Gene expression and cancer classification

This paper introduces BalanceIT, a method using genetic algorithms to balance clinical factors in RNA-Seq studies, improving differential gene expression and pathway analysis in autism research.

BlackSheep identifies molecules aberrantly enriched in small sample cohorts using non-parametric differential extreme value analysis.

WMW-A improves test power for small sample two-sample tests by using an auxiliary sample to construct a three-sample rank-based statistic.

The paper analyzes 2,692 gene expression datasets to show tissue heterogeneity affects 5-15% of samples, advocating for quality control methods to address this issue.

The paper introduces K2Taxonomer, an unsupervised algorithm for identifying molecular subgroups in bulk and single-cell transcriptomics data, and applies it to breast cancer TILs to find a shared transcriptional program associated with better prognosis.

This study uses tensor decomposition-based unsupervised feature extraction to identify differentially expressed transcripts in planarian RNA-seq data with a highly redundant de novo transcriptome, outperforming conventional methods.

GenomicSuperSignature compares new RNA-seq datasets to public archives for rapid interpretation using precomputed axes of variation.

This paper introduces SOPHIE, a method using generative neural networks to distinguish common from specific transcriptional responses across datasets.

iSubGen generates disease subtypes by integrating multiple data types, handling missing data and identifying clinically distinct patient groups.

The paper introduces Target-Decoy MineR to assess the biological relevance of variables in noisy datasets by calculating false-positive rates and biological relevance probabilities.

The paper develops a deep learning framework to integrate multi-omics data for cancer prognosis, showing improved risk prediction across 15 cancers and identifying prognostic markers in breast cancer.

noisyR reduces technical noise in sequencing data to enhance biological signal detection and improve downstream analysis consistency.

The paper was withdrawn by the authors and not intended for citation.

The paper evaluates generative models for sample augmentation in microarray datasets, comparing VAE, GAN, and GMM in a tuberculosis dataset to improve biomarker discovery.

The paper evaluates the transcriptional fidelity of cancer models using a machine learning tool called CancerCellNet, finding that genetically engineered mice and tumoroids generally show higher fidelity than other model types.

The paper benchmarks RNA-seq association analyses for continuous exposures using DESeq2, edgeR, limma, and linear regression, finding linear regression methods are faster and better at controlling false detections.

This paper introduces PAN, a method to create sample-specific gene networks using annotations, improving breast cancer relapse prediction compared to existing methods.

The paper introduces a statistical test for detecting heterogeneous effects in omics data and shows its ability to identify disease-relevant genes missed by traditional methods.

This paper introduces GAIN-GTEx, a gene expression imputation method that outperforms existing approaches on RNA-Seq data from cancer types and diverse tissues.

The paper uses machine learning and differential expression analysis to identify secretory pathway genes associated with cancer characteristics, finding KIF20A and KIF23 as key genes across multiple cancer types.

The paper introduces an R package for divergence analysis of omics data, demonstrating its use with Cancer Genome Atlas data.

This study predicts tissue-specific gene expression from whole blood transcriptome using GTEx data, finding that blood expression can predict expression in many tissues and improve disease prediction.

SpinAdapt is an unsupervised RNA correction algorithm that enables transfer of molecular models between labs without requiring patient-level data, improving reproducibility and privacy.

This paper evaluates and adapts the CONSTANd normalization method for use with count data from sequencing, showing its efficiency and ability to remove bias across different experimental conditions.

This study compares sparse biclustering algorithms on simulated and real datasets, finding Bayesian algorithms with sparsity constraints perform well on simulated data but are slow, while post-processed non-negative matrix factorization algorithms show strong performance on real datasets.

The paper identifies 46 core genes in Pseudomonas aeruginosa PAO1 associated with multiple perturbations using a machine learning approach.

This study evaluates deconvolution methods for gene expression data using an open innovation competition and finds that random forest regression outperforms other approaches in accuracy and reproducibility.

This study analyzes the prognostic impact of cancer hallmark genes across 26 tumor types using RNA-seq and survival data from TCGA, identifying significant gene-expression associations with patient outcomes.

The paper compares two models for correcting cell type composition in blood gene expression data, finding that accounting for more cell types reduces the number of age-associated genes and highlights platelet-related pathways.

The paper develops ImageCCA to link histological image features with gene expression, identifying gene-morphology associations in TCGA and GTEx data.