Project Overview

For many cancer patients, doctors use genetic tests to match them with targeted treatments. But what happens when those tests don't reveal any options? This is a major challenge, especially for people with rare cancers. This research project is working to change that by looking beyond genetics and into something just as important—proteins.

Proteins play a crucial role in how cancer develops and responds to treatment. By analyzing unique protein patterns within a patient's tumor, this research team aims to identify new treatment opportunities—even in cases where no genetic markers are present. Leveraging cutting-edge data analysis, artificial intelligence (AI), and vast medical databases, the team is developing a comprehensive tumor profiling approach that prioritizes proteins while integrating genetic and clinical data to advance precision oncology. This approach serves as a protein-informed digital learning companion, empowering clinicians with deeper insights into treatment options that were previously inaccessible. Importantly, existing protein test results, while preferable, are not required, as the system will learn from others and augment available genetic and clinical data with inferred protein insights, broadening access to personalized cancer care.

This research project is pioneering a shift from genomic- to proteomic-cancer targetable treatments, expanding the reach of precision medicine to provide treatment options for even the most complex cases. A key component of this work is the development of a human-mediated, AI-generated corpus of hypothesized drug-protein target relationships and testing designs, serving as a foundational resource for AI-enabled cancer clinical care. By doing so, this corpus will establish guidelines and protocols for AI-assisted precision oncology. Through this approach, the project lays the groundwork for scalable, evidence-based AI applications in cancer treatment selection and response prediction.

Key Focus Areas

• Protein-informed tumor profiling for precision oncology
• AI-driven integration of proteomic, genomic, and clinical data
• AI-generated corpus of hypothesized drug-protein target relationships
• Guidelines and protocols for AI-assisted cancer clinical care
• Expanding treatment options for rare and complex cancers

Team Members

Funding

Supported by the MD Anderson Cancer Center – UT Austin Research Collaborations program, through the Collaborative Accelerator for Transformative Research Endeavors.

Project Details

For the official project description, team information, and related news, please visit the UT Austin Texas Research project page: