Name
Title | ||
|---|---|---|
Improving Protein Function Prediction using the Hierarchical Structure of the Gene Ontology |
Abstract | ||
|---|---|---|
High performance and accurate protein function prediction is an important problem in molecular biology. Many contemporary ontologies, such as Gene Ontology (GO), have a hierarchical structure that can be exploited to improve the prediction accuracy, and lower the computational cost, of protein function prediction. We leverage the hierarchical structure of the ontology in two ways. First, we present a method of creating hierarchy-aware training sets for machine-learned classifiers and we show that, in the case of GO molecular function, it is the most accurate method compared to not considering the hierarchy during training. Second, we use the hierarchy to reduce the computational cost of classification. We also introduce a sound methodology for evaluating hierarchical classifiers using global cross-validation. Biologists often use sequence similarity (e.g. BLAST) to identify a "nearest neighbor" sequence and use the database annotations of this neighbor to predict protein function. In these cases, we use the hierarchy to improve accuracy by a small amount. When no similar sequences can be found (which is true for up to 40% of some common proteomes), our technique can improve accuracy by a more significant amount. Although this paper focuses on a specific important application—protein function prediction for the GO hierarchy—the techniques may be applied to any classification problem over a hierarchical ontology. different levels of detail about that protein's functions, which leaves many proteins with incomplete or overly general annotations. Hierarchical ontologies are an effective way of addressing both of these issues. In ontologies such as EC (2), SCOP (3) and GO, both general and specific knowledge is represented in a hierarchical structure where general terms are represented by nodes near the root of the ontology and specific terms are represented by nodes near the leaves of the ontology. The hierarchy defines an inheritance (is-a) relationship between the term nodes, where each term is a special case of its parent terms. That is, any term is-a special case of each of its ancestor terms, where an ancestor is any term along the path from the term to the |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/CIBCB.2005.1594940 | CIBCB |
Keywords | Field | DocType |
genomics,protein function prediction,nearest neighbor,databases,accuracy,level of detail,machine learning,sequences,bioinformatics,ontologies,molecular biology,proteins,cross validation | Data mining,Ontology,Gene ontology,Computer science,Genomics,Artificial intelligence,Hierarchy,Molecular function,Ontology (information science),k-nearest neighbors algorithm,Bioinformatics,Protein function prediction,Machine learning | Conference |
ISBN | Citations | PageRank |
0-7803-9387-2 | 37 | 2.02 |
References | Authors | |
11 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Eisner, R. | 1 | 37 | 2.02 |
| Poulin, B. | 2 | 37 | 2.02 |
| D. Szafron | 3 | 1579 | 210.88 |
| P. Lu | 4 | 75 | 8.65 |