Precursor microRNA Identification Using Deep Convolutional Neural Networks

Bt, Do; Golkov,; Ge, Gürel; Cremers, Daniel

doi:10.1101/414656

Cited by 9 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning approaches overcome the need for feature engineering by learning the features from more basic input data. Several deep learning approaches such as convolutional neural networks (CNNs) ( Do et al, 2018 ) and recurrent neural networks (RNNs) ( Park et al, 2016 ; Cao et al, 2018 ) have been used for microRNA classification. While these approaches have addressed the limitations of feature engineering, they only predict loci and do not perform cleavage-site prediction.…”

Section: Introductionmentioning

confidence: 99%

Predicting Drosha and Dicer Cleavage Sites with DeepMirCut

Bell

Hendrix²

2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

MicroRNAs are a class of small RNAs involved in post-transcriptional gene silencing with roles in disease and development. Many computational tools have been developed to identify novel microRNAs. However, there have been no attempts to predict cleavage sites for Drosha from primary sequence, or to identify cleavage sites using deep neural networks. Here, we present DeepMirCut, a recurrent neural network-based software that predicts both Dicer and Drosha cleavage sites. We built a microRNA primary sequence database including flanking genomic sequences for 34,713 microRNA annotations. We compare models trained on sequence data, sequence and secondary structure data, as well as input data with annotated structures. Our best model is able to predict cuts within closer average proximity than results reported for other methods. We show that a guanine nucleotide before and a uracil nucleotide after Dicer cleavage sites on the 3′ arm of the microRNA precursor had a positive effect on predictions while the opposite order (U before, G after) had a negative effect. Our analysis was also able to predict several positions where bulges had either positive or negative effects on the score. We expect that our approach and the data we have curated will enable several future studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Drosha and Dicer Cleavage Sites with DeepMirCut

Bell

Hendrix²

2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

show abstract

“…The greatest advantage of this approach is that it does not require hand-crafted features. Do et al (2018) proposed a novel joint two-dimensional multi-channel method to identify pre-miRNAs, using the secondary structure encoded by the pairing matrix format as the input to the two-dimensional convolution network to achieve automatic feature extraction. These features were fed into fully connected layers for classification.…”

Section: Resultsmentioning

confidence: 99%

“…For instance, deepMiRGene (Park et al, 2017) uses long short-term memory (LSTM) to automatically extract features and process time-dependent problems in a sequence. Do et al (2018) introduced a convolutional neural network (CNN) to automatically extract features to identify miRNAs. Lee et al (2016) used an automatic encoder based on a deep recurrent neural network (RNN) to determine the interaction of miRNA sequences for miRNA target prediction.…”

Section: Introductionmentioning

confidence: 99%

CL-PMI: A Precursor MicroRNA Identification Method Based on Convolutional and Long Short-Term Memory Networks

Wang

Dong

et al. 2019

Front. Genet.

View full text Add to dashboard Cite

MicroRNAs (miRNAs) are the major class of gene-regulating molecules that bind mRNAs. They function mainly as translational repressors in mammals. Therefore, how to identify miRNAs is one of the most important problems in medical treatment. Many known pre-miRNAs have a hairpin ring structure containing more structural features, and it is difficult to identify mature miRNAs because of their short length. Therefore, most research focuses on the identification of pre-miRNAs. Most computational models rely on manual feature extraction to identify pre-miRNAs and do not consider the sequential and spatial characteristics of pre-miRNAs, resulting in a loss of information. As the number of unidentified pre-miRNAs is far greater than that of known pre-miRNAs, there is a dataset imbalance problem, which leads to a degradation of the performance of pre-miRNA identification methods. In order to overcome the limitations of existing methods, we propose a pre-miRNA identification algorithm based on a cascaded CNN-LSTM framework, called CL-PMI. We used a convolutional neural network to automatically extract features and obtain pre-miRNA spatial information. We also employed long short-term memory (LSTM) to capture time characteristics of pre-miRNAs and improve attention mechanisms for long-term dependence modeling. Focal loss was used to improve the dataset imbalance. Compared with existing methods, CL-PMI achieved better performance on all datasets. The results demonstrate that this method can effectively identify pre-miRNAs by simultaneously considering their spatial and sequential information, as well as dealing with imbalance in the datasets.

show abstract

“…mirHunter [42] which identifies both plant and animal pre-miRNAs, is such an example. Neural network (NN) algorithms such as convolutional neural networks (CNN), long short-term memory neural networks (LSTM) have also been utilized in pre-miRNA identification [43,44,45]. Most of these models are not trained with only plant pre-miRNAs but both humans and plants pre-miRNAs.…”

Section: Introductionmentioning

confidence: 99%