Modeling in-vivo protein-DNA binding by combining multiple-instance learning with a hybrid deep neural network
Authors:
Open Access
- 11 June 2019
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 8484
Abstract
Modeling in-vivo protein-DNA binding is not only fundamental for further understanding of the regulatory mechanisms, but also a challenging task in computational biology. Deep-learning based methods have succeed in modeling in-vivo protein-DNA binding, but they often (1) follow the fully supervised learning framework and overlook the weakly supervised information of genomic sequences that a bound DNA sequence may has multiple TFBS(s), and, (2) use one-hot encoding to encode DNA sequences and ignore the dependencies among nucleotides. In this paper, we propose a weakly supervised framework, which combines multiple-instance learning with a hybrid deep neural network and uses k-mer encoding to transform DNA sequences, for modeling in-vivo protein-DNA binding. Firstly, this framework segments sequences into multiple overlapping instances using a sliding window, and then encodes all instances into image-like inputs of high-order dependencies using k-mer encoding. Secondly, it separately computes a score for all instances in the same bag using a hybrid deep neural network that integrates convolutional and recurrent neural networks. Finally, it integrates the predicted values of all instances as the final prediction of this bag using the Noisy-and method. The experimental results on in-vivo datasets demonstrate the superior performance of the proposed framework. In addition, we also explore the performance of the proposed framework when using k-mer encoding, and demonstrate the performance of the Noisy-and method by comparing it with other fusion methods, and find that adding recurrent layers can improve the performance of the proposed framework.Keywords
Funding Information
- China Postdoctoral Science Foundation (2016M601646, 2017M611619)
This publication has 46 references indexed in Scilit:
- t-LSE: A Novel Robust Geometric Approach for Modeling Protein-Protein Interaction NetworksPLOS ONE, 2013
- Evaluation of methods for modeling transcription factor sequence specificityNature Biotechnology, 2013
- ChIP–seq and beyond: new and improved methodologies to detect and characterize protein–DNA interactionsNature Reviews Genetics, 2012
- A Linear Model for Transcription Factor Binding Affinity Prediction in Protein Binding MicroarraysPLOS ONE, 2011
- Diversity and Complexity in DNA Recognition by Transcription FactorsScience, 2009
- Genome-wide identification ofin vivoprotein-DNA binding sites from ChIP-Seq dataNucleic Acids Research, 2008
- Locating mammalian transcription factor binding sites: A survey of computational and experimental techniquesGenome Research, 2006
- Independent component analysis-based penalized discriminant method for tumor classification using gene expression dataBioinformatics, 2006
- Finding Short DNA Motifs Using Permuted Markov ModelsJournal of Computational Biology, 2005
- Long Short-Term MemoryNeural Computation, 1997