4.7 Article

Simple tricks of convolutional neural network architectures improve DNA-protein binding prediction

Journal

BIOINFORMATICS
Volume 35, Issue 11, Pages 1837-1843

Publisher

OXFORD UNIV PRESS
DOI: 10.1093/bioinformatics/bty893

Keywords

-

Funding

  1. National Natural Science Foundation of China [11661141019, 61621003, 61422309, 61379092]
  2. Strategic Priority Research Program of the Chinese Academy of Sciences (CAS) [XDB13040600]
  3. National Ten Thousand Talent Program for Young Topnotch Talents
  4. Key Research Program of the Chinese Academy of Sciences [KFZD-SW-219]
  5. National Key Research and Development Program of China [2017YFC0908405]
  6. CAS Frontier Science Research Key Project for Top Young Scientist [QYZDB-SSW-SYS008]

Ask authors/readers for more resources

Motivation: With the accumulation of DNA sequencing data, convolution neural network (CNN) based methods such as DeepBind and DeepSEA have achieved great success for predicting the function of primary DNA sequences. Previous studies confirm the importance of utilizing the reverse complement and flanking DNA sequences, which has a natural connection with data augmentation. However, it is not fully understood how these DNA sequences work during model training and testing. Results: In this study, we proposed several CNN tricks to improve the DNA sequence related prediction tasks and took the DNA-protein binding prediction as an illustrative task for demonstration. Different from the DeepBind, we treated the reverse complement DNA sequence as another sample, which enables the CNN model to automatically learn the complex relationships between the double strand DNA sequences. This trick promotes the using of deeper CNN models, improving the prediction performance. Next, we augmented the training sets by extending the DNA sequences and cropping each one to three shorter sequences. This approach greatly improves the prediction due to more environmental information from extending step and strong regularization effect of the cropping step. Moreover, this practice fits well with wider CNN models, which also increases the prediction accuracy. On the basis of DNA sequence augmentation, we integrated the results of different effective CNN models to mine the prediction potential of primary DNA sequences. On 156 datasets of predicting DNA-protein binding, our final prediction significantly outperformed the state-of-the-art results with an average AUC increase of 0.057 (P-value = 6 x 10(-62)).

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available