Progenos — Predictive Medicine from Human Genetics

Why Our Approach Wins

Problem: ~90% of drug targets fail due to weak human causal validation.
Standard Fix: GWAS-supported targets show ~2× higher approval odds.
Insight: Extreme phenotypes can break polygenicity and enrich rare causal variants.
Impact: 1.5–2.6× higher successful target identification.
Outcome: Lower attrition, higher probability of success, and ~40–50% lower cost per approved drug.

See the Evidence page for the full rationale and supporting narrative.

The Problem

Healthcare systems still spend most effort downstream, after disease has progressed. That delay limits outcomes and increases cost.

In drug development, weak human causal validation leads to high attrition, with roughly 90% of targets failing across the pipeline.

The Opportunity

Biobanks and population-scale genomics have made predictive risk modeling operational at real-world scale.

Targets supported by human genetics show around 2× higher approval odds; moving success probability from ~10% to ~20% can reduce expected R&D cost per approved drug by ~40–50%.

Bar chart comparing probability of approval: 10% traditional, 20% standard genetics, 22.5% advanced enrichment strategy. — Figure 1. Probability of approval improves from ~10% to ~20% with standard genetics, and can rise further with enrichment-based strategies.

What We Build

Our platform combines polygenic risk, disease architecture, and age-dependent modeling to produce practical risk intelligence for prevention and discovery teams.

We extend standard GWAS workflows with extreme-phenotype enrichment, helping uncover high-impact causal signals that can improve target and biomarker decisions.

Platform model summary
Element	Role in prediction
Polygenic risk scores	Estimate baseline inherited susceptibility at population scale.
Extreme-phenotype enrichment	Prioritize individuals with genotype-phenotype mismatch to reveal stronger causal signals.
Age-dependent modeling	Translate static genetic risk into time-aware screening and prevention strategy.
Biobank-scale datasets	Support robust, reproducible calibration across populations.

Why Teams Work With Us

Move from reactive care to earlier, risk-informed intervention.
Improve screening economics by matching pathway intensity to inherited risk.
Increase confidence in discovery decisions with stronger human genetic evidence.

Even modest gains beyond standard genetics can compound into materially lower attrition and faster, more capital-efficient R&D.

Bar chart showing indexed expected R and D cost per approved drug: 100 traditional, 50 standard genetics, 44.4 advanced strategy. — Figure 2. Since cost per approval scales inversely with probability of success, improvements in PoS drive substantial cost reduction.

Current Focus

We are working with collaborators in preventive medicine and therapeutics to validate genetics-first risk and target workflows in high-burden disease areas.