OpenMS
Loading...
Searching...
No Matches
RTPredict

This application is used to predict retention times for peptides or peptide separation.

This methods and applications of this model are described in several publications:

Nico Pfeifer, Andreas Leinenbach, Christian G. Huber and Oliver Kohlbacher Statistical learning of peptide retention behavior in chromatographic separations: A new kernel-based approach for computational proteomics. BMC Bioinformatics 2007, 8:468

Nico Pfeifer, Andreas Leinenbach, Christian G. Huber and Oliver Kohlbacher Improving Peptide Identification in Proteome Analysis by a Two-Dimensional Retention Time Filtering Approach J. Proteome Res. 2009, 8(8):4109-15

The input of this application is an svm model and a file with peptide identifications (idXML or text). The svm model file is specified by the svm_model parameter in the command line or the INI file. This file should have been produced by the RTModel application.
For retention time prediction the peptide sequences are extracted from the idXML/text inputfile and passed to the svm. The svm then predicts retention times according to the trained model. The predicted retention times are stored as

<userParam name="predicted_retention_time" value="<predicted retention time>" />

inside the peptide entities in the idXML output file.

For separation prediction you have to specify two output file names. 'out_id:positive' is the filename of the peptides which are predicted to be collected by the column and 'out_id:negative' is the file of the predicted flowthrough peptides.

Retention time prediction and separation prediction cannot be combined!

Note
Currently mzIdentML (mzid) is not directly supported as an input/output format of this tool. Convert mzid files to/from idXML using IDFileConverter if necessary.

The command line parameters of this tool are:

INI file documentation of this tool:

Todo:
This needs serious clean up! Combining certain input and output options will result in strange behaviour, especially when using text output/input.