LPRP: A Gene–Gene Interaction Network Construction Algorithm and Its Application in Breast Cancer Data Analysis

Su, Lingtao; Meng, Xiangyu; Ma, Qingshan; Bai, Tian; Liu, Guixia

doi:10.1007/s12539-016-0185-4

Cited by 8 publications

(5 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GoogleNet architecture on the other hand is a much deeper and wider architecture with 22 layers, while still having considerably lower number of parameters (5 million parameters) in the network than AlexNet (60 million parameters). An application of the “network in network” architecture (Lin et al, 2013 ) in the form of the inception modules is a key feature of the GoogleNet architecture. The inception module uses parallel 1 × 1, 3 × 3, and 5 × 5 convolutions along with a max-pooling layer in parallel, hence enabling it to capture a variety of features in parallel.…”

Section: Methodsmentioning

confidence: 99%

Using Deep Learning for Image-Based Plant Disease Detection

2016

View full text Add to dashboard Cite

Crop diseases are a major threat to food security, but their rapid identification remains difficult in many parts of the world due to the lack of the necessary infrastructure. The combination of increasing global smartphone penetration and recent advances in computer vision made possible by deep learning has paved the way for smartphone-assisted disease diagnosis. Using a public dataset of 54,306 images of diseased and healthy plant leaves collected under controlled conditions, we train a deep convolutional neural network to identify 14 crop species and 26 diseases (or absence thereof). The trained model achieves an accuracy of 99.35% on a held-out test set, demonstrating the feasibility of this approach. Overall, the approach of training deep learning models on increasingly large and publicly available image datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a massive global scale.

show abstract

Section: Methodsmentioning

confidence: 99%

Using Deep Learning for Image-Based Plant Disease Detection

2016

View full text Add to dashboard Cite

show abstract

“…Conversely, sparse models would be less sensitive to global changes in the topology of the network 18 . Research has shown that lower global clustering coefficients, that is, networks with more random connections, may help to explain the occurrence of brain disability, gene‐gene interactions in cancer and disease transmission 27‐29 …”

Section: Discussionmentioning

confidence: 99%

“…18 Research has shown that lower global clustering coefficients, that is, networks with more random connections, may help to explain the occurrence of brain disability, gene-gene interactions in cancer and disease transmission. [27][28][29] As contemporary paintings, networks may not be fully understood at first glance. Centrality measures provide additional information on the relative position and influence of nodes representing variables in the overall network structure, which aids observers to interpret the models.…”

Section: Discussionmentioning

confidence: 99%

Dynamics in oral health‐related factors of Indigenous Australian children: A network analysis of a randomized controlled trial

Soares

Santiago

Biazevic

et al. 2021

Comm Dent Oral Epid

View full text Add to dashboard Cite

Objectives: Network analysis is an innovative, analytic approach that enables visual representation of variables as nodes and their corresponding statistical associations as edges. It also provides a new way of framing oral health-related questions as complex systems of variables. We aimed to generate networks of oral health variables using epidemiological data of Indigenous children, and to compare network structures of oral health variables among participants who received immediate or delayed delivery of an oral health intervention.Methods: Epidemiological data from 448 mother-child dyads enrolled in a randomized controlled trial of dental caries prevention in South Australia, Australia, were obtained. Networks were estimated with nodes representing study variables and edges representing partial correlation coefficients between variables. Data included dental caries, impact on quality of life, self-rated general health, self-rated oral health, dental service utilization, knowledge of oral health, fatalism and self-efficacy in three time points. Communities of nodes, centrality, clustering coefficient and network stability were estimated. Results:The oral health intervention interacted with the network through self-rated general health and knowledge of oral health. Networks depicting groups shortly after receiving the intervention presented higher clustering coefficients and a similar arrangement of nodes. Networks tended to return to a preintervention state. Conclusion:The intervention resulted in increased connectivity and changes in the structure of communities of variables in both intervention groups. Our findings contribute to elucidating dynamics between variables depicting oral health networks over time.

show abstract

“…Su et al combine interaction networks with known breast cancer genes to identify potential drug targets [37]. Their Linear and Probabilistic Relations Prediction (LPRP) first creates a gene-gene interaction network from the given RNAseq data set and enhances it with network information from Pathway Commons [38].…”

Section: Related Workmentioning

confidence: 99%

Integrative Gene Selection on Gene Expression Data: Providing Biological Context to Traditional Approaches

Perscheid

Grasnick

Uflacker

2018

Journal of Integrative Bioinformatics

View full text Add to dashboard Cite

The advance of high-throughput RNA-Sequencing techniques enables researchers to analyze the complete gene activity in particular cells. From the insights of such analyses, researchers can identify disease-specific expression profiles, thus understand complex diseases like cancer, and eventually develop effective measures for diagnosis and treatment. The high dimensionality of gene expression data poses challenges to its computational analysis, which is addressed with measures of gene selection. Traditional gene selection approaches base their findings on statistical analyses of the actual expression levels, which implies several drawbacks when it comes to accurately identifying the underlying biological processes. In turn, integrative approaches include curated information on biological processes from external knowledge bases during gene selection, which promises to lead to better interpretability and improved predictive performance. Our work compares the performance of traditional and integrative gene selection approaches. Moreover, we propose a straightforward approach to integrate external knowledge with traditional gene selection approaches. We introduce a framework enabling the automatic external knowledge integration, gene selection, and evaluation. Evaluation results prove our framework to be a useful tool for evaluation and show that integration of external knowledge improves overall analysis results.

show abstract

LPRP: A Gene–Gene Interaction Network Construction Algorithm and Its Application in Breast Cancer Data Analysis

Cited by 8 publications

References 56 publications

Using Deep Learning for Image-Based Plant Disease Detection

Using Deep Learning for Image-Based Plant Disease Detection

Dynamics in oral health‐related factors of Indigenous Australian children: A network analysis of a randomized controlled trial

Integrative Gene Selection on Gene Expression Data: Providing Biological Context to Traditional Approaches

Contact Info

Product

Resources

About