Gene expression and cancer classification

Detecting boolean asymmetric relationships with a loop counting technique and its implications for analyzing heterogeneity within gene expression datasets

The paper introduces a method to detect boolean asymmetric relationships in gene expression data, identifying heterogeneity driven by asymmetric gene interactions and showing improved classifier performance.

A Regularized Cox Hierarchical Model for Incorporating Annotation Information in Predictive Omic Studies

The paper introduces a regularized hierarchical Cox model that integrates meta-features to improve prediction and feature selection for time-to-event outcomes in omic studies.

Classical statistical methods are powerful for the identification of novel targets for the survival of breast cancer patients

This study uses classical statistical methods to identify survival-related genes in breast cancer, finding two novel targets and validating results through bootstrapping.

Replacing Normalizations with Interval AssumptionsImproves the Rigor and Robustness of DifferentialExpression and Differential Abundance Analyses

The paper introduces interval assumptions to replace normalization in differential expression and abundance analyses, reducing false positives and negatives through more realistic and flexible assumptions.

Patterns of extreme outlier RNA expression in population data reveal sporadic over-activation of genes with co-regulated modules in subsets of individuals

The paper identifies sporadic over-activation of co-regulated genes with extreme outlier RNA expression in multiple species and tissues, showing these patterns are not inherited but may reflect gene regulatory network dynamics.

Evaluating Cross-Platform Batch Correction Methods for Integrated Microarray and RNA-seq Data Analysis

This study evaluates batch correction methods for integrating microarray and RNA-seq data, finding that limma provides the best balance of Type I error control and power for differential expression analysis.

pyRforest: A comprehensive R package for genomic data analysis featuring scikit-learn Random Forests in R

pyRforest integrates Python's Random Forest algorithms into R for efficient genomic data classification and analysis, offering improved interpretability and additional statistical methods.

A Graph Informed Framework Empowering Gene Pathway Discovery and Gene Expression-Assisted Disease Classification

This paper introduces a graph-informed framework that improves gene pathway analysis and disease classification by integrating gene regulatory networks into statistical methods, showing better performance in simulations and a lung cancer dataset.

Molecular Group and Correlation Guided Structural Learning for Multi-Phenotype Prediction

The paper introduces a supervised learning algorithm for multi-phenotype genomic prediction, showing improved performance in gene expression and DNA methylation analysis and cell type deconvolution.

RCoxNet: deep learning framework for enhanced cancer survival prediction integrating random walk with restart with mutation and clinical data

RCoxNet improves cancer survival prediction by integrating mutation and clinical data with a deep learning Cox model and random walk algorithm, achieving better performance than existing models.

StableMate: a new statistical method to select stable predictors in omics data

StableMate identifies stable predictors across omics datasets to improve reproducibility and interpretability of biological associations.

RNAseqCovarImpute: a multiple imputation procedure that outperforms complete case and single imputation differential expression analysis

RNAseqCovarImpute improves differential expression analysis by handling missing covariate data through multiple imputation, outperforming complete case and single imputation methods.

Feature selection by replicate reproducibility and non-redundancy

The paper introduces RNR, a feature selection algorithm that prioritizes reproducibility across replicates and non-redundancy, applied to microscopy and proteomics data.

Higher-order correction of persistent batch effects in correlation networks

This paper introduces COBRA, a method to correct batch effects in gene co-expression networks, showing that standard batch correction does not fully eliminate spurious co-expression associations.

Gene PointNet for Tumor Classification

This paper introduces a deep learning classifier using PointNet on RNA-Seq data to classify tumors with over 99% accuracy.

Pan-Cancer Drug Response Prediction Using Integrative Principal Component Regression

This paper introduces iPCR, a model that predicts patient drug responses by integrating genomic data from cell lines and tumors, showing improved performance over existing methods.

Machine learning based identification of candidate miRNA biomarkers for micro-invasive breast cancer diagnosis

The paper uses machine learning to identify miRNA biomarkers in blood samples for diagnosing micro-invasive breast cancer, finding ten miRNAs with good classification performance.

De-biased sparse canonical correlation for identifying cancer-related trans-regulated genes

The paper introduces a de-biased sparse canonical correlation analysis pipeline to identify cancer-related trans-regulated genes from multi-omic data, finding 256 genes associated with estrogen receptor-related CNAs in breast cancer.

Statistical estimation of sparsity and efficiency for molecular codes

The paper develops statistical methods to assess molecular codes' sparsity and efficiency in characterizing cell types across C. elegans and cancer, showing homeodomain proteins and HLA genes do so more effectively than random controls.

A bootstrap model comparison test for identifying genes with context-specific patterns of genetic regulation

DRAB identifies genes with context-specific genetic regulation by comparing models across tissues using bootstrapping and elastic net.

The minimal number of genes needed to identify a tumor

The paper shows that a small number of genes can accurately classify tumor types, using a method based on rough set theory.

Robust Evaluation of Deep Learning-based Representation Methods for Survival and Gene Essentiality Prediction on Bulk RNA-seq Data

This study evaluates deep learning-based representation methods for survival and gene essentiality prediction on bulk RNA-seq data, finding that non-DL methods perform comparably on survival tasks while DL methods excel in gene essentiality prediction.

CGPA: multi-context insights from the cancer gene prognosis atlas

CGPA provides a platform for multi-context gene-centric prognostic analysis, enabling customized exploration of gene relationships and biomarker discovery in cancer research.

Differentially Expressed Heterogeneous Overdispersion Genes Testing for Count Data

The paper introduces DEHOGT, a method for detecting differentially expressed genes in RNA-seq data that accounts for overdispersion, and shows it outperforms DESeq and EdgeR on synthetic data and detects more DE genes in microglial cells under stress hormone treatments.

The geometry of normal tissue and cancer gene expression manifolds

The paper analyzes the geometric relationship between normal tissue and cancer gene expression manifolds, showing they are disjoint and that tumors are translations of normal tissues along a cancer progression axis.

Optimizing murine sample sizes for RNA-seq studies revealed from large-scale comparative analysis

The paper determines optimal sample sizes for bulk RNA-seq experiments in mice by analyzing large-scale comparative studies and shows that increasing sample size reduces false positives and improves discovery rates.

tauX: A Gene Expression Ratio Strategy to Improve Machine Learning Applications in Precision Medicine

The paper introduces tauX, a gene expression ratio strategy that improves machine learning performance in precision medicine by refining gene expression features.

Mime: A flexible machine-learning framework to construct and visualize models for clinical characteristics prediction and feature selection

The paper introduces Mime, an R package for building and visualizing machine learning models to predict clinical outcomes and select features using transcriptional data.

GeneBag: training a cell foundation model for broad-spectrum cancer diagnosis and prognosis with bulk RNA-seq data

GeneBag is a cell foundation model trained on single-cell data and fine-tuned on bulk RNA-seq to diagnose and predict cancer prognosis with high accuracy.

Deciphering BRCAness Phenotype in Cancer: A Graph Convolutional Neural Network Approach with Layer-wise Relevance Propagation Analysis

The paper uses graph convolutional neural networks with layer-wise relevance propagation to analyze gene expression data and identify genes and pathways associated with BRCAness, outperforming traditional methods.