Deep learning in bioinformatics: introduction, application, and perspective in big data era

By Yu Li, Chao Huang, Lizhong Ding, Zhongxiao Li, Yijie Pan, Xin Gao. bioRxiv, 2019

335 citations recorded by the source corpus.

Deep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics. With the advances of the big data era in biology, it is foreseeable that deep learning will become increasingly important in the field and will be incorporated in vast majorities of analysis pipelines. In this review, we provide both the exoteric introduction of deep learning, and concrete examples and implementations of its representative applications in bioinformatics. We start from the recent achievements of deep learning in the bioinformatics field, pointing out the problems which are suitable to use deep learning. After that, we introduce deep learning in an easy-to-understand fashion, from shallow neural networks to legendary convolutional neural networks, legendary recurrent neural networks, graph neural networks, generative adversarial networks, variational autoencoder, and the most recent state-of-the-art architectures. After that, we provide eight examples, covering five bioinformatics research directions and all the four kinds of data type, with the implementation written in Tensorflow and Keras. Finally, we discuss the common issues, such as overfitting and interpretability, that users will encounter when adopting deep learning methods and provide corresponding suggestions. The implementations are freely available at https://github.com/lykaust15/Deep_learning_examples.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/6966d2b49fa885897e0b2e18ce144831c55f3e5f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

Machine learning for discovering missing or wrong protein function annotations (2019, methodology): “In particular, we instigate the use of Deep Learning methods, since the amount of data available is on a constant increase, and recent deep neural networks are capable of learning straight from DNA sequences (without the need of extracting features) [46] .”
DeepCryoPicker: fully automated deep neural network for single protein particle picking in cryo-EM (2019, methodology): “Many Deep Learning algorithms from the field of computer vision and bioinformatics such as [22, 23] use convolutional techniques to extract features from big data via layers in neural networks [12].”
Survey on categorical data for neural networks (2020, neutral): “…and convolutional neural networks for predicting expression of one-hot encoded DNA sequences, authors provide source code for techniques they cover [41, 42] Word2vec algorithm breakthrough automatic technique for natural language processing, transform natural language data to embedded vectors,…”
Universal Differential Equations for Scientific Machine Learning (2020, methodology): “The three ODE benchmarks utilized the Lorenz equations (LRNZ) weather prediction model from [6] and the standard ODE IVP Testset [7, 8]: ) The 28 ODE benchmarks utilized the Pleiades equation (PLEI) celestial mechanics simulation from [6] and the standard ODE IVP Testset [7, 8]: where (cid:0) on t…”
Fully-Connected Neural Networks with Reduced Parameterization for Predicting Histological Types of Lung Cancer from Somatic Mutations (2020, background): “A large number of analytic pipelines—such as sequence analysis, protein structure estimation, molecular property or interaction prediction, and biomedical image analysis—have incorporated deep-learning-based algorithms [1].”