miRClassify: An advanced web server for miRNA family classification and annotation

Zou, Quan; Mao, Yaozong; Hu, Lingling; Wu, Yunfeng; Ji, Zhiliang

doi:10.1016/j.compbiomed.2013.12.007

Cited by 96 publications

(63 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hierarchical classifier has worked well on miRNA family classification [39,40] and protein folds prediction [41][42][43]. It is the first time to be employed on enhancers identification.…”

Section: Two-layer Classification Frameworkmentioning

confidence: 99%

iEnhancer-PsedeKNC: Identification of enhancers and their subgroups based on Pseudo degenerate kmer nucleotide composition

Liu

2016

Neurocomputing

View full text Add to dashboard Cite

“…Hierarchical classifier has worked well on miRNA family classification [39,40] and protein folds prediction [41][42][43]. It is the first time to be employed on enhancers identification.…”

Section: Two-layer Classification Frameworkmentioning

confidence: 99%

iEnhancer-PsedeKNC: Identification of enhancers and their subgroups based on Pseudo degenerate kmer nucleotide composition

Liu

2016

Neurocomputing

View full text Add to dashboard Cite

“…A miRNA family consists of a group of miRNAs that derive from a common ancestor, which regulate a similar set of target genes and therefore share similar biological and therapeutic function (Zou et al, 2014). Currently, the common criteria used for the classification of miRNA families are based on sequence similarity in the seed regions.…”

Section: Mirna Families and Clusters In Giant Pandamentioning

confidence: 99%

Identification of conserved microRNAs in peripheral blood from giant panda: expression of mammary gland-related microRNAs during late pregnancy and early lactation

et al. 2015

View full text Add to dashboard Cite

ABSTRACT. The giant panda (Ailuropoda melanoleuca) is one of the world's most endangered mammals, and it has evolved several unusual biological and behavioral traits. During puberty, pregnancy, lactation, and involution, the mammary gland undergoes profound morphological and functional changes. A large number of microRNAs (miRNAs) have been identified to be involved in mammary gland development and lactation. In this study, we identified 202 conserved mature miRNAs, corresponding to 147 pre-miRNAs, in giant panda peripheral blood using a small RNAsequencing approach. In addition, 27 miRNA families and 29 miRNA clusters were identified. We analyzed the arm selection preference of pre-miRNAs and found that: 1) most giant panda pre-miRNAs generated one-strand miRNAs, and the 5p-arm only miRNAs have a higher expression level than 3p-arm only miRNAs; 2) there were more 5p-arm dominant miRNAs than 3p-arm dominant miRNAs; and 3) 5p-arm dominant miRNAs have a larger fold change within miRNA pairs than 3p-arm dominant miRNAs. Expression of 12 lactation-related miRNAs was detected across late pregnancy and early lactation stages by qPCR, and seven miRNAs were identified as clustered in one significant model. Most of these clustered miRNAs exhibited inhibitory roles in proliferation and differentiation of mammary epithelial cells. Functional analysis highlighted important roles of the seven as signed miRNAs in mammary development and metabolic changes, including blood vessel morphogenesis, macromolecule biosynthesis, cell cycle regulation, and protein transport.

show abstract

“…In turn, this can lead to better understanding the effects of 26 mutations in the non-coding region of the genome in terms of function and disease. To 27 this end, in this work, we apply deep learning techniques to investigate the role of 28 non-canonical sites and pairing beyond the canonical seed region in microRNA targets. 29 Almost all target prediction methods are rule-based or adopt machine learning (ML) 30 methodology with varying success.…”

mentioning

confidence: 99%

“…To 27 this end, in this work, we apply deep learning techniques to investigate the role of 28 non-canonical sites and pairing beyond the canonical seed region in microRNA targets. 29 Almost all target prediction methods are rule-based or adopt machine learning (ML) 30 methodology with varying success. Rule-based systems incorporate various 31 human-crafted descriptors to represent miRNA:gene target binding (e.g.…”

mentioning

confidence: 99%

See 1 more Smart Citation

miRAW: A deep learning approach to predict miRNA targets by analyzing whole miRNA transcripts

Plà

Zhong

Rayner

2017

Preprint

View full text Add to dashboard Cite

MicroRNAs (miRNAs) are small non-coding RNAs that regulate gene expression by binding to partially complementary regions within the 3'UTR of their target genes. Computational methods play an important role in target prediction and assume that the miRNA "seed region" (nt 2 to 8) is required for functional targeting, but typically only identify 80% of known bindings. Recent studies have highlighted a role for the entire miRNA, suggesting that a more flexible methodology is needed.We present a novel approach for miRNA target prediction based on Deep Learning (DL) which, rather than incorporating any knowledge (such as seed regions), investigates the entire miRNA and 3'UTR mRNA nucleotides to learn a uninhibited set of feature descriptors related to the targeting process.We collected more than 150,000 experimentally validated homo sapiens miRNA:gene targets and cross referenced them with different CLIP-Seq, CLASH and iPAR-CLIP datasets to obtain 20,000 validated miRNA:gene exact target sites. Using this data, we implemented and trained a deep neural network -composed of autoencoders and a feed-forward network -able to automatically learn features describing miRNA-mRNA interactions and assess functionality. Predictions were then refined using information such as site location or site accessibility energy.In a comparison using independent datasets, our DL approach consistently outperformed existing prediction methods, recognizing the seed region as a common feature in the targeting process, but also identifying the role of pairings outside this region. Thermodynamic analysis also suggests that site accessibility plays a role in targeting but that it cannot be used as a sole indicator for functionality.Data and source code available at: https://bitbucket.org/account/user/bipous/projects/MIRAW Author summary microRNAs are small RNA molecules that regulate biological processes by binding to the 3'UTR of a gene and their dysregulation is associated with several diseases. Computationally predicting these targets remains a challenge as they only partially match their target and so there can be hundreds of targets for a single microRNA.Current tools assume that most of the knowledge defining a microRNA-gene interaction can be captured by analysing the binding produced in the seed region (≈ the first 8nt in the miRNA). However, recent studies show that the whole microRNA can be important and form non-canonical targets. Here, we use a target prediction methodology miRAW: deep learning for miRNA target prediction -Pla et al.

show abstract

miRClassify: An advanced web server for miRNA family classification and annotation

Cited by 96 publications

References 17 publications

iEnhancer-PsedeKNC: Identification of enhancers and their subgroups based on Pseudo degenerate kmer nucleotide composition

iEnhancer-PsedeKNC: Identification of enhancers and their subgroups based on Pseudo degenerate kmer nucleotide composition

Identification of conserved microRNAs in peripheral blood from giant panda: expression of mammary gland-related microRNAs during late pregnancy and early lactation

miRAW: A deep learning approach to predict miRNA targets by analyzing whole miRNA transcripts

Contact Info

Product

Resources

About