ACP-GCN: The Identification of Anticancer Peptides Based on Graph Convolution Networks

Rao, Bing; Zhang, Lichao; Zhang, Guoying

doi:10.1109/access.2020.3023800

“…The main innovation of this architecture is to use the graph attention mechanism to construct a node information transfer function and to introduce the graph attention mechanism at the atomic and molecular levels, which is conducive to learning the local and global characteristics of molecules. In addition, Rao et al (2020) proposed a computational model based on graph convolutional network learning, using ACP prediction as a graphical classification task, named ACP-GCN. Experimental results have shown that the proposed method can effectively differentiate ACP from non-ACP and can outperform sequence feature learning.…”

Section: Machine Learning Screening Of Umami Peptidesmentioning

confidence: 99%

Research progress in the screening and evaluation of umami peptides

Qi

¹

,

Gao

²

,

Pan

³

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

Umami is an important element affecting food taste, and the development of umami peptides is a topic of interest in food‐flavoring research. The existing technology used for traditional screening of umami peptides is time‐consuming and labor‐intensive, making it difficult to meet the requirements of high‐throughput screening, which limits the rapid development of umami peptides. The difficulty in performing a standard measurement of umami intensity is another problem that restricts the development of umami peptides. The existing methods are not sensitive and specific, making it difficult to achieve a standard evaluation of umami taste. This review summarizes the umami receptors and umami peptides, focusing on the problems restricting the development of umami peptides, high‐throughput screening, and establishment of evaluation standards. The rapid screening of umami peptides was realized based on molecular docking technology and a machine learning method, and the standard evaluation of umami could be realized with a bionic taste sensor. The progress of rapid screening and evaluation methods significantly promotes the study of umami peptides and increases its application in the seasoning industry.

show abstract

“…Traditional convolutional neural networks (CNN) can extract features from Euclidean or grid structure data, such as images and text. But for non-Euclidean data like social networks, knowledge graphs, or chemical structures, due to its irregular data topology, CNN cannot directly operate on them [ 20 , 21 ]. A solution for machine learning on non-Euclidean data is Graph Convolutional Neural Network (GCN) [ 22 ].…”

Section: Methodsmentioning

confidence: 99%

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Chen

¹

,

Si

²

,

Un

³

et al. 2021

View full text Add to dashboard Cite

As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these experiments time consuming and costly, but experiments that involve animal testing are increasingly subject to ethical concerns. While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance. Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL algorithm. Using the Tox21 data, our optimal SSL-GCN models for predicting the twelve toxicological endpoints achieve an average ROC-AUC score of 0.757 in the test set, which is a 6% improvement over GCN models trained by supervised learning and conventional ML methods. Our SSL-GCN models also exhibit superior performance when compared to models constructed using the built-in DeepChem ML methods. This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data. The optimal unannotated to annotated data ratio ranges between 1:1 and 4:1. This study demonstrates the success of SSL in chemical toxicity prediction; the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases. Our optimal model SSL-GCN is hosted on an online server accessible through: https://app.cbbio.online/ssl-gcn/home.

show abstract

“…Graph Convolutional Neural Network (GCN) Traditional convolutional neural networks (CNN) can extract features from Euclidean or grid structure data, such as images and text. But for non-Euclidean data like social networks, knowledge graphs, or chemical structures, due to its irregular data topology, CNN cannot directly operate on them [20,21]. A solution for machine learning on non-Euclidean data is Graph Convolutional Neural Network (GCN) [22].…”

Section: Methodsmentioning

confidence: 99%

Chemical Toxicity Prediction Based on Semi-supervised Learning and Graph Convolutional Neural Network

Chen

¹

,

Si

²

,

Un

³

et al. 2021

Preprint

2

0

View full text Add to dashboard Cite

As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these experiments time consuming and costly, but experiments that involve animal testing are increasingly subject to ethical concerns. While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance. Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL algorithm. Using the Tox21 data, our optimal SSL-GCN models for predicting the twelve toxicological endpoints achieve an average ROC-AUC score of 0.757 in the test set, which is a 6% improvement over GCN models trained by supervised learning and conventional ML methods. Our SSL-GCN models also exhibit superior performance when compared to models constructed using the built-in DeepChem ML methods. This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data. The optimal unannotated to annotated data ratio ranges between 1:1 and 4:1. This study demonstrates the success of SSL in chemical toxicity prediction; the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases.

show abstract

ACP-GCN: The Identification of Anticancer Peptides Based on Graph Convolution Networks

Cited by 27 publications

References 60 publications

Research progress in the screening and evaluation of umami peptides

Research progress in the screening and evaluation of umami peptides

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Chemical Toxicity Prediction Based on Semi-supervised Learning and Graph Convolutional Neural Network

Contact Info

Product

Resources

About