Gene expression and cancer classification

Simulation study of factors affecting the accuracy of transcriptome models under complex environments

This study identifies key factors affecting field transcriptome model accuracy through simulation and validation with real data, showing gene expression patterns, sample size, and environmental coverage are most influential.

A flexible framework for minimal biomarker signature discovery from clinical omics studies without library size normalisation

This paper introduces FS-PLS, a feature selection method that generates minimal disease signatures from omics data without requiring library size normalization, achieving smaller and comparable performance to existing methods.

Performance Assessment of an Unsupervised Variable Selection Approach for Biomarker Discovery and Glioblastoma Subtyping

This study evaluates unsupervised variable selection methods for high-dimensional omics data and introduces TRIM-IT, a tool that identifies glioblastoma subtypes with distinct molecular profiles and survival outcomes.

Transcriptome Complexity Disentangled: A Regulatory Molecules Approach

This study identifies a small set of transcription factors and microRNAs that can predict genome-wide gene expression across multiple cancer types with high accuracy.

FROM CANCER MOLECULAR SUBTYPE TO AI HYPE: BENCHMARKING AI IN CANCER MOLECULAR SUBTYPING

This study benchmarks 35 AI classifiers across 153 cancer datasets to evaluate their performance in molecular subtype classification, identifying optimal data configurations and model types for different omics modalities and cancer types.

The effect of cold ischemia time on hypoxia, EMT, and apoptosis pathways in normal colon mucosa

This study evaluates how cold ischemia time affects gene expression in normal colon mucosa, identifying transcriptomic changes in hypoxia, EMT, and apoptosis pathways that may mimic malignancy.

A novel visual analysis interface enables integrative analyses of cancer transcriptomics data and iden-tifies potential markers of immunotherapy response via machine learning.

The paper introduces TCGEx, a web-based tool for analyzing cancer transcriptomics data, identifies microRNAs and cytokines linked to immunotherapy response in melanoma.

Machine learning reveals novel targets for both glioblastoma and osteosarcoma

This study uses machine learning to identify novel shared targets in glioblastoma and osteosarcoma, revealing C2ORF72 as a potential therapeutic and diagnostic target.

RCE-IFE: Recursive Cluster Elimination with Intra-cluster Feature Elimination

RCE-IFE reduces feature set size and improves model performance by recursively eliminating low-scoring feature clusters and intra-cluster features in a supervised setting.

Robust Prediction of Patient-Specific Cancer Hallmarks Using Neural Multi-Task Learning: a model development and validation study

This paper develops OncoMark, a neural multi-task learning framework to predict cancer hallmark activities from transcriptomics data, achieving high accuracy across internal and external datasets.

What is a differentially expressed gene?

The paper compares binary and rank-based methods for identifying differentially expressed genes using Bayesian statistics on a yeast dataset, highlighting issues with traditional thresholds and advocating for rank-based approaches.

Stable breast cancer prognosis

This paper introduces DGBCox, a stable prediction method for breast cancer prognosis under data distribution shift, showing improved accuracy and stability compared to existing methods.

Symmetry as a Fundamental Principle in Defining Gene Expression and Phenotypic Traits

The paper identifies invariant feature genes (IFGs) using a symmetric machine learning approach to distinguish healthy from disease states and finds drug targets in cancer IFGs.

A Bayesian framework for ranking genes based on their statistical evidence for differential expression

This paper introduces a Bayesian framework for differential gene expression analysis that ranks genes based on statistical evidence rather than binary classification, improving transparency and computational efficiency.

Biologically relevant integration of transcriptomics profiles from cancer cell lines, patient-derived xenografts and clinical tumors using deep learning

MOBER integrates transcriptomic data from cancer cell lines, xenografts, and clinical tumors using deep learning to remove batch effects and improve clinical translatability.

Interpreting Lung Cancer Health Disparity at Transcriptome Level

This study identifies biomarker genes and pathways contributing to lung cancer health disparities using a classification framework with SHAP to interpret disparities between racial and sex groups.

edgeR v4: powerful differential analysis of sequencing data with expanded functionality and improved support for small counts and larger datasets

edgeR v4 adds a continuous negative binomial for fractional counts, bias-corrected quasi-likelihood for small counts, C-based fitting, and new transcript, exon, methylation and fold-change-threshold analyses.

Learning robust gene expression embeddings for disease subtyping, biomarker identification and cross-species alignment

This paper introduces JECCA, a method for identifying shared biological signals across gene expression datasets, enabling disease subtyping, biomarker discovery, and cross-species analysis.

Multivariate optimization of k for k-nearest-neighbor feature selection with dichotomous outcomes: complex associations, class imbalance, and application to RNA-Seq in Major Depressive Disorder

The paper develops and evaluates methods for optimizing k in k-nearest-neighbor feature selection for imbalanced data, showing improved performance on RNA-Seq data from Major Depressive Disorder.

Phenotype Driven Data Augmentation Methods for Transcriptomic Data

This paper introduces phenotype-driven data augmentation methods for transcriptomic data, showing improvements in patient stratification over existing approaches.

Highly Effective Batch Effect Correction Method for RNA-seq Count Data

The paper introduces ComBat-ref, a batch effect correction method for RNA-seq data that improves sensitivity and specificity over existing methods.

Predicting plant traits using large conglomerate RNA-seq datasets

The paper predicts plant phenotypic traits using RNA-seq datasets and finds that few hundred samples suffice for tissue classification but thousands are needed for age prediction.

Predicting Tissue of Origin from Bulk Tumor Gene Expression using a Pre-trained Transformer Model

The paper develops a pre-trained transformer model to predict cancer tissue of origin from bulk gene expression data, achieving high accuracy across 32 tissue types.

Mutual information for detecting multi-class biomarkers when integrating multiple bulk or single-cell transcriptomic studies

The paper introduces MICA, a method to detect multi-class biomarkers across multiple transcriptomic studies, showing improved accuracy and biological insights in both bulk and single-cell data.

CPSM: R-package of an Automated Machine Learning Pipeline for Predicting the Survival Probability of Single Cancer Patient

The paper introduces CPSM, an R package that provides an automated machine learning pipeline for predicting individual cancer patient survival probabilities using multi-omics data.

Topological embedding and directional feature importance in ensemble classifiers for multi-class classification

The paper introduces a directional feature importance metric for decision tree classifiers and evaluates its performance on cancer proteomics data using multiple algorithms.

MAGE: Monte Carlo method for Aberrant Gene Expression

MAGE identifies aberrantly expressed genes by analyzing entire expression profiles rather than individual genes, outperforming conventional differential expression and density-based clustering methods.

Tracking cancer dynamics from normal tissue to malignancy using perfect N- and T-gene expression markers

The paper analyzes gene expression dynamics in normal and tumor tissues, identifying N-genes and T-genes that mark transitions to malignancy in prostate, lung, and liver cancers.

A Transformer-Based Approach to Survival Outcome Prediction

This paper adapts a pre-trained transformer model for bulk tumor data to predict patient survival outcomes, achieving strong correlations and outperforming traditional methods.

Neglecting normalization impact in semi-synthetic RNA-seq data simulation generates artificial false positives

The paper identifies an issue in RNA-seq data simulation where normalization neglect leads to false positives and provides corrected results showing dearseq's performance.