AI Framework ACSCeND Uncovers Hidden Cancer Stem-Like Cell States Linked to Tumour Recurrence and Immunotherapy Resistance
核心洞察
Researchers from SNBNCBS and Ashoka University (搜索) developed ACSCeND (搜索), an AI framework that identifies three distinct developmental states of cancer (搜索) stem-like cells from tumour gene-expression data.
ACSCeND (搜索) outperformed existing computational methods and was applied to more than 25,000 tumour samples from TCGA and PRECOG databases.
Tumours enriched with pluripotent-like cancer (搜索) stem cells were associated with poorer survival, higher recurrence likelihood, and reduced response to immunotherapies.
A new artificial intelligence framework that reveals hidden cancer (搜索) stem-like cell states from tumour gene-expression data could bring precision medicine one step closer to reality, particularly in areas with limited health facilities. The system, developed by researchers from the S. N. Bose National Centre for Basic Sciences (搜索) (SNBNCBS), an autonomous institute of the Department of Science and Technology (DST), Government of India, in collaboration with Ashoka University (搜索), identifies three distinct developmental states of cancer stem-like cells that are responsible for tumour recurrence, metastasis and treatment failure.
Cancer (搜索) remains one of humanity's greatest medical challenges. Although modern treatments can destroy millions of cancer cells, a small population of cells often survives, allowing tumours to return, spread to distant organs and develop resistance to therapy. Scientists have long believed that these rare cancer stem-like cells help tumours survive and return, and are responsible for tumour recurrence, metastasis and treatment failure. However, because these cells are extremely rare and constantly change their identity, accurately detecting them has remained one of the biggest challenges in cancer research.
A Framework Built on Prior AI Success
The work, led by Dr. Shubhasis Haldar, builds upon the team's earlier AI platform, OncoMark (搜索), which accurately decoded the biological hallmarks that drive cancer (搜索) progression across millions of cells with over 99% predictive accuracy. By enabling researchers to measure the fundamental processes that fuel tumour growth, metastasis and drug resistance, OncoMark demonstrated how artificial intelligence can uncover complex biological information hidden within massive genomic datasets.
Building on that success, the team turned its attention to one of cancer (搜索) biology's most difficult problems — identifying the elusive stem-like cells that drive tumour evolution. Their new framework, called ACSCeND (搜索) (AI-based Cancer Stem-like Cell Profiler and Neoplasm Deconvoluter), goes beyond conventional methods that assign tumours a single "stemness" score. Instead, it identifies three distinct developmental states of cancer stem-like cells — pluripotent-like, multipotent-like and unipotent-like — providing an unprecedented view of tumour heterogeneity.
Combining Single-Cell Resolution with Bulk Sequencing
The system combines knowledge learned from high-resolution single-cell sequencing with deep learning to analyse conventional bulk tumour RNA sequencing, allowing these hidden cell populations to be studied in thousands of patient samples where single-cell experiments are unavailable. The researchers rigorously validated ACSCeND (搜索) against existing computational approaches and showed that it consistently outperformed current methods across independent datasets and sequencing platforms.
The team then applied the framework to analyse more than 25,000 tumour samples from major international cancer (搜索) 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, a greater likelihood of tumour recurrence and reduced response to modern immunotherapies.
Implications for Precision Medicine
Beyond identifying these dangerous cells, ACSCeND (搜索) also uncovered the molecular programs that enable them to survive, adapt and evade the immune system. Such insights could help scientists discover new drug targets, identify patients who are more likely to relapse and design more effective precision cancer (搜索) therapies.
Artificial intelligence is rapidly becoming an indispensable partner in modern biomedical research, enabling researchers to detect hidden biological patterns across enormous genomic datasets that would be impossible to analyse manually. Studies such as OncoMark (搜索) and ACSCeND (搜索) illustrate how AI can accelerate discoveries that ultimately improve cancer (搜索) diagnosis, predict treatment response and guide the development of more effective therapies.