Bo Wang
@bowang87.bsky.social
Chief AI Officer @ UHN; Assistant Prof. @ U of Toronto; CIFAR AI Chair @ Vector Institute; AI & Biology
This pivotal work is the result of a collaborative effort led by Micaela E. Consens, with contributions from Cameron Dufault, Michael Wainberg, Duncan Forster, Mehran Karimzadeh, Hani Goodarzi, Fabian J. Theis, Alan Moses.
@uhnresearch.bsky.social
@vectorinstitute.ai
@uoft.bsky.social
@uhnresearch.bsky.social
@vectorinstitute.ai
@uoft.bsky.social
March 17, 2025 at 2:58 PM
This pivotal work is the result of a collaborative effort led by Micaela E. Consens, with contributions from Cameron Dufault, Michael Wainberg, Duncan Forster, Mehran Karimzadeh, Hani Goodarzi, Fabian J. Theis, Alan Moses.
@uhnresearch.bsky.social
@vectorinstitute.ai
@uoft.bsky.social
@uhnresearch.bsky.social
@vectorinstitute.ai
@uoft.bsky.social
⚡ Strengths, Limitations, & Future Directions: Gain insights into the current capabilities of genomic AI, its limitations, and the promising avenues for future research and application.
March 17, 2025 at 2:58 PM
⚡ Strengths, Limitations, & Future Directions: Gain insights into the current capabilities of genomic AI, its limitations, and the promising avenues for future research and application.
📊 Comparative Analysis of Models: We delve into the evolution from sequence-to-function models like DeepSEA and Enformer to sequence-to-sequence models such as DNABERT and Evo, highlighting their respective strengths and applications.
March 17, 2025 at 2:58 PM
📊 Comparative Analysis of Models: We delve into the evolution from sequence-to-function models like DeepSEA and Enformer to sequence-to-sequence models such as DNABERT and Evo, highlighting their respective strengths and applications.
🚀 Beyond Transformers—Introducing HyenaDNA: Explore innovative architectures like HyenaDNA, which offer efficient long-range genomic sequence modeling at single nucleotide resolution, pushing the boundaries of genomic research.
March 17, 2025 at 2:58 PM
🚀 Beyond Transformers—Introducing HyenaDNA: Explore innovative architectures like HyenaDNA, which offer efficient long-range genomic sequence modeling at single nucleotide resolution, pushing the boundaries of genomic research.
🧠 Transformers in Genomics: Discover how transformer architectures, renowned for their success in natural language processing, are adept at capturing long-range dependencies in genomic data, leading to more accurate models.
March 17, 2025 at 2:58 PM
🧠 Transformers in Genomics: Discover how transformer architectures, renowned for their success in natural language processing, are adept at capturing long-range dependencies in genomic data, leading to more accurate models.
Key Highlights:
🔬 The Challenges Addressed by gLMs: gLMs tackle the intricate task of interpreting vast genomic sequences, enabling predictions about gene regulation, variant effects, and more.
🔬 The Challenges Addressed by gLMs: gLMs tackle the intricate task of interpreting vast genomic sequences, enabling predictions about gene regulation, variant effects, and more.
March 17, 2025 at 2:58 PM
Key Highlights:
🔬 The Challenges Addressed by gLMs: gLMs tackle the intricate task of interpreting vast genomic sequences, enabling predictions about gene regulation, variant effects, and more.
🔬 The Challenges Addressed by gLMs: gLMs tackle the intricate task of interpreting vast genomic sequences, enabling predictions about gene regulation, variant effects, and more.
🙏 A huge team effort behind this work, with special appreciation to BowenLi Lab
for driving the project. Kudos to Haotian Cui, Yue Xu, Kuan Pang, Gen Li and Fanglin Gong!
for driving the project. Kudos to Haotian Cui, Yue Xu, Kuan Pang, Gen Li and Fanglin Gong!
February 18, 2025 at 3:08 PM
🙏 A huge team effort behind this work, with special appreciation to BowenLi Lab
for driving the project. Kudos to Haotian Cui, Yue Xu, Kuan Pang, Gen Li and Fanglin Gong!
for driving the project. Kudos to Haotian Cui, Yue Xu, Kuan Pang, Gen Li and Fanglin Gong!
