


Projects
AI tools developed in the Good Lab

CohortWhisperer (coming soon)
An agentic analysis framework that uncovers patient-specific mechanisms of therapy resistance.
The reasons why existing cancer therapies fail vary from patient to patient. We use agentic AI to identify these reasons, providing insights for enhanced therapies. CohortWhisperer reads multimodal data such as single-cell transcriptomes to propose semantic outcome explanations at the level of individuals. These explanations are then aggregated across patients and computationally validated, resulting in a curated matrix of patient-explanation assignments.
Zero-shot cell-type annotation of H&E images, learned from molecular measurements of single cells.
Cancer diagnosis depends on identifying cells in tissue images, which today still takes time-consuming assays or expert annotation. SpatialWhisperer transfers the rich cell-type knowledge of single-cell transcriptomics onto ordinary histopathology images, zero-shot and without task-specific labels, turning cheap and ubiquitous H&E into a molecularly interpretable, cell-resolved readout.
In collaboration with Jure Leskovec's lab (SNAP, Stanford Computer Science).
