PATHAK#

NLP-based method to mine gene and functional relationships from published articles.

Brif overview
  • Understanding gene function is a complex and challenging task, but it is important for advancing our understanding of biological systems and for developing new treatments for diseases.

  • A new method called PATHAK has been proposed to link genes with their potential function using sentence-level embedding of scientific documents based on pretraining a Transformer language model.

  • PATHAK was applied to a large dataset of papers focusing on Arabidopsis thaliana and the genes related to this plant species.

  • This is a significant development and adds to our understanding of the complex mechanisms at work within Arabidopsis thaliana and similar plant species.