Revolutionizing drug discovery through AI-assisted analytics for biomedical and pharmaceutical solutions.
No coding required
Choose from a variety of AI models tailored to your individual requirements
Faster results and thus more efficient selection of suitable compounds than with conventional methods
Minimal black box effect
(UNITE TECH & SERVICES PHOTONIC BIOIMAGING INSTITUT PASTEUR, PARIS)
“(…) Our work together being a joint scientific initiative to prospect leveraging biological image analysis using deep-learning, for the purpose of improving research tools used in drug discovery.
Thus far, the lead project in this effort has yielded insight on new tools for characterization of blood macrophage cell activation using an image-based deep-learning approach. (…) The resulting tool will have its value as an automated approach to rapidly detect macrophage activation in screening campaigns aimed to identify bioactivity in unknown compounds, or complex mixtures.”
Using Deep Learning to automatically detect and classify infections to phenotype agents applied to the disease.
In particular, the early stages of drug development are time-consuming and expensive. Any drug candidate that proves unsuitable at a later stage leads to high financial losses. Simply scanning chemical databases does not allow sufficient information about the actual mode of action in the body and can thus lead to false hits. Microscopic images help to better understand biological relationships and interactions. However, manual evaluation of these images involves considerable effort, which severely limits the number of substances that can be analyzed.
AI Hub – The Medical Brick is an AI-assisted approach with the goal to make a change.
What we do for you
Shortened drug development time (early discovery phase) with simultaneously larger number of drug candidates.
Faster and more cost-effective drug development.
Larger accessible chemical space with higher probability of successful agent selection.
Automated Drug discovery
An AI-supported and cloud-based platform for the identification of new immunomodulatory therapies and drugs.
With the help of the complete and in-depth analyses of microscopic images, we would not only like nto accelerate the diagnostic process, but also to support drug screening and drug discovery.
To this end, infections are detected and classified in an automated manner. Therefore a test of the active ingredients applied to the diseases can be carried out for their characteristics. We are thus laying the foundation for the polypharmacological approach in drug research:
Conclusions for the application of other, new and as yet unknown active substances.
The increasing number of known and unknown pathogens, viruses and bacteria and the growing resistance to antibiotics and other agents. We want to contribute to the field of Smart Health and provide an answer to the growing and urgent need for digital and sustainable solutions to address current and future challenges.
We have built the AI Hub project on this building block:
The drug discovery approach enables autonomous analysis and evaluation of chemical compounds and their pharmacological effect. Supported by vast amounts of microscopic images and a neural net-based object detection, promising agent candidates can be identified quickly and efficiently. The high degree of automation allows to scale up the drug discovery process, meaning more potential agents can be considered at the beginning, boosting the chance of success.
Artificial intelligence approaches are the focus of our project: deep machine learning algorithms are used to classify medical data.
We provide fast, reliable and automated analyses of chemical compounds for the selection of promising drug candidates in different fields.
Applicable to drug discovery in various fields, including e.g. cardiology, oncology, neurology and many more.
Meaningful results through the analysis of cell samples in their biological context and their supply in real time.
NEW ANGLE OF VISION
Revelation of so far unknown correlations and fields of application of already established agents through the independence of predefined parameters.
Rapid result validation as well as the opportunity of appropriate concentration or dose evaluation.
Extension of accessible chemical search space and automated analysis, allows early selection and risk minimization while keeping development costs low.
AI as a Service
For fast, reliable and automated analysis of chemical compounds to select promising drug candidates.