Gene expression and cancer classification

The paper introduces methods to generate correlated omics data for benchmarking, showing improved performance in DESeq2 and CYCLOPS when dependencies are included.

The paper introduces fastBMC, an algorithm that accelerates the identification of bivariate monotonic classifiers, improving classification performance on clinical datasets.

This paper introduces QRscore, a non-parametric test for detecting distributional shifts in gene expression, showing it outperforms existing methods in detecting variance and mean shifts.

The paper introduces EGNF, a graph-based framework for biomarker discovery that outperforms traditional methods in classification accuracy and interpretability across cancer datasets.

This paper introduces an autoencoder with orthogonal constraints for multi-omics data integration, showing improved reconstruction and classification performance on cancer data.

This study evaluates TabPFN's performance on high-dimensional RNA-seq data and finds that adaptations underperform compared to classical methods when using full feature sets.

EPCY ranks genes by predictive power using cross-validated classifiers and density estimation, outperforming DEG-based methods in selecting robust candidate genes.

The paper introduces anticlustering to balance batches and minimize batch effects in high-throughput sequencing, showing improved balance compared to existing methods.

The paper evaluates the reliability of NanoString Neuropathology panel measurements for mouse hippocampal gene expression and finds low reliability.

This review evaluates SVM-based cancer detection models using multi-omic data, highlighting their potential but noting limitations in generalizability due to lack of external validation.

This study uses machine learning and explainable AI to identify potential staging biomarkers in lung squamous cell carcinoma using TCGA-LUSC gene expression data.

This study applies Multiblock Lasso to RNA-Seq PANCAN data to select significant genes for cancer classification, demonstrating effective dimensionality reduction and accuracy maintenance.

This study uses transcriptomics and machine learning to identify signature genes and pathways in colon cancer, finding high classification accuracy and potential biomarkers.

The paper introduces AUC hyper-stability scores to improve the selection of Random Forest implementations for stable short biomarker signature discovery.

SurfacOmics is an R shiny application that identifies gene biomarkers using Elastic-Net Regularization and integrates biological knowledge for interpretation.

CLAMP integrates genetic associations and drug signatures with large-scale RNA-seq data to identify interpretable gene modules linked to complex diseases.

This study uses the Gini Index to compare gene expression specialization between normal and tumor cells, finding that tumor cells show reduced specialization.

This paper reviews the use of deep representation learning, particularly VAEs, in cancer omics to model temporal processes, highlighting limitations in capturing cancer progression dynamics.

This study develops SRT-CD, a machine learning system using tumor- and tissue-specific RNA transcripts to diagnose cancers and determine tissue origin with high accuracy.

RNAcare integrates clinical and transcriptomic data for bulk RNA-Seq analysis, enabling hypothesis generation about gene expression-clinical symptom relationships in rheumatoid arthritis.

CorrAdjust improves RNA-RNA correlation analysis by removing hidden confounders, enhancing the detection of biologically relevant interactions in human RNA-seq data.

MettleRNASeq improves RNA-Seq analysis by integrating machine learning to identify key genes and relationships in complex datasets, outperforming traditional methods in radiotherapy studies.

RPSLearner improves NSCLC subtype classification using random projection and stacking learning, achieving higher accuracy and AUC than existing methods.

GTEx_Pro preprocesses GTEx v8 data using TMM+CPM normalization and SVA batch correction to enhance multi-tissue analysis accuracy and reduce systematic variation.

This paper evaluates filter-based feature selection methods on microarray datasets, finding that mRMR outperforms others in classification accuracy, F1-score, and RMSE.

sampleclusteR automates clustering of transcriptomics samples using metadata from GEO and ArrayExpress, correctly grouping most samples across multiple datasets.

The paper introduces an ensemble framework for differential analysis that combines multiple models to improve performance across various omics data types.

This paper introduces AHALA, a novel optimization method for miRNA-based breast cancer subtyping, achieving high accuracy and identifying key miRNAs associated with subtypes.