Difference between revisions of "Poodle"
(→Poodle) |
(→Poodle-W) |
||
| (4 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
==Poodle-L== |
==Poodle-L== |
||
| − | |||
| − | Poodle-L is specialized on the prediction of long disordered regions (> 40 residues). |
||
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
||
| Line 19: | Line 17: | ||
|- |
|- |
||
! ML Method |
! ML Method |
||
| − | | two levels of |
+ | | two levels of SVMs |
|} |
|} |
||
| + | Poodle-L is specialized on the prediction of long disordered regions (> 40 residues). |
||
| − | ==Poodle-S== |
||
| + | It uses two SVMs. Each amino acid is represented by ten different physikochemical |
||
| + | properties (10 dimensions). The first SVM predicts the probability of a 40-residue |
||
| + | segment to be disordered. This output is used by the second SVM to predict predict |
||
| + | the probability of a single residue to be disordered. |
||
| + | ==Poodle-S== |
||
| − | Poodle-S is specialized on the prediction of short disordered regions. |
||
| − | This method uses physicochemical features and a reduced amino acid set of a position-specific scoring matrix. |
||
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
||
| Line 37: | Line 38: | ||
| [http://www.ncbi.nlm.nih.gov/pubmed/17599940 PubMed 17599940] |
| [http://www.ncbi.nlm.nih.gov/pubmed/17599940 PubMed 17599940] |
||
|- |
|- |
||
| − | ! ML |
+ | ! ML method |
| − | | |
+ | | SVM |
|} |
|} |
||
| + | Poodle-S is specialized on the prediction of short disordered regions. |
||
| − | ==Poodle-W== |
||
| + | This method defines seven regions on a protein. Depending of the physikochemical |
||
| + | compositions and a PSI-Blast profile a SVM decides for one of the seven regions |
||
| + | if it contains disorder. |
||
| + | The idea behind this is, that it is important where disorder happens and depending |
||
| − | Poodle-W predicts which protein of a set of proteins is the most disordered one. |
||
| + | on the place the contribution to disorder of physikochemical features varies. |
||
| + | |||
| + | ==Poodle-W== |
||
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
||
| Line 55: | Line 62: | ||
| [http://www.ncbi.nlm.nih.gov/pubmed/17338828 PubMed 17338828] |
| [http://www.ncbi.nlm.nih.gov/pubmed/17338828 PubMed 17338828] |
||
|} |
|} |
||
| + | |||
| + | Poodle-W predicts which proteins are intrinsically disordered. |
||
| + | It uses a method called Spectral Graph Transducer, which is a classification algorithm |
||
| + | (see "Transductive learning via spectral graph partitioning" by Dr. Joachims and |
||
| + | [http://mbs.cbrc.jp/poodle/help-w.html Poodle-W]). |
||
==Poodle-I== |
==Poodle-I== |
||
| − | |||
| − | Poodle-I seems to predict the disorder of a protein by combining different tools in a workflow. |
||
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
{| style="float: right; border: 1px solid #BBB; margin: .46em 0 0 .2em;" |
||
| Line 70: | Line 80: | ||
| CASP 8 Proceedings |
| CASP 8 Proceedings |
||
|} |
|} |
||
| + | |||
| + | Poodle-I seems to predict the disorder of a protein by combining different tools in a workflow. |
||
Latest revision as of 22:25, 6 June 2011
Poodle
Poodle is a set of tools for the prediction of the secondary structures. The different programs uses different machine learning approaches.
Poodle-L
| Author | Hirose S, Shimizu K, Kanai S, Kuroda Y, Noguchi T. |
|---|---|
| Year | 2007 |
| Reference | PubMed 17545177 |
| ML Method | two levels of SVMs |
Poodle-L is specialized on the prediction of long disordered regions (> 40 residues). It uses two SVMs. Each amino acid is represented by ten different physikochemical properties (10 dimensions). The first SVM predicts the probability of a 40-residue segment to be disordered. This output is used by the second SVM to predict predict the probability of a single residue to be disordered.
Poodle-S
| Author | Shimizu K, Hirose S, Noguchi T. |
|---|---|
| Year | 2007 |
| Reference | PubMed 17599940 |
| ML method | SVM |
Poodle-S is specialized on the prediction of short disordered regions. This method defines seven regions on a protein. Depending of the physikochemical compositions and a PSI-Blast profile a SVM decides for one of the seven regions if it contains disorder.
The idea behind this is, that it is important where disorder happens and depending on the place the contribution to disorder of physikochemical features varies.
Poodle-W
| Author | Shimizu K, Muraoka Y, Hirose S, Tomii K, Noguchi T. |
|---|---|
| Year | 2007 |
| Reference | PubMed 17338828 |
Poodle-W predicts which proteins are intrinsically disordered. It uses a method called Spectral Graph Transducer, which is a classification algorithm (see "Transductive learning via spectral graph partitioning" by Dr. Joachims and Poodle-W).
Poodle-I
| Author | Hirose S, Shimizu K, Inoue N, Kanai S, Noguchi T. |
|---|---|
| Year | 2008 |
| Reference | CASP 8 Proceedings |
Poodle-I seems to predict the disorder of a protein by combining different tools in a workflow.
