Fastprofkernel

From Rost Lab Open
Jump to: navigation, search

Contents

Description

fastprofkernel is a Debian package that uses an accelerated version of the original profile kernel [1] to automatically train SVM based classification models. It can assign user-defined classes to so far uncharacterized proteins.

The package ships with two executable: profkernel-core and profkernel-workflow.

profkernel-core is a speed-optimized, but input/output identical variant of the original profile kernel implementation.

profkernel-workflow uses profkernel-core and trains or applies a SVM based classification model. It provides two modes of operation. In the first mode, 'training', the user provides evolutionary protein profiles and their class assignments (labels) as input and profkernel-workflow outputs a folder with all model files required for predictions. In the second mode, 'prediction', the user provides the path to such a model folder and to the query profiles. profkernel-workflow then predicts their classes.

Availability

We have included both executables in a Debian package, together with man pages and a sample classification problem. There are two common ways to install it.

  • Via our Debian repository (package "fastprofkernel").
  • By manual download and installation of the binary .deb package (please see the manual of your distribution for how to install .deb packages).

For installation on non-Debian based systems, you can download the .tar.gz source package and compile and install it with the included make based installation (see the README file).

Bugs and Other Issues

Please report bugs and other issues via Bugzilla.

Reference

T. Hamp, T. Goldberg and Rost, B. (2013): Accelerating the Original Profile Kernel. PLoS One, 8(4), e68459

Contact

For questions, please contact hampt@rostlab.org

Personal tools