GenDisMix - Revision history

Keilwagen: /* Paper */

2010-02-23T06:32:16Z

Paper

← Older revision		Revision as of 06:32, 23 February 2010
Line 13:		Line 13:

	== Paper ==		== Paper ==
	The paper '''''Unifying generative and discriminative learning principles''''' has been ~~submitted to~~ [http://www.biomedcentral.com/~~bmcbioinformatics~~/ BMC Bioinformatics].		The paper '''''Unifying generative and discriminative learning principles''''' has been published in [http://www.biomedcentral.com/1471-2105/11/98 BMC Bioinformatics].

	== Binary ==		== Binary ==

Grau at 14:09, 25 January 2010

2010-01-25T14:09:04Z

← Older revision		Revision as of 14:09, 25 January 2010
Line 35:		Line 35:
	uk ... unkown file (the file name of the data in FastA-format that shall be classified, OPTIONAL) = null		uk ... unkown file (the file name of the data in FastA-format that shall be classified, OPTIONAL) = null
	* Example: <code>java -cp .:jstacs-1.3.jar GenDisMixApp fg=fgfile.fasta bg=bgfile.fasta gen=0.4 dis=0.4 essBG=8 eps=1E-6 threads=2 outfile=classifier.xml</code>		* Example: <code>java -cp .:jstacs-1.3.jar GenDisMixApp fg=fgfile.fasta bg=bgfile.fasta gen=0.4 dis=0.4 essBG=8 eps=1E-6 threads=2 outfile=classifier.xml</code>


	== References in Jstacs ==		== References in Jstacs ==
	* Example: [[Train classifiers using GenDisMix (a hybrid learning principle)]]		* Example: [[Train classifiers using GenDisMix (a hybrid learning principle)]]
	* API for [http://www.jstacs.de/api/de/jstacs/classifier/scoringFunctionBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier]		* API for [http://www.jstacs.de/api/de/jstacs/classifier/scoringFunctionBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier]

Grau at 14:08, 25 January 2010

2010-01-25T14:08:44Z

← Older revision		Revision as of 14:08, 25 January 2010
Line 19:		Line 19:
	* [http://www.jstacs.de/downloads/GenDisMixApp.java Sources of the binary]		* [http://www.jstacs.de/downloads/GenDisMixApp.java Sources of the binary]
	* Requirements: [http://java.sun.com Java] v. 5 or later, [[Downloads \| Jstacs 1.3]] or later		* Requirements: [http://java.sun.com Java] v. 5 or later, [[Downloads \| Jstacs 1.3]] or later
	* Put jstacs-1.3.jar (contained in [[Downloads \| Jstacs 1.3]] binary) into the same directory as GenDisMixApp.java or GenDisMixApp.class, respectively		* Put <code>jstacs-1.3.jar</code> (contained in [[Downloads \| Jstacs 1.3]] binary) into the same directory as <code>GenDisMixApp.java</code> or <code>GenDisMixApp.class</code>, respectively
	* Compile by calling <code>javac -cp jstacs-1.3.jar GenDisMixApp.java</code>		* Compile by calling <code>javac -cp jstacs-1.3.jar GenDisMixApp.java</code>
	* Run by calling <code>java -cp .:jstacs-1.3.jar GenDisMixApp</code> (Unix,Linux) or <code>java -cp .;jstacs-1.3.jar GenDisMixApp</code> (Windows)		* Run by calling <code>java -cp .:jstacs-1.3.jar GenDisMixApp</code> (Unix,Linux) or <code>java -cp .;jstacs-1.3.jar GenDisMixApp</code> (Windows)

