Cancer, as one of the serious diseases jeopardizing human health, has not yet emerged as an effective means of completely overcoming it. Tailoring the most suitable treatment plan for cancer patients is a major challenge. Artificial intelligence (AI), represented by machine learning and deep learning, has boomed in recent years, bringing new development opportunities for cancer treatment.
The U.S. National Cancer Institute (NCI) published a paper describing an innovative AI tool (PERCEPTION) that is capable of predicting a patient's response and resistance to a specific drug by analyzing single-cell transcriptomic data from tumors.
Predicting patient response to specific treatments is a tough task in precision oncology. Traditional bulk transcriptome-based approaches fail to capture the heterogeneity within tumors. Through the development of single-cell transcription technologies, new insights into the response to tumor therapy. However, translating these data into clinical decision-making tools still faces many challenges, including the complexity of the data, the lack of analytical methods, and the need for large amounts of data.
PERCEPTION is a precision oncology AI model that combines machine learning and deep learning techniques to process and analyze single-cell transcriptomic data. Researchers used extensive data from cancer cell lines and patient samples to train and validate PERCEPTION. The model can accurately identify molecular signatures associated with treatment response and predict patient sensitivity to specific drugs. This approach is innovative in that it takes into account heterogeneity within tumors, which is not possible with traditional batch sequencing-based approaches.
In addition, the researchers developed a new data enhancement technique to improve the predictive power of the model by simulating the state of cells after drug treatment.
PERCEPTION can accurately predict patient response to a wide range of anti-cancer drugs, including in independent clinical trials. It identifies genes and signaling pathways associated with treatment sensitivity and resistance by analyzing single-cell transcriptomic profiles of tumor cells.
PERCEPTION reveals multiple mechanisms of drug resistance, including known and new potential resistance pathways.
PERCEPTION evaluates the effects of drug combination therapy and provides new strategies for clinical treatment by predicting the synergistic effects of different drug combinations.
The research found that PERCEPTION can be expanded to a certain extent to other cancer types beyond specific cancers, suggesting that the model has the potential for a wide range of applications.
This research demonstrates the potential of AI applications in precision oncology, especially in predicting treatment response and drug resistance. PERCEPTION's high accuracy and ability to be used in a wide range of applications make it a promising tool for clinical decision-making.
Protheragen-ING AI-Pharma has always focused on providing our clients with leading AI technologies to accelerate drug discovery and screening. Our services are designed to advance precision medicine and bring more effective treatment options to cancer patients. If you are interested in our services or have a question, please feel free to contact us for more details.
Original Article:
Sinha S.; et al. (2024). PERCEPTION predicts patient response and resistance to treatment using single-cell transcriptomics of their tumors. Nature Cancer. 2024: 1-15.
Services Related in the Article:
AI-powered Drug Discovery and Design
AI-assisted Drug High Throughput Screening
We harness the power of artificial intelligence to transform the landscape of drug discovery. Our mission is to accelerate the development of life-saving medicines by leveraging cutting-edge AI technologies.
