A novel approach to feature extraction from classification models based on information gene pairs

Li, J.; Tang, Xianglong; Liu, J.; Huang, Jianhua; WANG, Yingyao

doi:10.1016/j.patcog.2007.11.019

Cited by 10 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pathways play an important role in the development of complex diseases. It is critical to find key pathways for accurate diagnosis, 45 prediction, 46 precise treatment and interpretation of complex diseases. The increasing availability of high-throughput biological data of complex diseases and the development of various biological networks provided better conditions to build accurate pathway analysis models, but there is still a lack of multiresolution knowledge bases to support accurate pathway analysis.…”

Section: Discussion and Future Perspectivesmentioning

confidence: 99%

Network-based methods for identifying critical pathways of complex diseases: a survey

Zhang

Xue

et al. 2016

Mol. BioSyst.

View full text Add to dashboard Cite

Biological pathways play important roles in the development of complex diseases, such as cancers, which are multifactorial complex diseases that are generally caused by mutation of multiple genes or dysregulation of pathways. It has become one of the most important issues to analyze pathways through combining multiple types of high-throughput data, such as genomics and proteomics, to understand the mechanisms of complex diseases. Currently, several network-based pathway analysis methods have been proposed. In this overview, we review seven major network-based pathway analysis methods and enumerate their benefits and limitations from an algorithmic perspective to provide a reference for the next generation of pathway analysis methods. Finally, we discuss the challenges that the next generation of methods faces.

show abstract

Section: Discussion and Future Perspectivesmentioning

confidence: 99%

Network-based methods for identifying critical pathways of complex diseases: a survey

Zhang

Xue

et al. 2016

Mol. BioSyst.

View full text Add to dashboard Cite

show abstract

“…The M76378 and H08393 genes were selected as the informative genes for colon cancer in [29]. The D14812 gene was among the top-ranked genes in the experiments conducted by the authors in [30,31]. Figure 2 summarizes the storage space utilized by the data set: the model build time, accuracy, mean absolute and root mean squared error, and area under the receiver operating characteristic curve (AUC) for the colon cancer data set before and after the application of the hybrid SPR algorithm.…”

Section: Predictive Gene Selectionmentioning

confidence: 99%

Section: Predictive Gene Selectionmentioning

confidence: 99%

Hybrid SPR algorithm to select predictive genes for effectual cancer classification

Sundaram¹,

Venkata²,

Parthasarathy³

2013

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:Designing an automated system for classifying DNA microarray data is an extremely challenging problem because of its high dimension and low amount of sample data. In this paper, a hybrid statistical pattern recognition algorithm is proposed to reduce the dimensionality and select the predictive genes for the classification of cancer. Colon cancer gene expression profiles having 62 samples of 2000 genes were used for the experiment. A gene subset of 6 highly informative genes was selected by the algorithm, which provided a classification accuracy of 93.5%.

show abstract

“…Machine learning algorithms and statistical models also are widely used to identify cancer biomarkers. For example, the 70-gene biomarkers (Van’t Veer et al, 2002), wound-response gene biomarkers (Chang et al, 2005), and several of our gene biomarkers (Li et al, 2008; Li et al, 2010; Zhang et al, 2017) are all identified using machine learning algorithms. The 21-gene biomarkers (Van’t Veer and Bernards, 2008) and immunotherapy response biomarkers (Ock et al, 2017; Jiang et al, 2018) are based on statistical models.…”

Section: Introductionmentioning

confidence: 99%

IBI: Identification of Biomarker Genes in Individual Tumor Samples

Wang

2019

Front. Genet.

View full text Add to dashboard Cite

Individual patient biomarkers have an important role in personalized treatment. Although various high-throughput sequencing technologies are widely used in biological experiments, these are usually conducted only once or a few times for each patient, which makes it a challenging problem to identify biomarkers in individual patients. At present, there is a lack of effective methods to identify biomarkers in individual sample data. Here, we propose a novel method, IBI, to identify biomarkers in individual tumor samples. Experimental results from several tumor data sets showed that the proposed method could effectively find biomarker genes for individual patients, including common biomarkers related to the mechanisms of the development of cancer, which can be used to predict survival and drug response in patients. In summary, these results demonstrate that the proposed method offers a new perspective for analyzing individual samples.

show abstract

A novel approach to feature extraction from classification models based on information gene pairs

Cited by 10 publications

References 24 publications

Network-based methods for identifying critical pathways of complex diseases: a survey

Network-based methods for identifying critical pathways of complex diseases: a survey

Hybrid SPR algorithm to select predictive genes for effectual cancer classification

IBI: Identification of Biomarker Genes in Individual Tumor Samples

Contact Info

Product

Resources

About