Evaluating a Gene Information Summarization System
Author Information
Author(s): Yang Jianji, Cohen Aaron, Hersh William
Primary Institution: Oregon Health & Science University
Hypothesis
Can an automatic summarizer improve the analysis process of microarray datasets for genomic researchers?
Conclusion
The evaluation results suggest that GICSS can be useful for researchers in the genomic area.
Supporting Evidence
- The clusters generated by GICSS were validated by scientists during their microarray analysis process.
- Presenting sentences in the abstract provided significantly more important information to users than just showing the title.
- GICSS output was significantly better than PubMed titles in terms of average precision scores.
Takeaway
Scientists can use a special computer program to help them find important information about genes faster when they study diseases.
Methodology
The study involved a hybrid evaluation method where scientists evaluated the output of the GICSS system while analyzing their own microarray data.
Potential Biases
Participants may have been fatigued, affecting their judgment on cluster quality.
Limitations
The evaluation was limited by the workload on participants and the need for familiarity with the genes being analyzed.
Participant Demographics
Biomedical researchers from Oregon Health & Science University.
Statistical Information
P-Value
p < 0.001
Statistical Significance
p < 0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website