Gene expression and cancer classification

A new pipeline for cross-validation fold-aware machine learning prediction of clinical outcomes addresses hidden data-leakage in omics based 'predictors'.

The paper introduces pipeML, a framework for leakage-free machine learning in omics data by enabling fold-aware cross-validation, improving model evaluation accuracy.

EES-Transformer: A Dual-Path Transformer for Tissue Classification and Gene Representation Learning from Extreme Expression Sets

EES-Transformer V2 classifies tissues and learns gene representations from extreme expression sets, achieving high accuracy and revealing tissue-specific gene interactions.

Transfer Learning Models for Bacterial Strain Dissemination Biomarkers using Weighted Non-Parallel Proximal Support Vector Machines

The paper develops a transfer learning model using weighted 1-norm non-parallel proximal support vector machines to identify biomarkers of bacterial infection and dissemination in mice, achieving 97% balanced accuracy.

Reproducible Tools and Enhanced Computational Workflows for Batch Effect Evaluation of High-Throughput Data Using BatchQC

The paper introduces BatchQC, an R package for assessing and correcting batch effects in high-throughput data with reproducible tools and workflows.

DEPower: approximate power analysis with DESeq2

DEPower provides a web tool for power analysis in RNA-seq experiments based on DESeq2 assumptions, enabling researchers to determine sample size requirements for detecting differential expression.

Fuzzifier*: Robust and Sensitive Multi-omics Data Analysis

Fuzzifier* provides a differential analysis framework for multi-omics data, identifying reliable and sensitive features by analyzing value distributions and foldchange patterns across groups.

Sample Size Requirements for Machine Learning Classification of Binary Outcomes in Bulk RNA-Seq Data

The paper determines sample size requirements for ML classification in bulk RNA-seq data and finds that ML methods generally need larger samples than differential analysis power analysis.

Fast, accurate and scalable normalization for RNA sequencing data with the RUVprps software package

The paper introduces RUVprps, a software package for normalizing RNA-seq data by removing unwanted variation, offering improved performance and features for analysis.

Identification of Multiple Prognostic Biomarker Sets for Risk Stratification in SKCM

This paper identifies seven distinct sets of prognostic biomarkers for predicting high-risk SKCM patients using transcriptomics data and machine learning models.

A Robust and Interpretable Feature Engineering Approach for Low-Data Biological Classification

This paper introduces DFE, a feature engineering method that improves biological classification by reducing overfitting and enhancing interpretability, showing superior performance on RNA-sequencing datasets.

DESeq2-MultiBatch: Batch Correction for Multi-Factorial RNA-seq Experiments

DESeq2-MultiBatch corrects batch effects in multifactorial RNA-seq experiments by leveraging DESeq2's internal model, preserving biological differences and improving data analysis.

DoReMiTra: An R/Bioconductor data package for orchestrating the analysis of radiation transcriptomic studies

DoReMiTra provides a unified radiation transcriptomics dataset collection with standardized metadata and pre-processed data for benchmarking and integrative analysis.

Identification of Monotonically Classifying Pairs of Genes for Ordinal Disease Outcomes

This study extends a gene pair classification method to ordinal outcomes, showing comparable performance with higher interpretability in glioblastoma and ovarian cancer.

CanID: a robust and accurate RNAseq Expression-based diagnostic classification scheme for pediatric malignancies

CanID is a machine learning classifier for pediatric cancer subtypes using RNAseq data, achieving 99% accuracy for solid tumors and 92-93% for hematologic malignancies.

Not every gene is special: one simple rule to control the false discovery rate when analysing high-throughput sequencing data

This study shows that scale misspecification in differential expression analyses leads to poor false discovery rate control and provides guidance on choosing appropriate scale uncertainty.

Caris-ComBat-seq: Directionally Harmonizing Large-Scale RNA-seq Datasets

The paper introduces Caris-ComBat-seq, a method to harmonize RNA-seq data by directionally adjusting batches, separating training and adjustment steps, and handling outliers, validated on large tumor datasets.

PRECOG update: An augmented resource of clinical outcome associations with gene expression for pediatric and immunotherapy cohorts

The paper updates the PRECOG resource by adding pediatric and immunotherapy datasets, enabling analysis of gene expression associations with clinical outcomes using statistical models and deconvolution.

Direction-Driven Feature Engineering for Low-Data BiologicalClassification

This paper introduces TDDF, a feature engineering method for biological classification in low-data settings, achieving high AUC scores and identifying key cancer genes.

Quantifying predictability of gene expression from histology image

The paper introduces a metric to quantify gene expression predictability from histology images and identifies genes that can or cannot be predicted.

Estimating drivers of breast tissue transitions from normal to tumor state

The paper identifies shared driver genes across breast tissue transitions from normal to tumor states and TANTs to tumor subtypes, revealing their involvement in cancer-related pathways.

omicML: An Integrative Bioinformatics and Machine Learning Framework for Transcriptomic Biomarker Identification

omicML identifies transcriptomic biomarkers by integrating data preprocessing, differential expression analysis, and machine learning for diagnostic model development.

CancerSubminer: an integrated framework for cancer subtyping using supervised and unsupervised learning on DNA methylation profiles

CancerSubminer improves cancer subtyping by combining supervised and unsupervised learning on DNA methylation data, identifying prognostic subtypes across multiple cancers.

Machine Learning Approach to Integrate and Analyse Multiomics data to Identify Actionable Biomarkers for Head and Neck Squamous Cell Carcinoma (HNSCC)

This paper uses machine learning to integrate multi-omics data from HNSCC patients, identifying biomarkers with high classification accuracy.

Recalibrating differential gene expression by genetic dosage variance prioritizes functionally relevant genes

This paper recalibrates differential gene expression by genetic dosage variance to prioritize functionally relevant genes, showing enrichment in metabolic and regulatory pathways.

Tree-based differential testing using inferentialuncertainty for RNA-Seq

The paper introduces mehenDi, a tree-based differential testing method for RNA-Seq that accounts for inferential uncertainty, improving detection of differentially expressed transcripts and inner nodes.

Unsupervised machine learning reveals temporal components of gene expression in HeLa cells following release from cell cycle arrest

This study uses unsupervised machine learning to identify temporal gene expression components in HeLa cells after cell cycle release, revealing oscillatory and transient patterns linked to cell cycle phases and cancer-related processes.

A Bayesian Informative Shrinkage Approach for Large-scale Multiple Hypothesis Testing (BISHOT): with Applications in Differential Analysis of Omics Data

The paper introduces a Bayesian method for differential analysis of omics data that incorporates prior knowledge across platforms or species, improving robustness and generalizability.

THRESHOLD: A Comprehensive Transcriptomic Analysis Tool for Evaluating Gene Saturation and Impact in Disease Progression

THRESHOLD evaluates gene saturation in disease progression using TCGA datasets, revealing co-regulation patterns and identifying biomarkers in bladder, prostate, and breast cancers.

Clustering Gene Co-expression Using 2D Contour Analysis and Autoencoder-based Embedding

The paper introduces a framework using 2D contour analysis and autoencoder embeddings to cluster co-expressed genes, achieving high correlation with visual coherence.

Generating Correlated Data for Omics Simulation

The paper introduces methods to generate correlated omics data for benchmarking, showing improved performance in DESeq2 and CYCLOPS when dependencies are included.