Current Trends in Drug Sensitivity Prediction.

Area of Science:

• Oncology
• Pharmacogenomics
• Bioinformatics

Background:

• Cancer cell line panels are crucial models for identifying drug sensitivity markers and developing novel anticancer therapies.
• The growing volume of in vitro drug sensitivity and cell line profiling data prompts investigation into predictive capabilities for clinical applications.

Purpose of the Study:

• To review methods for predicting anticancer drug activity in cancer cell lines using machine learning.
• To summarize existing studies that integrate genomic and chemical data from large cell line panels for drug sensitivity prediction.

Main Methods:

• Summarizing cytotoxicity assays for determining in vitro drug activity.
• Reviewing drug sensitivity prediction studies utilizing data from NCI60, Cancer Cell Line Encyclopedia (CCLE), and Genomics of Drug Sensitivity in Cancer (GDSC) projects.
• Integrating genomic and chemical profiling data with machine learning models.

Main Results:

• Cancer cell line data, when integrated with machine learning, shows potential for predicting drug sensitivity.
• Leveraging large datasets like CCLE and GDSC enables more robust prediction models.
• The review highlights the utility of these models in understanding drug response mechanisms.

Conclusions:

• Drug sensitivity prediction using cancer cell line data is a promising field with significant potential for personalized cancer treatment.
• Further research is needed to address current limitations and enhance predictive accuracy for clinical translation.
• Continued integration of multi-omics data and advanced machine learning techniques will drive future advancements.