MIT’s CellLENS AI maps immune cell behavior to advance cancer treatment

MIT researchers have developed CellLENS (Cell Local Environment and Neighborhood Scan), a new AI system that reveals hidden cell subtypes by analyzing molecular, spatial, and morphological data simultaneously. The deep learning tool promises to advance precision medicine by enabling scientists to identify rare immune cell subtypes and understand how their location and activity relate to disease processes, particularly in cancer immunotherapy.

What you should know: CellLENS combines convolutional neural networks and graph neural networks to create comprehensive digital profiles for individual cells within tissues.

• The system analyzes RNA or protein molecules, spatial location, and microscopic appearance simultaneously—traditionally examined separately by researchers.
• When applied to healthy tissue and cancer samples including lymphoma and liver cancer, CellLENS uncovered rare immune cell subtypes and revealed their relationship to disease processes.
• The tool can identify cells based not just on type, but on their specific function and location within tumors.

Why this matters: Current methodologies often miss critical molecular or contextual information that could improve cancer treatment outcomes.

• Immunotherapies may target cells that only exist at tumor boundaries, limiting their effectiveness.
• The ability to detect multiple layers of cellular information could lead to more precise cancer diagnostics and targeted therapies.
• Understanding how immune systems interact with tumors at the cellular level is crucial for developing better immunotherapies.

How it works: The AI system builds comprehensive profiles by fusing three domains of cellular information that were previously analyzed separately.

• CellLENS groups cells with similar biology, separating even those that appear similar in isolation but behave differently based on their surroundings.
• The deep learning approach can detect morphology and spatial positioning within tissues.
• The system effectively identifies new biomarkers that provide specific information about diseased cells.

What they’re saying: Lead researcher Bokai Zhu, an MIT postdoc, explains the enhanced precision the tool provides.

• “Initially we would say, oh, I found a cell. This is called a T cell. Using the same dataset, by applying CellLENS, now I can say this is a T cell, and it is currently attacking a specific tumor boundary in a patient.”
• Alex K. Shalek, director of MIT’s Institute for Medical Engineering and Science, emphasized the tool’s potential: “I’m extremely excited by the potential of new AI tools, like CellLENS, to help us more holistically understand aberrant cellular behaviors within tissues.”

Who else is involved: The research represents a collaboration between multiple prestigious institutions.

• The study was published in Nature Immunology and led by researchers from MIT, Harvard Medical School, Yale University, Stanford University, and University of Pennsylvania.
• Zhu is affiliated with the Broad Institute of MIT and Harvard and the Ragon Institute of MGH, MIT, and Harvard.
• Shalek also holds positions at the Koch Institute for Integrative Cancer Research, the Broad Institute, and the Ragon Institute.