A Comparative Analysis of Feature Selection Algorithms for Cancer Classification Using Gene Expression Microarray Data
Bibliographic record
Abstract
DNA Microarray technology allows simultaneous analysis of gene expression levels, making it useful in cancer classification.However, analyzing Microarray data is challenging due to the large number of genes and their sparsity.Feature selection has emerged as an effective method to overcome these challenges.This research aims to study the impact of three well-known feature selection algorithms (ReliefF, Chi Square, and ANOVA) in enhancing the accuracy of gene expression profile classification.A three-stage approach was employed: data preprocessing, feature selection, and feature classification.The focus is on selecting relevant features to accurately represent the problem under study.Four classifiers, i.e., SVM, GNB, LDA, and KNN, were evaluated using the aforementioned feature selection algorithms.The proposed methodology was tested on 10 publicly available gene expression datasets.Using all genes, the SVM classifier showed the best accuracy and F1 scores, followed by the LDA classifier.When applying the ReliefF feature selection algorithm, the SVM classifier performed best with a 5% dataset ratio.Moreover, the ANOVA feature selection algorithm yielded optimal results with the SVM classifier at dataset ratios of 3%, 4%, and 5%.Lastly, the Chi-square feature selection consistently produced the best results with both SVM and GNB classifiers for all dataset ratios.The study underscores the significance of feature selection for improving gene expression profile classification accuracy.The findings of this research offer promising insights into the analysis of microarray data, which can be instrumental in enhancing the accuracy of cancer classification.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".