2162
Comment:
|
3132
|
Deletions are marked like this. | Additions are marked like this. |
Line 1: | Line 1: |
#acl BaderLabGroup:read,write,revert,delete All: | ## page was renamed from PDZProteomeScanning ## page was renamed from PDZInteractionPredictionProject #acl All:read |
Line 3: | Line 5: |
== Proteome scanning of PDZ domain interactions using support vector machines == | = Proteome scanning of PDZ domain interactions using support vector machines = |
Line 6: | Line 8: |
## <<TableOfContents>> | <<TableOfContents>> |
Line 14: | Line 16: |
== SVM Predictions == SVM predictions were validated using known interactions from PDZBase, a domain peptide interaction database. The number of interactions which corresponded to known protein protein interactions (PPIs) from iRefIndex (BIND, BioGRID, CORUM, DIP, HPRD, !IntAct, MINT)was also calculated. The following are SVM proteome scanning predictions for human, fly and worm PDZ domains. The format of the output is: <predicted binder> <decision value> [PB|IR(.)] <transcript ids> * PB = Found in PDZBase * IR = Corresponds to a PPI in iRefIndex (transcript index1, ..., transcript index n) SVM Predictons: * [[attachment:HumanSVMPredictions.zip|Human (zip)]] * [[attachment:FlySVMPredictions.zip|Fly (zip)]] * [[attachment:WormSVMPredictions.zip|Worm (zip)]] |
|
Line 15: | Line 31: |
a. Supplementary Information (pdf) a. [[attachment:PDZSVMData.zip|Data Files (zip)]] |
* [[attachment:SupplementaryInformation.pdf|Supplementary Information (pdf)]] * [[attachment:PDZSVMData.zip|Data Files (zip)]] |
Line 42: | Line 58: |
* Bingo 2.3 * Cytoscape 2.6.3 * Cytoscape-task 2.6.3 |
Proteome scanning of PDZ domain interactions using support vector machines
Contents
Background
An accurate predictor of genomic PDZ domain interactions would allow the proteomes of organisms to be scanned for potential binders. Such an application would require an accurate and precise predictor to avoid generating too many false positive hits given the large amount of possible interactors in a given proteome. Once validated these predictions will greatly increase the coverage of current PDZ domain interaction networks and further our understanding of the roles that PDZ domains play in a variety of biological processes.
Results
We built an SVM using mouse and human experimental training data to predict PDZ domain interactions. We showed that it correctly predicts known interactions from proteomes of different organisms and compared to published state of art predictors, is more accurate and precise.
SVM Predictions
SVM predictions were validated using known interactions from PDZBase, a domain peptide interaction database. The number of interactions which corresponded to known protein protein interactions (PPIs) from iRefIndex (BIND, BioGRID, CORUM, DIP, HPRD, IntAct, MINT)was also calculated.
The following are SVM proteome scanning predictions for human, fly and worm PDZ domains. The format of the output is:
<predicted binder> <decision value> [PB|IR(.)] <transcript ids>
- PB = Found in PDZBase
- IR = Corresponds to a PPI in iRefIndex (transcript index1, ..., transcript index n)
SVM Predictons:
Supplementary
- Models
- Chen model parameter and binding site encoding files
- Stiffler model parameter files
- Proteomes
- Ensembl proteome files for Human, Worm and Fly
- Experiment Interaction files (in peptide file format)
- Fly files from Chen
- Human files from Sidhu
- Mouse files from Stiffler
- Worm files from Chen
- Curated Interaction files (flat files)
- PDZBase for Human (Worm and Fly included, but not used)
- Human Protein Reference Database
- Phage codon bias files
- Models
Source Code
- jfreechart 1.0.12 (and dependencies)
- weka 3.9.1
auc calculator (Davis & Goadrich, 2006)
BioJava 1.5
- iText 2.1.3
- jmatio
- Bingo 2.3
- Cytoscape 2.6.3
- Cytoscape-task 2.6.3
- BRAIN 1.0.5 (pdzsvm)
- libSVM 2.8.9 (pdzsvm)
Team
- Shirley Hui
- Gary Bader