Drug discovery and development is a long, costly, and high-risk process:
It takes 10–15 years and costs $1–2 billion for each new drug approval.
Over 90% of drug
Candidates fail during clinical trials, primarily due to lack of efficacy.
These failures are directly linked to the lack of predictive validity in preclinica
Models.
AI unlocks a new frontier in drug discovery, but its potential is only realized when paired with human-centric, translational in-vitro models.
At VALID, we create complex, disease-relevant hiPSC-based in-vitro models with increased predictive validity at scale.
By connecting human genetics with VALID's physiologically relevant experimental models, we generate meaningful "OMICs-AI data." This powerful combination enables novel insights into human disease, therapeutic targets, and drug discovery.
Can AI solve this problem alone? We don’t think so.
Bad experimental models → Bad Data → Bad Targets → Bad Therapeutics → Failures in Drug Discovery
Key Opportunity:
Improving the predictive validity of preclinical and experimental models is the most powerful way to increase drug discovery success.