Text mining in cancer gene and pathway prioritization

Area of Science:

• Computational biology and bioinformatics
• Genomics and cancer research
• Text mining and natural language processing

Background:

• Gene prioritization is crucial for efficient cancer research, reducing wet lab costs by ranking candidate genes.
• Numerous gene prioritization tools exist, integrating diverse data like gene sequences, expression, function, regulation, domains, interactions, and pathways.

Purpose of the Study:

• To review existing gene prioritization tools within an integrative 'Omic hierarchy view of cancer.
• To focus on the analysis of text mining components within these tools.
• To identify challenges and suggest future directions for text mining in gene prioritization.

Main Methods:

• Review of existing literature and gene prioritization tools.
• Analysis of text mining methodologies employed in these tools.
• Evaluation of data sources integrated by prioritization tools.

Main Results:

• Text mining progress in gene prioritization has been relatively slow.
• Current text mining methods face several challenges in effectively contributing to gene prioritization.
• Prioritizing pathways may offer greater benefits than prioritizing individual genes.

Conclusions:

• More effective text mining algorithms are needed to improve gene prioritization.
• Future research should explore pathway prioritization as a potentially more impactful strategy.
• Integrating advanced text mining could enhance the efficiency and success rate of experimental cancer gene validation.