🌐 Beyond mRNA drugs, LUMI-lab exemplifies a scalable framework for AI-driven molecular discovery, pushing boundaries in material science & drug delivery.
📜 Read the preprint: 🔗 biorxiv.org/content/10.1...
💻 Code available on GitHub: 🔗 github.com/bowenli-lab/...
📜 Read the preprint: 🔗 biorxiv.org/content/10.1...
💻 Code available on GitHub: 🔗 github.com/bowenli-lab/...
LUMI-lab: a Foundation Model-Driven Autonomous Platform Enabling Discovery of New Ionizable Lipid Designs for mRNA Delivery
The complexity of molecular discovery requires autonomous systems that efficiently explore vast and uncharted chemical spaces. While integrating artificial intelligence (AI) with robotic automation ha...
biorxiv.org
February 18, 2025 at 3:08 PM
🌐 Beyond mRNA drugs, LUMI-lab exemplifies a scalable framework for AI-driven molecular discovery, pushing boundaries in material science & drug delivery.
📜 Read the preprint: 🔗 biorxiv.org/content/10.1...
💻 Code available on GitHub: 🔗 github.com/bowenli-lab/...
📜 Read the preprint: 🔗 biorxiv.org/content/10.1...
💻 Code available on GitHub: 🔗 github.com/bowenli-lab/...
🚀 Why it matters?
LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡
LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡
February 18, 2025 at 3:08 PM
🚀 Why it matters?
LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡
LNPs are the backbone of mRNA therapeutics, yet discovery has been slow due to data scarcity. LUMI-lab shows that AI-powered autonomous labs can accelerate mRNA delivery innovation🚀💡
- 1,700+ new LNPs synthesized & tested across 10 iterative cycles
- Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design
- 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells
- Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design
- 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells
February 18, 2025 at 3:08 PM
- 1,700+ new LNPs synthesized & tested across 10 iterative cycles
- Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design
- 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells
- Brominated lipids autonomously identified as a novel structural feature that enhances mRNA transfection—an insight previously unrecognized in LNP design
- 20.3% in vivo CRISPR gene editing efficiency in lung epithelial cells
🔥 Key Highlights:
- Foundation model trained on 28M molecules using a three-step strategy:
- Unsupervised pretraining to capture broad molecular knowledge
- Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system
- Foundation model trained on 28M molecules using a three-step strategy:
- Unsupervised pretraining to capture broad molecular knowledge
- Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system
February 18, 2025 at 3:08 PM
🔥 Key Highlights:
- Foundation model trained on 28M molecules using a three-step strategy:
- Unsupervised pretraining to capture broad molecular knowledge
- Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system
- Foundation model trained on 28M molecules using a three-step strategy:
- Unsupervised pretraining to capture broad molecular knowledge
- Continual pretraining to specialize in lipid-like molecules - Active learning fine-tuning within a closed-loop experimental system
🔬 What is LUMI-lab?
LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data.
LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data.
February 18, 2025 at 3:08 PM
🔬 What is LUMI-lab?
LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data.
LUMI-lab integrates molecular foundation models with autonomous robotic experiments to efficiently explore new LNPs (lipid nanoparticles, mRNA delivery vehicles) with minimal wet-lab data.
🎉 Results speak for themselves:
- 63.1% accuracy on ChestAgentBench
- State-of-the-art performance on CheXbench
- Outperforms both general-purpose and specialized medical models
🙏 Huge shoutout to
Adibvafa, Jun, Alif, and Hongwei for their exceptional work on this project!
- 63.1% accuracy on ChestAgentBench
- State-of-the-art performance on CheXbench
- Outperforms both general-purpose and specialized medical models
🙏 Huge shoutout to
Adibvafa, Jun, Alif, and Hongwei for their exceptional work on this project!
February 18, 2025 at 2:21 AM
🎉 Results speak for themselves:
- 63.1% accuracy on ChestAgentBench
- State-of-the-art performance on CheXbench
- Outperforms both general-purpose and specialized medical models
🙏 Huge shoutout to
Adibvafa, Jun, Alif, and Hongwei for their exceptional work on this project!
