Gene expression and cancer classification

This paper proposes a deep learning method to identify cancer-related genes using semi-supervised and unsupervised algorithms, showing improved performance over traditional statistical methods.

The paper introduces a new information-theoretic distance measure, TSD, to assess transcriptomic similarity between tissue samples using RNA-seq data and curated gene signatures.

This paper applies style transfer methods to RNA-Seq data harmonization and treatment outcome prediction, showing improved style and semantics prediction accuracy compared to existing approaches.

PDXGEM builds a gene expression model to predict cancer patient responses to anticancer therapies using data from patient-derived xenograft models.

The paper introduces TDimpute, a transfer learning-based deep neural network for imputing missing RNA-seq data using DNA methylation, showing improved accuracy across 16 cancer datasets.

The paper introduces CODC, a copula-based model to identify differential coexpression between gene pairs across two conditions, showing improved performance on TCGA RNA-Seq data.

EBSeq improves computational efficiency for multi-group differential expression analysis by updating algorithms and pruning techniques.

The paper introduces a two-stage framework using mixed mutual information and scalable Bayesian networks to analyze multimodal cancer data, identifying 11 candidate genes with 6 validated in literature.

This paper benchmarks differential expression analysis tools for RNA-seq, showing how replicate numbers affect performance and recommending specific tools for different replicate ranges.

The paper introduces a density-based clustering method using percolation theory to identify functionally related gene modules from noisy, high-dimensional RNA sequencing data across different organisms.

The paper identifies a diagnostic signature for myocardial infarction using differential expressed genes and validates it on independent datasets.

ClusterMine integrates biological knowledge to cluster samples based on gene set expression profiles, improving interpretability of clusters.

The paper introduces CompDTU, a method for differential transcript usage analysis that addresses scalability and quantification uncertainty, improving sensitivity and reducing false positives.

CCLA authenticates cancer cell lines using gene expression profiles with high accuracy and speed, offering a web server for public use.

This paper introduces a sparse-input neural network (spinn) to classify 32 cancer types using somatic point mutations, achieving 73% accuracy on independent test data.

This paper introduces a robust hierarchical co-clustering algorithm to identify toxicogenomic biomarkers and their regulatory doses of chemical compounds, showing improved performance over traditional methods in the presence of outliers.

The paper introduces parsimonious models to improve gene expression data accuracy by selectively recovering signal and discarding noise, achieving significant accuracy gains with minimal computational cost.

The paper introduces TAC, a method using CNNs to classify tabular data by converting it to images, and shows it performs as well as existing non-CNN classifiers on gene expression data.

The paper introduces NBAMSeq, a statistical model for RNA-Seq data that improves detection of nonlinear effects while maintaining linear effect performance.

This paper introduces a self-training method for gene expression-based cancer classification that works across different data types and normalization methods.

This study uses a k-means based unsupervised feature selection method to identify biomarkers associated with different clinical phases of Huntington's disease.

The paper introduces the C-SHIFT normalization method to recover the covariance matrix from gene expression data by minimizing noise and improving accuracy over existing techniques.

This paper introduces BESC, a method to correct microarray batch effects without requiring known batch identities or removing true biological differences, using signatures from a reference set.

The paper identifies gene expression correlation patterns (AEPs) associated with cancer prognosis across 22 cancer types using transcriptomic data from 5,001 patients.

The paper identifies issues in re-analyzing observational omics studies, highlighting problems with false positives, method limitations, and lack of confounders in public metadata.

CAMPP is an open-source R pipeline that simplifies high-throughput data analysis for non-experts, providing tools for normalization, clustering, differential expression, and biomarker prediction.

The paper introduces a gene filtering method to improve supervised network analysis by removing irrelevant features, enhancing scalability and accuracy of downstream analyses like sparse canonical correlation analysis.

This paper introduces sparse contrastive principal component analysis to extract stable and relevant biological signals from high-dimensional data and evaluates it on multiple datasets.

The paper develops machine learning models to classify early and late stages of invasive ductal carcinoma using RNA-seq data from 610 patients, and provides a web server for prediction.

The paper introduces ppcseq, a Bayesian tool to detect artifactual calls in differential transcript abundance analyses by identifying outliers in negative binomial models.