AI Detects Aggressive Tumors with Protein Markers
AI tool PROTsi Identifies Stemness Proteins to Personalise Cancer Treatment
Table of Contents
A groundbreaking artificial intelligence tool, PROTsi, developed by researchers at the University of São Paulo (USP), is poised to revolutionise cancer treatment by identifying key proteins associated with the stemness phenotype, a characteristic linked to tumour aggressiveness and treatment resistance.
Unlocking Cancer’s Aggressive Nature
The development of PROTsi stems from a deep understanding of cancer biology, specifically the role of cancer stem cells (CSCs). These cells, possessing stem-like properties, are believed to drive tumour growth, metastasis, and recurrence, making them a critical target for effective therapies.
“We arrived at them by associating the stemness phenotype with tumour aggressiveness,” explained Professor Tathiane malta, from the Multiomics and Molecular Oncology Laboratory at the Ribeirão Preto Medical School of the University of São Paulo (FMRP-USP). This insight guided the team in their quest to develop a tool that could pinpoint the molecular underpinnings of this aggressive behaviour.
Strong Validation and Promising applications
The PROTsi tool has demonstrated robust predictive power during its validation phase. It effectively distinguishes between tumour and non-tumour samples and clearly separates stem from differentiated cells. while the model shows particular strength in certain cancers, including uterine, head and neck, pancreatic, and paediatric brain tumours, the researchers’ ambition is for broader applicability.
“We sought to build a model that can be applied to any cancer, but we found that it works better for some than for others. We’re making a data source available for future work,” said Professor Malta, highlighting the ongoing nature of scientific discovery and the potential for future refinements.
toward Better cancer treatment
The research underscores the transformative potential of artificial intelligence in personalising cancer treatment. By identifying stemness-driving proteins, PROTsi opens avenues for the development of novel, targeted therapies, whether they are general cancer treatments or specific to particular tumour types.
Renan Santos Simões, co-frist author of the article, emphasised the collaborative spirit behind this advancement. “Science advances slowly, carefully, and is built by many hands. It’s gratifying to realize that we’re contributing to this process. That’s what motivates us: knowing that what we do today can make a real difference for patients, improving treatments and quality of life.”
What’s Next?
Professor Malta and her team at USP are actively engaged in developing additional computational models to further enhance PROTsi’s predictive capabilities. The current iteration already represents a important leap forward, translating complex molecular data into actionable clinical insights.
This project exemplifies cutting-edge scientific innovation with a clear, overarching ambition: to make cancer treatment more precise, targeted, and ultimately, more effective for patients worldwide.
Related topics: Analysis, Artificial Intelligence, Cancer research, Computational techniques, Drug Targets, Machine learning, Oncology, Precision Medicine, Protein Expression, Proteomics, Translational Science