Cancer is not made up of identical cells. Tumors are complex ecosystems where some cells are far more dangerous than others. Identifying these high-risk cells has been a major challenge, because existing technologies either capture detailed information from a small number of cells or broader data from many patients, but not both.

The new AI tool, called SIDISH, bridges this gap by combining these two types of data. It learns from large patient datasets while also zooming in on individual cells, allowing researchers to identify which cells are linked to poor outcomes and disease progression.

Using this approach, the team was able to detect small populations of high-risk cancer cells across multiple cancer types, link these cells to worse patient survival, identify key genes and pathways driving aggressive disease, and simulate potential treatments in silico (virtually) to find targets that could reduce these harmful cells

Importantly, the tool doesn’t just describe the disease, but it can help predict how a patient’s cancer might behave and suggest more personalized treatment strategies.

By revealing the hidden drivers of cancer at the cellular level, this research moves us closer to precision medicine, where therapies are tailored not just to the patient, but to the most dangerous cells within their tumor.

Read the Article

SIDISH integrates single-cell and bulk transcriptomics to identify high-risk cells and guide precision therapeutics through in silico perturbation. Jolasun Y, Song K, Zheng Y, Wang J, Fonseca GJ, Eidelman DH, Ding J.
Nat Commun. 2025 Dec 10;16(1):11271.

Read More

AI tool pinpoints cells driving aggressive cancers. New approach opens door to better-targeted treatments and faster drug discovery for complex diseases. McGill Newsroom. April 15, 2026.

The post AI Tool Identifies Aggressive Cancer Cells appeared first on Meakins-Christie Laboratories.

Among these innovations, work led by Dr. Jun Ding stands out for its potential to transform how we understand and treat complex lung diseases. His team is using advanced AI models to study idiopathic pulmonary fibrosis (IPF), a serious condition where lung tissue becomes scarred and progressively loses function.

Instead of focusing only on individual genes or drugs, Dr. Ding’s approach looks at how cells change over time during disease progression. By analyzing lung cells from both healthy individuals and patients at different stages of IPF, his team built a generative AI model that can simulate how cells transition from healthy to diseased states.

This approach offers a powerful new way to identify early biological changes that signal disease onset, discover new biomarkers for diagnosis, pinpoint targets for treatment, and test whether existing drugs could be repurposed to slow or reverse disease.

As Dr. Ding explains, many complex diseases are driven by abnormal changes in cell states. If scientists can understand and potentially reverse these changes, they may be able to stop disease progression rather than just treat symptoms. Looking ahead, researchers believe that AI could guide the majority of new drug development within the next decade, marking a major shift toward more precise, efficient, and personalized medicine.

Read More

These diseases were thought to be incurable. Now AI is unlocking new treatments. BBC. by Laurie Clarke. March 10, 2026

The post AI is Transforming Drug Discovery – Jun Ding Featured by BBC appeared first on Meakins-Christie Laboratories.

Deborah Assayag (Priority Announcement)
The Longitudinal Use of Oscillometry in Interstitial Lung Diseases

Jonathon Campbell
Co-Investigators: Benjamin Smith, Kevin Schwartzman, Dick Menzies, Andrea Benedetti
Functional Outcomes, Lung health, and Livelihood Outcomes among people With Tuberculosis (FOLLOW-TB): a pan-Canadian prospective cohort study

Maziar Divangahi
Harnessing the power of trained immunity in disease tolerance against influenza virus

Elizabeth Fixman (Priority Announcement)
Sex-specific mechanisms by which environmental triggers promote durable changes to the lung to exacerbate type 2 innate and adaptive immunity

Irah King
Mechanisms of tissue-resident T cell activation for intestinal host defense

Larry Lands (Co-Principal Investigator)
Nominated Principal Investigator: Juan Ianowski (University of Saskatchewan)
Function of pulmonary ionocytes and club cells in human airway and their contribution to cystic fibrosis lung disease

Larry Lands (Co-Principal Investigator)
Nominated Principal Investigator: Sze Man Tse (Centre hospitalier universitaire Sainte-Justine)
Predicting biologic therapy response in children with severe asthma: the Medication response and Asthma Therapy in CHildren with severe Asthma (MATCHA) Study

Sushmita Pamidi
Co-Investigators: Andrea Benedetti, John Kimoff
Sleep-Disordered Breathing During Pregnancy and Long-Term Postpartum Blood Pressure Pattern

Bryan Ross
Co-Investigators: Jean Bourbeau, Jun Ding, Sabah Hussain, Larry Lands
Enhancing the Clinical Benefits of COPD Chronic Management: The SUPplementation with URolithin-A during Pulmonary Rehabilitation in COPD (SUPRA-COPD) Trial

The post CIHR Project Grant Results – Fall 2025 appeared first on Meakins-Christie Laboratories.

