A thorough analysis of the contribution of experimental, derived and sequence-based predicted protein-protein interactions for functional annotation of proteins

• DOI: 10.1371/journal.pone.0242723
• Publication Date: 2020-11-25T18:26:22Z
• Authors: Stavros Makrodimi...; Marcel Reinders; Roeland van Ham
• Keywords: Sequence (biology); Gene Annotation; Interaction network; Protein sequencing

Physical interaction between two proteins is strong evidence that the are involved in same biological process, making Protein-Protein Interaction (PPI) networks a valuable data resource for predicting cellular functions of proteins. However, PPI largely incomplete non-model species. Here, we tested to what extent these still useful genome-wide function prediction. We used network-based classifiers predict Biological Process Gene Ontology terms from protein four species: Saccharomyces cerevisiae , Escherichia coli Arabidopsis thaliana and Solanum lycopersicum (tomato). The had reasonable performance well-studied yeast, but performed poorly other showed this poor can be considerably improved by adding edges predicted various sources, such as text mining, associations STRING database more than interactions neural network sequence-based features.