Grau at 14:07, 25 January 2010

2010-01-25T14:07:44Z

← Older revision		Revision as of 14:07, 25 January 2010
Line 19:		Line 19:
	* [http://www.jstacs.de/downloads/GenDisMixApp.java Sources of the binary]		* [http://www.jstacs.de/downloads/GenDisMixApp.java Sources of the binary]
	* Requirements: [http://java.sun.com Java] v. 5 or later, [[Downloads \| Jstacs 1.3]] or later		* Requirements: [http://java.sun.com Java] v. 5 or later, [[Downloads \| Jstacs 1.3]] or later
			* Put jstacs-1.3.jar (contained in [[Downloads \| Jstacs 1.3]] binary) into the same directory as GenDisMixApp.java or GenDisMixApp.class, respectively
	* Compile by calling <code>javac -cp jstacs-1.3.jar GenDisMixApp.java</code>		* Compile by calling <code>javac -cp jstacs-1.3.jar GenDisMixApp.java</code>
	* Run by calling <code>java -cp .:jstacs-1.3.jar GenDisMixApp</code> (Unix,Linux) or <code>java -cp .;jstacs-1.3.jar GenDisMixApp</code> (Windows)		* Run by calling <code>java -cp .:jstacs-1.3.jar GenDisMixApp</code> (Unix,Linux) or <code>java -cp .;jstacs-1.3.jar GenDisMixApp</code> (Windows)

Grau at 14:06, 25 January 2010

2010-01-25T14:06:13Z

← Older revision		Revision as of 14:06, 25 January 2010
Line 22:		Line 22:
	* Run by calling <code>java -cp .:jstacs-1.3.jar GenDisMixApp</code> (Unix,Linux) or <code>java -cp .;jstacs-1.3.jar GenDisMixApp</code> (Windows)		* Run by calling <code>java -cp .:jstacs-1.3.jar GenDisMixApp</code> (Unix,Linux) or <code>java -cp .;jstacs-1.3.jar GenDisMixApp</code> (Windows)
	* Arguments:		* Arguments:
	~~<source lang="java5">~~		home ... home directory (the path to the data directory, default = ./) = ./
	home ... home directory (the path to the data directory, default = ./) = ./		fg ... foreground file (the file name of the foreground data file in FastA-format) = null
	fg ... foreground file (the file name of the foreground data file in FastA-format) = null		bg ... background file (the file name of the background data file in FastA-format) = null
	bg ... background file (the file name of the background data file in FastA-format) = null		gen ... generative weight (the weight of the generative component, valid range = [0.0, 1.0]) = null
	gen ... generative weight (the weight of the generative component, valid range = [0.0, 1.0]) = null		dis ... discriminative weight (the weight of the discriminative component, valid range = [0.0, 1.0]) = null
	dis ... discriminative weight (the weight of the discriminative component, valid range = [0.0, 1.0]) = null		eps ... epsilon (numerical optimization is stopped if gain less than epsilon, default = 1.0E-6) = 1.0E-6
	eps ... epsilon (numerical optimization is stopped if gain less than epsilon, default = 1.0E-6) = 1.0E-6		threads ... threads (the number of threads used for the computation, default = 1) = 1
	threads ... threads (the number of threads used for the computation, default = 1) = 1		essFG ... essFG (the equivalent sample size used for the foreground class, default = 4.0) = 4.0
	essFG ... essFG (the equivalent sample size used for the foreground class, default = 4.0) = 4.0		essBG ... essFG (the equivalent sample size used for the background class, default = 4.0) = 4.0
	essBG ... essFG (the equivalent sample size used for the background class, default = 4.0) = 4.0		outfile ... outfile (the name of the file where to store the classifier in XML-format, default = gendismix.xml) = gendismix.xml
	outfile ... outfile (the name of the file where to store the classifier in XML-format, default = gendismix.xml) = gendismix.xml		uk ... unkown file (the file name of the data in FastA-format that shall be classified, OPTIONAL) = null
	uk ... unkown file (the file name of the data in FastA-format that shall be classified, OPTIONAL) = null
	~~</source>~~
	* Example: <code>java -cp .:jstacs-1.3.jar GenDisMixApp fg=fgfile.fasta bg=bgfile.fasta gen=0.4 dis=0.4 essBG=8 eps=1E-6 threads=2 outfile=classifier.xml</code>		* Example: <code>java -cp .:jstacs-1.3.jar GenDisMixApp fg=fgfile.fasta bg=bgfile.fasta gen=0.4 dis=0.4 essBG=8 eps=1E-6 threads=2 outfile=classifier.xml</code>

