Gene expression and cancer classification

This paper introduces a Bayesian framework to detect gene expression outliers in single samples by creating a consensus background distribution without requiring a manual comparison set.

The paper introduces gene selection methods to identify key biomarkers in cancer data, showing improved classification and pathway detection compared to existing methods.

The paper introduces a non-parametric specificity score to identify tissue-specific genes from unbalanced datasets and applies it to GTEx data.

This paper introduces a statistical nonparametric method to identify consistently important features across samples and demonstrates its application to RNA sequencing data.

iSeqQC is an expression-based quality control tool that detects outliers caused by batch effects or phenotypic dissimilarity using statistical methods.

M3C improves consensus clustering by simulating null distributions to reduce bias and false positives in determining the number of clusters.

The paper normalizes gene expression data using multiple housekeeping genes to identify consistent genetic correlations in breast cancer, finding that multiple gene normalization improves correlation consistency compared to single gene normalization.

This paper introduces a graph-based normalization algorithm for RNA-seq data that improves reference transcript recovery and normalization quality without relying on prior assumptions or reference transcripts.

AOE integrates gene expression data from GEO, AE, and GEA, providing a unified search tool accessible via the GEA website.

The paper develops a Bayesian method to improve gene expression signal detection in LINCS L1000 data, showing better reliability and informativeness than existing approaches.

The paper introduces an ensemble classifier using XGBoost to robustly classify tumor samples into six immune subtypes based on gene-level features.

This study identifies a three-gene biomarker panel for hepatocellular carcinoma using large-scale transcriptomics data, showing high accuracy and prognostic potential across multiple platforms.

The paper constructs a colorectal cancer diagnosis model using expression profiles and a BPNN algorithm, achieving high accuracy and AUC values.

The paper evaluates zero-handling models in genomic and microbiome data, showing significant disagreement in identifying differentially expressed sequences and finding simple count models sufficient across processes.

The paper uses independent component analysis on bulk tissue microarrays to derive gene expression signatures that reveal biologically relevant transcriptional modules in Drosophila brain tissues.

This paper introduces a deep learning-based clustering method for gene expression data that integrates biological information, outperforming existing methods on yeast and human datasets.

DrEdGE is a web-based tool that allows genomicists to create interactive visualizations of RNA-seq datasets, enabling non-experts to explore and query data for gene and pattern discovery.

The paper introduces qtQDA, a classification method for RNA-seq data that uses quantile transformation and regularized QDA, showing good performance on real datasets.

consensusDE identifies consistent differential expression across RNA-seq algorithms while integrating RUV correction to improve stability.

AdaTiSS provides a data-adaptive method to quantify tissue specificity scores for genes, improving comparability across tissues and genes.

This study evaluates how cluster analysis choices affect cancer subtype identification using four human cancer datasets, finding that sample size has limited impact while heterogeneity and subtype distribution significantly influence performance.

This paper improves cancer subtyping by fusing pan-transcriptomics data, using Monte-Carlo consensus clustering, and creating deep classifiers, identifying six novel pancreatic ductal adenocarcinoma subtypes with better reproducibility.

PROMO is a tool for analyzing multi-omic cancer datasets with clinical labels, enabling subtype discovery and biomarker identification without coding.

DeepMF improves subtype discovery and data recovery in cancer omics data by handling noise and missing values with a deep learning-based matrix factorization model.

This study evaluates 11 feature selection methods across 27 biomedical datasets to determine their performance based on data complexity and provides recommendations for method selection.

This paper introduces a corrected estimator for mutual information that accounts for measurement error, showing improved accuracy in simulated and real gene expression data.

The paper introduces a data-driven approach to identify reliable biomarkers across platforms for single-sample classification, showing improved performance in tumor type and molecular status classification.

The paper investigates how technical noise affects bulk RNA-seq differential gene expression analysis and proposes noise-adjustment methods to improve consistency across tools.

EBADIMEX detects joint differential expression and methylation and classifies cancer samples using empirical Bayes methods and moderated tests.

PCAGO is a web tool that uses PCA to analyze RNA-Seq data, offering normalization, filtering, visualization, and parameter selection to improve clustering and interpretation.