Gene expression and cancer classification

BulkRNABert: Cancer prognosis from bulk RNA-seq based language models

BulkRNABert uses a pre-trained transformer model on bulk RNA-seq data to improve cancer classification and survival prediction across multiple cancer types.

A Deep Learning method for classification of HNSCC and HPV patients using single-cell transcriptomics

This paper develops a deep learning model using single-cell transcriptomics to classify HNSCC and distinguish HPV+ from HPV- patients, achieving high AUROC scores on a validation dataset.

Beyond variability: a novel gene expression stability metric to unveil homeostasis and regulation

The paper introduces a gene expression stability metric, the gene homeostasis Z-index, to identify genes under active regulation in different organs and highlights its advantage over traditional mean-based methods.

Identification of Cancer Risk Groups through Multi-Omics Integration using Autoencoder and Tensor Analysis

This study integrates multi-omics data using autoencoders and tensor analysis to identify cancer risk groups, showing significant stratification with p-value < 0.05.

Phantasus: web-application for visual and interactive gene expression analysis

Phantasus is a web-application that provides interactive gene expression analysis and access to over 84000 public datasets, enabling users to perform analysis from data loading to differential expression.

Improved differential expression analysis of miRNA-seq data by modeling competition to be counted

This study introduces NBSR, a method for differential expression analysis of miRNA-seq data that outperforms existing approaches on simulated and experimental datasets.

Feature Selection Using Lasso Regression Enhances Deep Learning Model Performance For Diagnosis Of Lung Cancer from Transcriptomic Data

The paper combines LASSO regression with a deep neural network to improve lung cancer diagnosis from transcriptomic data, achieving high accuracy and specificity.

NPmatch: Latent Batch Effects Correction of Omics data by Nearest-Pair Matching

NPmatch corrects latent batch effects in omics data using nearest-pair matching, outperforming existing methods across diverse datasets.

PerSEveML: A Web-Based Tool to Identify Persistent Biomarker Structure for Rare Events Using Integrative Machine Learning Approach

PerSEveML identifies persistent biomarker structures for rare events using an integrative machine learning approach and provides visualization tools for hypothesis generation.

SIEVEseq: One-stop differential expression, variability, and skewness analyses using RNA-Seq data

SIEVEseq provides a unified statistical framework for analyzing RNA-Seq data to detect differential expression, variability, and skewness, showing improved performance over existing methods.

Group Heteroscedasticity - A Silent Saboteur of Power and False Discovery in RNA-Seq Differential Expression

This paper introduces Robseq, a statistical model for RNA-Seq differential expression that addresses FDR inflation caused by group heteroscedasticity, showing improved control of false discovery and type-I error rates.

Normalization of RNA-Seq Data using Adaptive Trimmed Mean with Multi-reference

This paper improves RNA-seq normalization by adapting the TMM method using Jaeckels Estimator, showing better performance in differential expression analysis.

Completion of the DrugMatrix Toxicogenomics Database using ToxCompl

The paper predicts missing toxicogenomics data in the DrugMatrix database using ToxiCompl, a hybrid method combining matrix factorization and Bayesian optimization, showing alignment with biological expectations.

Consensus Clustering for Robust Bioinformatics Analysis

This paper reviews consensus clustering methods, their stability scores, and applications to gene expression data, providing open-source R implementations.

Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data.

This paper benchmarks feature selection and extraction methods to enhance machine-learning performance in patient classification using metabolomics data.

GeneSurv: Multi-Gene Cancer Survival Analysis Tool

GeneSurv enables multi-gene cancer survival analysis by correlating gene expression with patient outcomes, demonstrating its utility in identifying prognostic gene associations in breast cancer.

A deep profile of gene expression across 18 human cancers

The paper introduces DeepProfile, a deep learning framework for analyzing gene expression in 18 cancers, revealing biological insights through latent space analysis and linking gene expression to clinical outcomes.

Evaluation of methods for RNA-Seq analysis for uncovering key components of estrogen receptor-alpha signaling pathway in breast cancer

The paper evaluates RNA-Seq analysis methods to identify key components of the estrogen receptor-alpha signaling pathway in breast cancer, finding that SAM-Seq uncovers more significant genes than DESeq2.

INSIDER: Interpretable Sparse Matrix Decomposition for Bulk RNA Expression Data Analysis

INSIDER is a statistical framework for analyzing bulk RNA expression data that models interactions between biological variables and decomposes variation into a shared latent space to improve interpretation and downstream analysis.

Stability of feature selection utilizing Graph Convolutional Neural Network and Layer-wise Relevance Propagation

The paper evaluates the stability of feature selection using GCNN+LRP and GCNN+SHAP for gene expression data, comparing them to classical ML methods.

BatchEval Pipeline: Batch Effect Evaluation Workflow for Multiple Datasets Joint Analysis

BatchEval Pipeline evaluates batch effects in multi-dataset transcriptomics analysis and provides a report to guide batch correction.

Critical Differential Expression Assessment for Individual Bulk RNA-Seq Projects

The paper evaluates differential expression methods in bulk RNA-Seq by comparing edgeR-robust and DESeq2 in cell line and cancer data, highlighting the need for method testing in genomics projects.

A self-adaptive and versatile tool for eliminating multiple undesirable variations from transcriptome

DeepAdapter is a deep neural network that removes undesirable variations from transcriptomic data, improving accuracy across different batches, platforms, and sample types.

GeneSelectR: An R Package Workflow for Enhanced Feature Selection from RNA Sequencing Data

GeneSelectR is an R package that integrates machine learning and bioinformatics for feature selection in RNAseq data, prioritizing biologically relevant features through ML performance and GO analysis.

BAMBI: Integrative biostatistical and artificial-intelligence method discover coding and non-coding RNA genes as biomarkers

BAMBI identifies coding and non-coding RNA genes as biomarkers for disease diagnosis and prognosis with high accuracy and biological interpretability.

PCA-Plus: Enhanced principal component analysis with illustrative applications to batch effects and their quantitation

PCA-Plus enhances principal component analysis to better detect, visualize, and quantify batch effects and group differences in multi-omic data.

Omada: Robust clustering of transcriptomes through multiple testing

Omada automates transcriptomic clustering by integrating machine learning, improving accessibility and robustness across diverse RNA expression datasets.

MetaNorm: Incorporating Meta-analytic Priors into Normalization of NanoString nCounter Data

MetaNorm improves normalization of NanoString nCounter data by incorporating meta-analytic priors, enhancing stability and computational efficiency.

Investigation of normalization procedures for transcriptome profiles of compounds oriented toward practical study design

This study evaluates normalization procedures for transcriptome profiles of compounds, finding that batch-corrected baseline distributions work well for large datasets and offering guidance for small datasets.

Optimizer's dilemma: optimization strongly influences model selection in transcriptomic prediction

This study compares the impact of different optimization methods on model performance and sparsity in transcriptomic prediction using LASSO logistic regression.