Large-scale single-cell datasets are creating new opportunities to understand biology, model drug response, and accelerate discovery. As these datasets grow, two needs are becoming increasingly important: generating clean, high-quality single-cell data at unprecedented scale to train AI models and applying analytical frameworks that can turn complex results into biological insight.

This webinar will feature two complementary presentations focused on different aspects of these challenges.

First, Johnny Yu, CSO and cofounder of Tahoe Therapeutics, will discuss the generation of Tahoe-100 Million, the largest publicly available single-cell dataset to date. Spanning 50 cancer cell lines, 379 drugs at three concentrations and more than 56,000 conditions, Tahoe-100M comprises over 100 million single-cell transcriptomes from co-cultured, drug-treated cells. It provides a training dataset capable of powering predictive models of drug action, shifting discovery from one-perturbation-at-a-time studies toward AI-driven prediction of efficacy, resistance and combination effects.

Following, Britt Flaherty, director at QIAGEN Digital Insights, will focus on the critical analytical challenge of extracting mechanistic insight from large and complex single-cell datasets. While single-cell workflows often rely on clustering, marker gene identification and descriptive annotation, these approaches can limit the ability to translate high-dimensional cellular states into biologically meaningful and experimentally actionable hypotheses.

The speakers will discuss a case study in neuroblastoma to demonstrate how a dataset of this scale can uncover cellular response mechanisms, prioritize therapeutic hypotheses, and generate actionable insights into disease biology.

Attendees will learn:

• - About the Tahoe-100 Million dataset and Tahoe’s plans to build an even larger dataset consisting of 300 million single cells

• - How Parse Biosciences Evercode single-cell RNA sequencing technology enables the generation of high-resolution, single-cell data at scale

• - How large-scale single-cell datasets can support AI models for predicting drug MoA, efficacy, resistance, and combination effects

• - How to harmonize, curate, contextualize, and rapidly interrogate large-scale single-cell datasets to support cross-study comparisons, perturbation-driven analyses, and hypothesis generation

• - How to use integrated pathway- and network-driven interpretation to move analyses beyond clustering to prioritize targets, uncover signaling programs, and accelerate translational insight