Yue Li

Membre académique associé

Professeur adjoint, McGill University, École d'informatique

Sujets de recherche

Apprentissage multimodal

Apprentissage profond

Biologie computationnelle

Génétique

Génomique unicellulaire

Grands modèles de langage (LLM)

IA en santé

Modèles bayésiens

Site web

Google Scholar

Biographie

J'ai obtenu un doctorat en informatique et biologie computationnelle de l'Université de Toronto en 2014. Avant de me joindre à l’Université McGill, j'ai été associé postdoctoral au Computer Science and Artificial Intelligence Laboratory (CSAIL) du Massachusetts Institute of Technology (MIT) (2015-2018).

Mes recherches portent sur le développement de modèles d'apprentissage probabilistes interprétables et de modèles d'apprentissage profond pour modéliser les données génétiques et épigénétiques, les dossiers de santé électroniques et les données génomiques unicellulaires.

En intégrant systématiquement des données multimodales et longitudinales, je cherche à obtenir des applications qui auront des effets tangibles en médecine computationnelle, y compris la construction de systèmes de recommandation clinique intelligents, la prévision des trajectoires de santé des patients, les prédictions personnalisées de risques polygéniques, la caractérisation des mutations génétiques fonctionnelles multitraits, et la dissection des éléments réglementaires spécifiques au type de cellule qui sont à la base des traits complexes et des maladies chez l'homme. Mon programme de recherche couvre trois domaines principaux impliquant l'apprentissage automatique appliqué à la génomique computationnelle et à la santé.

Étudiants actuels

Jun Bai

Postdoctorat - McGill

Doctorat - McGill

Vicky Dong

Maîtrise recherche - McGill

Claris Gu

Maîtrise recherche - McGill

Eric Huang

Maîtrise recherche - McGill

Github

Yixuan Li

Doctorat - McGill

Superviseur⋅e principal⋅e :

Archer Yang

Dylan Mann-Krzisnik

Doctorat - McGill

Marshall Meng

Maîtrise recherche - McGill

Superviseur⋅e principal⋅e :

Doctorat - McGill

Maîtrise recherche - McGill

Co-superviseur⋅e :

Jun Ding

Github

Wilbur Wang

Maîtrise recherche - McGill

Mona Wang Wang

Doctorat - McGill

Kunpeng Xu

Postdoctorat - McGill

Co-superviseur⋅e :

Archer Yang

Shadi Zabad

Doctorat - McGill

Github

Publications

TrajGPT: Irregular Time-Series Representation Learning of Health Trajectory.

Ziyang Song

Qincheng Lu

Mike He Zhu

David Buckeridge

Yue Li

In the healthcare domain, time-series data are often irregularly sampled with varying intervals through outpatient visits, posing challenges… (voir plus) for existing models designed for equally spaced sequential data. To address this, we propose Trajectory Generative Pre-trained Transformer (TrajGPT) for representation learning on irregularly-sampled healthcare time series. TrajGPT introduces a novel Selective Recurrent Attention (SRA) module that leverages a data-dependent decay to adaptively filter irrelevant past information. As a discretized ordinary differential equation (ODE) framework, TrajGPT captures underlying continuous dynamics and enables a time-specific inference for forecasting arbitrary target timesteps without auto-regressive prediction. Experimental results based on the longitudinal EHR data PopHR from Montreal health system and eICU from PhysioNet showcase TrajGPT's superior zero-shot performance in disease forecasting, drug usage prediction, and sepsis detection. The inferred trajectories of diabetic and cardiac patients reveal meaningful comorbidity conditions, underscoring TrajGPT as a useful tool for forecasting patient health evolution.

2025-10-13

IEEE journal of biomedical and health informatics (publié)

doi.org

Single-nucleus chromatin accessibility profiling identifies cell types and functional variants contributing to major depression

Anjali Chawla

Doruk Cakmakci

Laura M. Fiori

Wenmin Zang

Malosree Maitra

Jennie Yang

Dariusz Żurawek

Gabriella Frosi

Reza Rahimian

Haruka Mitsuhashi

Maria Antonietta Davoli

Ryan Denniston

Gary Gang Chen

Volodymyr Yerko

Deborah Mash

Kiran Girdhar

Schahram Akbarian

Naguib Mechawar

Matthew Suderman

Yue Li … (voir 2 de plus)

Corina Nagy

Gustavo Turecki

2025-08-05

Nature Genetics (publié)

doi.org

Single-nucleus chromatin accessibility profiling identifies cell types and functional variants contributing to major depression.

