Automatic Pathway Building in Biological Association Networks
Author Information
Author(s): Yuryev Anton, Mulyukov Zufar, Kotelnikova Ekaterina, Maslov Sergei, Egorov Sergei, Nikitin Alexander, Daraselia Nikolai, Mazo Ilya
Primary Institution: Ariadne Genomics Inc
Hypothesis
Can automatic curation of Biological Association Networks improve the reconstruction of signaling pathways?
Conclusion
The automatically curated MedScan data is adequate for automatic generation of good quality signaling networks.
Supporting Evidence
- Medscan technology extracts relations between proteins, small molecules, and diseases.
- The curated data is used for automatic pathway reconstruction.
- 106 pairs of regulome pathways and manually curated pathways were identified as valid for comparison.
- Pathways constructed for the same ligand have 62.1% in node overlap and 18.2% in relation overlap.
- 7,585 tissue-specific pathways were constructed using gene expression data.
Takeaway
This study shows that a computer program can help create maps of how different proteins interact in the body, which can help scientists understand how cells work.
Methodology
The study used natural language processing technology called Medscan to extract relations from scientific literature and developed algorithms for automatic curation and pathway reconstruction.
Potential Biases
The algorithms may introduce biases due to the historical nature of scientific literature and the jargon used by scientists.
Limitations
The study's findings are based on the accuracy of the Medscan technology and the quality of the literature it processes.
Statistical Information
P-Value
<0.0001
Statistical Significance
p<0.0001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website