Omics-based deep learning approaches for lung cancer decision-making and therapeutics development

Area of Science:

• Genomics
• Bioinformatics
• Artificial Intelligence

Background:

• Lung cancer remains a leading global cause of cancer deaths.
• Advancements in nucleic acid analysis and multi-omics data generation are transforming lung cancer research.
• Minimally invasive procedures and technological developments drive the need for innovative analytical methods.

Purpose of the Study:

• To summarize data sources for deep learning-based lung cancer genomics.
• To provide an update on recent deep learning models applied to lung cancer.
• To review current challenges and discuss future research directions in this field.

Main Methods:

• Review of existing literature on deep learning applications in lung cancer genomics.
• Analysis of multi-omics data using artificial intelligence models.
• Summarization of data sources and recent deep learning models.

Main Results:

• Deep learning models are increasingly effective for lung cancer prediction, classification, and prognosis.
• Genome-based deep learning shows promise in identifying molecular signatures and predicting treatment response.
• Various data sources and recent models for deep learning in lung cancer genomics have been identified.

Conclusions:

• Deep learning offers rapid and effective methods to improve lung cancer patient diagnosis, prognosis, and treatment.
• Further research is needed to address current issues and explore future directions in deep learning-based lung cancer genomics.
• The integration of multi-omics data with AI holds significant potential for advancing lung cancer research and clinical practice.