The quest to develop vaccines for AIDS and cancer, two of the most complex and deadly diseases, has long tested the limits of medical science. But today, technology can help to solve these complex diseases, particularly with quantum computing and Artificial Intelligence (AI).
A study by University of Toronto scientists and Insilico Medicine, published in Nature Biotechnology, demonstrated how integrating quantum computing, generative AI and classical computing techniques enabled researchers to design molecules targeting KRAS ( mutated oncogenes). This cancer-driving protein was long deemed “undruggable.”
One of the biggest bottlenecks in traditional vaccine development is accurately predicting how a protein will fold or bind in a complex biological environment. However, quantum computing allows researchers to simulate these scenarios and simultaneously process with greater precision and speed, potentially fast-tracking the identification of viable vaccine candidates.
According to the UK’s National Quantum Computing Centre (NQCC) 2024–25 healthcare insights report, quantum computing is not merely a scientific curiosity, but is becoming a necessity.
Meanwhile, the country aims to integrate quantum technology across the NHS by 2030, acknowledging the complexities of regulatory compliance and clinical adoption.
Unlike classical systems that process information using binary digits (bits), quantum computers use quantum bits or qubits. While traditional supercomputers check one solution at a time, quantum computers can explore many possibilities at once using qubits. This makes them much faster for tasks like simulating how a drug interacts with a disease-causing protein, saving weeks or even months in research time.
Generative AI complements these capabilities by proposing novel drug molecules or protein structures, while machine learning models predict how these interact with the human body. This synergy helps develop treatments more efficiently.
“Generative AI and quantum computing expedite drug discovery by predicting interactions with protein targets and optimising molecules for reactions like protein folding,” Madhur Singhal, managing partner for pharma and lifesciences at Praxis Global Alliance, told AIM.
Additionally, concepts such as reverse vaccinology use AI to analyse pathogen genomes for likely protective antigens since cancer represents a collection of diseases with distinct mutations. Also, HIV has a high mutation rate that enables it to frequently evade immune detection.
Ayush Singh, practice member at Praxis, a research and consulting firm, said, “AI models trained on massive datasets can help uncover tumour-specific antigens for cancer, or identify conserved regions in HIV for vaccine targeting.”
Quantum computing also has the potential to significantly impact two underserved areas of medicine–rare diseases and women’s health. The NQCC report emphasises this.
“The shift brought about by deep tech extends far beyond vaccines. AI and quantum computing are transforming every stage of pharmaceutical development. From innovative manufacturing and automated packaging to climate-controlled logistics via IoT and blockchain,” adds Singhal.
In a study published in Scientific Reports, researchers introduced a quantum hybrid classical convolutional neural network (QCCNN) to improve breast cancer diagnosis. By combining quantum computing with classical machine learning, the QCCNN model enhances accuracy and speed in medical image analysis.
Still, hurdles remain.
Quantum computing hardware is still maturing, and the so-called “quantum advantage”, where quantum systems consistently outperform classical computers, hasn’t yet been fully realised across all healthcare applications. Meanwhile, AI raises ethical concerns, data privacy, regulatory frameworks for AI predictions and challenges in model interpretability (black box problem).