rg::reprof(3pm) [debian man page]
RG::Reprof(3pm) User Contributed Perl Documentation RG::Reprof(3pm) NAME
RG::Reprof::Reprof - protein secondary structure and accessibility predictor SYNOPSIS
use RG::Reprof::Reprof; DESCRIPTION
See module commented source for further details. Methods OBJ RG::Reprof::Reprof->new( model_dir => PATH ) Default model_dir: /tmp/lkajan/root/share/reprof. Returns new instance of RG::Reprof::Reprof. int $OBJ->run( input_file => PATH, out_file => PATH, mutation_file => PATH, specific_models => hashref, output_func => coderef ) out_file may be a directory. mutation_file may be undefined. specific_models may be undefined. This is a hash of model and feature files with 'model_name' keys like: { 'fub_model' => '/path/to/model_file', 'fub_features' => '/path/to/features_file' } Check the module source for the list for model names. void output_func( out_file, sec_pred, acc_pred, sequence ) - function to call when output is ready. If undefined, the built-in write_output() function is called that prints results to one or more files. The following positional parameters are passed to this function: out_file Output file name. sec_pred Secondary structure prediction, see source for details. acc_pred Accessibility prediction, see source for details. sequence Reference to array of residues of input sequence (e.g. [ 'M', 'A', 'G', ... ] ). AUTHOR
Original version by Peter Hoenigschmid <hoenigschmid@rostlab.org> and Burkhard Rost. Some perl module work and documentation by Laszlo Kajan <lkajan@rostlab.org>. SEE ALSO
<http://rostlab.org/> perl v5.14.2 2012-01-13 RG::Reprof(3pm)
Check Out this Related Man Page
PROFNET(1) User Commands PROFNET(1) NAME
profnet_* - neural network implementations in Fortran SYNOPSIS
profnet_* [OPTION|filePar] DESCRIPTION
profnet_* binaries are neural network implementations in Fortran. Due to the original design of the code, a specific binary is compiled for each particular network architecture, changing certain constants in the source code. Therefore, there is a binary for every network architecture used. Note: certain array structures are intentionally indexed out of bounds in some of the binaries. Note: This binary should only be used to run with pre-made training data, do not try to use it to train your network as it will produce undesired results. It was made to be used only as part of wrapping (dependent) packages and not as a standalone neural network program. OPTIONS
This list is not exhaustive. filePar file with input parameters (also gives fileIn, fileOut) 1 "switch" 2 number of input units 3 number of hidden units 4 number of output units 5 number of samples 6 bitacc (typically 100) 7 file with input vectors 8 file with junctions 9 file with output of NN ("none" -> no file written) 10 optional=dbg [inter] will bring up dialog NOTES
1st MUST be "switch"! tested only with 2 layers! AUTHOR
Burkhard Rost <rost@rostlab.org> Bug fixes and enhancements by Laszlo Kajan <lkajan@rostlab.org> and Guy Yachdav <gyachdav@rostlab.org> COPYRIGHT AND LICENSE
Copyright 1998-2011 by Burkhard Rost <rost@rostlab.org> EMBL, CUBIC (Columbia University, NY, USA) and LION Biosciences (Heidelberg, DE) Copyright 2009-2011 by Laszlo Kajan <lkajan@rostlab.org> Technical University Munich (Munich, DE) Copyright 2009-2011 by Guy Yachdav <gyachdav@rostlab.org> CUBIC (Columbia University, NY, USA) and Technical University Munich (Munich, DE) 1.0.21- 2011-06-16 PROFNET(1)