One-dimensional pairwise CNN for the global alignment of two DNA sequences

Ji, Luping; Pu, Xiaorong; Qu, Hong; Liu, Guisong

doi:10.1016/j.neucom.2014.08.023

Cited by 8 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An important disadvantage of the transformer model is its inefficiency in processing long sequences, mainly due to the computation and memory complexity of the self-attention module [ 41 ]. CNN can extract local features in the sequence to shorten the length of the sequence [ 42 , 43 ]. Therefore, this research proposes the CNN + Transformer model structure, which combines a CNN and a transformer model.…”

Section: Methodsmentioning

confidence: 99%

A deep learning approach for orphan gene identification in moso bamboo (Phyllostachys edulis) based on the CNN + Transformer model

et al. 2022

View full text Add to dashboard Cite

Background Orphan gene play an important role in the environmental stresses of many species and their identification is a critical step to understand biological functions. Moso bamboo has high ecological, economic and cultural value. Studies have shown that the growth of moso bamboo is influenced by various stresses. Several traditional methods are time-consuming and inefficient. Hence, the development of efficient and high-accuracy computational methods for predicting orphan genes is of great significance. Results In this paper, we propose a novel deep learning model (CNN + Transformer) for identifying orphan genes in moso bamboo. It uses a convolutional neural network in combination with a transformer neural network to capture k-mer amino acids and features between k-mer amino acids in protein sequences. The experimental results show that the average balance accuracy value of CNN + Transformer on moso bamboo dataset can reach 0.875, and the average Matthews Correlation Coefficient (MCC) value can reach 0.471. For the same testing set, the Balance Accuracy (BA), Geometric Mean (GM), Bookmaker Informedness (BM), and MCC values of the recurrent neural network, long short-term memory, gated recurrent unit, and transformer models are all lower than those of CNN + Transformer, which indicated that the model has the extensive ability for OG identification in moso bamboo. Conclusions CNN + Transformer model is feasible and obtains the credible predictive results. It may also provide valuable references for other related research. As our knowledge, this is the first model to adopt the deep learning techniques for identifying orphan genes in plants.

show abstract

Section: Methodsmentioning

confidence: 99%

A deep learning approach for orphan gene identification in moso bamboo (Phyllostachys edulis) based on the CNN + Transformer model

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The 1D pairwise convolutional neural network (CNN) algorithm described in [24] failed to align two long sequences with lengths of 24343 NTs and 42028 NTs. This finding implied that considerable memory is required to use this method in aligning a pair of extremely long DNA sequences.…”

Section: Related Workmentioning

confidence: 99%

Sequence Alignment Using Machine Learning-Based Needleman–Wunsch Algorithm

et al. 2021

View full text Add to dashboard Cite

Biological pairwise sequence alignment can be used as a method for arranging two biological sequence characters to identify regions of similarity. This operation has elicited considerable interest due to its significant influence on various critical aspects of life (e.g., identifying mutations in coronaviruses). Sequence alignment over large databases cannot yield results within a reasonable time, power, and cost. heuristic methods, such as FASTA, the BLAST family have been demonstrated to perform 40 times faster than DP-based (e.g., Needleman-Wunsch) techniques they cannot guarantee an optimum alignment result An optimized software platform of a widely used DNA sequence alignment algorithm called the Needleman-Wunsch (NW) algorithm based on a lookup table, is described in this study. This global alignment algorithm is the best approach for identifying similar regions between sequences. This study presents a new application of classical machine learning (ML) to global sequence alignment. Customized ML models are used to implement NW global alignment. An accuracy of 99.7% is achieved when using a multilayer perceptron with the ADAM optimizer, and up to 2912 Giga cell updates per second are realized on two real DNA sequences with a length of 4.1 M nucleotides. Our implementation is valid for RNA/DNA sequences. This study aims to parallelize the computation steps involved in the algorithm to accelerate its performance by using ML algorithms. All datasets used in this study are available from https://ieeedataport.org/documents/dna-sequence-alignment-datasets-based-nw-algorithm. INDEX TERMSBioinformatics, DNA, RNA, Pairwise sequence alignment (PWSA), Needleman-Wunsch (NW) algorithm, Machine learning (ML) algorithms, Multilayer perceptron (MLP), XGBoost algorithm. CONTRIBUTION:This study presented six DNA/RNA sequence alignment datasets for one of the most common alignment algorithms, namely, the Needleman-Wunsch (NW) algorithm. It proposed a fast and parallel implementation of the NW algorithm by using machine learning techniques. This research is an extension and improved version of our previous work [1]. The current implementation achieved 99.7% accuracy by using a multilayer perceptron with the ADAM optimizer and up to 2912 Giga cell updates per second on two real DNA sequences with an of length 4.1 M nucleotides. Our implementation is valid for extremely long sequences by using the divide-and-conquer strategy.

show abstract

“…As per the different convolution kernels, the convolutional operation can be 1D convolution, 2D convolution, and higher-dimensional convolution. [25] The convolutional operation is to slide kernel on the feature maps. The weights W x are multiplied with the extracted feature maps with bias parameter b x added to construct the final output of the convolutional layer.…”

Section: Convolutional Layermentioning

confidence: 99%

A novel one‐dimensional convolutional neural network architecture for chemical process fault diagnosis

Niu

Xia

2021

Can J Chem Eng

View full text Add to dashboard Cite

In recent years, industrial production has become increasingly automated, with the widespread application of informational and digital technology. Fault detection and diagnosis (FDD) technology is also playing an increasingly important role in the chemical process industry. However, owing to the weak generalization ability of prior models, or prior methods not being suitable for industrial sensor signal data, the fault detection rate is not satisfactory, which is a significant limitation of many fault diagnosis methods in practical applications. In response to this problem, the one-dimensional convolutional neural network (1D-CNN) model can directly process signal samples without changing the one-dimensional characteristics of the data, which may be more suitable for processing such signal data. Therefore, a new 1D-CNN architecture is proposed for FDD. The network architectures, including convolutional layers, pooling layers, fully connected layers, and various parameters, are optimized in the proposed method. The Tennessee Eastman process (TE process) is employed to assess prominent performance of the method. To comprehensively reflect the performance of the model, three evaluation indexes are selected in this study: accuracy, F1-score, and fault detection rate. The experimental results indicate that compared with other diagnostic methods, the 1D-CNN model has excellent feature extraction ability, which can remarkably improve diagnostic capability in the TE process.

show abstract

One-dimensional pairwise CNN for the global alignment of two DNA sequences

Cited by 8 publications

References 37 publications

A deep learning approach for orphan gene identification in moso bamboo (Phyllostachys edulis) based on the CNN + Transformer model

A deep learning approach for orphan gene identification in moso bamboo (Phyllostachys edulis) based on the CNN + Transformer model

Sequence Alignment Using Machine Learning-Based Needleman–Wunsch Algorithm

A novel one‐dimensional convolutional neural network architecture for chemical process fault diagnosis

Contact Info

Product

Resources

About