NeuroTIS: Enhancing the prediction of translation initiation sites in mRNA sequences via a hybrid dependency network and deep learning framework

Wei, Chao; Zhang, Junying; Yuan, Xiguo; He, Zongzhen; Liu, Guojun; Wu, Jin-Hui

doi:10.1016/j.knosys.2020.106459

Cited by 14 publications

(20 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, using the free Japanese-Chinese machine translation software now available on the Internet, many mistranslations can still be seen when translating Sino-Japanese homonyms into Chinese. Therefore, I believe that the translation processing of Japanese homonyms in Japanese-Chinese machine translation is one of the important research topics [9,10].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Model-Based Machine Learning for Chinese and Japanese Translation

Wang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

This paper takes deep learning as the background of researcher design, combines the relevant cutting-edge research results in recent years, addresses the linguistic characteristics of Japanese and the problems faced by completing Japanese machine translation system, and determines the neural network structure of encoding-decoding for Japanese translation based on the characteristics of high similarity between Japanese and Chinese and after referring to the neural network architecture of English translation, and the basic structure and the corresponding improvement of the hidden layer unit calculation are carried out. The training model is optimized and an integrated Japanese machine translation system is implemented. Finally, the translation models of Japanese and Chinese intertranslation and Japanese and Chinese intertranslation are tested, and the optimal model fusion achieves a BLEU value of 39.52.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning Model-Based Machine Learning for Chinese and Japanese Translation

Wang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…A total number of 10873 sequences are obtained after removing repeated entries. H24842 and M19900 come from our previous work Wei et al (2020). We adopt the hold-out strategy, randomly selecting 8000, 20000, 15000 sequences as training set to test the remaining 2873, 4842, and 4900 sequences, for H10873, H24842, and M19900 datasets, respectively.…”

Section: Datasetsmentioning

confidence: 99%

“…Many existing computational methods Hatzigeorgiou, Mache and Reczko (1996); Guigó (1997); Zhang, Lin, Yan and Zhang (1998); Hatzigeorgiou (2002); Shuo and Yi-sheng (2009); Tzanis, Berberidis and Vlahavas (2012); Wei, Zhang, Yuan, He, Liu and Wu (2020) have been proposed for protein coding regions prediction in genomic or transcript sequence during the past decades. They first encode a biological sequence into numerical values and then feed them into a classifier for final prediction.…”

Section: Introductionmentioning

confidence: 99%

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding^★,★★

Wei

Zhang

Yuan

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Protein coding regions prediction is a very important but overlooked subtask for tasks such as prediction of complete gene structure, coding/noncoding RNA. Many machine learning methods have been proposed for this problem, they first encode a biological sequence into numerical values and then feed them into a classifier for final prediction. However, encoding schemes directly influence the classifier capability to capture coding features and how to choose a proper encoding scheme remains uncertain. Recently, we proposed a protein coding region prediction method in transcript sequences based on a bidirectional recurrent neural network with non-overlapping kmer, and achieved considerable improvement over existing methods, but there is still much room to improve the performance. In fact, kmer features that count the occurrence frequency of trinucleotides only reflect the local sequence order information between the most contiguous nucleotides, which loses almost all the global sequence order information. In viewing of the point, we here present a deep learning framework with hybrid encoding for protein coding regions prediction in biological sequences, which effectively exploiting global sequence order information, non-overlapping kmer features and statistical dependencies among coding labels. Evaluated on genomic and transcript sequences, our proposed method significantly outperforms existing state-of-the-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

“…• Inspired by our previous work Wei et al (2020), we extend label dependencies to genomic sequences and significantly improve the prediction performance on genomic sequences over existing methods.…”

Section: Introductionmentioning

confidence: 99%

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding

Wei

Zhang

Yuan

2022

Digital Signal Processing

Self Cite

View full text Add to dashboard Cite

NeuroTIS: Enhancing the prediction of translation initiation sites in mRNA sequences via a hybrid dependency network and deep learning framework

Cited by 14 publications

References 39 publications

Deep Learning Model-Based Machine Learning for Chinese and Japanese Translation

Deep Learning Model-Based Machine Learning for Chinese and Japanese Translation

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding^★,★★

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding

Contact Info

Product

Resources

About

NeuroTIS: Enhancing the prediction of translation initiation sites in mRNA sequences via a hybrid dependency network and deep learning framework

Cited by 14 publications

References 39 publications

Deep Learning Model-Based Machine Learning for Chinese and Japanese Translation

Deep Learning Model-Based Machine Learning for Chinese and Japanese Translation

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding★,★★

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding

Contact Info

Product

Resources

About

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding^★,★★