The model is
only half
the story
CellStories Bio is building patient-informed preclinical models designed to reveal how different patients respond before therapies reach the clinic.
Partner with us ↗
The problem
Promising in the lab.
Failing in the clinic.
~90%
of drug candidates entering clinical trials fail to reach approval.
$2.5B
average cost per approved drug.
10 years
from lab to market.
40%
of drug candidates survive Phase II.
Nature Biotechnology, 2014
Mouse and cell-based models do not fully capture the complexity of human disease. Promising preclinical findings too often fail to translate into clinical benefit.
In heterogeneous diseases, patients with the same diagnosis can differ substantially in their clinical history, symptoms and response to treatment. Average treatment effects can mask meaningful differences between patient subgroups.
We believe that understanding whether a therapy works starts with understanding whom it works for. By integrating clinical history, symptom profiles and patient experience with patient-derived models, we aim to identify subgroups most likely to benefit, and inform patient selection for clinical trials.
Our focus
Starting with women’s health.
Conditions that affect half the population remain some of the least funded, least studied areas in medicine.
Fibroids, endometriosis, and other reproductive conditions affect millions, yet the research base behind them is a fraction of what conditions of comparable prevalence receive elsewhere in medicine.
Global
5%
of all global R&D funding went to women's health research in 2020
Alzheimer’s
12%
of U.S. Alzheimer’s research funding targets women, who make up two-thirds of patients
Heart disease
25%
of cardiovascular clinical trial participants in Europe are women, despite heart disease being a leading cause of death among them
McKinsey Health Institute · Women's Health Access Matters (WHAM) · European Society of Cardiology
Our first focus is uterine fibroids.
We’re building patient-derived 3D uterine models to capture the complexity and heterogeneity of fibrotic disease, creating a more human-relevant system for testing therapies and understanding differences in response.
Where we’re heading
De-risk what moves forward
Our goal is to build better preclinical models that support stronger clinical decisions. By combining patient-derived biology with clinical context, we aim to identify promising candidates, understand treatment response and guide what advances.
Build a digital twin
Our ambition is an AI-powered platform that predicts how patient groups respond to molecules, screening candidates, uncovering therapeutic possibilities and revisiting compounds conventional models may have overlooked.