Open Source Machine Learning for

|

Ersilia is a nonprofit organisation that supports research for infectious and neglected diseases. Our goal is to facilitate adoption of artificial intelligence tools to accelerate the development of new medicines. We focus on establishing collaborations in low-resourced settings where the costs of drug discovery are prohibitive.

We are on a mission to make scientific progress accessible to all

Ersilia Open Source Initiative is registered with the Charity Commission for England and Wales

Open Science

We want to democratise drug discovery by providing a friendly and transparent resource available to everyone.

Global Reach

We empower research where medical care is most needed by fostering collaborations with health organizations in low- and middle-income countries.

Predictive Models

We illuminate neglected regions of the chemical space to enable drug repurposing, hit-to-lead optimisation and generation of new molecules.

Our Strategy

Researchers interested in a specific disease, target or pathogen can use our tools to prioritize drug candidates. The way around is also true. Given a drug of interest, Ersilia will scope for potential indications, mechanisms of action or toxicities.

Increase the visibility of existing methods

We collect and deploy AI/ML models currently scattered in scientific papers, code repositories and supplementary materials.

Our awesome features
Exploit results of drug screening campaigns

We search the scientific literature for relevant experimental datasets and use them to train our own AI/ML models.

Our awesome features
Foster in-country research

We actively seek collaborators working in infectious and neglected diseases to jointly develop customised tools.

Our awesome features
Emphasis on local resources

We leverage the potential of natural products to identify new chemical leads for endemic diseases.

Our awesome features

Stay up to date!

Join our mailing list to receive a monthly report of our work, including project results, new releases and stats about our growth. We promise to stick to one email per month, no less no more.

Join now
Loading...

Thank you for subscribing!