Welcome to master_project’s documentation!

This is the documentation on my master thesis project about “ML-based gene expression profiling of publicly available RNA-Seq data.”

Contents:

• Getting Started
  • Features
  • Main Workflow Overview
  • Prerequisites
  • Setting-up conda environment
  • Alternative set up with docker container
• Metadata acquisition
  • Acquisition of RNA-Seq data
  • Obtain RNA-Seq expression data
  • Metadata
• Preprocessing
  • Parsing stringTie-TPM
  • Parsing FeatureCounts
  • Merging Replica
  • Batch Correction
• Analysis
  • Dimension Reduction / Embeddings with PCA, t-SNE and UMAP
• Machine-Learning on RNA-Seq data
  • Machine Learning
  • KEGG database
  • Feature importances
• python_scripts
  • dim_reduction module
  • extract_gene_ids2name module
  • fileUtils package
  • get_protein_atlas module
  • icgc_metadata_processing module
  • machine_learning_tool module
  • metadata_processing module
  • merge_replica module
  • merge_gene_counts module
  • parseFeatureCounts module
  • parseTPM module
  • sra_metadata_processing module
  • tcga_metadata_processing module
  • xml_soup module