Densely Convolutional Neural Network for Transcription Factor Binding Sites Prediction Using DNA Sequence and Histone Modification
1
Citation
23
Reference
10
Related Paper
Citation Trend
Abstract:
Transcription factor binding sites (TFBSs) prediction is crucial for decoding cis-regulation. However, current deep learning methods fail to simultaneously consider the multiscale features from DNA sequences and histone modifications in an efficient manner. To this end, we propose a novel D ensely C onvolutional N eural N etwork using DNA S equence and H istone Modification, dubbed as DCNN-SH, for TFBSs prediction. Our model adopts densely convolutional blocks to reuse multi-length motifs and multi-order dependencies of nucleotides. This unique design allows our model to consider the multi-scale features using smaller convolutional kernels compared to current methods. Our work is the first to apply densely network for TFBSs prediction. Extensive experiments over 300 ChIP-seq datasets demonstrate that our model significantly outperforms several state-of-the-art prediction methods in terms of accuracy, ROC-AUC and PR-AUC.Keywords:
DNA binding site
Sequence (biology)
When the traditional LT code is used for encoding and decoding, if there is no encoded packets with degree 1 in the remaining encoded groups, the decoding will stop and the decoding cannot be continued. That will affects the decoding efficiency. For this reason, this paper proposes an improved enhanced decoding method. When BP decoding stops, the remaining coded packets will be decoded using the secondary decoding method, which can improves the success rate of decoding.
List decoding
Berlekamp–Welch algorithm
Code (set theory)
Cite
Citations (0)
In previous work, we presented two different generalized decoding strategies for the relay channel, called SeqBack and SimBack decoding, that make use of regular encoding and backward decoding. In this paper, we show that the rates achievable by SeqBack and SimBack decoding are equal. Furthermore, we show that regular encoding/sliding window decoding can achieve the same rate as regular encoding/backward decoding.
List decoding
Sliding window protocol
Cite
Citations (5)
This chapter presents algorithmic techniques for decoding with linear models. We begin with some definitions, then discuss several views of decoding that are useful for understanding decoding algorithms. We present important methods for exactly solving decoding problems. We briefly discuss some approximate techniques, as they are becoming increasingly important for rich NLP models.
List decoding
Cite
Citations (0)
Sphere decoding is a technique able to achieve the optimal performance of the maximum likelihood decoder, but its high and variable complexity can make the practical implementation infeasible. In this paper, we present an adaptive system, called adaptive SD-OSIC, as a way of reducing the decoding complexity while maintaining the error performance of conventional sphere decoding.
List decoding
Cite
Citations (0)
A simplified multistage decoding method using threshold technique for multilevel coding is presented. It can decrease the time delay of the multistage decoding greatly without the loss of the decoding performance and therefore make the real-time decoding for multilevel codes possible.< >
List decoding
Cite
Citations (0)
Real time object detection in traffic surveillance is one of the latest topics in today's world using Region based Convolutional Neural Networks algorithm in comparison with Convolutional Neural Networks. Real-Time Object Detection is performed using Regional Convolutional Neural Networks (N=78) over Convolutional Neural Networks (N=78) with the split size of training and testing dataset 70% and 30% respectively. Regional Convolutional Neural Networks had significantly better accuracy (75.6%) compared to Convolutional Neural Networks (47.7%) and attained significance value of p=0.041. Regional Convolutional Neural Networks achieved significantly better object detection than Convolutional Neural Networks for identifying real-time objects in traffic surveillance.
Cite
Citations (8)
Joint equalization and TCM decoding scheme with multiple decoding depths is proposed for ATSC DTV systems, which reduces error propagation and improves the performance. The additional device is the decoding output unit with the complexity slightly higher than that with decoding depth of 1. With the channel profiles described in this paper, convergence threshold is decreased by 6 dB when using the decoding output with decoding depth of 1 instead of hard decision as feedback data. Another 3 dB is reduced with decoding depth of 6. Thus 9 dB in total is reduced compared with hard decision.
List decoding
Cite
Citations (0)
This paper studies the application of beyond bound decoding method for high speed optical communications. This hard-decision decoding method outperforms traditional minimum distance decoding method, with a total net coding gain of 10.36 dB.
List decoding
Coding gain
Cite
Citations (1)
In this paper, a universal decoding method is proposed to solve the problems in both base band and frequency band systems. Theoretical analysis and simulation results indicate that, the proposed decoding method shows preferable performance for suppressing NBI and is proved to be a good choice of IS-OFDM for decoding in the frequency band transmitting systems.
Frequency band
List decoding
Cite
Citations (0)
Inactivation decoding is a technique that efficiently combines BP decoding and Gaussian elimination for decoding BATS codes. To improve the decoding performance of the conventional inactivation decoding, the Gaussian elimination step in the decoding process is optimized based on the fact that some input packets may be resolved even when the linear system of equations is not full rank. The simulation results demonstrate that our proposed method achieves a better decoding performance than the conventional method but with increased computational complexity.
List decoding
Gaussian elimination
Berlekamp–Welch algorithm
Cite
Citations (0)