Dream5 - Revision history

Grau at 08:03, 9 February 2011

2011-02-09T08:03:41Z

← Older revision		Revision as of 08:03, 9 February 2011
Line 7:		Line 7:

	=== Results ===		=== Results ===
	We implement this approach as extension of [[Dispom]] and evaluate it on the benchmark data of [http://wiki.c2b2.columbia.edu/dream/index.php/~~D5c~~ Dream5 challenge 2], a rigorous benchmark for the analysis of PBM data. We find an improved overall performance compared to the [http://wiki.c2b2.columbia.edu/dream/results/DREAM5/?c=2_1 participants of the challenge]. Besides discriminative learning of model parameters, one reason for the superior performance of Dispom is the consideration of dependencies between adjacent positions of the binding sites, which suggests exploiting dependencies between adjacent base pairs in transcription factor binding sites whenever enough training data are available. Another important property is that this novel approach is robust to typical artifacts of PBM experiments, which facilitates its application to PBM data without the need for prior normalization.		We implement this approach as extension of [[Dispom]] and evaluate it on the benchmark data of [http://wiki.c2b2.columbia.edu/dream/index.php/D5c2 Dream5 challenge 2], a rigorous benchmark for the analysis of PBM data. We find an improved overall performance compared to the [http://wiki.c2b2.columbia.edu/dream/results/DREAM5/?c=2_1 participants of the challenge]. Besides discriminative learning of model parameters, one reason for the superior performance of Dispom is the consideration of dependencies between adjacent positions of the binding sites, which suggests exploiting dependencies between adjacent base pairs in transcription factor binding sites whenever enough training data are available. Another important property is that this novel approach is robust to typical artifacts of PBM experiments, which facilitates its application to PBM data without the need for prior normalization.

	== Paper ==		== Paper ==

Keilwagen at 21:46, 8 February 2011

2011-02-08T21:46:45Z

← Older revision		Revision as of 21:46, 8 February 2011
Line 7:		Line 7:

	=== Results ===		=== Results ===
	We implement this approach as extension of [~~Disoom \|~~ Dispom] and evaluate it on the benchmark data of [http://wiki.c2b2.columbia.edu/dream/index.php/D5c Dream5 challenge 2], a rigorous benchmark for the analysis of PBM data. We find an improved overall performance compared to the [http://wiki.c2b2.columbia.edu/dream/results/DREAM5/?c=2_1 participants of the challenge]. Besides discriminative learning of model parameters, one reason for the superior performance of Dispom is the consideration of dependencies between adjacent positions of the binding sites, which suggests exploiting dependencies between adjacent base pairs in transcription factor binding sites whenever enough training data are available. Another important property is that this novel approach is robust to typical artifacts of PBM experiments, which facilitates its application to PBM data without the need for prior normalization.		We implement this approach as extension of [[Dispom]] and evaluate it on the benchmark data of [http://wiki.c2b2.columbia.edu/dream/index.php/D5c Dream5 challenge 2], a rigorous benchmark for the analysis of PBM data. We find an improved overall performance compared to the [http://wiki.c2b2.columbia.edu/dream/results/DREAM5/?c=2_1 participants of the challenge]. Besides discriminative learning of model parameters, one reason for the superior performance of Dispom is the consideration of dependencies between adjacent positions of the binding sites, which suggests exploiting dependencies between adjacent base pairs in transcription factor binding sites whenever enough training data are available. Another important property is that this novel approach is robust to typical artifacts of PBM experiments, which facilitates its application to PBM data without the need for prior normalization.

	== Paper ==		== Paper ==

Grau at 19:50, 8 February 2011

2011-02-08T19:50:05Z

← Older revision		Revision as of 19:50, 8 February 2011
Line 7:		Line 7:

	=== Results ===		=== Results ===
	We implement this approach as extension of Dispom and evaluate it on the benchmark data of Dream5 challenge 2, a rigorous benchmark for the analysis of PBM data. We find an improved overall performance compared to the participants of the challenge. Besides discriminative learning of model parameters, one reason for the superior performance of Dispom is the consideration of dependencies between adjacent positions of the binding sites, which suggests exploiting dependencies between adjacent base pairs in transcription factor binding sites whenever enough training data are available. Another important property is that this novel approach is robust to typical artifacts of PBM experiments, which facilitates its application to PBM data without the need for prior normalization.		We implement this approach as extension of [Disoom \| Dispom] and evaluate it on the benchmark data of [http://wiki.c2b2.columbia.edu/dream/index.php/D5c Dream5 challenge 2], a rigorous benchmark for the analysis of PBM data. We find an improved overall performance compared to the [http://wiki.c2b2.columbia.edu/dream/results/DREAM5/?c=2_1 participants of the challenge]. Besides discriminative learning of model parameters, one reason for the superior performance of Dispom is the consideration of dependencies between adjacent positions of the binding sites, which suggests exploiting dependencies between adjacent base pairs in transcription factor binding sites whenever enough training data are available. Another important property is that this novel approach is robust to typical artifacts of PBM experiments, which facilitates its application to PBM data without the need for prior normalization.

