Recurrent Neural Networks for Sequential Phenotype Prediction in Genomics

One of the major challenges in analyzing modern biological data is dealing with ill-posed problems and missing data. In this paper, we propose a genotype imputation and phenotype sequences prediction system based on matrix factorization (MF) and recurrent neural networks (RNNs). The proposed RNN model uses rectified linear units (ReLUs) as the activation function. Experimental results show good performance of the proposed model, compared to the long-short-term memory (LSTM) and sparse partial least square (SPLS) models.

[1]  Shahryar Rahnamayan,et al.  Micro-differential evolution with vectorized random mutation factor , 2014, 2014 IEEE Congress on Evolutionary Computation (CEC).

[2]  Bahareh Nikpour,et al.  Optimum Localization of Wind Turbine Sites Using Opposition Based Ant Colony Optimization , 2013, 2013 Sixth International Conference on Developments in eSystems Engineering.

[3]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[4]  S. Keleş,et al.  Sparse partial least squares regression for simultaneous dimension reduction and variable selection , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[5]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[6]  P. Donnelly,et al.  A Flexible and Accurate Genotype Imputation Method for the Next Generation of Genome-Wide Association Studies , 2009, PLoS genetics.

[7]  Sharon L R Kardia,et al.  Imputing missing genotypic data of single-nucleotide polymorphisms using neural networks , 2008, European Journal of Human Genetics.

[8]  Lei Zhang,et al.  Tumor Classification Based on Non-Negative Matrix Factorization Using Gene Expression Data , 2011, IEEE Transactions on NanoBioscience.

[9]  Hojjat Salehinejad,et al.  A Pistachio Nuts Classification Technique: An ANN Based Signal Processing Scheme , 2008, 2008 International Conference on Computational Intelligence for Modelling Control & Automation.

[10]  Julianne Baarbe,et al.  Alterations in cortical and cerebellar motor processing in subclinical neck pain patients following spinal manipulation. , 2013, Journal of manipulative and physiological therapeutics.

[11]  Karin Schnass,et al.  Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$ -Minimization , 2009, IEEE Transactions on Information Theory.

[12]  Shahryar Rahnamayan,et al.  Image thresholding using micro opposition-based Differential Evolution (Micro-ODE) , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[13]  Alioune Ngom,et al.  A new Kernel non-negative matrix factorization and its application in microarray data analysis , 2012, 2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB).

[14]  Shahryar Rahnamayan,et al.  3D localization in large-scale Wireless Sensor Networks: A micro-differential evolution approach , 2014, 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC).

[15]  Dongjun Chung,et al.  An Introduction to the ‘spls’ Package, Version 1.0 , 2008 .

[16]  Jian-Huang Lai,et al.  Nonlinear nonnegative matrix factorization based on Mercer kernel construction , 2011, Pattern Recognit..

[17]  Shahryar Rahnamayan,et al.  Micro-differential evolution: Diversity enhancement and a comparative study , 2015, Appl. Soft Comput..

[18]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[19]  Shahryar Rahnamayan,et al.  Type-II opposition-based differential evolution , 2014, 2014 IEEE Congress on Evolutionary Computation (CEC).

[20]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[21]  Ananth Ranganathan,et al.  The Levenberg-Marquardt Algorithm , 2004 .

[22]  M.M.A. Salama,et al.  Opposition-Based Differential Evolution , 2008, IEEE Transactions on Evolutionary Computation.

[23]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[24]  G. Abecasis,et al.  MaCH: using sequence and genotype data to estimate haplotypes and unobserved genotypes , 2010, Genetic epidemiology.

[25]  J. Marchini,et al.  Genotype imputation for genome-wide association studies , 2010, Nature Reviews Genetics.

[26]  Hojjat Salehinejad,et al.  Dynamic Fuzzy Logic-Ant Colony System-Based Route Selection System , 2010, Appl. Comput. Intell. Soft Comput..

[27]  Hojjat Salehinejad,et al.  Cognitive radio networks spectrum allocation: An ACS perspective , 2012, Sci. Iran..

[28]  Geoffrey E. Hinton,et al.  A Simple Way to Initialize Recurrent Networks of Rectified Linear Units , 2015, ArXiv.

[29]  Heidi Haavik,et al.  A novel protocol to investigate motor training-induced plasticity and sensorimotor integration in the cerebellum and motor cortex. , 2014, Journal of neurophysiology.

[30]  B. Browning,et al.  Rapid and accurate haplotype phasing and missing-data inference for whole-genome association studies by use of localized haplotype clustering. , 2007, American journal of human genetics.

[31]  Yoshua Bengio,et al.  Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.

[32]  Razvan Pascanu,et al.  Theano: new features and speed improvements , 2012, ArXiv.