The Joe Chan Lab combines machine learning with disruptive single-cell sequencing and multiplex spatial imaging to study lineage plasticity in cancer, with a particular focus on histological transformation, as a mechanism of acquired resistance, immune escape, and metastasis. The lab has a special interest in quantifying plasticity across space, time, and cancer types. 

Lineage plasticity is the ability for a cell to change its phenotypic state or identity under evolutionary pressure. The most overt example of plasticity in cancer is histological transformation, where tumor cells under therapeutic pressure change to a completely different cancer type that is independent of the originally targeted gene program. Such a lineage transformation can take place as a switch from adenocarcinoma (adeno) to a more aggressive histology (i.e. neuroendocrine, squamous) across multiple cancer types (i.e. lung, prostate, colon, bladder). This plasticity often results in intra-tumoral heterogeneity with both adeno and NE cancer coexisting within the same tumor, complicating the treatment strategy as we often need to treat both cancer types at once. 

A challenge to understanding this process has been a reliance on sequencing the bulk tumor, which can only estimate the average signal. We are therefore interested in using single-cell sequencing and imaging to isolate and parse discrete intratumoral populations generated under plasticity. These are powerful technologies to dissect cancer evolution but produce sparse, high-dimensional, high-scale data that present a number of statistical challenges that demand computational innovation. Our multidisciplinary approach uses graph-based, probabilistic modeling, topological data analysis, linear and deep learning approaches to build interpretable frameworks that reveal how tumor plasticity highjacks normal, developmental, and regenerative processes to generate diverse cell populations that interact with each other and the surrounding microenvironment to mediate tumor progression over time. 

Additional details can be found in www.joechanlab.org.