Projets novateurs réalisés

L2M – Automating Chromatography Process

Minerva Analytics Inc. is a technology startup focused on automating manual and repetitive processes in research laboratories. The goal is to free scientists from routine tasks so they can concentrate on complex analysis and innovation. Through AI-powered software tools, Minerva transforms traditional lab workflows—often reliant on manual data entry, disconnected spreadsheets, and inefficient communication—into streamlined, intelligent systems.

L2M – Gen AI powered cyber threat assessment platform

We are developing a next-generation cybersecurity tool that uses large language models (LLMs), a form of generative AI, to help small and medium-sized businesses (SMBs) detect hidden weaknesses in their systems before they can be exploited. Unlike traditional tools that rely on fixed rules and often flood users with too many alerts, our platform understands patterns in system logs the way a security expert would. It connects directly to existing log data sources like Zeek, Suricata, Windows Events, or AWS CloudTrail, and uses an AI model combined with the latest threat databases (like CVEs and CISA KEV) to spot outdated technologies or risky configurations—such as old encryption or legacy file-sharing systems. When it finds a risk, the system explains the issue clearly and provides a ready-to-use report, making it easy for non-experts to take action. The platform runs entirely within the organization’s own infrastructure, keeping all sensitive data private, and only shares anonymized updates, making it especially suitable for privacy-sensitive industries like healthcare or utilities. The partner organization will benefit from a cutting-edge solution that enhances cybersecurity without the need for extra staffing or major infrastructure changes. It reduces the time and effort needed for vulnerability assessments, helps prioritize what to fix first, and keeps businesses protected from modern AI-driven threats—while being cost-effective and easy to integrate.

L2M – Next-Generation iEEG Electrodes with Integrated Optical and Oxygenation Sensors for Precision Neurodiagnostics

This project explores the market opportunity for a next-generation intracranial EEG (iEEG) electrode system that integrates optical and oxygenation sensors to enhance brain monitoring in clinical and research settings. The proposed innovation addresses a critical gap in current neurodiagnostic tools by enabling simultaneous acquisition of electrical activity and hemodynamic signals from the brain. This dual-modality capability has the potential to significantly improve seizure localization in patients with drug-resistant epilepsy and broaden applications in functional brain mapping and brain-computer interface research.

The goal of this Lab2Market Validate project is to conduct focused market research to assess clinical needs, identify early adopters, and evaluate the competitive landscape. Through stakeholder interviews with neurologists, neurosurgeons, clinical researchers, and healthcare technology buyers, we aim to validate the product’s value proposition, understand regulatory considerations, and define key product features that align with user requirements.

Insights gained through this process will inform the development of a commercialization roadmap, including IP strategy, clinical integration pathways, and go-to-market plans. This research will lay the foundation for launching a health technology venture based in Alberta, focused on bringing advanced neurodiagnostic hardware to market with strong clinical impact and global scalability.

Development of a Neural Network-Based Model for Generating CT uMaps from Standalone PET Imaging

One type of diagnostic imaging used in nuclear medicine is positron emission tomography, (PET). PET images display the function of the tissue being imaged, for example sugar metabolism, without displaying the anatomy. In hospitals, people undergoing PET imaging will also be imaged with computed tomography (CT) which displays the anatomy, and the two images are overlapped.
The extra CT image is time consuming and provides the person being imaged with a small extra radiation dose. Cubresa is working to develop a standalone PET imaging system for faster image collection and a lower radiation dose at the cost of reduced anatomical information. One issue with images that rely on radiation, such as PET and CT, is that some of the radiation that comes from the person being image does not make it to the detectors to make the image because of a process called attenuation. Extensive research has been done and CT images are corrected for attenuation. Similar research is not as thoroughly completed with PET images because the attenuation corrections from the CT images can be used on the PET images. This project aims to begin further development of the attenuation correct for standalone PET images.

L2M – JOYfuel

The project background for JOYfuel stems from the pervasive issue of current social media platforms, whose default algorithms often prioritize engagement over user well-being, leading to passive consumption, digital distraction, and a significant ‘time tax’ on individuals’ productivity and mental health. Laroye AI’s core business idea is JOYfuel, an AI-powered mobile application that provides a critically needed alternative by empowering users to set personal intentions (e.g., learning goals, wellness practices, skill development). Our AI then curates personalized, distraction-free content feeds from diverse online sources, allowing users to transform their “doomscroll” into a “productive scroll.” The clear industry need is for tools that restore user agency and make online time genuinely supportive of individual aspirations.

L2M – Plant based adhesives for a greener future

The goal of this research is to employ protein derived from canola meal, a readily accessible agricultural byproduct generated in Canada, to create a biodegradable, non-toxic adhesive. This breakthrough contributes to Canada’s agriculture sector, lowers environmental and health concerns in the wood production industry, and promotes the country’s green economy goals by eliminating synthetic, petroleum based adhesives.

