Cancer extracellular vesicle (EV) liquid biopsy AI signatures as predictors of response to immune checkpoint inhibitors.

Immunotherapy drugs that unlock a person’s immune system to attack tumours have shown remarkable promise in treating cancer. Unfortunately not all patients respond to these immune therapies and researchers still do not understand why some patients respond while others do not
Cancer cells release small particles called extracellular vesicles (EVs) into our blood. EVs carry messages that can instruct our immune system to shut down or to avoid attacking the cancer.

Développement d’un dispositif et d’un outil d’accompagnement au repreneuriat

Le nombre d’entrepreneurs et de dirigeants de PME de plus de 50 ans au Canada et particulièrement au Nouveau-Brunswick s’accroît et, ces derniers devront bientôt céder leur entreprise. Dans ce contexte, il devient crucial d’assurer la relève entrepreneuriale ou le « repreneuriat ».

Impact of microparticles in cancer progression - Year two

Blood platelets are the principal source of cells known to shed small extracellular vesicles which package biologically active molecules. We have recently identified a new type of these vesicles (called microparticles/MPs) that contain mitochondria, which represent the energy producing motors for living cells. We have also discovered that MPs preferentially bind and internalize into leukemia cells to transfer their contents. As a result, recipient cancer cells gain energy producing capacity, which leads to increased cancer processes.

Artificial intelligence for automated identification of cannabaceae family plant diseases and gender on low-resource devices

Automated and early identification of plant diseases from their leaves is an important task in agriculture and can have positive impacts on crop yield and quality. Crop pathogens and pests reduce the yield and quality of agricultural production. They cause substantial economic losses and have a direct impact on food security and nutrition worldwide. Due to the wide variety of crops and diseases, even a farmer or pathologist can often fail to identify plant diseases by visualizing the affected leaves. However, visual observation remains the primary approach to disease identification.

Characterization of noncoding RNA products of the Pax-5 gene

Our research team studies genetic elements that lead to the development and progression of cancer. One of these genes, called Pax-5, normally controls cellular activity and growth of healthy cells. However, deregulated levels of Pax-5 products also lead to cell hyperactivity and cancer. Recently, we have identified a new class of products, which derive from the Pax-5 gene; called circular RNAs (circRNAs). Studies on circRNAs show that they usually bind and inhibit important regulators (ex: microRNAs) of cell hyperactivity and homeostasis.

Machine learning for the extraction and classification of medical data from unstructured medical documents

This project addresses challenging needs of medicolegal report writers. Subject matter experts who provide expert witness testimony in the form of a medicolegal report, are asked to review thousands of pages of documents from a variety of sources to formulate their opinions. Report Mate’s goal is to develop an online platform aimed at medical report writing experts to manage large amounts of document data and help synthesize it into a chronological, searchable database to facilitate the creation of expert witness reports.

Les drones intelligents d’une stagiaire de l’Inde règlent un problème agricole

Les fermetures de frontières et les restrictions de voyages internationaux en raison de la pandémie de COVID-19 n’empêchent pas certains des meilleurs talents du monde de collaborer avec des chercheuses et chercheurs du Canada cet été.

Predictive artificial intelligence for qualifying loan applications

The project focuses on the development of AI-based predictive models to improve the process of approval of credit applications both at the level of private and commercial loans. We will focus our work on analysis produced by these models fed not only with financial data, but also with customer behavior data. We will also pay particular attention to clients whose amount of information traditionally used to activate a favorable borrowing decision does not meet the criteria traditionally required.

Psychometric evaluation of the Show Up Questionnaire and estimation of innovation climate latent profiles

ShowUp is a new product by Dovico that provides teammates the opportunity to improve their workplace culture. The evaluation is conducted with the help of a questionnaire. Dovico aims to use the results of these questionnaires in a machine learning setting to predict innovative culture in teams and organizations.

Haine, désinformation et francophonie minoritaire

La haine en ligne et la désinformation contribuent à la polarisation sociale et à la marginalisation des groupes les plus vulnérables. Ils représentent une menace importante au bon fonctionnement de notre démocratie. Actuellement, aucune recherche n’aborde la haine et la désinformation contre les minorités francophones au Canada. Pourtant au Nouveau-Brunswick, les messages hostiles sur les médias sociaux et la diffusion des fausses nouvelles ont été largement mobilisés afin de marginaliser la minorité francophone.