Text mining and curation

Trainer Sofie Van Landeghem
BITS Courses TRAINING AT VIB

Goal

  • Apply publicly available text mining tools to harvest information from the biomedical literature
  • Understand the opportunities and limitations of text mining techniques
  • Link text mining results to information recorded in public databases such as NCBI Entrez, Uniprot, Ensembl and KEGG
  • Evaluate and manually correct (?curate?) the automatically retrieved textual information to ensure high quality data for integration in research projects

Summary

This training will explain the basics of text mining, presenting the opportunities as well as the challenges of automatically extracting information from the literature. Further, the course will demonstrate how text mining data can be incorporated into a variety of applications and research projects, covering not only human biology but also (other) animals, plants, bacteria, fungi and viruses. To ensure high quality of the textual data, the second day of the workshop will focus on manual evaluation and curation of the automatically retrieved information.

Prerequisites

No specific prior knowledge is required. BITS provides 15 laptops for their training sessions. Depending on the number of participants (max 20), it is possible that you have to share the laptop with one other participant but you can also choose to bring your own laptop for this training session.

Schedule

See the TRAINING AT VIB website for a detailed schedule of this training.

Training material

  • Slides: Day 1 by Sofie Van Landeghem
  • Slides: Day 2 by Sofie Van Landeghem
  • Exercises day1: Introduction by Sofie Van Landeghem
  • Exercises day1: External databases by Sofie Van Landeghem
  • Exercises day1: Tools by Sofie Van Landeghem
  • Exercises day1: Applications by Sofie Van Landeghem
  • Slides with solutions to the exercises: Day 1 by Sofie Van Landeghem
  • Exercises day2: Challenges by Sofie Van Landeghem
  • Exercises day2: Evaluation by Sofie Van Landeghem
  • Exercises day2: Curation guidelines by Sofie Van Landeghem
  • Exercises day2: Curation exercises by Sofie Van Landeghem
  • Slides with solutions to the exercises: Day 2 by Sofie Van Landeghem

Links

None

Scientific topics Text mining, Data submission, annotation and curation
Target audience Life Science Researchers, PhD students, post-docs