Imagine trying to find a specific key for a lock by testing millions of random keys one by one in a slow, expensive lab. This project uses AI and bacteria to quickly design and refine those 'keys' (nanobodies) to lock onto cancer cells. Instead of using mice, they use zebrafish and computer models to prove the drug works much faster.
Therapeutic antibody discovery is currently too slow, expensive, and reliant on animal testing. This inefficiency hinders the ability to capture a share of the projected 500 USD billion market by 2030.
An integrated nanobody discovery platform featuring AI-guided maturation, microfluidic selection devices, and a zebrafish-based preclinical validation model.
If you are a drug discovery firm dealing with the long and expensive process of animal immunization — this project developed an integrated nanobody platform that fully eliminates animal immunization. This reduces the time and cost of identifying therapeutic candidates for the cancer market.
If you are a biotech startup dealing with inefficient epitope mapping — this project developed AI tools for structure-based mapping and humanization. This allows for faster optimization of nanobodies before entering clinical trials.
If you are a precision medicine provider dealing with slow preclinical validation — this project developed a zebrafish larvae model for patient-derived tumor xenografts. This accelerates the validation of antibody candidates compared to traditional mammalian models.
It replaces expensive animal immunization and mammalian preclinical validation with bacterial libraries, microfluidic devices, and zebrafish models. Based on available project data, this removes the need for large equipment and facilities associated with mammal labs.
The project focuses on creating a platform that integrates selection and maturation. Based on available project data, the use of miniaturized microfluidic devices suggests a move toward scalable, cost-effective in vitro selection.
Based on available project data, the project is in the signed phase (2024-2027), and specific licensing terms are not yet detailed in the summary.
AI is used for three specific tasks: structure-based epitope mapping, guided affinity maturation, and nanobody humanization. This replaces some of the manual, iterative laboratory engineering steps.
The project period runs from 2024-01-01 to 2027-12-31. Based on available project data, the platform is being developed to be brought to market by the end of this period.
The consortium is highly multidisciplinary, consisting of 8 partners across 5 countries. It has a strong research bias with 4 research organizations and 2 universities, balanced by 2 SMEs (25% industry ratio). This structure suggests a focus on high-risk technical development (AI, microfluidics, and zebrafish models) with a clear path toward commercialization via the SME partners.
Contact AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS in Spain
Contact us to connect with the ALADDIN consortium for early-stage licensing opportunities.
