Vector Institute

🎉 Exciting News in Genomic Foundation Models! 🎉 Genetic variants (GVs) are key in diagnosing and treating genetic diseases. With the plummeting costs of next-generation sequencing, we now have a treasure trove of GV data. But this surge presents a challenge for clinicians: how to prioritize patient-specific GVs and integrate them with existing databases for better patient care. 🔍 Deep learning models, and more recently foundation models, have shown promise in variant effect prediction (VEP), but they often oversimplify the problem into binary classifications: pathogenic or benign. These models also lack standardized performance assessments and fail to consider the complexities of genetic expression, such as penetrance and expressivity, across different biological contexts. 💡 Enter: Representation Learning! We believe it’s the key to effectively classifying and aligning unknown GVs with clinically-verified ones. Introducing our large-scale dataset: 🌟 GV-Rep 🌟 Designed for foundation models, it features: --Comprehensive Dataset: 7 million records, including data from 3,166,541 MAVEs, 17,548 gene knockout tests across 1,107 cell lines, QTLs across 14 tissue types, 1,808 oligenic variant combinations, and 156 clinically verified GVs. --Detailed Analysis: Exploring the structure and properties of the dataset. --Experimentation with Genomic Foundation Models (GFMs): Revealing the gap between current GFM capabilities and accurate GV representation, especially for cell- and tissue-level tasks. We hope GV-Rep will advance genomic foundation models and bridge this gap. 📚 Preprint: https://lnkd.in/gy722qZi 💻 Code: https://lnkd.in/ghKgrzMt Huge shoutout to Vallijah Subasri, an ML scientist in our team, and Zehui Li, an intern Vector Institute, for their leadership in this project! Stay tuned for our full paper with detailed experiments and more clinically meaningful use cases! 🚀

🌟 We're thrilled to announce the publication of "A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice," now available on arXiv. 🔍 This extensive 65-page analysis, referencing over 500 scholarly articles, covers significant advancements in recommender systems from 2017 to 2024. It skillfully bridges theoretical concepts with real-world applications across industries such as e-commerce, healthcare, and finance. 📚 Abstract: Recommender Systems (RS) play an integral role in enhancing user experiences by providing personalized item suggestions. This survey reviews the progress in RS inclusively from 2017 to 2024, effectively connecting theoretical advances with practical applications. We explore the development from traditional RS techniques like content-based and collaborative filtering to advanced methods involving deep learning, graph-based models, reinforcement learning, and large language models. We also discuss specialized systems such as context-aware, review-based, and fairness-aware RS. The primary goal of this survey is to bridge theory with practice. It addresses challenges across various sectors, including e-commerce, healthcare, and finance, emphasizing the need for scalable, real-time, and trustworthy solutions. Through this survey, we promote stronger partnerships between academic research and industry practices. The insights offered by this survey aim to guide industry professionals in optimizing RS deployment and to inspire future research directions, especially in addressing emerging technological and societal trends 🤝 Special thanks to our co-authors for their invaluable contributions: - Shaina Raza, PhD, Vector Institute - Mizanur Rahman, RBC - Safi K., Vector Institute - Armin Toroghi, Vector Institute/University of Toronto - Ananya Raval, Vector Institute - Farshad Navah, BMO We also appreciate the expert guidance from Scott Sanner and the supportive insights from Andres Rojas, Ali Taiyeb, and Deval Pandya, who were instrumental throughout this project, and Veronica Chatrath for her contribution in the ideation phase. 🌐 We hope this paper serves as a key resource for those in academia or industry looking to deepen their understanding of recommender systems. Dive into the full paper here! 🔗 https://lnkd.in/dXGhwv-a #RecommenderSystems #MachineLearning #DeepLearning #AI #Research #VectorInstitute #Innovation #Technology #Academia #Industry

