LncMirNet: Predicting LncRNA–miRNA Interaction Based on Deep Learning of Ribonucleic Acid Sequences
Abstract
:1. Introduction
2. Materials and Methods
2.1. Materials
2.1.1. Datasets
2.1.2. Constructing Positive and Negative Samples
2.2. Methods
2.2.1. Overall Workflow
2.2.2. Construction Features
k-mer Features of RNA Sequence
Composition/Transition/Distribution (CTD) Features
Distributed Representation Feature of RNA Sequence by doc2vec
Graph Embedding Methods to Represent RNA Sequence
Constructing Matrix Features by Histogram-Dd
2.2.3. Prediction Model by Convolutional Neural Networks
2.3. Implementation of LncMirNet
2.4. Evaluation Criteria
3. Results
3.1. Experimental Settings
3.2. The Effects of Feature Combination
3.3. Comparison with Six Other Methods on All Data
3.4. Negative Samples Analysis
4. Discussion
5. Conclusions
6. Data Availability Statement
Supplementary Materials
Author Contributions
Funding
Conflicts of Interest
References
- Yang, S.; Wang, Y.; Zhang, S.; Hu, X.; Ma, Q.; Tian, Y. NCResNet: Noncoding Ribonucleic Acid Prediction Based on a Deep Resident Network of Ribonucleic Acid Sequences. Front. Genet. 2020, 11, 1–13. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Huang, J.Z.; Chen, M.; Chen, D.; Gao, X.C.; Zhu, S.; Huang, H.; Hu, M.; Zhu, H.; Yan, G.R. A Peptide Encoded by a Putative lncRNA HOXB-AS3 Suppresses Colon Cancer Growth. Mol. Cell 2017, 68, 171–184.e6. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Chakravarty, D.; Sboner, A.; Nair, S.S.; Giannopoulou, E.; Li, R.; Hennig, S.; Mosquera, J.M.; Pauwels, J.; Park, K.; Kossai, M.; et al. The oestrogen receptor alpha-regulated lncRNA NEAT1 is a critical modulator of prostate cancer. Nat. Commun. 2014, 5, 1–16. [Google Scholar] [CrossRef] [PubMed]
- Bhan, A.; Mandal, S.S. LncRNA HOTAIR: A master regulator of chromatin dynamics and cancer. Biochim. Biophys. Acta Rev. Cancer 2015, 1856, 151–164. [Google Scholar] [CrossRef] [Green Version]
- Sun, M.; Nie, F.; Wang, Y.; Zhang, Z.; Hou, J.; He, D.; ** NLP curves: A review of natural language processing research. IEEE Comput. Intell. Mag. 2014, 9, 48–57. [Google Scholar] [CrossRef]
- Ito, E.A.; Katahira, I.; da Rocha Vicente, F.F.; Pereira, L.F.P.; Lopes, F.M. BASiNET—Biological sequences network: A case study on coding and non-coding RNAs identification. Nucleic Acids Res. 2018, 46, 1–9. [Google Scholar] [CrossRef] [PubMed]
- Le, Q.; Mikolov, T. Distributed representations of sentences and documents. In Proceedings of the 31st International Conference on Machine Learning, ICML 2014; **ng, E.P., Jebara, T., Eds.; PMLR: Bei**g, China, 2014; Volume 4, pp. 2931–2939. [Google Scholar]
- Simonovsky, M.; Komodakis, N. GraphVAE: Towards generation of small graphs using variational autoencoders. In International Conference on Artificial Neural Networks; Springer: Cham, Switzerland, 2018; pp. 412–422. [Google Scholar] [CrossRef] [Green Version]
- Min, S.; Lee, B.; Yoon, S. Deep learning in bioinformatics. Brief. Bioinform. 2017, 18, 851–869. [Google Scholar] [CrossRef] [Green Version]
Sample Availability: All data and code are available from the authors. |
k-mer | k-mer, CTD | k-mer, CTD, doc2vec | k-mer, CTD, doc2vec, Graph Embedding | |
---|---|---|---|---|
Training | 0.8609 | 0.8802 | 0.9048 | 0.9140 |
Test | 0.8004 | 0.8188 | 0.8321 | 0.8534 |
Sensitivity | Specificity | F1-Score | Accuracy | AUC | MCC | |
---|---|---|---|---|---|---|
GEEL | 0.8040 | 0.8401 | 0.8187 | 0.8220 | 0.8982 | 0.6445 |
PmliPred | 0.8800 | 0.7118 | 0.8117 | 0.7959 | 0.9030 | 0.6004 |
BiLSTM | 0.8027 | 0.6263 | 0.7239 | 0.7145 | 0.7876 | 0.4359 |
SEAL | 0.7650 | 0.8097 | 0.7825 | 0.7874 | 0.8658 | 0.5754 |
SVD | 0.6548 | 0.6594 | 0.6595 | 0.6571 | 0.7156 | 0.3142 |
Katz | 0.5969 | 0.5961 | 0.5953 | 0.5964 | 0.6459 | 0.1930 |
LncMirNet | 0.9158 | 0.7910 | 0.8620 | 0.8534 | 0.9381 | 0.7124 |
Number of Positive Samples | Number of Negative Samples | AUC | |
---|---|---|---|
0.25 | 15,386 | 3846 | 0.8519 |
0.5 | 15,386 | 7693 | 0.8729 |
1.0 | 15,386 | 15,386 | 0.9381 |
2.0 | 15,386 | 30,772 | 0.9067 |
4.0 | 15,386 | 61,544 | 0.8834 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, S.; Wang, Y.; Lin, Y.; Shao, D.; He, K.; Huang, L. LncMirNet: Predicting LncRNA–miRNA Interaction Based on Deep Learning of Ribonucleic Acid Sequences. Molecules 2020, 25, 4372. https://doi.org/10.3390/molecules25194372
Yang S, Wang Y, Lin Y, Shao D, He K, Huang L. LncMirNet: Predicting LncRNA–miRNA Interaction Based on Deep Learning of Ribonucleic Acid Sequences. Molecules. 2020; 25(19):4372. https://doi.org/10.3390/molecules25194372
Chicago/Turabian StyleYang, Sen, Yan Wang, Yu Lin, Dan Shao, Kai He, and Lan Huang. 2020. "LncMirNet: Predicting LncRNA–miRNA Interaction Based on Deep Learning of Ribonucleic Acid Sequences" Molecules 25, no. 19: 4372. https://doi.org/10.3390/molecules25194372