Gated Graph Attention Network for Cancer Prediction

Qiu, Linling; Han, Li; Wang, Meihong; Wang, Xiaoli

doi:10.3390/s21061938

Cited by 10 publications

(18 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The overall structure of IAP is shown in Figure 1 , where the UCM is rendered as a black box. As an example, Figure 2 depicts the data flow of an IAP implementation of GGAT [ 46 ] (IAP-GGAT).…”

Section: Methodologiesmentioning

confidence: 99%

“…However, [ 43 ] mentioned that several problems arise from the existing deep learning models, such as overfitting, bad performance with small datasets and the struggle to deal with noisy features. Therefore, several techniques that make use of novel fields of deep learning have been proposed to handle some of these problems, such as BDR-CNN-GCN [ 44 ], which incorporates Graph Convolution Network (GCN) and CNN; some newly developed deep neural networks, as discussed by the authors of [ 45 ], who use Graph Attention Network (GAT) to identify personalised prognostic markers; and Gated Graph Attention (GGAT) network [ 46 ], which uses a gating mechanism to enhance its underlying GAT classifier.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers

Qiu

Mei-hong

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Due to the high mortality of many cancers and their related diseases, the prediction and prognosis techniques of cancers are being extensively studied to assist doctors in making diagnoses. Many machine-learning-based cancer predictors have been put forward, but many of them have failed to become widely utilised due to some crucial problems. For example, most methods require too much training data, which is not always applicable to institutes, and the complicated genetic mutual effects of cancers are generally ignored in many proposed methods. Moreover, a majority of these assist models are actually not safe to use, as they are generally built on black-box machine learners that lack references from related field knowledge. We observe that few machine-learning-based cancer predictors are capable of employing prior knowledge (PrK) to mitigate these issues. Therefore, in this paper, we propose a generalisable informed machine learning architecture named the Informed Attentive Predictor (IAP) to make PrK available to the predictor’s decision-making phases and apply it to the field of cancer prediction. Specifically, we make several implementations of the IAP and evaluate its performance on six TCGA datasets to demonstrate the effectiveness of our architecture as an assist system framework for actual clinical usage. The experimental results show a noticeable improvement in IAP models on accuracies, f1-scores and recall rates compared to their non-IAP counterparts (i.e., basic predictors).

show abstract

Section: Methodologiesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers

Qiu

Mei-hong

2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to improve the diagnostic performance of graph-based techniques for cancer grading, the authors used Contour-aware Information Aggregation Network (CIA-Net) with nuclear masks to extract nuclear shape and appearance features. Gated Graph Attention Network (GGAT) [26] was designed to extract the underlying semantic information in graph-structured data where the graph describes the relationship between genes and their associated molecular functions. The authors used a gating mechanism (GM) that interacts with the attention mechanism (AM) to overcome the limitation of 1-hop neighborhood reasoning (i.e., every node embedding contains information about the features of its immediate graph neighbors, which can be reached by a path of length 1 in the graph).…”

Section: Graph Neural Network (Gnn)mentioning

confidence: 99%

“…The main contribution of this survey includes a comprehensive overview of the applications of both conventional ML approaches and recent DL approaches for gene expression analysis. Although some of the prior reviews discuss case studies in gene expression analysis using DL architectures such as MLP, CNN, and RNN, no previous review offers a comprehensive discussion of the use of GNN [25,26] and TNN [27,28] architectures for gene expression analysis. On the other hand, GNN and TNN have the potential to become prevalent DL architectures for this task.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Methods for Cancer Classification Using Gene Expression Data: A Review

Alharbi

Vakanski

2023

Bioengineering

View full text Add to dashboard Cite

Cancer is a term that denotes a group of diseases caused by the abnormal growth of cells that can spread in different parts of the body. According to the World Health Organization (WHO), cancer is the second major cause of death after cardiovascular diseases. Gene expression can play a fundamental role in the early detection of cancer, as it is indicative of the biochemical processes in tissue and cells, as well as the genetic characteristics of an organism. Deoxyribonucleic acid (DNA) microarrays and ribonucleic acid (RNA)-sequencing methods for gene expression data allow quantifying the expression levels of genes and produce valuable data for computational analysis. This study reviews recent progress in gene expression analysis for cancer classification using machine learning methods. Both conventional and deep learning-based approaches are reviewed, with an emphasis on the application of deep learning models due to their comparative advantages for identifying gene patterns that are distinctive for various types of cancers. Relevant works that employ the most commonly used deep neural network architectures are covered, including multi-layer perceptrons, as well as convolutional, recurrent, graph, and transformer networks. This survey also presents an overview of the data collection methods for gene expression analysis and lists important datasets that are commonly used for supervised machine learning for this task. Furthermore, we review pertinent techniques for feature engineering and data preprocessing that are typically used to handle the high dimensionality of gene expression data, caused by a large number of genes present in data samples. The paper concludes with a discussion of future research directions for machine learning-based gene expression analysis for cancer classification.

show abstract

“…GNNs iteratively update node representations by aggregating information from neighboring nodes, efficiently leveraging both structural and feature information. Various GNN architectures [ 23 , 24 , 25 , 26 ] exhibit distinct characteristics and are employed in diverse scenarios. Some recent studies advocate utilizing a gene interaction graph [ 27 ], with gene expression serving as input, to predict breast cancer survival [ 28 ].…”

Section: Introductionmentioning

confidence: 99%

Smart Biosensor for Breast Cancer Survival Prediction Based on Multi-View Multi-Way Graph Learning

Ma,

Li,

Chu

et al. 2024

Sensors

View full text Add to dashboard Cite

Biosensors play a crucial role in detecting cancer signals by orchestrating a series of intricate biological and physical transduction processes. Among various cancers, breast cancer stands out due to its genetic underpinnings, which trigger uncontrolled cell proliferation, predominantly impacting women, and resulting in significant mortality rates. The utilization of biosensors in predicting survival time becomes paramount in formulating an optimal treatment strategy. However, conventional biosensors employing traditional machine learning methods encounter challenges in preprocessing features for the learning task. Despite the potential of deep learning techniques to automatically extract useful features, they often struggle to effectively leverage the intricate relationships between features and instances. To address this challenge, our study proposes a novel smart biosensor architecture that integrates a multi-view multi-way graph learning (MVMWGL) approach for predicting breast cancer survival time. This innovative approach enables the assimilation of insights from gene interactions and biosensor similarities. By leveraging real-world data, we conducted comprehensive evaluations, and our experimental results unequivocally demonstrate the superiority of the MVMWGL approach over existing methods.

show abstract

Gated Graph Attention Network for Cancer Prediction

Cited by 10 publications

References 37 publications

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers

Informed Attentive Predictors: A Generalisable Architecture for Prior Knowledge-Based Assisted Diagnosis of Cancers

Machine Learning Methods for Cancer Classification Using Gene Expression Data: A Review

Smart Biosensor for Breast Cancer Survival Prediction Based on Multi-View Multi-Way Graph Learning

Contact Info

Product

Resources

About