ARHMM - Revision history

Seifert: /* Download */

2019-07-10T06:16:56Z

Download

← Older revision		Revision as of 06:16, 10 July 2019
Line 17:		Line 17:

	== Download ==		== Download ==
	* [~~http~~://~~imc~~.~~zih~~.tu-dresden.de/~~downloads~~/~~ARHMM/ARHMM_Trainer.zip~~ ARHMM]: A ZIP file containing a JAR file for analyzing tumor gene expression data sets by ARHMMs. This file also contains the considered breast cancer and the glioma gene expression data sets.		* [https://imbcloud.medizin.tu-dresden.de:5001/sharing/jq1z2zaa2 ARHMM]: A ZIP file containing a JAR file for analyzing tumor gene expression data sets by ARHMMs. This file also contains the considered breast cancer and the glioma gene expression data sets.

	== Related Projects ==		== Related Projects ==

Seifert: /* Related Projects */

2016-10-16T07:19:52Z

Related Projects

← Older revision		Revision as of 07:19, 16 October 2016
Line 24:		Line 24:
	* [[PHHMM]]: improved analysis of Array-CGH data		* [[PHHMM]]: improved analysis of Array-CGH data
	* [[MeDIP-HMM]]: HMM-based analysis of DNA methylation profiles		* [[MeDIP-HMM]]: HMM-based analysis of DNA methylation profiles
	* [https://sites.google.com/site/mseifertweb~~/home~~/hmm-book HMM Book]: Hidden Markov Models with Applications in Computational Biology		* [https://sites.google.com/site/mseifertweb/hmm-book HMM Book]: Hidden Markov Models with Applications in Computational Biology

	== Follow Me ==		== Follow Me ==
	* [https://sites.google.com/site/mseifertweb/home Personal Homepage]		* [https://sites.google.com/site/mseifertweb/home Personal Homepage]

Seifert: /* Related Projects */

2016-10-16T07:19:02Z

Related Projects

← Older revision		Revision as of 07:19, 16 October 2016
Line 24:		Line 24:
	* [[PHHMM]]: improved analysis of Array-CGH data		* [[PHHMM]]: improved analysis of Array-CGH data
	* [[MeDIP-HMM]]: HMM-based analysis of DNA methylation profiles		* [[MeDIP-HMM]]: HMM-based analysis of DNA methylation profiles
	* [https://sites.google.com/site/~~michaelseiferthmm~~/hmm-book HMM Book]: Hidden Markov Models with Applications in Computational Biology		* [https://sites.google.com/site/mseifertweb/home/hmm-book HMM Book]: Hidden Markov Models with Applications in Computational Biology

	== Follow Me ==		== Follow Me ==
	* [https://sites.google.com/site/mseifertweb/home Personal Homepage]		* [https://sites.google.com/site/mseifertweb/home Personal Homepage]

Seifert: /* Follow Me */

2016-10-16T07:14:40Z

Follow Me

← Older revision		Revision as of 07:14, 16 October 2016
Line 27:		Line 27:

	== Follow Me ==		== Follow Me ==
	* [https://sites.google.com/site/~~michaelseiferthmm~~/home Personal Homepage]		* [https://sites.google.com/site/mseifertweb/home Personal Homepage]

Seifert: /* Paper */

2014-06-27T13:53:29Z

Paper

← Older revision		Revision as of 13:53, 27 June 2014
Line 11:		Line 11:
	== Paper ==		== Paper ==
	The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been published in [http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0100295 PLoS One].		The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been published in [http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0100295 PLoS One].

			Preprints: [http://imc.zih.tu-dresden.de/downloads/ARHMM/seifert_plosOne_article_preprint.pdf Article] and [http://imc.zih.tu-dresden.de/downloads/ARHMM/seifert_plosOne_appendix_preprint.pdf Appendix]

			Note: ARHMMs can also be applied to the analysis of log-ratio profiles of tumors analyzed by RNA-seq. I recently applied ARHMMs successfully to compare different glioma grades based on log-ratio profiles generated by Cuffdiff.

	== Download ==		== Download ==

Seifert: /* Paper */

2014-06-24T06:46:38Z

Paper

← Older revision		Revision as of 06:46, 24 June 2014
Line 10:		Line 10:

	== Paper ==		== Paper ==
	The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been ~~accepted by~~ [http://www.plosone.org/ PLoS One].		The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been published in [http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0100295 PLoS One].

