Muhammad Nabeel Asim1,2, Muhammad Ali Ibrahim3,4, Christoph Zehe5, Johan Trygg5,6, Andreas Dengel3,4, Sheraz Ahmed4,6. 1. Department of Computer Science, Technical University of Kaiserslautern, 67663, Kaiserslautern, Rhineland-Palatinate, Germany. Muhammad_Nabeel.Asim@dfki.de. 2. German Research Center for Artificial Intelligence GmbH, 67663, Kaiserslautern, Rhineland-Palatinate, Germany. Muhammad_Nabeel.Asim@dfki.de. 3. Department of Computer Science, Technical University of Kaiserslautern, 67663, Kaiserslautern, Rhineland-Palatinate, Germany. 4. German Research Center for Artificial Intelligence GmbH, 67663, Kaiserslautern, Rhineland-Palatinate, Germany. 5. Sartorius Stedim Cellca GmbH, 88471, Laupheim, Baden-Wurttemberg, Germany. 6. Computational Life Science Cluster (CLiC), Umea University, 90187, Umea, Sweden.
Abstract
BACKGROUND AND OBJECTIVE: Interactions of long non-coding ribonucleic acids (lncRNAs) with micro-ribonucleic acids (miRNAs) play an essential role in gene regulation, cellular metabolic, and pathological processes. Existing purely sequence based computational approaches lack robustness and efficiency mainly due to the high length variability of lncRNA sequences. Hence, the prime focus of the current study is to find optimal length trade-offs between highly flexible length lncRNA sequences. METHOD: The paper at hand performs in-depth exploration of diverse copy padding, sequence truncation approaches, and presents a novel idea of utilizing only subregions of lncRNA sequences to generate fixed-length lncRNA sequences. Furthermore, it presents a novel bag of tricks-based deep learning approach "Bot-Net" which leverages a single layer long-short-term memory network regularized through DropConnect to capture higher order residue dependencies, pooling to retain most salient features, normalization to prevent exploding and vanishing gradient issues, learning rate decay, and dropout to regularize precise neural network for lncRNA-miRNA interaction prediction. RESULTS: BoT-Net outperforms the state-of-the-art lncRNA-miRNA interaction prediction approach by 2%, 8%, and 4% in terms of accuracy, specificity, and matthews correlation coefficient. Furthermore, a case study analysis indicates that BoT-Net also outperforms state-of-the-art lncRNA-protein interaction predictor on a benchmark dataset by accuracy of 10%, sensitivity of 19%, specificity of 6%, precision of 14%, and matthews correlation coefficient of 26%. CONCLUSION: In the benchmark lncRNA-miRNA interaction prediction dataset, the length of the lncRNA sequence varies from 213 residues to 22,743 residues and in the benchmark lncRNA-protein interaction prediction dataset, lncRNA sequences vary from 15 residues to 1504 residues. For such highly flexible length sequences, fixed length generation using copy padding introduces a significant level of bias which makes a large number of lncRNA sequences very much identical to each other and eventually derail classifier generalizeability. Empirical evaluation reveals that within 50 residues of only the starting region of long lncRNA sequences, a highly informative distribution for lncRNA-miRNA interaction prediction is contained, a crucial finding exploited by the proposed BoT-Net approach to optimize the lncRNA fixed length generation process. AVAILABILITY: BoT-Net web server can be accessed at https://sds_genetic_analysis.opendfki.de/lncmiRNA/.
BACKGROUND AND OBJECTIVE: Interactions of long non-coding ribonucleic acids (lncRNAs) with micro-ribonucleic acids (miRNAs) play an essential role in gene regulation, cellular metabolic, and pathological processes. Existing purely sequence based computational approaches lack robustness and efficiency mainly due to the high length variability of lncRNA sequences. Hence, the prime focus of the current study is to find optimal length trade-offs between highly flexible length lncRNA sequences. METHOD: The paper at hand performs in-depth exploration of diverse copy padding, sequence truncation approaches, and presents a novel idea of utilizing only subregions of lncRNA sequences to generate fixed-length lncRNA sequences. Furthermore, it presents a novel bag of tricks-based deep learning approach "Bot-Net" which leverages a single layer long-short-term memory network regularized through DropConnect to capture higher order residue dependencies, pooling to retain most salient features, normalization to prevent exploding and vanishing gradient issues, learning rate decay, and dropout to regularize precise neural network for lncRNA-miRNA interaction prediction. RESULTS: BoT-Net outperforms the state-of-the-art lncRNA-miRNA interaction prediction approach by 2%, 8%, and 4% in terms of accuracy, specificity, and matthews correlation coefficient. Furthermore, a case study analysis indicates that BoT-Net also outperforms state-of-the-art lncRNA-protein interaction predictor on a benchmark dataset by accuracy of 10%, sensitivity of 19%, specificity of 6%, precision of 14%, and matthews correlation coefficient of 26%. CONCLUSION: In the benchmark lncRNA-miRNA interaction prediction dataset, the length of the lncRNA sequence varies from 213 residues to 22,743 residues and in the benchmark lncRNA-protein interaction prediction dataset, lncRNA sequences vary from 15 residues to 1504 residues. For such highly flexible length sequences, fixed length generation using copy padding introduces a significant level of bias which makes a large number of lncRNA sequences very much identical to each other and eventually derail classifier generalizeability. Empirical evaluation reveals that within 50 residues of only the starting region of long lncRNA sequences, a highly informative distribution for lncRNA-miRNA interaction prediction is contained, a crucial finding exploited by the proposed BoT-Net approach to optimize the lncRNA fixed length generation process. AVAILABILITY: BoT-Net web server can be accessed at https://sds_genetic_analysis.opendfki.de/lncmiRNA/.
Keywords:
Bag of tricks; Deep learning; Deep learning strategies; Lightweight neural network; Long non-coding RNA; Micro-RNA; Robust interaction predictor; lncRNA–miRNA interaction prediction
Authors: Zhen Chen; Pei Zhao; Fuyi Li; Tatiana T Marquez-Lago; André Leier; Jerico Revote; Yan Zhu; David R Powell; Tatsuya Akutsu; Geoffrey I Webb; Kuo-Chen Chou; A Ian Smith; Roger J Daly; Jian Li; Jiangning Song Journal: Brief Bioinform Date: 2020-05-21 Impact factor: 11.622
Authors: Manuela Lanzafame; Gaia Bianco; Luigi M Terracciano; Charlotte K Y Ng; Salvatore Piscuoglio Journal: Int J Mol Sci Date: 2018-02-28 Impact factor: 5.923