	== Paper ==		== Paper ==

Grau at 19:48, 8 February 2011

2011-02-08T19:48:20Z

← Older revision		Revision as of 19:48, 8 February 2011
Line 34:		Line 34:

	=== Predictions ===		=== Predictions ===
	Loads a trained model from a file and predicts intensities for a given set of probe sequences in Dream5 ~~prediction~~ format (see [http://wiki.c2b2.columbia.edu/dream/index.php/D5c2#Submission Dream5 homepage]).		Loads a trained model from a file and predicts intensities for a given set of probe sequences in Dream5 submission format (see [http://wiki.c2b2.columbia.edu/dream/index.php/D5c2#Submission Dream5 homepage]).
	* Run by calling <code>java -jar Dream5Predict.jar</code>		* Run by calling <code>java -jar Dream5Predict.jar</code>
	* Arguments:		* Arguments:

Grau at 19:47, 8 February 2011

2011-02-08T19:47:58Z

← Older revision		Revision as of 19:47, 8 February 2011
Line 42:		Line 42:
	outfile ... outfile (File where the predictions are stored., default = predictions.txt)		outfile ... outfile (File where the predictions are stored., default = predictions.txt)

	* Example: <code>java -jar ~~Dream5~~.jar file=TF1_ME.txt model=mymodel.xml outfile=predicitions_TF1_ME.txt</code>		* Example: <code>java -jar Dream5Predict.jar file=TF1_ME.txt model=mymodel.xml outfile=predicitions_TF1_ME.txt</code>

Grau at 19:47, 8 February 2011

2011-02-08T19:47:33Z

← Older revision		Revision as of 19:47, 8 February 2011
Line 12:		Line 12:
	The paper '''''Accurate prediction of protein binding microarray data by discriminative de-novo motif discovery''''' has been submitted to ISMB 2011.		The paper '''''Accurate prediction of protein binding microarray data by discriminative de-novo motif discovery''''' has been submitted to ISMB 2011.

	== ~~Binary~~ ==		== Binaries ==
			We provide two binaries, one for training a model from PBM data including sequences and associated intensities and one for predicting intensities for given probe sequences using a trained model. By this means, training can be accomplished on e.g. a computation server, while the computationally less expensive predictions can be made on an ordinary workstation.

	* [http://www.jstacs.de/downloads/Dream5.zip Binaries for training and prediction] as ZIP-archive		* [http://www.jstacs.de/downloads/Dream5.zip Binaries for training and prediction] as ZIP-archive
	* [http://www.jstacs.de/downloads/Dream5-sources.zip Sources of the binaries], require Jstacs 1.4 sources to build		* [http://www.jstacs.de/downloads/Dream5-sources.zip Sources of the binaries], require Jstacs 1.4 sources to build

	=== Training ===		=== Training ===
			Trains a model from PBM data in Dream5-format (see [http://wiki.c2b2.columbia.edu/dream/index.php/D5c2 Dream5 homepage]) and stores the trained model to a file.
	* Run by calling <code>java -jar Dream5.jar</code>		* Run by calling <code>java -jar Dream5.jar</code>
	* Arguments:		* Arguments:
Line 31:		Line 34:

	=== Predictions ===		=== Predictions ===
			Loads a trained model from a file and predicts intensities for a given set of probe sequences in Dream5 prediction format (see [http://wiki.c2b2.columbia.edu/dream/index.php/D5c2#Submission Dream5 homepage]).
	* Run by calling <code>java -jar Dream5Predict.jar</code>		* Run by calling <code>java -jar Dream5Predict.jar</code>
	* Arguments:		* Arguments:

Grau at 17:41, 8 February 2011

2011-02-08T17:41:07Z

Grau at 17:40, 8 February 2011

2011-02-08T17:40:08Z

← Older revision		Revision as of 17:40, 8 February 2011
Line 37:		Line 37:
	model ... model (File with the trained model stored as XML, path relative to home directory., default = model.xml)		model ... model (File with the trained model stored as XML, path relative to home directory., default = model.xml)
	outfile ... outfile (File where the predictions are stored., default = predictions.txt)		outfile ... outfile (File where the predictions are stored., default = predictions.txt)


	* Example: <code>java -jar Dream5.jar file=TF1_ME.txt model=mymodel.xml outfile=predicitions_TF1_ME.txt</code>		* Example: <code>java -jar Dream5.jar file=TF1_ME.txt model=mymodel.xml outfile=predicitions_TF1_ME.txt</code>