Jun Ding leads a team developing advanced AI models to accelerate drug discovery for diseases like Idiopathic Pulmonary Fibrosis (IPF). Their work, supported by Anaconda’s platform, identified a safe and affordable hypertension drug, costing about $10 per month, that could perform as well as current IPF therapies priced at $10,000 per month.

Beyond drug discovery, his team also created the AI tool scSemiProfiler that cuts the cost of single-cell sequencing projects by up to 90%, making large-scale studies that were once financially out of reach possible.

Recognition by Anaconda underscores the visibility and global impact of Jun Ding’s AI4Health research, reinforcing his leadership at the intersection of artificial intelligence and medicine.

Read the Case Study on Anaconda.com

McGill Researchers Discover $10 Drug Candidate to Replace $10,000 Treatment. How AI scientists leveraged the Anaconda AI Platform to identify a $10 drug that could replace a $10,000 treatment and save countless lives. Anaconda.com, October 2025.

The post Jun Ding’s AI4Health Works Featured by Anaconda, a Global AI Leader appeared first on Meakins-Christie Laboratories.

In a study published in Nature Communications, the team showed that DOLPHIN detected over 800 disease markers missed by traditional approaches in pancreatic cancer cells. The tool distinguished aggressive cancers from less severe cases, offering insights that could help doctors match patients to the right treatments earlier and more accurately.

Beyond immediate applications, DOLPHIN lays the foundation for building virtual cell models—digital simulations of cell behavior that could speed drug discovery and reduce reliance on trial-and-error in the clinic.

Read the Article

DOLPHIN advances single-cell transcriptomics beyond gene level by leveraging exon and junction reads.
Song K, Zheng Y, Zhao B, Eidelman DH, Tang J, Ding J. Nat Commun. 2025 Jul 4;16(1):6202.

In the News

New AI tool detects hidden warning signs of disease. Researchers say a closer look inside cells could be used by physicians to detect diseases earlier and better match patients to therapies. by Keila DePape, McGill Newsroom. October 1, 2025.

The post AI Tool DOLPHIN Uncovers Hidden Disease Markers Inside Single Cells appeared first on Meakins-Christie Laboratories.

In a recent study published in Nature Biomedical Engineering, UNAGI helped identify Nifedipine—a common blood pressure drug—as a possible treatment for idiopathic pulmonary fibrosis (IPF) and COVID-19-related lung damage. This prediction was confirmed in lab experiments using human lung tissue, showing that the drug could reduce signs of lung scarring.

UNAGI works by studying how individual cells change during disease. It uses single-cell data and deep learning to model disease progression and test potential treatments virtually. This method saves time, reduces costs, and opens the door to finding new therapies faster than traditional research methods.

This technology has also been applied to other diseases, like Duchenne muscular dystrophy, showing its potential to benefit many patients. Dr. Ding’s AI tools were even featured in Nature as part of a global spotlight on cutting-edge technologies advancing cell biology.

Read the Publication

A deep generative model for deciphering cellular dynamics and in silico drug discovery in complex diseases. Zheng Y, Schupp JC, Adams T, Clair G, Justet A, Ahangari F, Yan X, Hansen P, Carlon M, Cortesi E, Vermant M, Vos R, De Sadeleer LJ, Rosas IO, Pineda R, Sembrat J, Königshoff M, McDonough JE, Vanaudenaerde BM, Wuyts WA, Kaminski N, Ding J. Nat Biomed Eng. 2025 Jun 20. doi: 10.1038/s41551-025-01423-7. Online ahead of print.

Read More

Simulating disease to accelerate drug discovery with AI. Dr. Jun Ding’s UNAGI platform — and a suite of AI-powered tools — advance in-silico therapeutics, decode cellular dynamics, and streamline drug discovery across diseases. The Institute News. June 26, 2025

The post UNAGI: Simulating Disease to Discover New Treatments with AI appeared first on Meakins-Christie Laboratories.

Jun Ding: Chercheurs-boursiers et chercheuses-boursières (Junior 2).
Title: Décodage des dynamiques cellulaires dans les maladies avec la multi-omique unicellulaire pour des interventions thérapeutiques grâce aux réseaux génératifs profonds.

Bryan Ross: Chercheurs-boursiers cliniciens et chercheuses-boursières cliniciennes (Junior 1).
Title: Comprendre et prévenir les exacerbations de la MPOC pour réduire la charge des soins et améliorer la qualité de vie.

Nicole Ezer: Chercheurs-boursiers cliniciens et chercheuses-boursières cliniciennes (Junior 2).
Title: La Détection du Cancer du Poumon au Québec- accélérer le diagnostique précoce du cancer du poumon et optimiser le traitement des comorbidités pulmonaires

The post 2025-2026 FRQS Salary Awards appeared first on Meakins-Christie Laboratories.

