Name
Abstract | ||
|---|---|---|
Currently, the most accurate fold-recognition method is to perform profile-profile alignments and estimate the statistical significances of those alignments by calculating Z-score or E-value. Although this scheme is reliable in recognizing relatively close homologs related at the family level, it has difficulty in finding the remote homologs that are related at the superfamily or fold level.In this paper, we present an alternative method to estimate the significance of the alignments. The alignment between a query protein and a template of length n in the fold library is transformed into a feature vector of length n + 1, which is then evaluated by support vector machine (SVM). The output from SVM is converted to a posterior probability that a query sequence is related to a template, given SVM output. Results show that a new method shows significantly better performance than PSI-BLAST and profile-profile alignment with Z-score scheme. While PSI-BLAST and Z-score scheme detect 16 and 20% of superfamily-related proteins, respectively, at 90% specificity, a new method detects 46% of these proteins, resulting in more than 2-fold increase in sensitivity. More significantly, at the fold level, a new method can detect 14% of remotely related proteins at 90% specificity, a remarkable result considering the fact that the other methods can detect almost none at the same level of specificity. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1093/bioinformatics/bti384 | Bioinformatics |
Keywords | Field | DocType |
svm output,alternative method,close homologs,length n,profile alignment,z-score scheme,support vector machine,new method detects,accurate fold-recognition method,family level,new method,feature vector,statistical significance,posterior probability,fold recognition | Feature vector,SUPERFAMILY,Pattern recognition,Computer science,Threading (protein sequence),Support vector machine,Posterior probability,Artificial intelligence,Bioinformatics | Journal |
Volume | Issue | ISSN |
21 | 11 | 1367-4803 |
Citations | PageRank | References |
14 | 0.82 | 9 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sangjo Han | 1 | 46 | 2.43 |
| Byung Chul Lee | 2 | 37 | 4.32 |
| Seung Taek Yu | 3 | 14 | 0.82 |
| Chanseok Jeong | 4 | 37 | 2.98 |
| Soyoung Lee | 5 | 14 | 0.82 |
| Dongsup Kim | 6 | 320 | 23.11 |