Scalable, multimodal and AI-enabled approaches are increasingly being used in single cell analysis. Researchers are also combining different types of single-cell data, including spatial biology and perturbation studies, to better understand how cells behave and interact.
In this upcoming webinar series, Scaling Single-Cell Biology ONLINE, we explore how leading researchers are scaling single-cell workflows, integrating multi-omic and spatial datasets, and applying AI-driven approaches to interpret increasingly complex biological data.
Register to watch on-demand
Please note, by registering for one webinar in the series, you will automatically gain access to the subsequent webinars.
Webinar 1: From high-throughput profiling to population-scale insight
Register to watch on-demand
Single-cell technologies are now moving from focused experiments to large-scale studies across transcriptomics, proteomics, disease cohorts, tissue atlases, and organism-wide profiling. Researchers are now applying single-cell methods to areas such as immune monitoring, drug response and ageing research, while working to keep studies reliable and cost-effective.
This webinar will help you understand:
- Novel approaches for overcoming major barriers to scaling single-cell biology, including throughput limitations, high costs, complex analysis, and fragmented workflows.
- Strategies that are enabling faster, more integrated analysis to gain deeper, more efficient biological insights.
Talk 1: Low-cost sample preparation and high-throughput analysis towards scalable single-cell proteomics
Ryan Kelly, Professor, Brigham Young University
- How simplified sample preparation is enabling single-cell and other low-input proteomics, with >10k cells per day prepared at low cost.
- Why high-throughput separations are necessary to match the speed of latest-generation mass spectrometers, including approaches that interface multiple analytical columns with a mass spectrometer.
- How the MSConnect software package can automate aspects of experimental design and data analysis.
- How these advances can be broadly applied to other biological materials, reducing the cost of proteome profiling to just $10.
Talk 2: Cost-efficient scaling of single-cell transcriptomics via deep generative semi-profiling
Jun Ding, Principal Investigator, McGill University
- Conceptual framework of semi-profiling: integrating bulk RNA-seq with limited single-cell measurements to infer high-resolution cellular states at scale.
- Deep generative modeling for reconstructing single-cell expression landscapes from bulk cohorts.
- Active sample selection strategies to maximize information gain while minimizing sequencing cost.
- Benchmarking results demonstrating comparable performance to full single-cell profiling at a fraction of the cost.
- Applications in large-scale disease cohorts and implications for population-level single-cell studies.
Talk 3: Scaling single-cell sequencing to millions of cells to map population dynamics across tissues and time
Junyue Cao, Assistant Professor, The Rockefeller University
- Scaling single-cell profiling to organism-wide coverage by using our EasySci platform.
- Nonlinear dynamics of cellular aging and cross-organ immune remodeling.
- Extending the atlas to the epigenome: organism-wide chromatin accessibility profiling to map aging-associated regulatory changes and sex-dimorphic programs.
Webinar 2: The development of single-cell omics – integration with spatial, CRISPR perturbation and beyond
Register to watch on-demand
Real biological complexity lies in the interplay of the transcriptome, epigenome, and proteome. Researchers are now combining spatial context, temporal dynamics, and CRISPR perturbation screens to help decode complex biology.
In this webinar, we will highlight:
- Applications of single-cell multi-omics analysis to map tissue microenvironments.
- Practical design strategies for perturbation experiments at single-cell resolution.
- How to integrate temporal and longitudinal datasets to follow cell fate over time.
Talk 1: Decoding cellular responses with scalable single-cell genomics
José McFaline-Figueroa, Assistant Professor of Biomedical Engineering, Columbia University
- Scalable single-cell technologies for studying how genetic and chemical perturbations reshape cell states and gene function.
- Coupling to deep learning frameworks to resolve perturbation-induced changes to cell identity and state transitions.
- Targeted single-cell approaches that enable efficient, high-throughput measurement of selected transcripts.
- Flexible, multiplexed targeted profiling paired with perturbation screens.
Talk 2: Decoding embryonic development: the power of combining temporal data with perturbations
Eileen Furlong, Head of Genome Biology Unit, EMBL
- For regulation – more beyond RNA: Single cell ATAC-seq.
- Single cell information on chromatin modifications (scCUT&Tag).
- The power and challenges of mutant data.
- Challenges and potential of inferring gene regulatory networks.
Talk 3: Measuring, modeling, and reprogramming tissue organization
Fei Chen, Core Institute Member, The Broad Institute of MIT and Harvard
- Mapping tissue architecture at single-cell resolution.
- Understanding how spatial context shapes cell state and cell-cell interactions.
- Capturing cellular history across tissues over time.
- Identifying signalling dependencies within diseased tissues.
- Moving from descriptive tissue maps toward predictive models and tissue engineering.
Webinar 3: The data conundrum – AI for single-cell data at scale
Register to watch on-demand
The power of single-cell lies in its complexity, but data analysis remains the biggest challenge. Analysis also remains the biggest bottleneck in single-cell research, and as dataset sizes grow, so does the need for better data handling, visualisation and interpretation tools.
This webinar will focus on:
- How researchers are unlocking value for large-scale single-cell analysis.
- How AI and ML help uncover novel biology.
- Tools that will support cell type annotation, trajectory inference and atlas building.
Talk 1: AI for single-cell modeling in complex, high-dimensional biomedical datasets
Shuo Wen, Doctoral Assistant, Machine Learning for Biomedicine Lab, EPFL
- IRIS is a new multimodal data technology that captures paired cellular morphology and transcriptomic information at single-cell resolution.
- We propose a cross-modal generative framework, COSMIC, for multimodal cellular data to connect morphology and gene expression.
- Generative modelling reveals morphology-transcriptome relationships at single-cell resolution.
- A prostate cancer cell line case study demonstrates cross-modal generation, showing how the model links cellular morphology with transcriptomic signals and reveals biologically meaningful relationships.
Talk 2: Studying immunomodulation using interpretable machine learning approaches
Jishnu Das, Assistant Professor, University of Pittsburgh
- ML approaches for analyzing single-cell and spatial omic datasets to move beyond prediction to the inference of possible mechanisms.
- Incorporation of biological networks (gene regulatory and protein-protein interaction networks) into the framework to enhance the quality of inference.
- Use of agentic AI to deploy these approaches at scale.
- Broad applications of these techniques in infectious and autoimmune disease.
Talk 3: Predicting cell fate with AI: modeling single-cell multiomic dynamics to simulate genetic perturbations
Christina Leslie, Member, Computational and Systems Biology Program, Memorial Sloan Kettering Cancer Center
- How neural ODE-based models (DynaVelo) capture dynamic cell state transitions from single-cell multiomic data.
- Integrating RNA velocity and transcription factor motif activity to improve trajectory inference.
- Using AI to predict the impact of loss-of-function mutations on cellular dynamics.
- In silico identification of transcription factor perturbations to rescue disrupted cell states.
- Inferring dynamic, cell-state-specific gene regulatory networks from multiomic datasets.
