Making the Medicines
Most Likely to Work

Related Sciences (RS) is a data science-driven drug foundry designed from the ground up to take full advantage of the last decade's extraordinary advances in biology, engineering, and machine learning. RS uses a proprietary predictive AI platform to systematically identify the best new drug creation opportunities out of millions and a novel decentralized R&D model to bring the world's top scientists together to make them. RS leverages these capabilities to build an evergreen pipeline of new medicines with exceptional clinical and economic promise.

Evidence-Driven Strategy

To prioritize RS investment into the new medicines with the greatest chances of success, RS seeks to discover data science-driven insights into big risk-reward questions like:

What Factors Increase a Drug's Odds of Success?

A biotech’s early decision of which drug target(s) to pursue for which disease(s) can influence its future chances of success and failure by 200-500%+. Systematic analysis of biomedicine's historical outcomes leveraging machine learning can elucidate factors that can prospectively enhance each drug program's built-in odds of clinical and economic success ("Money Ball for biotech")?  1, 2, 5

Which Strategies and Models Enhance Risk-Reward?

RS spent years studying biotech's top operators and investors to identify new strategies and operating models that can enhance scientific quality and tech-enablement while enhancing cost and capital efficiency.

Are the Best Discoveries Made into Medicines?

Analysis of all current biomedical knowledge on the RS data platform reveals the surprising finding that ~75% of all target-disease opportunities with the strongest evidence of links have never been tried: 20,000+ opportunities are just waiting to be made into promising new medicines. 4

A Golden Era
for Drug Creation

Parallel revolutions in data science, biology, therapeutic modalities, discovery technologies, and the capabilities of the global research services sector, compound the probability of transformative new discoveries and position drug creation for decades of high value creation.  

Data, Machine Learning, and AI

Approximately 250 million target-disease pairs collectively represent the "cures solution space" to treat all known diseases. Selecting which target-disease opportunities to prioritize is the hard part.

Fortunately, as human clinical and genetics datasets continue to grow rapidly each year, the strongest potential disease targets are continually revealed. And as large language and machine learning models become increasingly capable, it becomes possible to apply data science to systematically evaluate all lines of evidence in tandem to rank and make quantitative predictions about the very best new drug creation opportunities out of millions.

Multi-Technology Discovery

Over the last decade, 10+ new therapeutic modalities have been invented, refined, and clinically validated, significantly broadening the drug-ability of historically challenging targets and unlocking superior new drug safety and efficacy properties.

In parallel, revolutions in drug discovery technologies--AI-enabled structural prediction, in silico screening and design, high-throughput robotics, and advanced new compound libraries and screening methods--further increase success rates, speed, and efficiency.

When combined, these extraordinary advances open up a golden era for drug discovery in which new, better drugs can be created for 5,000+ untreated or underserved disease populations.

Decentralized Science

Science is inherently global, and yet most US biotech remains local, with ~60-70% of US biotech VC invested in just 2 states.  

Fortunately, the proliferation of remote collaboration tools unlocks extraordinary opportunities to reinvent traditional scientific staffing models to overcome geographic constraints and engage with the best scientific talent wherever it may be found.

Large, fully virtual teams can now work together seamlessly across countries, research disciplines, vendors, and both academia and industry, collaboratively crafting world-class R&D strategies to improve quality and remove scientific blind spots.

Hub-and-Spoke R&D

Over the last decade, as large Pharma companies shuttered their early-stage research centers, a flood of talented R&D scientists made their way into global contract research organizations (CROs) dramatically expanding their offerings, capabilities, and scale.  

As a result, a flourishing new virtual R&D economy now offers democratized, on-demand access to a wide range of highly specialized R&D capabilities, enabling biotech companies to 1) take better advantage of a broader swathe of new technologies to increase success rates, drug quality, pace, and efficiency; and 2) convert fixed overhead into fully variable expenses under lean, specialized management teams, eliminating the 40-60% of capex historically focused on building out labs and hiring generalists.

A Fully-Integrated
Drug Foundry

Instead of betting on any one technology, target, or disease, the RS operating and investment model is predicated on integration as the innovation, combining modular capabilities that enable our drug creation efforts to benefit from superior scientific quality, technology enablement, capital efficiency, and scalability.

AI/ML Ranking Platform

New Investment Model

Decentralized Science

Hub-and-Spoke R&D

"Moneyball for Biotech"

FacetsTM️ AI/ML Platform

Must 90%+ of drugs inevitably fail? Or can programs with far higher chances of success be identified prospectively?  RS FacetsTM is a proprietary machine learning platform designed to ingest all activities in global biomedicine and systematically predict the best new drug discovery opportunities for every disease on an unbiased, quantified, and explainable basis.

New Datasets & ML Models

3 Layer Architecture:

See Everything

All of Biomedicine in One Dataset

Assess Risk

Quantitative Opportunity Ranking

Choose Wisely

Predictive AI/ML Models

A Specialized New Investment Model

Drug Creation, Systematized

On a risk-adjusted basis, preclinical drug discovery generates among the highest risk-adjusted value of any stage in drug development.2  Instead of rebuilding overhead in each new company, RS centralizes and systematizes world-class capabilities to efficiently discover valuable new drugs, and invests in unique portfolios of top-ranking programs.

Lean Processes, Specialized Teams

Data-Designed Portfolios

Flexible Exit Strategies

Better Science at Lower Cost

Decentralized Team Science

RS combines decentralized team science with fully virtual operations and shared back-office to enable world-class science without geographic constraint while reducing its R&D cost structures by 40%+.

Big Global Multi-disciplinary Teams

Fully Virtual + Shared Back-Office

Tax-Efficient Corporate Structure

Maximizing Technology Advantages

Hub-and-Spoke R&D

RS continually curates and partners with the world's most advanced drug discovery service providers to provide centralized access to the most advanced R&D capabilities under highly preferred cost structures and well-aligned risk-sharing business deals.

Risk-Sharing R&D Partnerships

Multi-Technology Enablement

Multi-Modality Discovery

Data-Driven Indication Strategy


RS is led by a multi-disciplinary team of drug discovery, data science, and venture capital veterans who have founded, built, and led biotech companies worth billions, and is backed by a luminary group of investors.


RS builds “constellations” -- data-designed portfolios of top-ranking drug programs in ascendant areas of commercial interest, led by decentralized teams of field-leading scientists tailored to the unique needs of each program and research area.


Building a new model to improve drug discovery efficiency and success rates benefits all of biomedicine's key stakeholders:


A greater number of transformational new medicines for virtually all types of disease are discovered sooner and successfully brought to market more often.


Breakthrough research is successfully translated into medicines more often, and our new model enables leading researchers to contribute to biotech R&D without needing to leave academia.


Biotech company failure is significantly reduced, driving significantly lower job turnover and training a deeper bench of capable biotech operators for the next generation of drugs.


Supply of high quality, clinic-ready drugs is dramatically increased and made available at acquisition prices that both incentivize biotech and are sustainable for pharma’s own economic models.


Better biotech risk-reward drives a much greater proportion of investor wins broadening interest among institutional investors to fund future biotech innovations.