L2M – Patient Repositioning Device

Healthcare workers face increasing challenges in protecting themselves from injuries caused by physically demanding tasks. One of the most injury-prone activities is repositioning patients in bed, such as sliding them up or down the mattress or turning them onto their side for sling placement and backside care. These tasks often require significant manual effort and involve awkward postures that can lead to musculoskeletal injuries. Our team is developing a motorized patient repositioning device designed to assist caregivers in safely and easily turning or moving patients in bed. This device will significantly reduce physical strain on staff, lower the risk of injury for workers, and increase the quality of care.

L2M –SynapPlay

This project aims to help older adults and people with neurological conditions such as stroke or Parkinson’s disease stay independent longer by developing a tablet-based digital therapeutic tool called SynapPlay. The platform combines physical and cognitive tasks with real-time feedback to improve balance, thinking skills, and motor control, all from the comfort of home. Through interviews and co-design workshops with older adults, caregivers, and healthcare providers, the project will identify key features and accessibility needs. The goal is to create a simple and effective home-based rehabilitation solution that supports healthy aging, reduces the burden on clinics, and builds on Canadian research to improve lives and strengthen digital health innovation.

L2M – NutraMate

The NutraMate project aims to revolutionize prescription management in pharmacies by implementing an AI-driven automation system that replaces traditional manual processes. Our cutting-edge technology will significantly reduce the documentation and data entry time while also having high accuracy and improving patient safety through advanced verification processes. Our product is seamlessly integrated into existing pharmacy workflows requiring no special training and low technological barrier for adoption. Our products offer wide range of services including inventory management, reducing operational costs, and enabling pharmacies to deliver faster, safer, and more reliable services.

The core objective of the NutraMate project is to enhance pharmacy operations by automating manual data entry and prescription management, which currently consume substantial time and resources. This shift towards AI automation will empower pharmacy staff to operate more efficiently, allowing them to focus on higher-value tasks, improving both workflow efficiency and patient outcomes. Additionally, NutraMate will provide actionable data analytics to streamline inventory management for enabling better decision-making related to inventory and patient management

L2M – BioinformHER

Bioinformatics is fundamental to modern medicine, driving breakthroughs in cancer, pandemics, and disease understanding, however, while demand for this field continues to grow, its workforce still does not reflect the people it serves. Fewer than 20% of bioinformaticians are women, and less than 5.7% are Black [1]. This homogeneity reflects and perpetuates systemic biases across science leading to significant lost of innovation and non-inclusive research. This talent gap also hinders the industry’s ability to meet growing demand for skilled professionals.
BioinformHER is an EdTech platform solving this dual challenge. We are making bioinformatics education accessible, inspiring, and achievable for women and underrepresented minorities. Unlike typical online courses, we combine hands-on learning and community mentorship with powerful storytelling from female scientists who have overcome systemic barriers in the field. This approach helps learners build both confidence and skill. With over 7,500 engaged traction and 40 past interns, we are creating a more inclusive generation of scientists who ensure that biomedical research reflects and serves the challenges and overlooked problems of all communities, not just a select few. Unlike conventional MOOCs, which focus solely on content delivery, BioinformHER creates a supportive ecosystem where users see themselves reflected in instructors and mentors, making career success feel both possible and attainable. Our freemium model ensures that cost is not a barrier to entry and guarantees access to a self-sustaining engaging community of learners, while premium features options for personalized mentorship to create individualized, clear career pathways to foster the transition from learning to professional and career success.

Toward Accurate Bond Breaking: Revising Natural Orbital Functionals in RDMFT

This project aims to improve computational methods in quantum chemistry by developing better ways to calculate molecular properties. The research focuses on enhancing existing mathematical tools (called functionals) to make them more accurate, especially for molecular fragmentation processes. The project will create user-friendly software that will be freely available to scientists worldwide. For the participating institutions, this collaboration will strengthen their research capabilities: The University of the Basque Country (UPV/EHU) will expand its expertise in quantum chemistry methods, while McMaster University will benefit from new international partnerships and improved computational tools. This partnership sets the foundation for future joint research projects between these institutions.

Scalable Quantum-Enhanced Generative Models for Drug Discovery: Extending QCBM with NQS and CUDA Quantum for Multi-target Inhibitor Design

This project proposes a scalable quantum-enhanced generative model for drug discovery, targeting the design of KRAS inhibitors through the integration of Neural Quantum States (NQS), Quantum Circuit Born Machines (QCBMs), and CUDA Quantum acceleration. By replacing traditional quantum circuits with adaptive NQS representations and extending QCBM capacity to 32 qubits, the framework enables more expressive and efficient sampling of molecular space. Reinforcement-inspired optimization and virtual screening tools are incorporated to refine molecule generation toward biologically relevant candidates. The platform aims to overcome current limitations in scalability and generalizability of quantum models, offering a fast, adaptive, and physically grounded approach to multi-target drug design.