👋 Are you ready for new opportunities? Vector Sponsors are looking to hire! Check out these open roles on Vector's Talent Hub: ➕ RBC - Senior Machine Learning & Data Engineer ➕ Thomson Reuters - Vice President, Data and Analytics, Reuters ➕ Deloitte - Analyst/Senior Associate, Credit Risk Models - Financial Engineering & Modeling ➕ Roche - RWD Analytics Engineer ➕ Sun Life Financial - Senior Data Scientist (Health) ➕ Deep Genomics - Senior Machine Learning Operations Engineer (ML Ops) - Accelerating Drug Discovery with AI https://lnkd.in/gXAnhhzd - 👋 Êtes-vous prêt à saisir de nouvelles opportunités ? Les sponsors de Vecteur cherchent à embaucher ! Consultez ces postes à pourvoir sur le Hub des talents de Vecteur : ➕ RBC - Senior Machine Learning & Data Engineer ➕ Thomson Reuters - Vice President, Data and Analytics, Reuters ➕ Deloitte - Analyst/Senior Associate, Credit Risk Models - Financial Engineering & Modeling ➕ Roche - RWD Analytics Engineer ➕ Sun Life Financial - Senior Data Scientist (Health) ➕ Deep Genomics - Senior Machine Learning Operations Engineer (ML Ops) - Accelerating Drug Discovery with AI

Happy to share our new paper published in Neuropsychologia: https://lnkd.in/eE_8EWZn

📊 You don’t need any experience in coding for our Excel to AI workshop! It is designed for Black & Indigenous in Canada students from all backgrounds. Register: https://lnkd.in/gNEu26RN Here’s what you’ll gain: • Basic knowledge of Python • Insights on how your skills can translate to a career in AI • A professional development certificate of completion • An invitation to attend Vector’s AI Summit and Career Fair in September Workshop dates: September 16, 18, 23, 25, 2024 from 1:00 PM - 3:00 PM ET, online via Zoom Your journey from Excel to AI starts here. Apply by August 20, 2024 at 1:00 PM ET! At the Vector Institute we are committed to driving excellence and leadership in Canada’s knowledge, creation, and use of AI to foster economic growth and improve the lives of Canadians. In order to relieve disadvantage and alleviate the under-representation of Black and Indigenous people in AI, and to attempt to achieve equal opportunity in the field of AI, programs like this are offered to qualified Black and Indigenous persons, studying at or having recently graduated from a Canadian post-secondary institute, who self-identify as such in the application process. This initiative is designed to meet the criteria of a special program under the Ontario Human Rights Code. #LearnCode #Python #DiversityInTech #Opportunities #RemarkableAI - Vous n'avez pas besoin d'expérience en codage pour participer à notre atelier Excel to AI ! Il est conçu pour les étudiants noirs et indigènes de toutes origines. Voici ce que vous apprendrez : - Connaissance de base de Python - Des idées sur la façon dont vos compétences peuvent déboucher sur une carrière dans l'intelligence artificielle. - Un certificat de développement professionnel - Une invitation à participer au sommet de l'IA et au salon de l'emploi de Vector en septembre Dates de l'atelier : 16, 18, 23, 25, 2024 septembre de 13h00 à 15h00 ET, en ligne via Zoom Votre voyage d'Excel à l'IA commence ici. Postulez avant le 20 août 2024 à 13:00 ET ! À l'Institut Vecteur, nous nous engageons à promouvoir l'excellence et le leadership dans la connaissance, la création et l'utilisation de l'IA au Canada afin de favoriser la croissance économique et d'améliorer la vie des Canadiens. Afin d'atténuer les désavantages et la sous-représentation des Noirs et des Autochtones dans le domaine de l'IA, et pour tenter d'atteindre l'égalité des chances dans le domaine de l'IA, des programmes comme celui-ci sont offerts aux Noirs et aux Autochtones qualifiés qui étudient dans un établissement postsecondaire canadien ou qui en sont récemment sortis et qui s'identifient comme tels dans le cadre du processus de demande. Cette initiative est conçue pour répondre aux critères d'un programme spécial en vertu du Code des droits de l'homme de l'Ontario.

Vector is thrilled to announce the addition of three remarkable individuals to our Board of Directors Shauneen Bruder, Ashley Casanovan, and Miyo Yamashita. Each brings a wealth of experience that will be invaluable as Vector continues to drive excellence and leadership in Canada's AI landscape. Join us in celebrating this new chapter as we continue to drive excellence to leverage responsible AI to foster economic growth and improve the lives of Canadians. - Vecteur est ravi d'annoncer l'ajout de trois personnes remarquables à son conseil d'administration : Shaunee Bruder, Ashley Casanovan et Miyo Yamashita. Chacun d'entre eux apporte une richesse d'expérience qui sera inestimable alors que Vecteur continue de favoriser l'excellence et le leadership enIA au Canada. Rejoignez-nous pour célébrer ce nouveau chapitre alors que nous continuons à viser l'excellence pour tirer parti d'une IA responsable afin de favoriser la croissance économique et d'améliorer la vie des Canadiens.

