Wavelet Feature Extraction and Genetic Algorithm for Biomarker Detection in Colorectal Cancer Data

Liu, Yihui; Aickelin, Uwe; Feyereisl, Jan; Durrant, Lindy G.

doi:10.2139/ssrn.2823262

Cited by 6 publications

(7 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the duality of CD46 signaling in anti- and pro-tumoral functions necessitates a careful evaluation of its function in oncogenesis. In patients with ovarian and breast cancer, expression of CD46 is linked to shorter relapse periods and worse prognosis ( 320 ) ( 321 ); similar outcomes are observed in patients with CRC ( 322 ) and multiple myeloma ( 320 ). In patients with HBV-HCC, the HBx protein upregulates CD46 in hepatoma and human immortalized liver cells and affords protection from complement mediated cell lysis mechanisms ( 323 ).…”

Section: Complement Proteins In Hccmentioning

confidence: 89%

“Complimenting the Complement”: Mechanistic Insights and Opportunities for Therapeutics in Hepatocellular Carcinoma

et al. 2021

View full text Add to dashboard Cite

Hepatocellular carcinoma (HCC) is the most common primary malignancy of the liver and a leading cause of death in the US and worldwide. HCC remains a global health problem and is highly aggressive with unfavorable prognosis. Even with surgical interventions and newer medical treatment regimens, patients with HCC have poor survival rates. These limited therapeutic strategies and mechanistic understandings of HCC immunopathogenesis urgently warrant non-palliative treatment measures. Irrespective of the multitude etiologies, the liver microenvironment in HCC is intricately associated with chronic necroinflammation, progressive fibrosis, and cirrhosis as precedent events along with dysregulated innate and adaptive immune responses. Central to these immunological networks is the complement cascade (CC), a fundamental defense system inherent to the liver which tightly regulates humoral and cellular responses to noxious stimuli. Importantly, the liver is the primary source for biosynthesis of >80% of complement components and expresses a variety of complement receptors. Recent studies implicate the complement system in liver inflammation, abnormal regenerative responses, fibrosis, carcinogenesis, and development of HCC. Although complement activation differentially promotes immunosuppressive, stimulant, and angiogenic microenvironments conducive to HCC development, it remains under-investigated. Here, we review derangement of specific complement proteins in HCC in the context of altered complement regulatory factors, immune-activating components, and their implications in disease pathogenesis. We also summarize how complement molecules regulate cancer stem cells (CSCs), interact with complement-coagulation cascades, and provide therapeutic opportunities for targeted intervention in HCC.

show abstract

Section: Complement Proteins In Hccmentioning

confidence: 89%

“Complimenting the Complement”: Mechanistic Insights and Opportunities for Therapeutics in Hepatocellular Carcinoma

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The wavelet-based noise reduction can be implemented using three ways as follows: namely, the maximum principle on wavelet transform-based de-noising way, the wavelet threshold value-based de-noising way and the regional correlation on wavelet coefficient-based de-noising way (Aziz-Alaoui and Chen, 2002; Gao and Zhou, 2010; Liu et al, 2013; Qiao and Cao, 2008). In this paper, a wavelet threshold value de-noising algorithm is introduced to process the crack observations of concrete dam.…”

Section: Wavelet De-noising Algorithm For Crack Observations Of Concrmentioning

confidence: 99%

Wavelet-fractal diagnosis model and its criterion for concrete dam crack status

Chen

Wen

et al. 2017

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

The methods on fractal, phase space reconstruction and wavelet are integrated to analyze the observed data of concrete dam cracks. The diagnosis model and appropriate criterion for evolution characteristics of concrete dam crack are developed. Firstly, a wavelet threshold value de-noising algorithm is introduced to process the crack observations of concrete dam. The phase space reconstruction for data series after noise reduction is investigated and the parameter selection method is presented. Then the correlation dimension and Kolmogorov entropy-based models are built to evaluate the crack status of concrete dam. The corresponding criteria are given. Finally, the identification capability of the proposed approach is demonstrated with an actual case. It is indicated that the noise reduction of observed data has the important effect on improving the diagnosis accuracy of crack status. The observed behavior of dam crack has obvious fractal characteristics. The effective diagnosis for crack status of concrete dam can be implemented using the correlation dimension and Kolmogorov entropy-based criteria.

show abstract

“…Among the work done for censored survival data, most of them were focused on using forward, backward, step wise, penalized and shrinkage variable selection with Cox proportional hazard model, though machine learning classifiers (MLC) are more favored as they consider complex relations and non-linearity existed in the data during the modeling process, which is not the case in statistical methods [3]. However, they are less used in survival analysis due to the fact that censoring makes them less capable to be directly used for survival data [4,5]. Therefore, the censoring problem should be handled first.…”

Section: Introductionmentioning

confidence: 99%

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection

Attallah

Karthikesalingam

Holt

et al. 2017

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

show abstract

Wavelet Feature Extraction and Genetic Algorithm for Biomarker Detection in Colorectal Cancer Data

Cited by 6 publications

References 53 publications

“Complimenting the Complement”: Mechanistic Insights and Opportunities for Therapeutics in Hepatocellular Carcinoma

“Complimenting the Complement”: Mechanistic Insights and Opportunities for Therapeutics in Hepatocellular Carcinoma

Wavelet-fractal diagnosis model and its criterion for concrete dam crack status

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection

Contact Info

Product

Resources

About