Abstract | ||
---|---|---|
Deep learning methods have been successfully used in a variety of different contexts and achieved state of the art performance in many different tasks. In this paper, we explore the performance of deep learning methods in the task of predicting functional genetic variant. First, we test the performance of a few types of neural network models in making prediction using only DNA sequence. The result shows that convolutional neural network (CNN) has the best performance. Second, we explore the possibility of forming a hybrid network to make prediction with both DNA sequence and evolutionary nucleotide conservation information as input. We observe a better performance than using only conservation information by applying a dropout mask for the transformed feature of DNA sequence. We further discuss this technique as a possible common solution for combining features of different powers. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/COASE.2017.8256086 | 2017 13th IEEE Conference on Automation Science and Engineering (CASE) |
Keywords | Field | DocType |
evolutionary nucleotide conservation information,hybrid network,convolutional neural network,DNA sequence,neural network models,functional genetic variant,deep learning methods,deep learning framework | Convolutional neural network,Computer science,Artificial intelligence,DNA sequencing,Deep learning,Artificial neural network,Machine learning | Conference |
ISSN | ISBN | Citations |
2161-8070 | 978-1-5090-6782-4 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tianyi Sun | 1 | 0 | 0.34 |
Zhuo Liu | 2 | 118 | 16.03 |
Xing-Ming Zhao | 3 | 146 | 15.55 |
Rui Jiang | 4 | 330 | 40.72 |