The startup has developed an artificial intelligence platform that predicts molecular properties and target affinity using structured perception and feature fusion techniques. This technology streamlines data analysis workflows for biopharma research teams, enabling them to conduct fewer experiments while improving drug discovery outcomes.
Funding
$670K raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
The drug discovery process is often slow and expensive, with a significant portion of time and resources spent on optimizing drug molecules for safety and efficacy. Medicinal chemists face the challenge of balancing multiple molecular properties, such as potency, selectivity, and ADMET (absorption, distribution, metabolism, excretion, and toxicity), often through trial-and-error synthesis and testing.
Solution
DeepMirror offers an AI-powered platform designed to accelerate and streamline the drug discovery process, particularly in the hit-to-lead and lead optimization phases. The platform combines generative and predictive AI to suggest promising molecules for testing, reducing the need for extensive trial-and-error. DeepMirror's AI engine utilizes meta-learning and multi-model selection to achieve high performance on molecular property prediction tasks. The platform's user-friendly interface enables medicinal chemists to leverage advanced algorithms for informed decision-making regarding potency, selectivity, and other critical endpoints. By integrating data from previous experiments with a chemist's intuition, DeepMirror aims to help teams innovate and accelerate drug discovery on their own terms.
Target Audience
The primary customers are small to medium-sized biotech businesses and medicinal chemists aiming to accelerate drug development.
Features
- Generative AI engine that generates relevant molecules based on desired molecular properties and user input
- Predictive AI engine utilizing meta-learning and multi-model selection for state-of-the-art performance in molecular property prediction
- Prediction of protein-drug binding complexes with generative AI
- User-friendly interface designed for medicinal chemists
- Secure data storage with ISO 27001 certification
- Capability to predict potency, selectivity, and ADMET properties
- Integration of user's experimental data to train bespoke AI models