I'm thrilled to share an update about the Vector Institute’s Board of Directors . As we continue to drive AI innovation and adoption in Canada, our board plays a crucial role in steering our mission forward and help us remain focused on developing the people, skills, and resources to be best in class at the use of AI. Please join me in welcoming our new board members: Shauneen Bruder, current Chair of the Board of CN, brings her wealth of experience in corporate governance and operations in technology-driven financial services. Her strategic insights will be crucial as we navigate the evolving AI landscape. Ashley Casovan, Managing Director of IAPP's AI Governance Center, is a recognized technology policy expert. Her deep knowledge of responsible AI development and global AI governance will be instrumental in shaping our approach to ethical AI advancement. Dr. Miyo Yamashita brings extensive leadership experience across multiple sectors, including her current role as President and CEO of The Princess Margaret Cancer Foundation. Her background in AI strategy and bridging technology with societal impact will be invaluable to our work. At Vector Institute, we're committed to fostering AI research, adoption, and innovation that benefits all Canadians. Our new board members' diverse expertise in healthcare, finance, governance, and responsible AI aligns perfectly with our mission to drive excellence and leadership in Canada's AI ecosystem. We look forward to the fresh perspectives and dynamic leadership our new members will bring as we continue to advance AI research, drive industry adoption, and promote responsible AI development in Canada and beyond. #AIinnovation #LeadershipAnnouncement #CanadianAI

The 20th edition of CIFAR’s DLRL Summer School brought nearly 200 next-gen AI talent from around the world to Canada for 10 days of intense learning at the Vector Institute , bringing the global DLRL alumni count to nearly 3K. 🎉 Approximately half of this year’s attendees were international students, hailing from 25 countries. Notes Elissa Strome, Executive Director of the Pan-Canadian Strategy at CIFAR, “For twenty years, DLRL has grown in stature as an incredible opportunity for the world’s best emerging talent in AI to come and learn about the latest advances in the field. Our alumni have gone on to create some of the most important breakthroughs in the field, and they frequently cite DLRL and their time in Canada as planting the seed for their scientific ideas and collaborative networks. For Canada, the benefits are an enriched and diversified AI workforce and research networks and deeper opportunities for future global partnerships in this important field. It’s a win-win situation.” Read more about the event: https://lnkd.in/gtHiSBNu --------- La 20e École d’été APAR du CIFAR a rassemblé au Canada près de 200 talents en IA de la prochaine génération venus du monde entier pour 10 jours d’apprentissage intense à Vector Institute, portant le nombre d’ancien.nes de l’APAR à près de 3K. 🎉 Environ la moitié des personnes présentes étaient des étudiantes et étudiants étrangers, originaires de 25 pays du monde. « En 20 ans, l’École d’été sur l’APAR a pris de l’envergure et constitue à présent une occasion en or, pour les talents les plus prometteurs de l’IA dans le monde, de venir s’informer sur les dernières avancées du secteur, explique Elissa Strome, directrice exécutive de la Stratégie pancanadienne en matière d’IA du CIFAR. Les membres de nos cohortes sont à l’origine de certaines des plus grandes percées du domaine et attribuent souvent la naissance de leurs idées et de leurs réseaux de collaboration à leur participation à l’École. De son côté, le Canada y trouve une main-d’œuvre et des réseaux de recherche bonifiés et diversifiés en IA, ainsi que des possibilités accrues de partenariats mondiaux dans ce secteur important. Tout le monde y gagne. » En savoir plus: https://lnkd.in/gS6sb4Nt

Great quote from Alex Cui in Murad Hemmadi's story on the buzzy vibe at last week's #DLRL2024 summer school, where savvy recruiters from some of Canada's top AI employers engaged with early-career researchers attracted from everywhere in the world to attend our legendary summer school, this year hosted at Vector Institute: “What kind of person signs up, during the beautiful days of summer, to go and do more school?...People from around the world who are really curious and passionate about AI.” 💯

👏 Vector Researchers have over 50 papers accepted to this year’s [ICML] Int'l Conference on Machine Learning! Explore the remarkable work here 👇 https://lnkd.in/gDxAFJxu - 👏 Les chercheurs de Vecteur ont accepté plus de 50 articles à la conférence de cette année [ICML] Int'l Conference on Machine Learning ! Explorez le travail remarquable ici 👇