scholarly journals Employing Publically Available Biological Expert Knowledge from Protein-Protein Interaction Information

2010 ◽  
pp. 395-406
Author(s):  
Kristine A. Pattin ◽  
Jiang Gui ◽  
Jason H. Moore
Keyword(s):  
Protein Interaction ◽  
Expert Knowledge ◽  
Interaction Information ◽  
Protein Protein Interaction

PPICurator: A Tool for Extracting Comprehensive Protein-Protein Interaction Information

PROTEOMICS ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 1800291 ◽  
Author(s):  
Mansheng Li ◽  
Qiang He ◽  
Jie Ma ◽  
Fuchu He ◽  
Yunping Zhu ◽  
...  
Keyword(s):  
Protein Interaction ◽  
Interaction Information ◽  
Protein Protein Interaction

scholarly journals The expanded human disease network combining protein–protein interaction information

2011 ◽  
Vol 19 (7) ◽  
pp. 783-788 ◽  
Author(s):  
Xuehong Zhang ◽  
Ruijie Zhang ◽  
Yongshuai Jiang ◽  
Peng Sun ◽  
Guoping Tang ◽  
...  
Keyword(s):  
Protein Interaction ◽  
Human Disease ◽  
Disease Network ◽  
Interaction Information ◽  
Protein Protein Interaction ◽  
Human Disease Network

scholarly journals Identification of breast cancer candidate genes using gene co-expression and protein-protein interaction information

Oncotarget ◽  
2016 ◽  
Vol 7 (24) ◽  
pp. 36092-36100 ◽  
Author(s):  
Zhenyu Yue ◽  
Hai-Tao Li ◽  
Yabing Yang ◽  
Sajid Hussain ◽  
Chun-Hou Zheng ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Candidate Genes ◽  
Protein Interaction ◽  
Interaction Information ◽  
Protein Protein Interaction

scholarly journals Front Cover: PPICurator: A Tool for Extracting Comprehensive Protein-Protein Interaction Information

PROTEOMICS ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 1970021
Author(s):  
Mansheng Li ◽  
Qiang He ◽  
Jie Ma ◽  
Fuchu He ◽  
Yunping Zhu ◽  
...  
Keyword(s):  
Protein Interaction ◽  
Front Cover ◽  
Interaction Information ◽  
Protein Protein Interaction

scholarly journals Evolving knowledge graph similarity for supervised learning in complex biomedical domains

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Rita T. Sousa ◽  
Sara Silva ◽  
Catia Pesquita
Keyword(s):  
Supervised Learning ◽  
Semantic Similarity ◽  
Protein Interaction ◽  
Expert Knowledge ◽  
Learning Task ◽  
Knowledge Graph ◽  
Interaction Prediction ◽  
Protein Protein Interaction ◽  
Protein Interaction Prediction ◽  
Knowledge Graphs

Abstract Background In recent years, biomedical ontologies have become important for describing existing biological knowledge in the form of knowledge graphs. Data mining approaches that work with knowledge graphs have been proposed, but they are based on vector representations that do not capture the full underlying semantics. An alternative is to use machine learning approaches that explore semantic similarity. However, since ontologies can model multiple perspectives, semantic similarity computations for a given learning task need to be fine-tuned to account for this. Obtaining the best combination of semantic similarity aspects for each learning task is not trivial and typically depends on expert knowledge. Results We have developed a novel approach, evoKGsim, that applies Genetic Programming over a set of semantic similarity features, each based on a semantic aspect of the data, to obtain the best combination for a given supervised learning task. The approach was evaluated on several benchmark datasets for protein-protein interaction prediction using the Gene Ontology as the knowledge graph to support semantic similarity, and it outperformed competing strategies, including manually selected combinations of semantic aspects emulating expert knowledge. evoKGsim was also able to learn species-agnostic models with different combinations of species for training and testing, effectively addressing the limitations of predicting protein-protein interactions for species with fewer known interactions. Conclusions evoKGsim can overcome one of the limitations in knowledge graph-based semantic similarity applications: the need to expertly select which aspects should be taken into account for a given application. Applying this methodology to protein-protein interaction prediction proved successful, paving the way to broader applications.

Sign in / Sign up

Export Citation Format

Share Document