Our paper Characterizing the impacts of dataset imbalance on single-cell data integration is accepted by Nature Biotechnology. We've thoroughly assessed how dataset imbalances can twist the results of single-cell integration and batch-correction, affecting everything from cell-type classification to differential expression. Our work doesn't just highlight the issue; it offers solid solutions!
Our paper scGPT: toward building a foundation model for single-cell multi-omics using generative AI is accepted by Nature Methods. Developed through the analysis of over 33 million human cells, scGPT sets a new benchmark for application versatility, offering both fine-tuning and zero-shot capabilities.
Generative AI could revolutionize health care — but not if control is ceded to big tech link
AI under the microscope: the algorithms powering the search for cells link
Toronto hospital network appoints chief AI scientist in bid to improve health care. link
From building bone to children’s literacy: 36 U of T researchers awarded Canada Research Chairs. link
Scientists are on a quest to map the human body cell by cell, charting where and why disease happens. link
Towards foundation models of biological image segmentation link
Clinical Camel is an ongoing project aimed at developing an open-source healthcare-focused chatbot. Demo link
We introduce MAESTER - a new self-supervised method achieving STOA subcellular structure segmentation at pixel resolution! Press link
We had 400+ participants from all over the world. 1000+ submissions had been received in the leaderboard! The solutions from the winning team represent state-of-art methods for universal cell segmentation in both accuracy and efficiency. A summary paper will be out soon! Press link
Dr. Bo Wang was one of two winners selected by Drs. John Dick and Stuart Orkin. Dr. Wang was selected for his work on machine learning–based approaches to development trajectories of hematopoietic. Press link
Our paper BIONIC: biological network integration using convolutions is accepted by Nature Methods. BIONIC is a GNN (graph neural network)-based approach to integrating multiple biological networks to provide a holistic view of how genes/proteins interact in a cell. It is among the first DL methods that are capable of combining hundreds of large-scale biological networks.
Our paper One Cell At a Time (OCAT): a unified framework to integrate and analyze single-cell RNA-seq data is accepted by Genome Biology. OCAT is a fast and scalable scRNA-seq integration tool that preserves biological variations while being robust to heterogenous data compared to state-of-the-art methods, such as Seurat, Harmony, and Scanorama.
We are excited to officially announce that the Fast and Low-resource semi-supervised Abdominal oRgan sEgmentation challenge (FLARE22) will take place in MICCAI2022! Join the challenge now: Registration link!
Dr. Wang was interviewd by The Gloabl And Mail on "How AI will change what happens when you see a doctor" Press link.
The Temerty Centre for AI Research and Education in Medicine (T-CAIREM) at the University of Toronto’s Temerty Faculty of Medicine announced Professor Bo Wang as the inaugural Temerty Professor in AI Research and Education in Medicine! Congratulations! Announcement link.
Our paper Long-term mortality risk stratification of liver transplant recipients: real-time application of deep learning algorithms on longitudinal data is accepted by Lancet Digital Health. We have developed and validated an innovative deep learning model to predict a patient's long-term outcome after receiving a liver transplant with over 80% accuracy.
Our paper simATAC: a single-cell ATAC-seq simulation framework is accepted by Genome Biology. simATAC is a framework provided as an R package that generates a single-cell Assay for Transposase-Accessible Chromatin sequencing (scATAC-seq) count matrix, highly resembling real scATAC-seq datasets in library size, sparsity, and averaged chromatin accessibility signals. simATAC provides a robust and systematic approach to generate in silico scATAC-seq samples with cell labels for a comprehensive tool assessment.
Our paper Genotyping SARS-CoV-2 through an interactive web application is accepted by Lancet Digital Health. We provide the COVID-19 Genotyping Tool (CGT), which offers an online, user-friendly platform where researchers can compare the genome sequence of the SARS-CoV-2 virus in their hospital against the global picture.
A two-year grant DeepCell: analyze and integrate spatial single-cell RNA-seq data is accepted by CIFAR.
Our paper SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation is accepted by MICCAI 2020.
Our paper CDF-Net: Cross-Domain Fusion Network for accelerated MRI reconstruction is accepted by MICCAI 2020.
A five-year grant Integrative analysis of single-cell multi-omics data with interpretable deep learning methods is accepted by NSERC.
We launch the CiteNet website, a search engine designed for literature exploration.
Our paper Diversity Transfer Network for Few-Shot Learning is accepted by AAAI 2020 for oral presentation!
Our paper Moment Matching for Multi-Source Domain Adaptation is accepted by ICCV 2019 for oral presentation!
Chris Mcintosh and Bo Wang won the PMCC Innovation Award for their proposal of an AI-based automatic coronary artery interpretation system. Congratulations!
Bo Wang delivered his keynote presentation Artificial Intelligence for Cardiology at the Ottawa Heart Institute, Ottawa
Bo Wang was invited to present his work “Integrative Network Analysis for Single-cell RNA-seq and Beyond” at the National Research Council, Ottawa.
Do you have ideas that you think may help us do a better science? Then...
Contact us