Grau at 14:00, 25 January 2010

2010-01-25T14:00:49Z

← Older revision		Revision as of 14:00, 25 January 2010
Line 16:		Line 16:

	== Binary ==		== Binary ==
	* [http://www.jstacs.de/downloads/GenDisMixApp.~~class~~ GenDisMix binary]		* [http://www.jstacs.de/downloads/GenDisMixApp-bin.zip GenDisMix binary]
	* [http://www.jstacs.de/downloads/GenDisMixApp.java Sources of the binary]		* [http://www.jstacs.de/downloads/GenDisMixApp.java Sources of the binary]
	* Requirements: [http://java.sun.com Java] v. 5 or later, [[Downloads \| Jstacs 1.3]] or later		* Requirements: [http://java.sun.com Java] v. 5 or later, [[Downloads \| Jstacs 1.3]] or later

Grau at 13:53, 25 January 2010

2010-01-25T13:53:13Z

@@ Line 14: / Line 14: @@
 == Paper ==
 The paper '''''Unifying generative and discriminative learning principles''''' has been submitted to [http://www.biomedcentral.com/bmcbioinformatics/ BMC Bioinformatics].
 == References in Jstacs ==
 * Example: [[Train classifiers using GenDisMix (a hybrid learning principle)]]
 * API for [http://www.jstacs.de/api/de/jstacs/classifier/scoringFunctionBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier]

Keilwagen: New page: NOTOC by Jens Keilwagen, Jan Grau, Stefan Posch, Marc Strickert, and Ivo Grosse. == Description == === Background === The recognition of functional binding sites in genomic DNA remain...

2010-01-19T12:11:31Z

New page: __NOTOC__ by Jens Keilwagen, Jan Grau, Stefan Posch, Marc Strickert, and Ivo Grosse. == Description == === Background === The recognition of functional binding sites in genomic DNA remain...

New page

__NOTOC__
by Jens Keilwagen, Jan Grau, Stefan Posch, Marc Strickert, and Ivo Grosse.

== Description ==
=== Background ===
The recognition of functional binding sites in genomic DNA remains one of the fundamental challenges of genome research. During the last decades, a plethora of different and well-adapted models has been developed, but only little attention has be payed to the development of different and similarly well-adapted learning principles. Only recently it was noticed that discriminative learning principles can be superior over generative ones in diverse bioinformatics applications, too.

=== Results ===
Here, we propose a generalization of generative and discriminative learning principles containing the maximum likelihood, maximum a-posteriori, maximum conditional likelihood, maximum supervised posterior, generative-discriminative trade-off, and penalized generative-discriminative trade-off learning principles as special cases, and we illustrate its efficacy for the recognition of vertebrate transcription factor binding sites.

=== Conclusions ===
We find that the proposed learning principle helps to improve the recognition of transcription factor binding sites and enables better computational approaches for extracting as much information as possible from valuable wet-lab data. We make all implementations available in the open-source library Jstacs so that this learning principle can be easily applied to other classification problems in the field of genome and epigenome analysis.

== Paper ==
The paper '''''Unifying generative and discriminative learning principles''''' has been submitted to [http://www.biomedcentral.com/bmcbioinformatics/ BMC Bioinformatics].

== References in Jstacs ==
* Example: [[Train classifiers using GenDisMix (a hybrid learning principle)]]
* API for [http://www.jstacs.de/api/de/jstacs/classifier/scoringFunctionBased/gendismix/GenDisMixClassifier.html GenDisMixClassifier]