Gene expression and cancer classification

Baseline Acute Myeloid Leukemia Prognosis Models using Transcriptomic and Clinical Profiles by Studying the Impacts of Dimensionality Reductions and Gene Signatures on Cox-Proportional Hazard

This paper evaluates how dimensionality reduction techniques and gene signatures affect Cox-Proportional-Hazard models for AML prognosis using the Leucegene dataset.

robustica: customizable robust independent component analysis

robustica computes robust independent components with customizable clustering and distance metrics, showing improved precision and efficiency in analyzing tumor samples.

Optimal microRNA sequencing depth to predict cancer patient survival with random forest and Cox models

This paper benchmarks the impact of sequencing depth and patient number on survival prediction using miRNA-seq and mRNA-seq with Cox and random survival forest models.

Computational Pipeline to Identify Gene signatures that Define Cancer Subtypes

The paper develops a computational strategy to identify gene signatures defining cancer subtypes using multi-omics data, achieving 92% model accuracy and identifying 20 significant genes in breast and glioma cancers.

GMRC: Gene Median Ratio Clustering Algorithm to Rank Clusters and Identify Driver Genes in Intrahepatic Cholangiocarcinoma

The paper introduces GMRC, a clustering algorithm to rank clusters and identify driver genes in iCCA using gene-median ratio and gene cluster network analysis.

KBPRNA: A novel method integrating bulk RNA-seq data and LINCS-L1000 gene signatures to predict kinase activity based on machine learning

KBPRNA predicts kinase activity from bulk RNA-seq data using machine learning, outperforming existing methods in cancer tissue samples.

PSMC2 and CXCL8-Modulated Four Critical Gene Biomarkers and Druggable and Vaccinable Targets for Colorectal Cancer

The paper identifies four critical differentially expressed genes in colorectal cancer using transcriptomic data from multiple cohorts and validates their predictive power and potential as druggable/vaccinable targets.

The usage of transcriptomics datasets as sources of Real-World Data for clinical trialling

This paper constructs a patient repository by integrating transcriptomics datasets to generate real-world data for clinical trialling, improving downstream biological conclusions by 45%.

Highly Realistic Whole Transcriptome Synthesis through Generative Adversarial Networks

This paper uses GANs to generate realistic transcriptome images from gene expression data, enabling deep learning applications and revealing novel biological insights.

GMMchi: Gene Expression Clustering Using Gaussian Mixture Modeling

GMMchi detects bimodal gene expression patterns in cancer data using Gaussian Mixture Modeling and 2x2 contingency tables to analyze genetic and phenotypic correlations.

IPLS-LDA: An Improved Partial Least Square Discriminant Analysis for Heterogeneous Transcriptomics and Metabolomics Data Analysis

The paper introduces IPLS-LDA, an improved PLS-LDA method for analyzing heterogeneous transcriptomics and metabolomics data, achieving higher accuracy than existing SML methods.

SurvivalML: an integrative platform for the discovery and exploration of prognostic models in multi-center cancer cohorts

SurvivalML is a web platform that helps develop and validate prognostic models across multi-center cancer datasets by providing tools for data processing, model training, and evaluation.

Tensor decomposition- and principal component analysis-based unsupervised feature extraction to select more reasonable differentially expressed genes: Optimization of standard deviation versus state-of-art methods

The paper optimizes standard deviation in tensor decomposition and PCA to improve differential gene selection, achieving better alignment with the null hypothesis and increased biological reliability.

Benchmark of lasso-like penalties in the Cox model for TCGA datasets reveal improved performance with pre-filtering and wide differences between cancers

The paper benchmarks lasso-like penalties in Cox models for TCGA datasets, showing improved performance with pre-filtering and highlighting cancer-specific differences.

Projection in genomic analysis: A theoretical basis to rationalize tensor decomposition and principal component analysis as feature selection tools

This paper explains why PCA and tensor decomposition work well for feature selection in genomic data by relating them to projection pursuit and empirical P-value thresholds.

On taming the effect of transcript level intra-condition count variation during differential expression analysis: a story of dogs, foxes and wolves

The paper introduces TVscript, a tool to filter out transcripts with high intra-condition variation, improving differential expression analysis in multi-species RNA-seq data.

An evaluation of RNA-seq differential analysis methods

The paper evaluates RNA-seq differential analysis methods across simulated and real data, finding EBSeq and DESeq2 perform best under specific conditions.

Removing unwanted variation from large-scale cancer RNA-sequencing data

This paper identifies major sources of unwanted variation in cancer RNA-seq data and proposes a novel method to remove them using pseudo-replicates of pseudo-samples.

Development of Machine Learning Model for Pan-cancer Subgroup Identification using Multi-omics Data

This paper develops a machine learning model to identify novel pan-cancer subgroups using multi-omics data, showing that patients with different tumor types can share similar molecular characteristics.

BioTEA: containerized methods of analysis for microarray-based transcriptomics data

BioTEA is a containerized R/Bioconductor-based tool for differential expression analysis of microarray data, offering reproducibility and flexibility through customizable pipelines.

Progression Analysis of Disease with Survival (PAD-S) by SurvMap identifies different prognostic subgroups of breast cancer in a large combined set of transcriptomics and methylation studies

PAD-S with SurvMap identifies prognostic subgroups in breast cancer using transcriptomics and methylation data, showing significant survival differences and molecular features.

omicsGAT: Graph Attention Network for Cancer Subtype Analyses

omicsGAT integrates graph-based learning with attention mechanisms to improve cancer subtype analysis using RNA-seq data.

Factors influencing patterns of gene expression in large bowel mucosa

This study identifies demographic and sampling factors affecting gene expression in normal colorectal mucosa, with age, gender, and sample site showing significant associations.

Deep surveys of transcriptional modules with Massive Associative Kbiclustering (MAK)

MAK improves biclustering by correcting size bias and enhancing biological enrichment, finding novel biclusters in yeast data.

Blood-based transcriptomic signature panel identification for cancer diagnosis: Benchmarking of feature extraction methods

This study benchmarks eleven feature extraction methods for identifying blood-based transcriptomic biomarkers in cancer diagnosis, finding PLS-DA superior for classification and Ranger for robust feature selection.

Most High Throughput Expression Data Sets are Underpowered

The paper argues that high-throughput expression datasets are underpowered due to insufficient biological replicates and recommends at least six per condition to improve reliability.

Analyzing Biomarker Discovery: Estimating the Reproducibility of Biomarker Sets

This paper introduces a Reproducibility Score to assess biomarker set reproducibility and provides methods to estimate it using univariate hypothesis testing on dichotomous groups.

Cross-Platform Omics Prediction procedure enables precision medicine in patients with stage-III melanoma

The paper introduces a method to handle omics data variation across platforms and times, showing its use in three disease risk models for clinical application.

A combined test for feature selection on sparse metaproteomics data - an alternative to missing value imputation

This paper proposes a combined test for feature selection in sparse metaproteomics data, avoiding missing value imputation by addressing both missingness mechanisms and differential intensity.

MIAMI: Mutual Information-based Analysis of Multiplex Imaging data

The paper introduces MIAMI, a method using mutual information to analyze protein co-expression in cancer datasets, finding associations between marker co-expression and clinical outcomes.