Automatic extraction of reference gene from literature in plants based on texting mining

Area of Science:

• Molecular Biology
• Bioinformatics
• Computational Biology

Background:

• Quantitative real-time PCR (qRT-PCR) is a vital technique in biological research.
• Selecting stable reference genes is critical for accurate qRT-PCR results.
• Current methods for reference gene selection are often costly and time-consuming.

Purpose of the Study:

• To develop an automated and efficient method for discovering reliable reference genes from scientific literature.
• To reduce the experimental cost and time associated with traditional reference gene validation.

Main Methods:

• Integration of machine learning, natural language processing, and text mining techniques.
• Development of an auxiliary reference gene discovery system that mines existing literature.
• Validation of the proposed method for precision and recall in extracting reference genes and their experimental contexts.

Main Results:

• The proposed method demonstrated high precision and recall in identifying reference genes and their associated experimental environments.
• The system effectively mines accumulated scientific literature for reference gene information.
• The approach offers a reliable, economical, and efficient alternative for reference gene selection.

Conclusions:

• Literature mining combined with AI offers a powerful approach to identify suitable reference genes for qRT-PCR.
• This method significantly enhances the efficiency and reduces the cost of selecting reference genes for specific experimental conditions.
• The developed system provides a valuable tool for researchers conducting qRT-PCR experiments.