- 63.1% accuracy on ChestAgentBench
- State-of-the-art performance on CheXbench
- Outperforms both general-purpose and specialized medical models
🙏 Huge shoutout to
Adibvafa, Jun, Alif, and Hongwei for their exceptional work on this project!
📊 Introducing ChestAgentBench:
We're also releasing ChestAgentBench, a comprehensive medical agent benchmark built from 675 expert-curated clinical cases, featuring 2,500 complex medical queries across 7 categories.
Check it out: huggingface.co/datasets/wan...
We're also releasing ChestAgentBench, a comprehensive medical agent benchmark built from 675 expert-curated clinical cases, featuring 2,500 complex medical queries across 7 categories.
Check it out: huggingface.co/datasets/wan...
February 18, 2025 at 2:21 AM
📊 Introducing ChestAgentBench:
We're also releasing ChestAgentBench, a comprehensive medical agent benchmark built from 675 expert-curated clinical cases, featuring 2,500 complex medical queries across 7 categories.
Check it out: huggingface.co/datasets/wan...
We're also releasing ChestAgentBench, a comprehensive medical agent benchmark built from 675 expert-curated clinical cases, featuring 2,500 complex medical queries across 7 categories.
Check it out: huggingface.co/datasets/wan...
💡 Key Features:
- Unified Framework: Seamlessly integrates specialized medical tools with multimodal large language model reasoning.
- Dynamic Orchestration: Intelligent tool selection and coordination for complex queries.
- Clinical Focus: Designed for real-world medical workflows and deployment.
- Unified Framework: Seamlessly integrates specialized medical tools with multimodal large language model reasoning.
- Dynamic Orchestration: Intelligent tool selection and coordination for complex queries.
- Clinical Focus: Designed for real-world medical workflows and deployment.
February 18, 2025 at 2:21 AM
💡 Key Features:
- Unified Framework: Seamlessly integrates specialized medical tools with multimodal large language model reasoning.
- Dynamic Orchestration: Intelligent tool selection and coordination for complex queries.
- Clinical Focus: Designed for real-world medical workflows and deployment.
- Unified Framework: Seamlessly integrates specialized medical tools with multimodal large language model reasoning.
- Dynamic Orchestration: Intelligent tool selection and coordination for complex queries.
- Clinical Focus: Designed for real-world medical workflows and deployment.
🛠️ Integrated Tools:
- Visual QA: CheXagent & LLaVA-Med
- Segmentation: MedSAM & ChestX-Det
- Report Generation: CheXpert Plus
- Classification: TorchXRayVision
- Grounding: Maira-2
- Synthetic Data: RoentGen
- Visual QA: CheXagent & LLaVA-Med
- Segmentation: MedSAM & ChestX-Det
- Report Generation: CheXpert Plus
- Classification: TorchXRayVision
- Grounding: Maira-2
- Synthetic Data: RoentGen
February 18, 2025 at 2:21 AM
🛠️ Integrated Tools:
- Visual QA: CheXagent & LLaVA-Med
- Segmentation: MedSAM & ChestX-Det
- Report Generation: CheXpert Plus
- Classification: TorchXRayVision
- Grounding: Maira-2
- Synthetic Data: RoentGen
- Visual QA: CheXagent & LLaVA-Med
- Segmentation: MedSAM & ChestX-Det
- Report Generation: CheXpert Plus
- Classification: TorchXRayVision
- Grounding: Maira-2
- Synthetic Data: RoentGen
🎯 Why MedRAX?
While specialized AI models excel at specific chest X-ray tasks, they often operate in isolation. Medical professionals need a unified, reliable system that can handle complex queries while maintaining accuracy. MedRAX bridges this gap!
While specialized AI models excel at specific chest X-ray tasks, they often operate in isolation. Medical professionals need a unified, reliable system that can handle complex queries while maintaining accuracy. MedRAX bridges this gap!
February 18, 2025 at 2:21 AM
🎯 Why MedRAX?