	== Download ==		== Download ==

Seifert: /* Paper */

2014-05-26T19:44:43Z

Paper

← Older revision		Revision as of 19:44, 26 May 2014
Line 10:		Line 10:

	== Paper ==		== Paper ==
	The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been ~~recently~~ accepted by [http://www.plosone.org/ PLoS One].		The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been accepted by [http://www.plosone.org/ PLoS One].

	== Download ==		== Download ==

Seifert: /* Paper */

2014-05-26T19:43:41Z

Paper

← Older revision		Revision as of 19:43, 26 May 2014
Line 10:		Line 10:

	== Paper ==		== Paper ==
	The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been ~~submitted to~~ [http://www.~~ploscompbiol~~.org/ PLoS ~~Computational Biology~~].		The paper '''''Autoregressive Higher-Order Hidden Markov Models: Exploiting Local Chromosomal Dependencies in the Analysis of Tumor Expression Profiles''''' has been recently accepted by [http://www.plosone.org/ PLoS One].

	== Download ==		== Download ==

Seifert: /* Results */

2014-05-26T19:41:21Z

Results

← Older revision		Revision as of 19:41, 26 May 2014
Line 7:		Line 7:

	=== Results ===		=== Results ===
	We develop ~~the~~ novel model class of autoregressive higher-order Hidden Markov Models (HMMs) that carefully exploit local data-dependent chromosomal dependencies to improve the identification of differentially expressed genes in individual tumors. Autoregressive higher-order HMMs overcome generally existing limitations of standard first-order HMMs in the modeling of dependencies between genes in close chromosomal proximity by the usage of higher-order state-transitions in combination with autoregressive emissions as novel model features. We train autoregressive higher-order HMMs by a specifically developed Bayesian Baum-Welch algorithm that enables to integrate prior knowledge on the measurement distribution of genes. We apply autoregressive higher-order HMMs to the analysis of breast cancer and different types of brain tumor gene expression data and perform in-depth model evaluation studies. We find that autoregressive higher-order HMMs clearly improve the identification of overexpressed genes with underlying gene copy number duplications in breast cancer in comparison to mixture models, standard first- and higher-order HMMs, and other existing related methods. This performance benefit is attributed to the simultaneous usage of higher-order state-transitions in combination with autoregressive emissions, and could not be reached by using each of these two features independently. We also find that autoregressive higher-order HMMs are better able to identify differentially expressed genes in tumor independent of the underlying gene copy number status in comparison to the majority of related methods. This is further supported by the identification of well-known and of previously unreported hotspots of differential expression in glioblastomas demonstrating the efficacy of autoregressive higher-order HMMs for the analysis of individual tumor expression profiles. Moreover, we reveal interesting novel details of systematic alterations of gene expression levels in known cancer signaling pathways distinguishing oligodendrogliomas, astrocytomas and glioblastomas.		We develop a novel model class of autoregressive higher-order Hidden Markov Models (HMMs) that carefully exploit local data-dependent chromosomal dependencies to improve the identification of differentially expressed genes in individual tumors. Autoregressive higher-order HMMs overcome generally existing limitations of standard first-order HMMs in the modeling of dependencies between genes in close chromosomal proximity by the usage of higher-order state-transitions in combination with autoregressive emissions as novel model features. We train autoregressive higher-order HMMs by a specifically developed Bayesian Baum-Welch algorithm that enables to integrate prior knowledge on the measurement distribution of genes. We apply autoregressive higher-order HMMs to the analysis of breast cancer and different types of brain tumor gene expression data and perform in-depth model evaluation studies. We find that autoregressive higher-order HMMs clearly improve the identification of overexpressed genes with underlying gene copy number duplications in breast cancer in comparison to mixture models, standard first- and higher-order HMMs, and other existing related methods. This performance benefit is attributed to the simultaneous usage of higher-order state-transitions in combination with autoregressive emissions and could not be reached by using each of these two features independently. We also find that autoregressive higher-order HMMs are better able to identify differentially expressed genes in tumor independent of the underlying gene copy number status in comparison to the majority of related methods. This is further supported by the identification of well-known and of previously unreported hotspots of differential expression in glioblastomas demonstrating the efficacy of autoregressive higher-order HMMs for the analysis of individual tumor expression profiles. Moreover, we reveal interesting novel details of systematic alterations of gene expression levels in known cancer signaling pathways distinguishing oligodendrogliomas, astrocytomas and glioblastomas.