What makes RAMEN innovative is its ability to build smart, disease-focused maps of clinical variables (called Bayesian networks) that not only find direct links but also reveal subtle, indirect connections that may be critical for diagnosis and treatment. The researchers tested RAMEN on thousands of patient records and found that it consistently outperformed existing methods in identifying key indicators of disease severity, some of which were later confirmed using gene and protein data.

Because RAMEN works across different diseases and doesn’t rely on prior assumptions, it holds promise for improving personalized medicine—helping doctors tailor care based on patterns hidden in patient data. Its speed and scalability make it especially valuable for analyzing large healthcare datasets, paving the way for faster insights into disease mechanisms and better patient outcomes.

Read More

Efficient and scalable construction of clinical variable networks for complex diseases with RAMEN. Xiong Y, Wang J, Shang X, Chen T, Fraser DD, Fonseca GJ, Rousseau S, Ding J. Cell Rep Methods. 2025 Apr 21;5(4):101022. doi: 10.1016/j.crmeth.2025.101022. Epub 2025 Apr 10. PMID: 40215965

The post New AI Tool Reveals Hidden Clues to Disease Outcomes appeared first on Meakins-Christie Laboratories.

Basil Petrof. Co-Investigator: Jun Ding. The role of trained macrophages in dystrophic diaphragm pathology.

Sabah Hussain.  Co-Principal Investigator: Gilles Gouspillou. Co-Applicants: Jean-Philippe Leduc-Gaudet, Vanina Romanello, Marco Sandri. Regulation of skeletal muscle and peroxisomal homeostasis by Depp1 protein.

See the RI-MUHC website for more information on the Fall 2024 CIHR competition results.

The post CIHR Project Grant Results – Fall 2024 appeared first on Meakins-Christie Laboratories.

Dr. Jun Ding’s work was recognized in the Nature Technology Features, highlighting its transformative potential for single-cell research and therapeutic discovery. These tools democratize single-cell omics, integrate AI to simulate cellular processes, and enhance the scalability of studies, addressing limitations in cost, throughput, and clinical translation. Among the seven tools features, three of the tools were developed by Dr. Jun Ding and his lab at McGill and the RI-MUHC — scSemiProfiler, UNAGI, and CellAgentChat — all pivotal advancements in the field.

Nature credits Dr. Jun Ding’s contributions as crucial for advancing the the Human Cell Atlas’s goals and paving the way for breakthroughs in precision medicine and drug development. As single-cell technologies continue to grow, tools like these are expected to play an even larger role in biological discovery.

Nature Commentary

Computational technologies of the Human Cell Atlas. Dance A. Nature. 2024 Nov;635(8039):773-775.

scSemiProfiler:

This tool addresses the high cost of single-cell RNA sequencing by leveraging bulk RNA sequencing data with generative AI to reconstruct high-resolution single-cell profiles. Ding’s team demonstrated that scSemiProfiler could reduce sequencing costs by approximately 80%, making single-cell studies more accessible. For example, they used it to analyze immune cells from COVID-19 patients, generating accurate profiles with minimal single-cell data.

scSemiProfiler: Advancing large-scale single-cell studies through semi-profiling with deep generative models and active learning. Wang J, Fonseca GJ, Ding J. Nat Commun. 2024 Jul 16;15(1):5989.

UNAGI:

Designed for in silico drug discovery, UNAGI models disease progression at the cellular level. Ding’s lab used this tool to create a “sandbox” for idiopathic pulmonary fibrosis (IPF), simulating how cells evolve during disease. The model identified existing drugs like nintedanib while flagging new therapeutic candidates. This tool shows promise in revolutionizing drug discovery by simulating the effects of treatments before physical experiments.

Unagi: Deep Generative Model for Deciphering Cellular Dynamics and In-Silico Drug Discovery in Complex Diseases. Zheng Y, Schupp J, Adams T, Clair G, Justet A, Ahangari F, Yan X, Hansen P, Carlon M, Cortesi E, Vermant M, Vos R, D Sadeleer L, Rosas I, Pineda R, Sembrat J, Konigshoff M, Mcdonough J, Vanaudenaerde B, Wuyts W, Kaminski N, Ding J. Preprint at Research Square https://doi.org/10.21203/rs.3.rs-3676579/v1 (2023).

CellAgentChat:

Unlike conventional approaches, this tool models individual cells as autonomous agents that interact dynamically within their environments. By simulating these interactions, CellAgentChat enables researchers to predict cell-cell signaling pathways and test drug effects in silico. For example, using breast cancer data, the model identified key interactions and drug targets like the epidermal growth factor receptor.

Harnessing Agent-Based Modeling in CellAgentChat to Unravel Cell-Cell Interactions from Single-Cell Data. Raghavan V, Li Y, Ding J. Preprint at bioRxiv https://doi.org/10.1101/2023.08.23.554489 (2024).

The post Nature Commentary Highlights the Work of Jun Ding appeared first on Meakins-Christie Laboratories.