While specialized AI models excel at specific chest X-ray tasks, they often operate in isolation. Medical professionals need a unified, reliable system that can handle complex queries while maintaining accuracy. MedRAX bridges this gap!
While specialized AI models excel at specific chest X-ray tasks, they often operate in isolation. Medical professionals need a unified, reliable system that can handle complex queries while maintaining accuracy. MedRAX bridges this gap!
What is MedRAX?
MedRAX is the first versatile AI agent that seamlessly integrates state-of-the-art chest X-ray analysis tools and multimodal large language models into a unified framework, enabling dynamic reasoning for complex medical queries without additional training.
MedRAX is the first versatile AI agent that seamlessly integrates state-of-the-art chest X-ray analysis tools and multimodal large language models into a unified framework, enabling dynamic reasoning for complex medical queries without additional training.
February 18, 2025 at 2:21 AM
What is MedRAX?
MedRAX is the first versatile AI agent that seamlessly integrates state-of-the-art chest X-ray analysis tools and multimodal large language models into a unified framework, enabling dynamic reasoning for complex medical queries without additional training.
MedRAX is the first versatile AI agent that seamlessly integrates state-of-the-art chest X-ray analysis tools and multimodal large language models into a unified framework, enabling dynamic reasoning for complex medical queries without additional training.
Huge shoutout to the incredible PHD students Chloe Wang and Haotian Cui for leading this groundbreaking project! 🎉
Massive thanks to our amazing co-authors Andrew, Ronald, and Hani ( @genophoria.bsky.social )from
@arcinstitute.org
—this work wouldn't have been possible without you! 👏
Massive thanks to our amazing co-authors Andrew, Ronald, and Hani ( @genophoria.bsky.social )from
@arcinstitute.org
—this work wouldn't have been possible without you! 👏
February 17, 2025 at 3:52 PM
Huge shoutout to the incredible PHD students Chloe Wang and Haotian Cui for leading this groundbreaking project! 🎉
Massive thanks to our amazing co-authors Andrew, Ronald, and Hani ( @genophoria.bsky.social )from
@arcinstitute.org
—this work wouldn't have been possible without you! 👏
Massive thanks to our amazing co-authors Andrew, Ronald, and Hani ( @genophoria.bsky.social )from
@arcinstitute.org
—this work wouldn't have been possible without you! 👏
📄 Read the preprint: biorxiv.org/content/10.1...
💻 Explore the code/weights: github.com/bowang-lab/s...
#SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData
💻 Explore the code/weights: github.com/bowang-lab/s...
#SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData
scGPT-spatial: Continual Pretraining of Single-Cell Foundation Model for Spatial Transcriptomics
Spatial transcriptomics has emerged as a pivotal technology for profiling gene expression of cells within their spatial context. The rapid growth of publicly available spatial data presents an opportu...
biorxiv.org
February 17, 2025 at 3:52 PM
📄 Read the preprint: biorxiv.org/content/10.1...
💻 Explore the code/weights: github.com/bowang-lab/s...
#SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData
💻 Explore the code/weights: github.com/bowang-lab/s...
#SpatialTranscriptomics #SingleCell #AIResearch #MachineLearning #SpatialData
✨ Multi-Modal & Multi-Slide Integration – Seamless clustering & spatial domain identification across slides and modalities.
✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings.
✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings.
February 17, 2025 at 3:52 PM
✨ Multi-Modal & Multi-Slide Integration – Seamless clustering & spatial domain identification across slides and modalities.
✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings.
✨ Cell-Type Deconvolution & Gene Imputation – Unlocks cross-resolution & cross-modality harmonization with fine-tuned embeddings.
✨ Revolutionary MoE Decoders – A cutting-edge Mixture of Experts (MoE) architecture for protocol-aware gene expression decoding.
✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization.
✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization.
February 17, 2025 at 3:52 PM
✨ Revolutionary MoE Decoders – A cutting-edge Mixture of Experts (MoE) architecture for protocol-aware gene expression decoding.
✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization.
✨ Spatially-Aware Training Strategy – A neighborhood-based masked reconstruction approach to capture complex cell-type colocalization.