	== Paper ==		== Paper ==

Seifert at 14:09, 21 February 2014

2014-02-21T14:09:18Z

← Older revision		Revision as of 14:09, 21 February 2014
Line 7:		Line 7:

	=== Results ===		=== Results ===
	We develop the novel model class of autoregressive higher-order Hidden Markov Models (HMMs) that carefully exploit local data-dependent chromosomal dependencies to improve the identification of differentially expressed genes in individual tumors. Autoregressive higher-order HMMs overcome generally existing limitations of standard first-order HMMs in the modeling of dependencies between genes in close chromosomal proximity by the usage of higher-order state-transitions in combination with autoregressive emissions as novel model features. We train autoregressive higher-order HMMs by a specifically developed Bayesian Baum-Welch algorithm that enables to integrate prior knowledge on the measurement distribution of genes. We apply autoregressive higher-order HMMs to the analysis of breast cancer and different types of brain tumor gene expression data and perform in-depth model evaluation studies. We find that autoregressive higher-order HMMs clearly improve the identification of overexpressed genes with underlying gene copy number duplications in breast cancer in comparison to mixture models, standard first- and higher-order HMMs, and other existing related methods. This performance benefit is attributed to the simultaneous usage of higher-order state-transitions in combination with autoregressive emissions, and could not be reached by using each of these two features independently. We also find that autoregressive higher-order HMMs are better able to identify differentially expressed genes in tumor independent of the underlying gene copy number status in comparison to the majority of related methods. This is further supported by the identification of well-known and previously unreported hotspots of differential expression in glioblastomas demonstrating the efficacy of autoregressive higher-order HMMs for the analysis of individual tumor expression profiles. Moreover, we reveal interesting novel details of systematic alterations of gene expression levels in known cancer signaling pathways distinguishing oligodendrogliomas, astrocytomas and glioblastomas.		We develop the novel model class of autoregressive higher-order Hidden Markov Models (HMMs) that carefully exploit local data-dependent chromosomal dependencies to improve the identification of differentially expressed genes in individual tumors. Autoregressive higher-order HMMs overcome generally existing limitations of standard first-order HMMs in the modeling of dependencies between genes in close chromosomal proximity by the usage of higher-order state-transitions in combination with autoregressive emissions as novel model features. We train autoregressive higher-order HMMs by a specifically developed Bayesian Baum-Welch algorithm that enables to integrate prior knowledge on the measurement distribution of genes. We apply autoregressive higher-order HMMs to the analysis of breast cancer and different types of brain tumor gene expression data and perform in-depth model evaluation studies. We find that autoregressive higher-order HMMs clearly improve the identification of overexpressed genes with underlying gene copy number duplications in breast cancer in comparison to mixture models, standard first- and higher-order HMMs, and other existing related methods. This performance benefit is attributed to the simultaneous usage of higher-order state-transitions in combination with autoregressive emissions, and could not be reached by using each of these two features independently. We also find that autoregressive higher-order HMMs are better able to identify differentially expressed genes in tumor independent of the underlying gene copy number status in comparison to the majority of related methods. This is further supported by the identification of well-known and of previously unreported hotspots of differential expression in glioblastomas demonstrating the efficacy of autoregressive higher-order HMMs for the analysis of individual tumor expression profiles. Moreover, we reveal interesting novel details of systematic alterations of gene expression levels in known cancer signaling pathways distinguishing oligodendrogliomas, astrocytomas and glioblastomas.

	== Paper ==		== Paper ==
Line 13:		Line 13:

	== Download ==		== Download ==
	* [http://imc.zih.tu-dresden.de/downloads/ARHMM/ARHMM_Trainer.zip ARHMM]: A ZIP file containing a JAR file for analyzing tumor gene expression data sets by ARHMMs. This file also contains the considered breast cancer and the ~~glioblastoma~~ gene expression data sets.		* [http://imc.zih.tu-dresden.de/downloads/ARHMM/ARHMM_Trainer.zip ARHMM]: A ZIP file containing a JAR file for analyzing tumor gene expression data sets by ARHMMs. This file also contains the considered breast cancer and the glioma gene expression data sets.

	== Related Projects ==		== Related Projects ==