Pancreatic Cancer Biomarker Detection By Two Support Vector Strategies for Recursive Feature Elimination

Wang, Yan; Liu, Keke; Ma, Qin; Tan, Yongfei; Du, Wei; Lv, Yidan; Tian, Yuan; Wang, Hao

doi:10.2217/bmm-2018-0273

Cited by 15 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The above methods obtained sound prediction results, but these methods did not mention the dimensional advantages of the model. In reality, training the machine learning model utilizing high-dimensional features usually behaves poorly, This phenomenon is called Curse of Dimensionality ( Wilcox, 1961 ; Xu et al, 2017 ; Xu Y. et al, 2018 ; Zou et al, 2017 ; Wang et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Prediction of Anticancer Peptides Using a Low-Dimensional Feature Model

Zhou

Wang

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Cancer is still a severe health problem globally. The therapy of cancer traditionally involves the use of radiotherapy or anticancer drugs to kill cancer cells, but these methods are quite expensive and have side effects, which will cause great harm to patients. With the find of anticancer peptides (ACPs), significant progress has been achieved in the therapy of tumors. Therefore, it is invaluable to accurately identify anticancer peptides. Although biochemical experiments can solve this work, this method is expensive and time-consuming. To promote the application of anticancer peptides in cancer therapy, machine learning can be used to recognize anticancer peptides by extracting the feature vectors of anticancer peptides. Nevertheless, poor performance usually be found in training the machine learning model to utilizing high-dimensional features in practice. In order to solve the above job, this paper put forward a 19dimensional feature model based on anticancer peptide sequences, which has lower dimensionality and better performance than some existing methods. In addition, this paper also separated a model with a low number of dimensions and acceptable performance. The few features identified in this study may represent the important features of anticancer peptides.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Anticancer Peptides Using a Low-Dimensional Feature Model

Zhou

Wang

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…We employed support vector machines (SVM) [ 88 , 89 ], a powerful classification algorithm, to examine the performance of three distance functions and select an optimal feature subset. First, we ranked the features in decreasing order of the MRMD scores to obtain the feature list.…”

Section: Resultsmentioning

confidence: 99%

PredAmyl-MLP: Prediction of Amyloid Proteins Using Multilayer Perceptron

Zhang

Teng

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Amyloid is generally an aggregate of insoluble fibrin; its abnormal deposition is the pathogenic mechanism of various diseases, such as Alzheimer’s disease and type II diabetes. Therefore, accurately identifying amyloid is necessary to understand its role in pathology. We proposed a machine learning-based prediction model called PredAmyl-MLP, which consists of the following three steps: feature extraction, feature selection, and classification. In the step of feature extraction, seven feature extraction algorithms and different combinations of them are investigated, and the combination of SVMProt-188D and tripeptide composition (TPC) is selected according to the experimental results. In the step of feature selection, maximum relevant maximum distance (MRMD) and binomial distribution (BD) are, respectively, used to remove the redundant or noise features, and the appropriate features are selected according to the experimental results. In the step of classification, we employed multilayer perceptron (MLP) to train the prediction model. The 10-fold cross-validation results show that the overall accuracy of PredAmyl-MLP reached 91.59%, and the performance was better than the existing methods.

show abstract

“…FOS and JUND belong to the Activator Protein 1 family [ 41 ]. FOS, which encodes leucine zipper protein, was reported to be over-expressed in pancreatic cancer and was closely correlated with tumor proliferation, differentiation, and apoptosis [ 42 ]. JUND was also reported to regulate the progression of pancreatic cancer by activating the tumor suppressor gene RASSF10 [ 43 ].…”

Section: Discussionmentioning

confidence: 99%

Liver-Metastasis-Related Genes are Potential Biomarkers for Predicting the Clinical Outcomes of Patients with Pancreatic Adenocarcinoma

Dong

Tian

Yan

et al. 2021

Pathol. Oncol. Res.

View full text Add to dashboard Cite

It is widely acknowledged that metastasis determines the prognosis of pancreatic adenocarcinoma (PAAD), and the liver is the most primary distant metastatic location of PAAD. It is worth exploring the value of liver-metastasis-related genetic prognostic signature (LM-PS) in predicting the clinical outcomes of PAAD patients post R0 resection. We collected 65 tumors and 165 normal pancreatic data from The Cancer Genome Atlas (TCGA) and the Genotype-Tissue Expression project (GTEx), respectively. Differentially expressed genes (DEGs) between primary tumor and normal pancreatic samples were intersected with DEGs between primary tumor samples with liver metastasis and those without new tumor events. The intersected 45 genes were input into univariate Cox regression analysis to identify the prognostic genes. Thirty-three prognostic liver-metastasis-related genes were identified and included in least absolute shrinkage and selection operator (LASSO) analysis to develop a seven-gene LM-PS, which included six risk genes (ANO1, FAM83A, GPR87, ITGB6, KLK10, and SERPINE1) and one protective gene (SMIM32). The PAAD patients were grouped into low- and high-risk groups based on the median value of risk scores. The LM-PS harbored an independent predictive ability to distinguish patients with a high-risk of death and liver metastasis after R0 resection. Moreover, a robust prognostic nomogram based on LM-PS, the number of positive lymph nodes, and histologic grade were established to predict the overall survival of PAAD patients. Besides, a transcription factor‐microRNA coregulatory network was constructed for the seven LM-PS genes, and the immune infiltration and genomic alterations were systematically explored in the TGCA-PAAD cohort.

show abstract

Pancreatic Cancer Biomarker Detection By Two Support Vector Strategies for Recursive Feature Elimination

Cited by 15 publications

References 46 publications

Prediction of Anticancer Peptides Using a Low-Dimensional Feature Model

Prediction of Anticancer Peptides Using a Low-Dimensional Feature Model

PredAmyl-MLP: Prediction of Amyloid Proteins Using Multilayer Perceptron

Liver-Metastasis-Related Genes are Potential Biomarkers for Predicting the Clinical Outcomes of Patients with Pancreatic Adenocarcinoma

Contact Info

Product

Resources

About