Researchers from S. N. Bose National Centre for Basic Sciences (SNBNCBS), an autonomous institute of the Department of Science and Technology, Government of India, in collaboration with Ashoka University, have developed a new artificial intelligence framework called ACSCeND (AI-based Cancer Stem-like Cell Profiler and Neoplasm Deconvoluter). This AI system identifies three distinct developmental states of cancer stem-like cells: pluripotent-like, multipotent-like and unipotent-like, providing an unprecedented view of tumour heterogeneity.
The framework builds upon the team's earlier AI platform, OncoMark, which decoded biological hallmarks driving cancer progression across millions of cells with over 99% predictive accuracy. ACSCeND combines knowledge from high-resolution single-cell sequencing with deep learning to analyze conventional bulk tumour RNA sequencing, allowing hidden cancer stem cell populations to be studied in thousands of patient samples where single-cell experiments are unavailable.
Researchers rigorously validated ACSCeND against existing computational approaches and demonstrated that it consistently outperformed current methods across independent datasets and sequencing platforms. The team applied the framework to analyze more than 25,000 tumour samples from major international cancer databases including TCGA and PRECOG. The analyses revealed that tumours enriched with highly potent, pluripotent-like cancer stem cells were associated with poorer patient survival, greater likelihood of tumour recurrence and reduced response to modern immunotherapies.
Beyond identifying these dangerous cells, ACSCeND uncovered the molecular programs that enable cancer stem-like cells to survive, adapt and evade the immune system. These insights could help scientists discover new drug targets, identify patients who are more likely to relapse, and design more effective precision cancer therapies. The research represents a significant advancement in cancer biology's most difficult problem—identifying the elusive stem-like cells that drive tumour evolution and are responsible for treatment resistance.