A Deep Learning Framework for Identifying Essential Proteins by Integrating Multiple Types of Biological Information

Zeng, Min; Li, Min; Fei, Zhihui; Wu, Fang‐Xiang; Li, Yaohang; Pan, Yi; Wang, Jianxin

doi:10.1109/tcbb.2019.2897679

Cited by 94 publications

(70 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Guo et al used SVM (Support Vector Machines) to predict human gene essentiality based on the -interval Z curve derived features from nucleotide sequence data [8]. Zeng et al used deep learning method to predict gene essentiality by integrating gene expression data, subcellular localization data, and PPI networks together, and tested it on S. cerevisiae [9]. Hasan et al used a six hidden-layers neural network to predict gene essentiality in microbes based on sequence data [10].…”

mentioning

confidence: 99%

DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning

Zhang

Xiao

2020

Preprint

View full text Add to dashboard Cite

Motivation: Accurately predicting essential genes using computational methods can greatly reduce the effort in finding them via wet experiments at both time and resource scales, and further accelerate the process of drug discovery. Several computational methods have been proposed for predicting essential genes in model organisms by integrating multiple biological data sources either via centrality measures or machine learning based methods. However, the methods aiming to predict human essential genes are still limited and the performance still need improve. In addition, most of the machine learning based essential gene prediction methods are lack of skills to handle the imbalanced learning issue inherent in the essential gene prediction problem, which might be one factor affecting their performance. Results:We proposed a deep learning based method, DeepHE, to predict human essential genes by integrating features derived from sequence data and protein-protein interaction (PPI) network. A deep learning based network embedding method was utilized to automatically learn features from PPI network. In addition, 89 sequence features were derived from DNA sequence and protein sequence for each gene. These two types of features were integrated to train a multilayer neural network. A cost-sensitive technique was used to address the imbalanced learning problem when training the deep neural network. The experimental results for predicting human essential genes showed that our proposed method, DeepHE, can accurately predict human gene essentiality with an average AUC higher than 94%, the area under precision-recall curve (AP) higher than 90%, and the accuracy higher than 90%. We also compared DeepHE with several widely used traditional machine learning models (SVM, Naïve Bayes, Random Forest, Adaboost). The experimental results showed that DeepHE greatly outperformed the compared machine learning models. Conclusions:We demonstrated that human essential genes can be accurately predicted by designing effective machine learning algorithm and integrating representative features captured from available biological data. The proposed deep learning framework is effective for such task.Essential genes are a subset of genes which are indispensable to the survival or reproduction of a living organism. The prediction of gene essentiality is very important for understanding the minimal requirements of an organism, identifying disease genes, and finding new drug targets. The discovery of essential genes via wet-lab experimental methods are often time-consuming, laborious, and costly. With the accumulation of gene essentiality data in some model organisms and human cell lines, many computational methods have been proposed to predict essential genes by exploring the correlations between gene essentiality and all sorts of biological information.One focus in this direction is network based centrality measures. Many studies have demonstrated that highly connected proteins in a protein-protein interaction (PPI) network are more likely to be esse...

show abstract

mentioning

confidence: 99%

DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning

Zhang

Xiao

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…If q > 1, the walk tends to be closer to node u. In contrast, if q < 1, it tends to traverse nodes far from node u (Zeng et al, 2019).…”

Section: Using Node2vec To Learning Representationsmentioning

confidence: 97%

“…There is more concerned for the local information. Parameter q is an in-out parameter, which allows searches to distinguish "inward" and "outward" nodes (Zeng et al, 2019). If q > 1, the walk tends to be closer to node u.…”

Section: Using Node2vec To Learning Representationsmentioning

confidence: 99%

Predicting Microbe-Disease Association by Learning Graph Representations and Rule-Based Inference on the Heterogeneous Network

Lei

Wang

2020

Front. Microbiol.

View full text Add to dashboard Cite

More and more clinical observations have implied that microbes have great effects on human diseases. Understanding the relations between microbes and diseases are of profound significance for disease prevention and therapy. In this paper, we propose a predictive model based on the known microbe-disease associations to discover potential microbe-disease associations through integrating Learning Graph Representations and a modified Scoring mechanism on the Heterogeneous network (called LGRSH). Firstly, the similarity networks for microbe and disease are obtained based on the similarity of Gaussian interaction profile kernel. Then, we construct a heterogeneous network including these two similarity networks and microbe-disease associations' network. After that, the embedding algorithm Node2vec is implemented to learn representations of nodes in the heterogeneous network. Finally, according to these low-dimensional vector representations, we calculate the relevance between each microbe and disease by utilizing a modified rule-based inference method. By comparison with three other methods including LRLSHMDA, KATZHMDA and BiRWHMDA, LGRSH performs better than others. Moreover, in case studies of asthma, Chronic Obstructive Pulmonary Disease and Inflammatory Bowel Disease, there are 8, 8, and 10 out of the top-10 discovered disease-related microbes were validated respectively, demonstrating that LGRSH performs well in predicting potential microbe-disease associations.

show abstract

“…By contrast with traditional machine learning solutions, deep learning techniques are undergoing rapid development. Applications of deep learning involve information retrieval [4], natural language processing [5], human voice recognition [6], computer vision [7], anomaly detection [8], recommendation systems [9], bioinformatics [10], medicine [11,12], crop science [13], earth science [14], robotics [15][16][17][18], transportation engineering [19], communication technologies [20][21][22], and system simulation [23,24].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning on Computational-Resource-Limited Platforms: A Survey

Chen

Zhang

et al. 2020

Mobile Information Systems

View full text Add to dashboard Cite

Nowadays, Internet of Things (IoT) gives rise to a huge amount of data. IoT nodes equipped with smart sensors can immediately extract meaningful knowledge from the data through machine learning technologies. Deep learning (DL) is constantly contributing significant progress in smart sensing due to its dramatic superiorities over traditional machine learning. The promising prospect of wide-range applications puts forwards demands on the ubiquitous deployment of DL under various contexts. As a result, performing DL on mobile or embedded platforms is becoming a common requirement. Nevertheless, a typical DL application can easily exhaust an embedded or mobile device owing to a large amount of multiply and accumulate (MAC) operations and memory access operations. Consequently, it is a challenging task to bridge the gap between deep learning and resource-limited platforms. We summarize typical applications of resource-limited deep learning and point out that deep learning is an indispensable impetus of pervasive computing. Subsequently, we explore the underlying reasons for the high computational overhead of DL through reviewing the fundamental concepts including capacity, generalization, and backpropagation of a neural network. Guided by these concepts, we investigate on principles of representative research works, as well as three types of solutions: algorithmic design, computational optimization, and hardware revolution. In pursuant to these solutions, we identify challenges to be addressed.

show abstract

A Deep Learning Framework for Identifying Essential Proteins by Integrating Multiple Types of Biological Information

Cited by 94 publications

References 53 publications

DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning

DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning

Predicting Microbe-Disease Association by Learning Graph Representations and Rule-Based Inference on the Heterogeneous Network

Deep Learning on Computational-Resource-Limited Platforms: A Survey

Contact Info

Product

Resources

About