2019
DOI: 10.1101/2019.12.27.884965
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

iPromoter-BnCNN: a novel branched CNN based predictor for identifying and classifying sigma promoters

Abstract: Motivation: Promoter is a short region of DNA which is responsible for initiating transcription of specific genes. Development of computational tools for automatic identification of promoters is in high demand. According to the difference of functions, promoters can be of different types. Promoters may have both intra and inter class variation and similarity in terms of consensus sequences. Accurate classification of various types of sigma promoters still remains a challenge. Results: We present iPromo… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
9
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
4
2

Relationship

4
2

Authors

Journals

citations
Cited by 6 publications
(9 citation statements)
references
References 50 publications
0
9
0
Order By: Relevance
“…We used broadly applied methodological measures [14], [36], [39]- [41] to comprehensively analyze the efficiency of the promoter's prediction. These include Matthew's correlation coefficient (MCC), accuracy (Acc), sensitivity (Sn), specificity (Sp), and ROC curve.…”
Section: A Evaluation Parametermentioning
confidence: 99%
“…We used broadly applied methodological measures [14], [36], [39]- [41] to comprehensively analyze the efficiency of the promoter's prediction. These include Matthew's correlation coefficient (MCC), accuracy (Acc), sensitivity (Sn), specificity (Sp), and ROC curve.…”
Section: A Evaluation Parametermentioning
confidence: 99%
“…The kernel size and filter number of each convolution layer have been shown in the figure. 1D CNN plays important role in position independent local feature extraction [32,33]. Each branch of the architecture learns class distinguishing features regarding its corresponding input feature matrix independent of the other three branches.…”
Section: Model Architecturementioning
confidence: 99%
“…The third branch uses dimer physicochemical property based representation. These properties played an important role in DNA specific classification and identification tasks such as promoter classification [33], 6mA site identification [17], recombination spot identification [34] and DNase I hypersensitive sites identification [35]. This third branch facilitates learning the interaction between these property values in a sequence order basis.…”
Section: Model Architecturementioning
confidence: 99%
“…Although recurrent layers are reliable for converting biological sequences into fixedsize features vectors [16], convolutional layers have also demonstrated promising performance addressing similar problems. In fact, CNN have been demonstrated as an effective technique for feature extraction and classification for DNA, RNA, peptides, and protein sequences in a wide range of studies [29][30][31][32][33][34][35][36]. However, CNN has never been used for ACP classification task.…”
Section: Introductionmentioning
confidence: 99%