grain Yield in Rice (Oryza sativa L.)
Previous Article in Special Issue
Network Analyses of Integrated Differentially Expressed Genes in Papillary Thyroid Carcinoma to Identify Characteristic Genes
Article

A Multi-Label Supervised Topic Model Conditioned on Arbitrary Features for Gene Function Prediction

by 1, 2,*, 3 and 3,*
1
School of Information, Yunnan Normal University, Kunming 650500, China
2
Key Laboratory of Educational Informatization for Nationalities Ministry of Education, Yunnan Normal University, Kunming 650500, China
3
School of Software, Yunnan University, Kunming 650091, China
*
Authors to whom correspondence should be addressed.
Genes 2019, 10(1), 57; https://doi.org/10.3390/genes10010057
Received: 30 November 2018 / Revised: 1 January 2019 / Accepted: 10 January 2019 / Published: 17 January 2019
With the continuous accumulation of biological data, more and more machine learning algorithms have been introduced into the field of gene function prediction, which has great significance in decoding the secret of life. Recently, a multi-label supervised topic model named labeled latent Dirichlet allocation (LLDA) has been applied to gene function prediction, and obtained more accurate and explainable predictions than conventional methods. Nonetheless, the LLDA model is only able to construct a bag of amino acid words as a classification feature, and does not support any other features, such as hydrophobicity, which has a profound impact on gene function. To achieve more accurate probabilistic modeling of gene function, we propose a multi-label supervised topic model conditioned on arbitrary features, named Dirichlet multinomial regression LLDA (DMR-LLDA), for introducing multiple types of features into the process of topic modeling. Based on DMR framework, DMR-LLDA applies an exponential a priori construction, previously with weighted features, on the hyper-parameters of gene-topic distribution, so as to reflect the effects of extra features on function probability distribution. In the five-fold cross validation experiment of a yeast datasets, DMR-LLDA outperforms the compared model significantly. All of these experiments demonstrate the effectiveness and potential value of DMR-LLDA for predicting gene function. View Full-Text
Keywords: multi-label classification; topic model; gene function; probability distribution; Dirichlet-multinomial Regression multi-label classification; topic model; gene function; probability distribution; Dirichlet-multinomial Regression
Show Figures

Figure 1

MDPI and ACS Style

Liu, L.; Tang, L.; Jin, X.; Zhou, W. A Multi-Label Supervised Topic Model Conditioned on Arbitrary Features for Gene Function Prediction. Genes 2019, 10, 57. https://doi.org/10.3390/genes10010057

AMA Style

Liu L, Tang L, Jin X, Zhou W. A Multi-Label Supervised Topic Model Conditioned on Arbitrary Features for Gene Function Prediction. Genes. 2019; 10(1):57. https://doi.org/10.3390/genes10010057

Chicago/Turabian Style

Liu, Lin, Lin Tang, Xin Jin, and Wei Zhou. 2019. "A Multi-Label Supervised Topic Model Conditioned on Arbitrary Features for Gene Function Prediction" Genes 10, no. 1: 57. https://doi.org/10.3390/genes10010057

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop