Endocrine System Disruption - Revision history

Kirilas at 09:59, 15 June 2017

2017-06-15T09:59:57Z

← Older revision		Revision as of 09:59, 15 June 2017
Line 27:		Line 27:
	<br />		<br />

	<div class="mw-collapsible ~~mw-collapsed~~">		<div class="mw-collapsible">

	==Technical information==		==Technical information==

Kirilas: /* Model features & prediction accuracy */

2013-02-14T10:51:32Z

Model features & prediction accuracy

← Older revision		Revision as of 10:51, 14 February 2013
Line 45:		Line 45:
	===Model features & prediction accuracy===		===Model features & prediction accuracy===

	The predictive models of for both Log ''RBA'' cut-offs were derived using GALAS (Global, Adjusted Locally According to Similarity) modeling methodology (please refer to [http://www.ncbi.nlm.nih.gov/pubmed/20373217] for more details).		The predictive models for both Log ''RBA'' cut-offs were derived using GALAS (Global, Adjusted Locally According to Similarity) modeling methodology (please refer to [http://www.ncbi.nlm.nih.gov/pubmed/20373217] for more details).

	Each GALAS model consists of two parts:		Each GALAS model consists of two parts:

Kirilas: /* Model features & prediction accuracy */

2013-02-14T10:49:20Z

Model features & prediction accuracy

← Older revision		Revision as of 10:49, 14 February 2013
Line 49:		Line 49:
	Each GALAS model consists of two parts:		Each GALAS model consists of two parts:
	* Global (baseline) statistical model that reflects general trends in the variation of the property of interest.		* Global (baseline) statistical model that reflects general trends in the variation of the property of interest.
	* Similarity-based routine that performs local correction of baseline predictions taking into account the differences between baseline and experimental ~~LC50~~ values for the most similar training set compounds.		* Similarity-based routine that performs local correction of baseline predictions taking into account the differences between baseline and experimental values for the most similar training set compounds.
	<br>		<br>
	GALAS methodology also provides the basis for estimating reliability of predictions by the means of calculated Reliability Index (''RI'') value that takes into account:		GALAS methodology also provides the basis for estimating reliability of predictions by the means of calculated Reliability Index (''RI'') value that takes into account:
	* Similarity of tested compound to the training set molecules.		* Similarity of tested compound to the training set molecules.
	* Consistence of experimental ~~LC50~~ values and baseline model prediction for the most similar similar compounds from the training set.		* Consistence of experimental values and baseline model prediction for the most similar similar compounds from the training set.

	Reliability Index ranges from 0 to 1 (0 corresponds to a completely unreliable, and 1 - a highly reliable prediction) and serves as an indication whether a submitted compound falls within the Model Applicability Domain. Compounds obtaining predictions ''RI'' < 0.3 are considered outside of the Applicability Domain of the model.		Reliability Index ranges from 0 to 1 (0 corresponds to a completely unreliable, and 1 - a highly reliable prediction) and serves as an indication whether a submitted compound falls within the Model Applicability Domain. Compounds obtaining predictions ''RI'' < 0.3 are considered outside of the Applicability Domain of the model.

Kirilas: /* Calculated quantitative parameters */

2013-02-14T10:41:38Z

Calculated quantitative parameters

← Older revision		Revision as of 10:41, 14 February 2013
Line 35:		Line 35:

	===Calculated quantitative parameters===		===Calculated quantitative parameters===
	''In vitro'' measurement of estrogen receptor binding affinity (Log ''RBA'') estimates the relative affinity of compound to receptor compared to reference ligand estradiol: ''%RBA'' = IC50(''reference'')/IC50(''test compound'') * 100%. Here IC50 is the concentration at which the unlabeled ligand displaces half of specifically bound radiolabeled 17β-estradiol to the ER, (''reference'' estrogen in a typical experiment is the same 17β-estradiol). Experimental data were converted to binary representation with two cut-offs at Log ''RBA'' = -3, and Log ''RBA'' = 0. Predicted values are probabilities that tested compound will have Log ''RBA'' higher than the defined cut-offs. Based on the predictions compounds are classified as strong binders (Log ''RBA'' > 0), weak binders (Log ''RBA'' most probably falling in the range from -3 to 0), and non-binders (Log ''RBA'' < -3).		''In vitro'' measurement of estrogen receptor binding affinity (Log ''RBA'') estimates the relative affinity of compound to receptor compared to reference ligand estradiol:<br><br>
			''%RBA'' = IC50(''reference'')/IC50(''test compound'') * 100%.<br><br> Here IC50 is the concentration at which the unlabeled ligand displaces half of specifically bound radiolabeled 17β-estradiol to the ER, (''reference'' estrogen in a typical experiment is the same 17β-estradiol). Experimental data were converted to binary representation with two cut-offs at Log ''RBA'' = -3, and Log ''RBA'' = 0. Predicted values are probabilities that tested compound will have Log ''RBA'' higher than the defined cut-offs. Based on the predictions compounds are classified as strong binders (Log ''RBA'' > 0), weak binders (Log ''RBA'' most probably falling in the range from -3 to 0), and non-binders (Log ''RBA'' < -3).

	===Experimental data===		===Experimental data===

Kirilas: /* Technical information */

2013-02-14T10:04:20Z

Technical information

← Older revision		Revision as of 10:04, 14 February 2013
Line 43:		Line 43:

	===Model features & prediction accuracy===		===Model features & prediction accuracy===
	The predictive models of ~~Endocrine System Disruption~~ were ~~built~~ using ~~binomial PLS method~~ in ~~Algorithm Builder~~. ~~The models incorporated essential physicochemical properties~~ of ~~chemicals such as ionization~~ and ~~molecular size as well~~ as ~~fragmental descriptors including predefined substructures representing structural features known to have~~ a ~~profound influence on~~ the ~~analyzed property~~.
			The predictive models of for both Log ''RBA'' cut-offs were derived using GALAS (Global, Adjusted Locally According to Similarity) modeling methodology (please refer to [http://www.ncbi.nlm.nih.gov/pubmed/20373217] for more details).

			Each GALAS model consists of two parts:
			* Global (baseline) statistical model that reflects general trends in the variation of the property of interest.
			* Similarity-based routine that performs local correction of baseline predictions taking into account the differences between baseline and experimental LC50 values for the most similar training set compounds.
			<br>
			GALAS methodology also provides the basis for estimating reliability of predictions by the means of calculated Reliability Index (''RI'') value that takes into account:
			* Similarity of tested compound to the training set molecules.
			* Consistence of experimental LC50 values and baseline model prediction for the most similar similar compounds from the training set.

			Reliability Index ranges from 0 to 1 (0 corresponds to a completely unreliable, and 1 - a highly reliable prediction) and serves as an indication whether a submitted compound falls within the Model Applicability Domain. Compounds obtaining predictions ''RI'' < 0.3 are considered outside of the Applicability Domain of the model.

	The resulting models are highly accurate: overall accuracy of ER alpha affinity predictions exceeds 85% in both training and test sets in case of general binding model (Log ''RBA'' > -3), and exceeds 90% in case of strong binding (Log ''RBA'' > 0).		The resulting models are highly accurate: overall accuracy of ER alpha affinity predictions exceeds 85% in both training and test sets in case of general binding model (Log ''RBA'' > -3), and exceeds 90% in case of strong binding (Log ''RBA'' > 0).
	</div>		</div>
	</div>		</div>

Kirilas: /* Interface */

2013-02-14T10:02:46Z

Interface

← Older revision		Revision as of 10:02, 14 February 2013
Line 23:		Line 23:

	# The classification result of the estrogen receptor binding:<br>[[File:Estrogen_receptor_scale.png\|600px]]		# The classification result of the estrogen receptor binding:<br>[[File:Estrogen_receptor_scale.png\|600px]]
	# Calculated probabilities of strong (LogRBA>0) and overall (LogRBA>-3) estrogen receptor binding.		# Calculated probabilities and Reliability Indices (''RI'') of strong (LogRBA>0) and overall (LogRBA>-3) estrogen receptor binding.
	# Up to 5 records of similar compounds from the training set, including name, CAS number, LogRBA values, species and references.		# Up to 5 records of similar compounds from the training set, including name, CAS number, LogRBA values, species and references.
	<br />		<br />

Kristina: /* Interface */

2012-05-29T13:17:22Z

Interface

← Older revision		Revision as of 13:17, 29 May 2012
Line 19:		Line 19:
	<br />		<br />

	[[Image:~~estrogen_receptor~~.png\|center]]		[[Image:Estrogen_receptor.png\|center]]
	<br />		<br />

	# The classification result of the estrogen receptor binding:<br>[[File:~~estrogen_receptor_scale~~.png\|600px]]		# The classification result of the estrogen receptor binding:<br>[[File:Estrogen_receptor_scale.png\|600px]]
	# Calculated probabilities of strong (LogRBA>0) and overall (LogRBA>-3) estrogen receptor binding.		# Calculated probabilities of strong (LogRBA>0) and overall (LogRBA>-3) estrogen receptor binding.
	# Up to 5 records of similar compounds from the training set, including name, CAS number, LogRBA values, species and references.		# Up to 5 records of similar compounds from the training set, including name, CAS number, LogRBA values, species and references.

Kirilas: /* Features */

2012-05-24T14:53:30Z

Features

← Older revision		Revision as of 14:53, 24 May 2012
Line 13:		Line 13:
	* Predictions are supported by RI values that represent a quantitative evaluation of prediction confidence. High RI shows that the calculated value is likely to be accurate, while low RI indicates that no similar compounds with consistent data are present in the training set.		* Predictions are supported by RI values that represent a quantitative evaluation of prediction confidence. High RI shows that the calculated value is likely to be accurate, while low RI indicates that no similar compounds with consistent data are present in the training set.
	* The predictive models for both LogRBA cut-offs are based on a data set of more than 1500 compounds		* The predictive models for both LogRBA cut-offs are based on a data set of more than 1500 compounds
	* Provides a list of up to five most similar structures from the training set with ~~the~~ experimental values and references.		* Provides a list of up to five most similar structures from the training set with experimental LogRBA values and references.
	<br/>		<br/>

Kirilas: /* Features */

2012-05-24T14:52:39Z

Features

← Older revision		Revision as of 14:52, 24 May 2012
Line 11:		Line 11:
	===Features===		===Features===
	* Predicts probabilities of the test compound exhibiting LogRBA > 0 and LogRBA > 3, and classifies the analyzed chemicals according to their estrogen receptor binding affinity (strong binding, weak binding, no binding).		* Predicts probabilities of the test compound exhibiting LogRBA > 0 and LogRBA > 3, and classifies the analyzed chemicals according to their estrogen receptor binding affinity (strong binding, weak binding, no binding).
	* ~~Predictoins~~ are supported by RI values that represent a quantitative evaluation of prediction confidence. High RI shows that the calculated value is likely to be accurate, while low RI indicates that no similar compounds with consistent data are present in the training set.		* Predictions are supported by RI values that represent a quantitative evaluation of prediction confidence. High RI shows that the calculated value is likely to be accurate, while low RI indicates that no similar compounds with consistent data are present in the training set.
	* The predictive models for both LogRBA cut-offs are based on a data set of more than 1500 compounds		* The predictive models for both LogRBA cut-offs are based on a data set of more than 1500 compounds
	* Provides a list of up to five most similar structures from the training set with the experimental values and references.		* Provides a list of up to five most similar structures from the training set with the experimental values and references.
			<br/>

	== Interface ==		== Interface ==

Kirilas: /* Features */

2012-05-24T14:51:42Z

Features

← Older revision		Revision as of 14:51, 24 May 2012
Line 11:		Line 11:
	===Features===		===Features===
	* Predicts probabilities of the test compound exhibiting LogRBA > 0 and LogRBA > 3, and classifies the analyzed chemicals according to their estrogen receptor binding affinity (strong binding, weak binding, no binding).		* Predicts probabilities of the test compound exhibiting LogRBA > 0 and LogRBA > 3, and classifies the analyzed chemicals according to their estrogen receptor binding affinity (strong binding, weak binding, no binding).
			* Predictoins are supported by RI values that represent a quantitative evaluation of prediction confidence. High RI shows that the calculated value is likely to be accurate, while low RI indicates that no similar compounds with consistent data are present in the training set.
	* The predictive models for both LogRBA cut-offs are based on a data set of more than 1500 compounds		* The predictive models for both LogRBA cut-offs are based on a data set of more than 1500 compounds
	* Provides a list of up to five most similar structures from the training set with the experimental values and references.		* Provides a list of up to five most similar structures from the training set with the experimental values and references.
	~~<br />~~

	== Interface ==		== Interface ==