Machine Learning Model for Identifying Gene Biomarkers for Breast Cancer Treatment Survival

Tabl, Ashraf Abou; Alkhateeb, Abedalrhman; ElMaraghy, Waguih; Ngom, Alioune

doi:10.1145/3107411.3108217

Cited by 5 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These provide a platform to explore and understand the pathogenesis of cancer formation and proliferation from a molecular perspective. Analyzing the expression of genes among newly diagnosed BC patients [11][12][13][14][15] and those undergoing treatment [16,17] provides a better understanding of the disease progression and prognosis. Large-scale cancer genomics screening programs explore novel BC gene biomarkers to improve early detection and reduce mortality.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Machine Learning Approach to Screen Optimal Predictors for the Classification of Primary Breast Tumors from Gene Expression Microarray Data

2023

View full text Add to dashboard Cite

The high dimensionality and sparsity of the microarray gene expression data make it challenging to analyze and screen the optimal subset of genes as predictors of breast cancer (BC). The authors in the present study propose a novel hybrid Feature Selection (FS) sequential framework involving minimum Redundancy-Maximum Relevance (mRMR), a two-tailed unpaired t-test, and meta-heuristics to screen the most optimal set of gene biomarkers as predictors for BC. The proposed framework identified a set of three most optimal gene biomarkers, namely, MAPK 1, APOBEC3B, and ENAH. In addition, the state-of-the-art supervised Machine Learning (ML) algorithms, namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Neural Net (NN), Naïve Bayes (NB), Decision Tree (DT), eXtreme Gradient Boosting (XGBoost), and Logistic Regression (LR) were used to test the predictive capability of the selected gene biomarkers and select the most effective breast cancer diagnostic model with higher values of performance matrices. Our study found that the XGBoost-based model was the superior performer with an accuracy of 0.976 ± 0.027, an F1-Score of 0.974 ± 0.030, and an AUC value of 0.961 ± 0.035 when tested on an independent test dataset. The screened gene biomarkers-based classification system efficiently detects primary breast tumors from normal breast samples.

show abstract

Section: Introductionmentioning

confidence: 99%

A Hybrid Machine Learning Approach to Screen Optimal Predictors for the Classification of Primary Breast Tumors from Gene Expression Microarray Data

2023

View full text Add to dashboard Cite

show abstract

“…Machine learning approaches have been utilized to detect breast cancer treatment or survivals (Mangasarian and Wolberg, 2000; Cardoso et al, 2016; Abou Tabl et al, 2017; Tang et al, 2017; Zeng et al, 2018). many researchers have used DNA microarray technology to study breast cancer survivability (Mangasarian and Wolberg, 2000; Cardoso et al, 2016; Abou Tabl et al, 2017). Analyzing gene expression among breast cancer patients who undergo varying treatment types deepens the current understanding of the disease’s progression and prognosis.…”

Section: Introductionmentioning

confidence: 99%

“…Using samples from patients with high-risk clinical features in the early stages of breast cancer, Cardoso et al (2016) proposed the use of a statistical model to determine the necessity of chemotherapy treatment based on clinical data. In one of our earlier works, we built a prediction model based on various treatments without defining the period of survivability (Abou Tabl et al, 2017); that is, given a training dataset consisting of gene expression data of BC patients who survived or died after receiving a treatment therapy, we built a classification model that is used to predict whether a new patient will survive or die. In another work, we have implemented an unsupervised learning approach to find the separation between the treatment-survival groups of classes (Tabl et al, 2018a), the model is grouping different classes together in building the tree model while defining the border between the different groups of classes.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach for Identifying Gene Biomarkers Guiding the Treatment of Breast Cancer

et al. 2019

Self Cite

View full text Add to dashboard Cite

Genomic profiles among different breast cancer survivors who received similar treatment may provide clues about the key biological processes involved in the cells and finding the right treatment. More specifically, such profiling may help personalize the treatment based on the patients’ gene expression. In this paper, we present a hierarchical machine learning system that predicts the 5-year survivability of the patients who underwent though specific therapy; The classes are built on the combination of two parts that are the survivability information and the given therapy. For the survivability information part, it defines whether the patient survives the 5-years interval or deceased. While the therapy part denotes the therapy has been taken during that interval, which includes hormone therapy, radiotherapy, or surgery, which totally forms six classes. The Model classifies one class vs. the rest at each node, which makes the tree-based model creates five nodes. The model is trained using a set of standard classifiers based on a comprehensive study dataset that includes genomic profiles and clinical information of 347 patients. A combination of feature selection methods and a prediction method are applied on each node to identify the genes that can predict the class at that node, the identified genes for each class may serve as potential biomarkers to the class’s treatment for better survivability. The results show that the model identifies the classes with high-performance measurements. An exhaustive analysis based on relevant literature shows that some of the potential biomarkers are strongly related to breast cancer survivability and cancer in general.

show abstract

“…In this work, we extend an earlier method 6 that was used to predict the proper treatment therapy for better survivability, which is based on gene expression data in breast cancer by handling the multiclass problem using a greedy method of one-vs-rest classification model. In our earlier model, the survival periods of the patients vary, whereas in the proposed model, the only patients are considered to be survived who lived for more than 5 years after receiving the treatment.…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Identifying Relevant Genes for Breast Cancer Survivability on Specific Therapies

Tabl

Alkhateeb

Pham

et al. 2018

Evol Bioinform Online

Self Cite

View full text Add to dashboard Cite

Analyzing the genetic activity of breast cancer survival for a specific type of therapy provides a better understanding of the body response to the treatment and helps select the best course of action and while leading to the design of drugs based on gene activity. In this work, we use supervised and nonsupervised machine learning methods to deal with a multiclass classification problem in which we label the samples based on the combination of the 5-year survivability and treatment; we focus on hormone therapy, radiotherapy, and surgery. The proposed nonsupervised hierarchical models are created to find the highest separability between combinations of the classes. The supervised model consists of a combination of feature selection techniques and efficient classifiers used to find a potential set of biomarker genes specific to response to therapy. The results show that different models achieve different performance scores with accuracies ranging from 80.9% to 100%. We have investigated the roles of many biomarkers through the literature and found that some of the discriminative genes in the computational model such as ZC3H11A, VAX2, MAF1, and ZFP91 are related to breast cancer and other types of cancer.

show abstract

Machine Learning Model for Identifying Gene Biomarkers for Breast Cancer Treatment Survival

Cited by 5 publications

References 2 publications

A Hybrid Machine Learning Approach to Screen Optimal Predictors for the Classification of Primary Breast Tumors from Gene Expression Microarray Data

A Hybrid Machine Learning Approach to Screen Optimal Predictors for the Classification of Primary Breast Tumors from Gene Expression Microarray Data

A Machine Learning Approach for Identifying Gene Biomarkers Guiding the Treatment of Breast Cancer

A Novel Approach for Identifying Relevant Genes for Breast Cancer Survivability on Specific Therapies

Contact Info

Product

Resources

About