Predicting novel microRNA: a comprehensive comparison of machine learning approaches

Stegmayer, Georgina; Persia, Leandro E. Di; Rubiolo, María Florencia; Gérard, M.; Pividori, Milton; Yones, Cristian Ariel; Bugnon, Leandro A.; Rodriguez, Tadeo; Raad, Jonathan; Milone, Diego H.

doi:10.1093/bib/bby037

Cited by 38 publications

(33 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, to the best of our knowledge, there are no such datasets available. Actually, in most published works, the datasets used for training and testing the prediction methods are manually built, use diverse methodologies according to each study [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16], and require a (not negligible) long time. Secondly, it is very hard to fairly compare among different classifiers.…”

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Genome-wide hairpins datasets of animals and plants for novel miRNA prediction

et al. 2019

Self Cite

View full text Add to dashboard Cite

This article makes available several genome-wide datasets, which can be used for training microRNA (miRNA) classifiers. The hairpin sequences available are from the genomes of: Homo sapiens, Arabidopsis thaliana, Anopheles gambiae, Caenorhabditis elegans and Drosophila melanogaster . Each dataset provides the genome data divided into sequences and a set of computed features for predictions. Each sequence has one label: i) “positive”: meaning that it is a well-known pre-miRNA, according to miRBase v21; or ii) “unlabeled”: indicating that the sequence has not (yet) a known function and could be a possible candidate to novel pre-miRNA. Due to the fact that selecting an informative feature set is very important for a good pre-miRNA classifier, a representative feature set with large discriminative power has been calculated and it is provided, as well, for each genome. This feature set contains typical information about sequence, topology and structure. Dataset was publically shared in https://sourceforge.net/projects/sourcesinc/files/mirdata/.

show abstract

Section: Experimental Design Materials and Methodsmentioning

confidence: 99%

Genome-wide hairpins datasets of animals and plants for novel miRNA prediction

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first stage is data set preparation. Candidate peptide sequences were typically collected from a validated database [44]. To build a high-quality predictive model, training and test sets were required.…”

Section: A Framework Of the Proposed Cpp Predictormentioning

confidence: 99%

Improved Prediction of Cell-Penetrating Peptides via Effective Orchestrating Amino Acid Composition Feature Representation

Cai

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Cell-penetrating peptides (CPPs) promote the transport of pharmacologically active molecules, such as nanoparticles, plasmid DNA and short interfering RNA. Accurate prediction of new CPPs is a prerequisite for in-depth study of such molecules. Biological experimental predictions can provide an accurate description of the penetrating properties of CPPs. However, predicting CPPs by wet laboratory experiments is both resource-intensive and time-consuming. Therefore, the development of effective calculation method prediction has become an important topic in the study of CPPs. Recently, numerous methods developed for predicting CPPs use amino acid composition, alone and the accuracies of such methods have been limited. In this study, we proposed a new CPP prediction framework, which integrates four amino acid composition features, and utilizes these features to help train Support Vector Machine (SVM) model as a classifier to predict CPPs. When performing on the training dataset CPP924, the proposed method achieves an accuracy of 92.3%, which is significantly better than the state-of-the-art methods. These results suggest that the framework can orchestrate various amino acid composition features predicted models flexibly with good performances.

show abstract

“…This high imbalance is very difficult to handle by any ML model (Bugnon et al, 2019). In spite of the fact that there is a myriad of methods for pre-miRNA classification published (Li et al, 2010;Gomes and et al, 2013;Shukla et al, 2017;Stegmayer et al, 2018;Chen et al, 2019), a study has clearly shown that the prediction of pre-miRNAs is yet far-away from being satisfactory solved because existing methods have a very high rate of false positives (Demirci et al, 2017). That is, they provide an excessively long list of candi-dates to novel pre-miRNAs, that cannot be validated with wet-experiments.…”

Section: Introductionmentioning

confidence: 99%

High precision in microRNA prediction: a novel genome-wide approach based on convolutional deep residual networks

Yones

Raad

Bugnon

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Motivation: MicroRNAs (miRNAs) are small non-coding RNAs that have a key role in the regulation of gene expression. The importance of miRNAs is widely acknowledged by the community nowadays, and the precise prediction of novel candidates with computational methods is still very needed. This could be done by searching homologous with sequence alignment tools, but this will be restricted only to sequences very similar to the known miRNA precursors (pre-miRNAs). Furthermore, other important properties of pre-miRNAs, such as the secondary structure, are not taken into account by these methods. Many machine learning approaches were proposed in the last years to fill this gap, but these methods were tested in very controlled conditions, which are not fulfilled, for example, when predicting in newly sequenced genomes, where no miRNAs are known. If these methods are used under real conditions, the precision achieved is far from the one published. Results: This work provides a novel approach for dealing with the computational prediction of pre-miRNAs: a convolutional deep residual neural network. The proposed model has been tested on several complete genomes of animals and plants, achieving a precision up to 5 times higher than other approaches at the same recall rates. Also, a novel validation methodology is used to ensure that the performance reported can be achieved when using the method on new unknown species. Availability: To provide fast an easy access to mirDNN, a web demo is available in http://sinc.unl.edu.ar/web-demo/mirdnn/. It can process fasta files with multiple sequences to calculate the prediction scores, and can generate the nucleotide importance plots. The full source code of this project is available at http://sourceforge.net/projects/sourcesinc/files/mirdnn Contact: cyones@sinc.unl.edu.ar

show abstract

Predicting novel microRNA: a comprehensive comparison of machine learning approaches

Cited by 38 publications

References 60 publications

Genome-wide hairpins datasets of animals and plants for novel miRNA prediction

Genome-wide hairpins datasets of animals and plants for novel miRNA prediction

Improved Prediction of Cell-Penetrating Peptides via Effective Orchestrating Amino Acid Composition Feature Representation

High precision in microRNA prediction: a novel genome-wide approach based on convolutional deep residual networks

Contact Info

Product

Resources

About