A robust meta-classification strategy for cancer diagnosis from gene expression data

2005 ◽  
Author(s):  
G. Alexe ◽  
G. Bhanot ◽  
B. Venkataraghavan ◽  
R. Ramaswamy ◽  
J. Lepre ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Cancer Diagnosis ◽  
Expression Data ◽  
Classification Strategy

scholarly journals Analyzing gene expression data for pediatric and adult cancer diagnosis using logic learning machine and standard supervised methods

2019 ◽  
Vol 20 (S9) ◽  
Author(s):  
Damiano Verda ◽  
Stefano Parodi ◽  
Enrico Ferrari ◽  
Marco Muselli
Keyword(s):  
Gene Expression ◽  
Gene Expression Data ◽  
Cancer Diagnosis ◽  
Cancer Biology ◽  
Nearest Neighbor ◽  
Support Vector ◽  
Expression Data ◽  
Network Support ◽  
Supervised Methods ◽  
Learning Machine

Abstract Background Logic Learning Machine (LLM) is an innovative method of supervised analysis capable of constructing models based on simple and intelligible rules. In this investigation the performance of LLM in classifying patients with cancer was evaluated using a set of eight publicly available gene expression databases for cancer diagnosis. LLM accuracy was assessed by summary ROC curve (sROC) analysis and estimated by the area under an sROC curve (sAUC). Its performance was compared in cross validation with that of standard supervised methods, namely: decision tree, artificial neural network, support vector machine (SVM) and k-nearest neighbor classifier. Results LLM showed an excellent accuracy (sAUC = 0.99, 95%CI: 0.98–1.0) and outperformed any other method except SVM. Conclusions LLM is a new powerful tool for the analysis of gene expression data for cancer diagnosis. Simple rules generated by LLM could contribute to a better understanding of cancer biology, potentially addressing therapeutic approaches.

Cancer Data Classification by Quantum Inspired Immune Clone Optimization-based Optimal Feature Selection using Gene Expression Data: Deep Learning Approach (Preprint)

2020 ◽  
Author(s):  
Nageswara Rao Eluri
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Feature Selection ◽  
Gene Expression Data ◽  
Cancer Diagnosis ◽  
Classification Accuracy ◽  
Expression Data ◽  
Cancer Data ◽  
Optimal Feature Selection ◽  
Optimal Feature

UNSTRUCTURED Gene selection is considered as the fundamental process under the bioinformatics field, as the cancer classification accuracy completely focused on the genes, which provides biological relevance to the classifying problems. The accurate classification of diverse types of tumor is seeking immense demand in the cancer diagnosis task. However, the existing methodologies pertain to cancer classification are mostly clinical basis, and so its diagnosis capability is limited. Nowadays, the significant problems of cancer diagnosis are solved by the utilization of gene expression data, by which, the researchers have been introducing many possibilities to diagnose cancer in an appropriate and effective way. This paper plans to develop the cancer data classification using gene expression data. Initially, five benchmark gene expression datasets, i.e., “Colon cancer, defused B-cell Lymphoma, Leukaemia, Wisconsin Diagnostic Breast Cancer and Wisconsin Breast Cancer Data” are collected for performing the experiment. The proposed classification model involves three main phases: “(a) Feature extraction, (b) Optimal Feature Selection, and (c) Classification”. From the collected gene expression data, the feature extraction is performed using the first order and second-order statistical measures after data pre-processing. In order to diminish the length of the feature vectors, optimal feature selection is performed, in which a new meta-heuristic algorithm termed as Quantum Inspired Immune Clone Optimization Algorithm (QICO) is used. Once the relevant features are selected, the classification is performed by a deep learning model called Recurrent Neural Network (RNN). Moreover, the number of hidden neurons of RNN is optimized by the same Q-ICOA. The optimal feature selection and classification is performed for selecting the most suitable features and thus maximizing the classification accuracy. Finally, the experimental analysis reveals that the proposed model outperforms the QICO-based feature selection over other heuristic-based feature selection and optimized RNN over other machine learning algorithms

Sign in / Sign up

Export Citation Format

Share Document