iPcc: a novel feature extraction method for accurate disease class discovery and prediction
Xianwen Ren1, Yong Wang, Xiang-Sun Zhang
1MOH Key Laboratory of Systems Biology of Pathogens, Institute of Pathogen Biology, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China.
Nucleic Acids Research
|June 14, 2013
Summary
A new method, iPcc, enhances gene expression profiling for disease diagnosis. By creating a "correlation feature space," it improves the accuracy and robustness of existing classification algorithms using noisy gene expression data.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Gene expression profiling is crucial for disease diagnosis and classification.
- Numerous computational methods have advanced feature selection, classification, and clustering.
- Translational research requires improved accuracy and robustness in these analyses.
Purpose of the Study:
- To introduce iPcc, a novel feature extraction method for gene expression profiling.
- To enhance the accuracy and robustness of disease diagnosis and classification.
- To bridge the gap between laboratory findings and clinical applications.
Main Methods:
- Development of iPcc, a novel feature extraction technique.
- Definition of a 'correlation feature space' using iterative Pearson's correlation coefficient.
- Application to simulated and real gene expression datasets.
Main Results:
- iPcc effectively highlights latent patterns in noisy gene expression data.
- Demonstrated significant improvements in the robustness of classification algorithms.
- Showcased enhanced accuracy for disease diagnosis and classification.
Conclusions:
- iPcc offers a powerful approach to gene expression data analysis.
- The method improves the reliability of computational tools for clinical applications.
- iPcc facilitates the translation of gene expression profiling from research to clinical practice.
Related Concept Videos
01:17Classification of Illness
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...
01:26Classification of Systems-I
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as: