- Very small patient cohorts

- Limited access to biological samples

- Fragmented, heterogeneous datasets

- Heavy reliance on prior knowledge

As a result, generating reproducible biological insight can take months, or may not be feasible at all.

Built on 20+ years of precision medicine and systems biology research, Mavatar Discovery integrates thousands of public transcriptomic datasets across diseases, tissues, and biological contexts.

Instead of relying on isolated datasets, researchers explore connected biological systems, revealing reproducible molecular patterns that remain hidden in traditional analyses.

By learning from related diseases with shared biological features, researchers can generate hypotheses and explore mechanisms, even when direct patient data is scarce.

This data-driven approach is currently being applied in non-clinical research collaborations, including exploratory work with Sobi, a global biopharma company unlocking the potential​ of breakthrough innovations, transforming everyday life for​ people living with rare diseases. The collaboration is focused on IFNγ-related biological pathways in disease subtypes. Read more here.

- Explore genetic factors by placing known disease genes into broader biological networks

- Investigate therapy mechanisms by analyzing pathways linked to existing treatments

- Study tissue-specific biology across relevant tissues and cell types

- Explore comorbidities by identifying shared molecular signatures across conditions

All analyses are exploratory, data-driven, and fully traceable to public transcriptomic sources.

For Academic & Translational Research

- Faster hypothesis generation → quicker path to publications

- Stronger biological context → insights beyond single-gene findings

- Competitive pilot data → stronger grant applications

- Less time on pipelines and coding → more focus on science

For Pharma & Drug Development

- Earlier biological insight → shorter discovery timelines

- Better targets & biomarkers → reduced early-stage uncertainty

- Stronger go/no-go decisions → more confident R&D investment

- Scalable analysis → consistent insights across programs

Mavatar Discovery is disease-agnostic. The examples below are illustrative.

- Rare genetic skin disorders (e.g. Epidermolysis Bullosa)

- Rare neuroinflammatory & neurodegenerative diseases (e.g. ALS, leukodystrophies)

- Rare immunological & autoinflammatory diseases (e.g. Familial Mediterranean Fever, TRAPS)

- Rare metabolic & mitochondrial disorders (e.g. Leigh syndrome)

- Rare cancers, (e.g. Acute Myeloid Leukemia (AML)

Because Mavatar Discovery is disease-agnostic, it can be applied to a broad range of rare conditions and research questions wherever relevant transcriptomic data exists across related diseases, tissues, or biological contexts.

To support researchers working in areas where data and resources are limited, Mavatar has launched the Rare Disease Discovery Awards.

The initiative provides selected researchers with year-long access to Mavatar Discovery, giving them a data-driven foundation to explore disease mechanisms, generate hypotheses, and support early-stage research without building custom analysis pipelines.

Selected researchers receive:

A one-year, full-access license to Mavatar Discovery

Scientific onboarding and support

Access to integrated transcriptomic datasets for exploratory research