SVM Technique for Evaluating Proteotypic PeptidesSTEPP is an evaluating proteotypic peptides tools. | |
Download |
SVM Technique for Evaluating Proteotypic Peptides Ranking & Summary
Advertisement
- License:
- Others
- Publisher Name:
- Pacific Northwest National Laboratory
- Publisher web site:
- Operating Systems:
- Windows XP/2000/98
- File Size:
- 711KB
SVM Technique for Evaluating Proteotypic Peptides Tags
SVM Technique for Evaluating Proteotypic Peptides Description
The STEPP software contains an implementation of a trained SVM (Support Vector Machine) that can compute a score representing how "proteotypic" a peptide is by LC-MS. The program can read a protein file, perform an in-silico digestion, and compute the observability score for each tryptic or partially tryptic peptide. Note that larger (positive) scores mean a peptide is predicted to be more proteotypic while lower (Negative) scores mean the peptide is not predicted to be proteotypic. The SVM model used by STEPP is a simple descriptor space based on 35 properties of amino Acid content, charge, hydrophilicity, and Polarity for the quantitative Prediction of proteotypic peptides. The model was trained and validated with three independently derived AMT databases (Shewanella oneidensis, Salmonella typhimurium, Yersinia pestis). The SVM resulted in an average accuracy measure of ~0.8 with a standard deviation of less than 0.025.
SVM Technique for Evaluating Proteotypic Peptides Related Software