Gene expression and cancer classification

Improving the classification of neuropsychiatric conditions using gene ontology terms as features

This paper improves neuropsychiatric condition classification by using gene ontology terms as features, enhancing performance, stability, and interpretability of classifiers.

Defining common principles of gene co-expression refines molecular stratification in cancer

The paper defines common gene co-expression principles across cancers to improve molecular stratification by identifying consistent expression modules and their associations with mutation states.

Using balances to engineer features for the classification of health biomarkers: a new approach to balance selection

This paper explores using balances to engineer features for classifying health biomarkers and benchmarks transformation methods across different biomarker types.

Jackknife model averaging prediction methods for complex phenotypes with gene expression levels by integrating external pathway information

This paper introduces JMAP, a model averaging method for genetic risk prediction that integrates pathway information, showing improved accuracy over existing methods in simulations and real cancer datasets.

DNA Repair Gene Expression Adjusted by the PCNA Metagene Predicts Survival in Multiple Cancers

The paper investigates how DNA repair gene expression, adjusted by the PCNA metagene, predicts overall survival in 18 cancers using TCGA data, finding significant predictive power in 61% of cancers.

Stabilized Independent Component Analysis outperforms other methods in finding reproducible signals in tumoral transcriptomes

The paper introduces a stabilized ICA method that improves reproducibility and interpretability of transcriptomic signals across cancer datasets, and applies it to colorectal cancer.

Topconfects: a package for confident effect sizes in differential expression analysis provides improved usability ranking genes of interest

Topconfects ranks differentially expressed genes by confident log fold change effect sizes, improving biological interpretation over p-value-based rankings.

NOJAH: Not Just Another Heatmap for Genome-Wide Cluster Analysis

NOJAH is an interactive tool for genome-wide cluster analysis and heatmap construction, providing replicable results through integrated workflows and documentation.

Self-Organizing Map Methodology for Sorting Differential Expression Data of MMP-9 Inhibition

The paper uses a self-organizing map to analyze differential expression data from MMP-9 inhibitor-treated T-cells, identifying novel gene targets regulated by MMP-9.

Dissecting differential signals in high-throughput data from complex tissues

The paper develops a method to detect differential signals in high-throughput data from mixed cell-type samples and shows its superior performance through simulations and real datasets.

On triangular inequalities of correlation-based distances for gene expression profiles

This paper introduces a new distance metric, dr, that satisfies the triangular inequality for gene expression profiles and shows it provides more robust clustering than the absolute correlation distance.

Novel Data Transformations for RNA-seq Data Analysis

The paper proposes eight RNA-seq data transformations to improve analysis accuracy, showing that limma+rv and limma+l2 perform best in simulations and real data.

Deep Learning of Representations for Transcriptomics-based Phenotype Prediction

The paper evaluates representation learning techniques for transcriptomics-based phenotype prediction using public data and finds that l2-regularized regression on centered log-ratio transformed abundances performs best.

An Integrative Boosting Approach for Predicting Survival Time With Multiple Genomics Platforms

This paper introduces I-Boost, a method that improves survival time prediction by integrating multiple genomics data types with clinical variables, showing better accuracy than existing methods.

Interpretation of Omics dynamics in a single subject using local estimates of dispersion between two transcriptomes

The paper introduces iDEG, a method to identify differentially expressed genes in a single subject without replicates, showing improved accuracy over existing methods in simulations.

Analyses of cancer data in the Genomic Data Commons Data Portal with new functionalities in the TCGAbiolinks R/Bioconductor package

The paper introduces new features in the TCGAbiolinks R/Bioconductor package to improve cancer data analysis, including better differential expression analysis, tumor purity estimation, and integration of normal samples from GTEx.

Compositional Data Analysis is necessary for simulating and analyzing RNA-Seq data

The paper introduces absSimSeq, a tool for simulating RNA-Seq data that accounts for compositional data properties, and shows that compositional normalization improves differential analysis performance.

netDx: Interpretable patient classification using integrated patient similarity networks

netDx is a supervised patient classification framework that integrates diverse data types and provides interpretable results, showing high performance in cancer survival prediction.

A novel approach to modeling transcriptional heterogeneity identifies the oncogene candidate CBX2 in invasive breast carcinoma

The paper develops a statistical method to model transcriptional heterogeneity in breast tumors, identifying CBX2 as an oncogene overexpressed in invasive breast carcinoma and linked to poorer survival.

A semi-parametric Bayesian approach, iSBA, for differential expression analysis of RNA-seq data

The paper introduces a semi-parametric Bayesian method for differential expression analysis in RNA-seq data, showing improved performance over existing methods.

Deep Genomic Signature for early metastasis prediction in prostate cancer

This study introduces DGS, a method combining denoising autoencoders and transfer learning to predict prostate cancer metastasis using both labelled and unlabelled gene expression data, achieving higher accuracy than existing signatures.

SUBSTRA: Supervised Bayesian Patient Stratification

SUBSTRA is a Bayesian method for patient stratification that balances predictive performance and interpretability by using regularized biclustering and iterative feature weighting.

IRIS-EDA: An integrated RNA-Seq interpretation system for gene expression data analysis

IRIS-DGE is a server-based tool for differential gene expression analysis that integrates multiple R-based methods and provides interactive visualizations for RNA-seq data.

ACE: A Workbench using Evolutionary Genetic Algorithms for analysing association in TCGA Data

ACE identifies correlations between clinical and genomic data in TCGA using an evolutionary algorithm for efficient analysis.

Differential Principal Components Reveal Patterns of Differentiation in Case/Control Studies

The paper introduces drPCA, a supervised dimensionality reduction method that improves differentiation in case/control studies by using differential vectors, and shows it outperforms PCA and PLS-DA in cancer gene expression datasets.

MS.liverK: an R package for transcriptome-based computation of molecular subtypes and functional signatures in liver cancer

MS.liverK is an R package that implements tools for computing molecular subtypes and functional signatures in liver cancer using transcriptome data.

Iso-relevance Functions - A Systematic Approach to Ranking Genomic Features by Differential Effect Size

The paper introduces a framework to rank genomic features by differential effect size, showing that pseudocounts optimize the balance between fold-change and difference sorting.

Differential expression feature extraction (DEFE) and its application in RNA-seq data analysis

The paper introduces DEFE, a method to extract differential expression patterns from RNA-seq data, and applies it to identify genes associated with wheat resistance to Fusarium head blight.

eUTOPIA: Solution for omics data preprocessing and analysis

eUTOPIA provides an intuitive R Shiny application for preprocessing and analyzing microarray data without requiring computational expertise.

Testing for batch effect through age predictors

The paper develops a deep-learned age predictor from transcriptomic data and shows that batch effects can obscure age-related changes.