tcga-brca

discovering novel biomarkers in RNA-Seq data with tree-based models and survival analysis

This repository contains several popular Attention-based Multiple Instance Learning (ABMIL) algorithms in PyTorch implementation.

Differential gene expression analysis of TCGA breast cancer RNA-seq data using DESeq2

Multi-omics machine learning project for breast cancer clinical subtype classification using TCGA-BRCA data.

Graph Neural Network framework for absolute breast cancer risk prediction using TCGA-BRCA clinical and gene expression data with an iCARE-inspired risk estimation approach.

Using active learning on TCGA database.

Reproducible bulk RNA-seq analysis pipeline for TCGA-BRCA integrating DESeq2, gene annotation, GO/KEGG enrichment, automated reporting, and Streamlit visualization.

Multi-omics breast cancer analysis covering MOFA2 factor discovery, survival analysis and interactive Shiny dashboard

Multi-task VAE for BRCA cancer detection and PAM50 subtype classification on TCGA/GTEx gene expression, with sparse gene-panel analysis.

Python project for classification of normal vs tumoral samples using TCGA gene expression data for Scientific Programming Course 2021 (MSc Bioinformatics for Computational Genomics)

This project utilizes R as a computational tool to analyze RNA-Seq data from TCGA-BRCA. It identifies differentially expressed genes and enriched pathways between Basal-like and Luminal A breast cancer subtypes.

A computational framework utilizing Boolean implication networks to decipher asymmetric regulatory logic in 17q-amplified breast cancer, integrating transcriptomic and epigenomic data under BRCA1 stratification.

FIrst_taste_of_Machine_learning_in_R