Gene expression and cancer classification

l1kdeconv: an R package for peak calling analysis with LINCS L1000 data

The paper introduces an R package for deconvolution of LINCS L1000 data using outlier detection and aggregate Gaussian mixture modeling, showing improved stability and performance.

Smooth Quantile Normalization

This paper introduces a normalization method for genomic data that accounts for biological differences in distributions while reducing technical variation.

Tradict enables accurate prediction of eukaryotic transcriptional states from 100 marker genes

Tradict predicts transcriptome-wide gene abundances and transcriptional programs using 100 marker genes, showing robustness and accuracy across 23,000 RNA-Seq datasets.

RNA-Seq 2G: Online Analysis Of Differential Gene Expression With Comprehensive Options Of Statistical Methods

RNA-Seq 2G provides a web portal with 25 differential expression methods for RNA-seq data, showing that data distribution assumptions significantly affect results.

blkbox: Integration Of Multiple Machine Learning Approaches To Identify Disease Biomarkers

blkbox integrates nine machine learning algorithms to identify disease biomarkers by selecting the best classifier for a dataset, offering feature selection and visualization without parameter optimization.

Lowest expressing microRNAs capture indispensable information - identifying cancer types

This study identifies cancer types using lowly expressed microRNAs from TCGA data, achieving 91% recall after data discretization.

Differential Expression Analysis for RNAseq using Poisson Mixed Models

This paper introduces a Poisson mixed model for differential expression analysis in RNAseq, accounting for over-dispersion and sample non-independence, showing improved power in real data.

Similarity identification in gene expression patterns as a new approach in phenotype classification

This paper introduces SIGN, a method for phenotype classification using gene expression patterns, showing it can classify cancer subtypes, identify cell types, and classify drugs based on mechanism of action.

PatternMarkers & GWCoGAPS for novel data-driven biomarkers via whole transcriptome NMF

The paper introduces PatternMarkers and GWCoGAPS to identify data-driven biomarkers from whole-genome data using NMF, demonstrating their application on GTex data.

Designing the database for microarray experiments metadata

The paper describes the creation of a specialized database for microarray experiments and demonstrates its use with 32 placenta datasets under pre-eclampsia conditions.

Classification of RNA-Seq Data via Gaussian Copulas

This paper introduces a Gaussian copula-based method for RNA-Seq classification that accounts for gene dependencies, improving accuracy over independence-based models.

Cox-nnet: an artificial neural network Cox regression for prognosis prediction

Cox-nnet improves prognosis prediction using high-throughput transcriptomics data with higher accuracy than existing methods and provides biological insights.

Transformation and model choice for RNA-seq co-expression analysis

This paper investigates data transformations and model selection for RNA-seq co-expression analysis using Gaussian mixture models and proposes an R package for implementation.

Exploiting expression patterns across multiple gene isoforms to identify radiation response biomarkers in early-stage breast cancer patients.

The paper introduces two statistical methods to identify radiation response biomarkers in early-stage breast cancer by analyzing gene isoform expression patterns.

limma powers differential expression analyses for RNA-sequencing and microarray studies

limma couples gene-wise linear models with empirical Bayes variance moderation and weights; voom extends it to RNA-seq, and added functions test differential splicing and gene sets.

Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2

DESeq2 uses empirical Bayes priors to shrink negative binomial dispersions and log fold changes, giving reproducible effect sizes and error-controlled differential expression calls for RNA-seq.