Omada

Omada performs automated unsupervised clustering of RNA sequencing (RNAseq) transcriptomic data to identify stable molecular subgroups and link them to clinical variables.

Key Features:

• Automated Machine Learning Integration: Leverages automated machine learning algorithms to perform exploratory clustering of transcriptomic data.
• Robust Unsupervised Clustering: Identifies stable partitions within RNAseq expression profiles, including datasets with less clear biological distinctions.
• Clinical Relevance: Associates identified molecular subgroups with clinical data to link expression profiles to clinical outcomes.
• Data Quality Assessment: Highlights dataset-level quality issues such as biased measurements to inform the reliability of downstream analyses.

Scientific Applications:

• Disease mechanism discovery: Enables exploration of molecular heterogeneity to uncover mechanisms underlying disease states.
• Biomarker identification: Supports discovery of novel biomarkers from expression-defined subgroups.
• Patient stratification: Facilitates stratification of cohorts based on transcriptomic profiles.
• Precision medicine: Supports linking molecular and clinical associations to inform precision medicine initiatives.

Methodology:

Applies automated machine learning and unsupervised clustering algorithms to RNAseq transcriptomic data; validated by testing across five diverse RNAseq datasets with varying expression signal strengths.