Gene expression and cancer classification

The Effects of Nonlinear Signal on Expression-Based Prediction Performance

This study compares neural networks and logistic regression for transcriptomic prediction, finding both linear and non-linear signals are present but not always sufficient for neural networks to outperform linear models.

Integrated Analysis of Tissue-specific Gene Expression in Diabetes by Tensor Decomposition Can Identify Possible Associated Diseases.

The paper improves a tensor decomposition method for integrating gene expression profiles from multiple tissues and identifies disease associations beyond individual tissue analyses.

Use of a graph neural network to the weighted gene co-expression network analysis of Korean native cattle

The paper introduces gmcNet, a graph neural network for WGCNA module clustering, showing improved performance in modularity and differential expression compared to existing methods in Korean native cattle.

Wilcoxon rank-sum test still outperforms dearseq after accounting for the normalization impact in semi-synthetic RNA-seq data simulation

The paper re-evaluates differential expression methods on semi-synthetic RNA-seq data without normalization, finding the Wilcoxon rank-sum test still outperforms dearseq in FDR control and power.

Accurate pan-cancer tumor purity estimation from gene expression data

This paper introduces PUREE, a method to estimate tumor purity from gene expression data, achieving high accuracy across multiple cancer types and outperforming existing methods.

OmicSelector: automatic feature selection and deep learning modeling for omic experiments.

OmicSelector automates feature selection and deep learning modeling for omic experiments, identifying overfitting-resistant biomarker sets with high diagnostic potential.

A sparse negative binomial classifier with covariateadjustment for RNA-seq data

The paper develops a sparse negative binomial classifier for RNA-seq data that adjusts for covariates and improves prediction accuracy and feature selection.

MATTE: anti-noise module alignment for phenotype-gene-related analysis

MATTE identifies differentially expressed genes and modules in noisy transcriptome data, improving analysis of phenotype-related biological insights.

sMAP: An interactive microarray data analysis tool for early-stage researchers

sMAP is an interactive tool for microarray data analysis designed for early-stage researchers, enabling differential gene expression analysis and biomarker discovery with educational resources.

TransCell: In silico characterization of genomic landscape and cellular responses from gene expressions through a two-step deep transfer learning

TransCell predicts genomic and cellular responses from gene expression using transfer learning, achieving strong performance in drug sensitivity and gene effect score prediction.

Comprehensive Analysis of Ubiquitously Expressed Genes in Human, From a Data-Driven Perspective

The paper identifies ubiquitously expressed genes (UEGs) in humans using a data-driven approach and provides their global expression patterns as a resource for further study.

A Pairwise Imputation Strategy for Retaining Predictive Features When Combining Multiple Datasets

This paper proposes a pairwise imputation strategy to retain predictive features when combining genomic datasets, showing improved performance over using only common features.

Generalizing predictions to unseen sequencing profiles via deep generative models

This study introduces DeepBioGen, a deep generative model for augmenting sequencing profiles to improve prediction model generalizability on unseen data.

Mutually exclusive spectral biclustering and its applications in cancer subtyping

This paper introduces MESBC, a mutually exclusive biclustering algorithm that improves cancer subtyping accuracy and identifies clinically relevant subtypes in lung and breast cancer datasets.

Fast and robust imputation for miRNA expression data using constrained least squares

The paper introduces a fast and accurate imputation method for miRNA expression data using constrained least squares, outperforming existing methods in speed and accuracy.

The Decision of the Optimal Rank of a Non-negative Matrix Factorization Model for Gene Expression Datasets Utilizing Unit Invariant Knee Method

This paper introduces the unit invariant knee method to determine the optimal rank for non-negative matrix factorization of gene expression datasets, showing it works well on real and simulated data.

MoSBi: Automated signature mining for molecular stratification and subtyping

MoSBi automates biclustering analysis across multi-omics data to identify robust molecular signatures for stratification and subtyping.

ReDisX: a Continuous Max Flow-based framework to redefine the diagnosis of diseases based on identified patterns of genomic signatures

ReDisX redefines disease diagnosis by classifying patients based on genomic signatures, revealing disease subpopulations and identifying GZMB as a potential drug repurposing marker.

Comprehensive evaluation of machine learning models and gene expression signatures for prostate cancer prognosis using large population cohorts

This study evaluates 15 machine learning algorithms and 30 gene expression signatures for prostate cancer prognosis using 1,558 patients, finding survival analysis models outperform binary classifiers and identifying top signatures comparable to commercial panels.

ExhauFS: exhaustive search-based feature selection for classification and survival regression

ExhauFS performs exhaustive feature selection for classification and survival regression, demonstrating its utility on cancer datasets.

Transcriptome diversity is a systematic source of bias in RNA-sequencing data

The paper identifies transcriptome diversity as a major source of systematic bias in RNA-seq data and shows it explains significant variability in gene expression across organisms and datasets.

A large-sample crisis? Exaggerated false positives by popular differential expression methods

The paper shows that popular differential expression methods like DESeq2 and edgeR have high false discovery rates in population-level RNA-seq data, recommending the Wilcoxon rank-sum test instead.

Benchmarking 50 classification algorithms on 50 gene-expression datasets

The paper benchmarks 50 classification algorithms on 50 gene-expression datasets to evaluate their performance in patient subgroup classification.

Powerful and interpretable control of false discoveries in differential expression studies

The paper introduces adaptive interpolation-based post hoc methods for differential expression studies to provide stronger statistical guarantees on false discoveries.

Deep learning-based pan-cancer classification model reveals cancer-specific gene expression signatures

This study uses deep learning to classify 37 cancer types from TCGA data, identifying cancer-specific gene expression signatures with >97% accuracy.

ERROR MODELLED GENE EXPRESSION ANALYSIS (EMOGEA) PROVIDES A SUPERIOR OVERVIEW OF TIME COURSE RNA-SEQ MEASUREMENTS AND LOW COUNT GENE EXPRESSION

EMOGEA improves RNA-seq analysis by incorporating measurement uncertainty, enhancing interpretation of time-course and low-count gene expression data.

ALOHA: Aggregated local extrema splines for high-throughput dose-response analysis

ALOHA improves dose-response analysis by using Bayesian splines to model gene responses and cluster co-regulated genes, leading to better identification of biological pathways and benchmark doses.

Two-stage Linked Component Analysis for Joint Decomposition of Multiple Biologically Related Data Sets

The paper introduces 2s-LCA, a method for joint analysis of multiple biological data sets, and applies it to human brain development data to identify shared gene expression patterns.

PairGP: Gaussian process modeling of longitudinal data from paired multi-condition studies

PairGP models longitudinal gene expression data from paired multi-condition studies to identify condition groups with different dynamics.

Identification of differentially distributed gene expression and distinct sets of cancer-related genes identified by changes in mean and variability

The paper identifies cancer-related genes by analyzing changes in gene expression variability and distribution, finding distinct sets of genes missed by traditional differential expression analysis.