Investigations on factors influencing HPO-based semantic similarity calculation
| Autor: | Xuequn Shang, Jiajie Peng, Qianqian Li |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
0301 basic medicine
Computer Networks and Communications Computer science 0206 medical engineering Health Informatics 02 engineering and technology computer.software_genre lcsh:Computer applications to medicine. Medical informatics DNA sequencing Set (abstract data type) 03 medical and health sciences Annotation Semantic similarity Human Phenotype Ontology Humans Biological ontology business.industry Genetic heterogeneity Research Causative gene Computational Biology Human phenotype ontology Molecular Sequence Annotation Computer Science Applications Semantics 030104 developmental biology Phenotype Biological Ontologies lcsh:R858-859.7 Data mining Artificial intelligence business computer 020602 bioinformatics Natural language processing Algorithms Information Systems |
| Zdroj: | Journal of Biomedical Semantics, Vol 8, Iss S1, Pp 61-69 (2017) Journal of Biomedical Semantics |
| ISSN: | 2041-1480 |
| Popis: | Background Although disease diagnosis has greatly benefited from next generation sequencing technologies, it is still difficult to make the right diagnosis purely based on sequencing technologies for many diseases with complex phenotypes and high genetic heterogeneity. Recently, calculating Human Phenotype Ontology (HPO)-based phenotype semantic similarity has contributed a lot for completing disease diagnosis. However, factors which affect the accuracy of HPO-based semantic similarity have not been evaluated systematically. Results In this study, we proposed a new framework called HPOFactor to evaluate these factors. Our model includes four components: (1) the size of annotation set, (2) the evidence code of annotations, (3) the quality of annotations and (4) the coverage of annotations respectively. Conclusions HPOFactor analyzes the four factors systematically based on two kinds of experiments: causative gene prediction and disease prediction. Furthermore, semantic similarity measurement could be designed based on the characteristic of these factors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|