Anjali Chawla

Doruk Cakmakci

Laura M. Fiori

Wenmin Zang

Malosree Maitra

Jennie Yang

Dariusz Żurawek

Gabriella Frosi

Reza Rahimian

Haruka Mitsuhashi

MA Davoli

Ryan Denniston

Gary Gang Chen

V. Yerko

Deborah Mash

Kiran Girdhar

S. Akbarian

Naguib Mechawar

Matthew Suderman

Yue Li … (voir 2 de plus)

Corina Nagy

Gustavo Turecki

2025-08-05

Nature Genetics (publié)

doi.org

Single-nucleus chromatin accessibility profiling identifies cell types and functional variants contributing to major depression

Anjali Chawla

Doruk Cakmakci

Laura M. Fiori

Wenmin Zang

Malosree Maitra

Jennie Yang

Dariusz Żurawek

Gabriella Frosi

Reza Rahimian

Haruka Mitsuhashi

Maria Antonietta Davoli

MA Davoli

Ryan Denniston

Gary Gang Chen

Volodymyr Yerko

Deborah Mash

Kiran Girdhar

Schahram Akbarian

Naguib Mechawar

Matthew Suderman … (voir 3 de plus)

Yue Li

Corina Nagy

Gustavo Turecki

2025-08-05

Nature Genetics (publié)

doi.org

Toward whole-genome inference of polygenic scores with fast and memory-efficient algorithms.

Shadi Zabad

Chirayu Anant Haryan

Simon Gravel

Sanchit Misra

Yue Li

2025-07-03

American Journal of Human Genetics (publié)

doi.org

Harnessing agent-based frameworks in CellAgentChat to unravel cell-cell interactions from single-cell and spatial transcriptomics

Vishvak Raghavan

Yumin Zheng

Yue Li

Jun Ding

2025-07-01

Genome Research (publié)

doi.org

FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting

Mike He Zhu

Jun Bai

Na Li

Xiaoxiao Li

Dianbo Liu

David Buckeridge

Yue Li

2025-05-17

NPJ Digital Medicine (publié)

doi.org

ECLARE: multi-teacher contrastive learning via ensemble distillation for diagonal integration of single-cell multi-omic data

Dylan Mann-Krzisnik

Yue Li

Integrating multimodal single-cell data, such as scRNA-seq and scATAC-seq, is key for decoding gene regulatory networks but remains challeng… (voir plus)ing due to issues like feature harmonization and limited quantity of paired data. To address these challenges, we introduce ECLARE, a novel framework combining multi-teacher ensemble knowledge distillation with contrastive learning for diagonal integration of single-cell multi-omic data. ECLARE trains teacher models on paired datasets to guide a student model for unpaired data, leveraging a refined contrastive objective and transport-based loss for precise cross-modality alignment. Experiments demonstrate ECLARE’s competitive performance in cell pairing accuracy, multimodal integration and biological structure preservation, indicating that multi-teacher knowledge distillation provides an effective mean to improve a diagonal integration model beyond its zero-shot capabilities. Additionally, we validate ECLARE’s applicability through a case study on major depressive disorder (MDD) data, illustrating its capability to reveal gene regulatory insights from unpaired nuclei. While current results highlight the potential of ensemble distillation in multi-omic analyses, future work will focus on optimizing model complexity, dataset scalability, and exploring applications in diverse multi-omic contexts. ECLARE establishes a robust foundation for biologically informed single-cell data integration, facilitating advanced downstream analyses and scaling multi-omic data for training advanced machine learning models.

2025-01-27

bioRxiv (prépublication)

doi.org

scGraphETM: Graph-Based Deep Learning Approach for Unraveling Cell Type-Specific Gene Regulatory Networks from Single-Cell Multi-Omics Data

Wenqi Dong

Manqi Zhou

Boyu Han

Yi Wang

Yue Li

2025-01-27

bioRxiv (prépublication)

doi.org

SpaTM: Topic Models for Inferring Spatially Informed Transcriptional Programs

Adrien Osakwe

Wenqi Dong

Qihuang Zhang

Robert Sladek

Yue Li

Spatial transcriptomics has revolutionized our ability to characterize tissues and diseases by contextualizing gene expression with spatial … (voir plus)organization. Available methods require researchers to either train a model using histology-based annotations or use annotation-free clustering approaches to uncover spatial domains. However, few methods provide researchers with a way to jointly analyze spatial data from both annotation-free and annotation-guided perspectives using consistent inductive biases and levels of interpretability. A single framework with consistent inductive biases ensures coherence and transferability across tasks, reducing the risks of conflicting assumptions. To this end, we propose the Spatial Topic Model (SpaTM), a topic-modeling framework capable of annotation-guided and annotation-free analysis of spatial transcriptomics data. SpaTM can be used to learn gene programs that represent histology-based annotations while providing researchers with the ability to infer spatial domains with an annotation-free approach if manual annotations are limited or noisy. We demonstrate SpaTM’s interpretability with its use of topic mixtures to represent cell states and transcriptional programs and how its intuitive framework facilitates the integration of annotation-guided and annotation-free analyses of spatial data with downstream analyses such as cell type deconvolution. Finally, we demonstrate how both approaches can be used to extend the analysis of large-scale snRNA-seq atlases with the inference of cell proximity and spatial annotations in human brains with Major Depressive Disorder.

2025-01-27

bioRxiv (prépublication)

doi.org

Towards whole-genome inference of polygenic scores with fast and memory-efficient algorithms

Shadi Zabad

Chirayu Anant Haryan

Simon Gravel

Sanchit Misra

Yue Li

2025-01-22

bioRxiv (prépublication)

doi.org