Quantum-inspired AI could tailor patients' cancer treatment to their entire molecular background
For a child diagnosed with neuroblastoma—the most common infant cancer, occurring when early nerve cells grow out of control—the path to treatment isn't simple. Some types of neuroblastoma resolve on their own, while ...
"It's much more than just one gene—everything that's happening in the cells of the patient matters," said Orly Alter, an associate professor of biomedical engineering at the University of Utah's Scientific Computing & Imaging Institute.
Current artificial intelligence and machine learning (AI/ML) approaches require massive amounts of training data and, specifically, vastly more patient samples than genetic features.
This makes them poorly suited for predicting patient outcomes in most clinical trials, which typically enroll just 20 to 100 people. For example, a recent large language model of the 30,000-nucleotide genome of the COVID-19 virus required about 110 million samples. Translating this to the 3-billion-nucleotide human genome, a conventional AI approach would need 33 trillion patients.
By using the mathematics of quantum mechanics, Alter and her collaborators developed a novel AI/ML technique that can improve treatment selection and drug success rates. Their work appears in the journal APL Quantum.
Billions of molecular features
"Our quantum approach allows us to find the relevant information in every layer of the data, for example, from the patients' blood in addition to their tumors," Alter said.
"Even for very few patients, we can still take everything in—their millions to billions of molecular features—and make sense of them. We can, therefore, understand the disease mechanisms and predict drug targets to improve patients' outcomes. We also validate our AI/ML predictions of targets and outcomes experimentally, which is widely considered a biotechnology holy grail."
Using the quantum mechanical principles of entanglement and superposition, Alter and team's novel AI/ML framework split approximately 6 million tumor and blood genomic features from only 101 neuroblastoma patient samples into three orthogonal sets of two linked patterns each, where two of the sets predict health outcomes, and the third is correlated with normal gender variation. Credit: Orly Alter, University of Utah
Orly Alter presents "AI/ML-Powered Biomarker Discovery for Personalized Medicine," at the Precision Medicine World Conference (PMWC) 2024 (Santa Clara, CA, January 24–26, 2024). Credit: Orly Alter, University of Utah
The quantum mechanics-based technique allowed Orly Alter and her team to take in approximately 6 million tumor and blood DNA and tumor RNA features from only 71 neuroblastoma patient samples, and derive, test, and interpret new predictors of patients' life expectancy in response to treatment. The new predictors consistently outperformed standard biomarkers and are applicable to the general population. Credit: Orly Alter, University of Utah