Subset of GO terms selected when prioritizing abstract terms and optimizing for protein coverage, on the yeast dataset.

<p>Subset of GO terms selected when prioritizing abstract terms and optimizing for protein coverage, on the yeast dataset.</p>

Saved in:

Bibliographic Details
Main Author:	Andreas Denger (12111159) (author)
Other Authors:	Volkhard Helms (35164) (author)
Published:	2024
Subjects:	Biochemistry Medicine Cell Biology Genetics Biotechnology Infectious Diseases Biological Sciences not elsewhere classified Information Systems not elsewhere classified various research fields unlike previous approaches supervised learning methods sufficient sample size strong class separability provides important information median f1 score low sample count key biological pathways form complex networks employ machine learning training predictive models dataset containing 98 95 ± 0 92 ± 0 87 ± 0 30 go terms 11 go terms meta -) proteome div >< p creating training datasets membrane transporters within pipeline automatically reduced training dataset go terms go datasets membrane transporters protein datasets wide variety wide range transport proteins transmembrane transporters thaliana </ substrate transport specific substrates specific functions respective functions reducing redundancy pipeline found molecular functions minimal redundancy including plants including biotechnology hierarchical relationships full redundancy frequently annotated covered proteins coli </ cerevisiae </ cell eukaryotes biology behind automated pipeline 67 %,
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items