The ECoSystem

Precision medicine through polymathic AI

Representing biology at higher levels of abstraction requires a full tech stack approach

We are  vertically integrating many component parts of drug discovery into a complex coordination model. We believe we cannot outsource anything mission-critical without sacrificing quality, so we have unified everything we need in house to discover drugs for patients with brain diseases.
THE CORE

Multimodal data generation combined with biology and chemistry foundation models

Cosyne therapeutics data generation
Digitising Biology
Hyper-scale single-cell dataset derived from patient tissue
We have created a single-cell CRISPRi perturbation dataset that is larger than all other published data sets in the world combined (1). We grow cells from patient surgical resections in 3D, allowing us to recreate the clinical situation as closely as possible. To date, we have perturbed the entire functional genome in millions of single cells in thousands of genetic contexts. The tools we built to generate this dataset are scalable across many brain diseases.
Cosyne Therapeutics Biology foundation model
Biology foundation models
Exploiting the vulnerability of disease to identify precision drug targets
Our dataset was custom-built to train our biology foundation models, which allows us to predict the association between gene perturbation and transcriptomic-phenotypic responses within a given genetic context. With this capability, we can identify precision drug targets and companion genetic biomarkers.

Pipeline

Target ID
Hit to Lead
Lead Op
IND
Clinical trials
Best in class
First in class
Our first drug programme aims to generate a best-in-class asset to help millions of patients with neurological diseases.
Our second programme aims to generate a first-in-class asset to treat a universally fatal brain disease.
A science first company creating  a step change in the way drugs are developed.
Lorem ipsum dolor sit amet consectetur. Pharetra phasellus suscipit dolor justo arcu a nibh volutpat ornare. Parturient at ridiculus turpis pharetra cras. Enim arcu ullamcorper massa in vel faucibus arcu. Turpis duis ullamcorper venenatis ut faucibus.

Amet proin sit mauris tellus feugiat viverra pretium nunc varius. Egestas interdum rhoncus quam vel ut. Elit mi netus nec ut turpis aliquam nisi.
Polly
Lorem ipsum dolor sit amet consectetur. Pharetra phasellus suscipit dolor justo arcu a nibh volutpat ornare. Parturient at ridiculus turpis pharetra cras.
Lauren
Hi Polly, what do you make of this issue?
Pipeline
Lorem ipsum dolor sit amet consectetur. Pharetra phasellus suscipit dolor justo arcu a nibh volutpat ornare. Parturient at ridiculus turpis pharetra cras. Enim arcu ullamcorper massa in vel faucibus arcu. Turpis duis ullamcorper venenatis ut faucibus.Amet proin sit mauris tellus feugiat viverra pretium nunc varius. Egestas interdum rhoncus quam vel ut. Elit mi netus nec ut turpis aliquam nisi.
Lorem ipsum dolor sit amet consectetur. Pharetra phasellus suscipit dolor justo arcu a nibh volutpat ornare. Parturient at ridiculus turpis pharetra cras. Enim arcu ullamcorper massa in vel faucibus arcu. Turpis duis ullamcorper venenatis ut faucibus.Amet proin sit mauris tellus feugiat viverra pretium nunc varius. Egestas interdum rhoncus quam vel ut. Elit mi netus nec ut turpis aliquam nisi.
Publications
LLM alignment through projection embedded rules and chain of thought reasoning
Amet proin sit mauris tellus feugiat viverra pretium nunc varius. Egestas interdum rhoncus quam vel ut. Elit mi netus nec ut turpis aliquam nisi.
LLM alignment through projection embedded rules and chain of thought reasoning
Amet proin sit mauris tellus feugiat viverra pretium nunc varius. Egestas interdum rhoncus quam vel ut. Elit mi netus nec ut turpis aliquam nisi.
Sources