Grau at 17:39, 8 February 2011

2011-02-08T17:39:00Z

← Older revision		Revision as of 17:39, 8 February 2011
Line 13:		Line 13:

	== Binary ==		== Binary ==
	* [http://www.jstacs.de/downloads/Dream5.zip Binaries for training and prediction]		* [http://www.jstacs.de/downloads/Dream5.zip Binaries for training and prediction] as ZIP-archive
	* [http://www.jstacs.de/downloads/Dream5-sources.zip Sources of the binaries], require Jstacs 1.4 sources to build		* [http://www.jstacs.de/downloads/Dream5-sources.zip Sources of the binaries], require Jstacs 1.4 sources to build

Grau at 17:38, 8 February 2011

2011-02-08T17:38:03Z

← Older revision		Revision as of 17:38, 8 February 2011
Line 14:		Line 14:
	== Binary ==		== Binary ==
	* [http://www.jstacs.de/downloads/Dream5.zip Binaries for training and prediction]		* [http://www.jstacs.de/downloads/Dream5.zip Binaries for training and prediction]
	* [http://www.jstacs.de/downloads/~~GenDisMixApp~~.~~java~~ Sources of the binaries], require Jstacs 1.4 sources to build		* [http://www.jstacs.de/downloads/Dream5-sources.zip Sources of the binaries], require Jstacs 1.4 sources to build

	=== Training ===		=== Training ===

← Older revision		Revision as of 17:41, 8 February 2011
Line 19:		Line 19:
	* Run by calling <code>java -jar Dream5.jar</code>		* Run by calling <code>java -jar Dream5.jar</code>
	* Arguments:		* Arguments:
	home ... home directory (The home directory where the data reside., default = .)		home ... home directory (The home directory where the data reside., default = .)
	file ... input file (The input file in Dream5 format (column 1: TF, column 2: array type, column 3: sequences, column 4: signal, last column: flag), one file per TF and array type, path relative to home directory.)		file ... input file (The input file in Dream5 format (column 1: TF, column 2: array type, column 3: sequences, column 4: signal, last column: flag), one file per TF and array type, path relative to home directory.)
	mo ... motif order (The order of the inhomogeneous Markov model for the motif., default = 1)		mo ... motif order (The order of the inhomogeneous Markov model for the motif., default = 1)
	fo ... flanking oder (The order of the homogeneous Markov model for flanking sequence and background., default = 3)		fo ... flanking oder (The order of the homogeneous Markov model for flanking sequence and background., default = 3)
	starts ... starts (The number of starts of the optimization., default = 5)		starts ... starts (The number of starts of the optimization., default = 5)
	threads ... threads (The number of threads, i.e. cores, that are used for optimization., default = 1)		threads ... threads (The number of threads, i.e. cores, that are used for optimization., default = 1)
	q ... q (A-priori fraction of data points with weight greater than 0.5, default = 0.025)		q ... q (A-priori fraction of data points with weight greater than 0.5, default = 0.025)
	model ... model (File where the trained model is stored as XML, path relative to home directory., default = model.xml)		model ... model (File where the trained model is stored as XML, path relative to home directory., default = model.xml)

	* Example: <code>java -jar Dream5.jar file=TF1_HK.txt starts=1 threads=2 model=mymodel.xml</code>		* Example: <code>java -jar Dream5.jar file=TF1_HK.txt starts=1 threads=2 model=mymodel.xml</code>
Line 33:		Line 33:
	* Run by calling <code>java -jar Dream5Predict.jar</code>		* Run by calling <code>java -jar Dream5Predict.jar</code>
	* Arguments:		* Arguments:
	home ... home directory (The home directory where the data reside., default = .)		home ... home directory (The home directory where the data reside., default = .)
	file ... input file (The input file in Dream5 format for predictions (column 1: TF, column 2: array type, column 3: sequence), one file per TF and array type, path relative to home directory.)		file ... input file (The input file in Dream5 format for predictions (column 1: TF, column 2: array type, column 3: sequence), one file per TF and array type, path relative to home directory.)
	model ... model (File with the trained model stored as XML, path relative to home directory., default = model.xml)		model ... model (File with the trained model stored as XML, path relative to home directory., default = model.xml)
	outfile ... outfile (File where the predictions are stored., default = predictions.txt)		outfile ... outfile (File where the predictions are stored., default = predictions.txt)

	* Example: <code>java -jar Dream5.jar file=TF1_ME.txt model=mymodel.xml outfile=predicitions_TF1_ME.txt</code>		* Example: <code>java -jar Dream5.jar file=TF1_ME.txt model=mymodel.xml outfile=predicitions_TF1_ME.txt</code>