P-gp Substrates - Revision history

Kirilas at 10:06, 15 June 2017

2017-06-15T10:06:48Z

← Older revision		Revision as of 10:06, 15 June 2017
Line 48:		Line 48:


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

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

Kirilas: /* Reference database */

2013-02-15T09:37:34Z

Reference database

← Older revision		Revision as of 09:37, 15 February 2013
Line 66:		Line 66:

	===Reference database===		===Reference database===
	~~P-gp Specificity\~~P-gp DB ~~module contains a browsable database~~ of 2,290 compounds with experimental data related to their interactions with P-gp. Each compound in the DB is classified as a P-gp substrate or non-substrate (inconclusive or contradictive data are marked as Yes/No or No/Yes in the ''''Substrate''' field) and efficiency of P-gp mediated transport is provided for substrates. '''High efficiency''' describes compounds that are transported with the rate similar to the best substrates (vinblastine, daunorubicin, paclitaxel). Similarly, drugs comprising the database are classified according to their '''Inhibitor''' liability. '''Potency''' field denotes effectivity of P-gp inhibition, '''High potency''' representing compounds that inhibit P-gp as good as standard inhibitor verapamil or even better.		ACD/Percepta includes a browsable P-gp DB comprised of 2,290 compounds with experimental data related to their interactions with P-gp. Each compound in the DB is classified as a P-gp substrate or non-substrate (inconclusive or contradictive data are marked as Yes/No or No/Yes in the ''''Substrate''' field) and efficiency of P-gp mediated transport is provided for substrates. '''High efficiency''' describes compounds that are transported with the rate similar to the best substrates (vinblastine, daunorubicin, paclitaxel). Similarly, drugs comprising the database are classified according to their '''Inhibitor''' liability. '''Potency''' field denotes effectivity of P-gp inhibition, '''High potency''' representing compounds that inhibit P-gp as good as standard inhibitor verapamil or even better.

	In the '''Assays''' section, the methods that were used in the analysis of P-gp substrate/inhibitor specificity are listed:		In the '''Assays''' section, the methods that were used in the analysis of P-gp substrate/inhibitor specificity are listed:
Line 75:		Line 75:
	* '''MDR reversion''' – sensitization of P-gp expressing cells to “MDR profile” drugs (taxanes, anthracyclines, vinca alkaloids)		* '''MDR reversion''' – sensitization of P-gp expressing cells to “MDR profile” drugs (taxanes, anthracyclines, vinca alkaloids)
	* '''P-gp ATPase modulation''' – activation or inhibition of P-gp ATPase. This assay does not differentiate P-gp substrates and inhibitors.		* '''P-gp ATPase modulation''' – activation or inhibition of P-gp ATPase. This assay does not differentiate P-gp substrates and inhibitors.


	===Model features & prediction accuracy===		===Model features & prediction accuracy===

Kirilas: /* Model features & prediction accuracy */

2013-02-15T09:36:54Z

Model features & prediction accuracy

← Older revision		Revision as of 09:36, 15 February 2013
Line 78:		Line 78:

	===Model features & prediction accuracy===		===Model features & prediction accuracy===
	The ~~model was developed with Algorithm Builder~~ using ~~a novel~~ methodology ~~consisting~~ of two parts:		The predictive models of P-gp substrate specificity 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).
	* Global baseline statistical model employing binomial PLS with multiple bootstrapping using a predefined set of fragmental descriptors.
	* ~~Local~~ correction to baseline ~~prediction based on analysis of~~ experimental ~~data~~ for similar compounds.		Each GALAS model consists of two parts:
	~~The underlying~~ methodology ~~enables obtaining an intrinsic evaluation~~ of ~~prediction confidence~~ by the means of Reliability Index (RI) values calculated for each prediction. RI ranging from 0 to 1 serves as an indication whether a submitted compound falls within the Model Applicability Domain. Two criteria influence the calculation of Reliability Index of a prediction:		* Global baseline statistical model employing binomial PLS with multiple bootstrapping using a predefined set of fragmental descriptors, that reflects general trends in P-gp substrate specificity.
	* Similarity of ~~the analyzed molecule~~ to ~~compounds in~~ the ~~Self-~~training ~~Library~~ (prediction is unreliable if no similar compounds have been found ~~in the Library~~).		* 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.
	* ~~Consistency~~ of experimental ~~data~~ for similar compounds (discrepant data for similar molecules lead to lower RI values).		<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 (prediction is unreliable if no similar compounds have been found).
			* Consistence of experimental values and baseline model prediction for the most similar similar compounds from the training set (discrepant data for similar molecules, i.e. alternating P-gp substrates and non-substrates lead to lower ''RI'' values).

			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.
			<br><br>

	The presented method also forms the basis of model Trainability. 'Trainable model' methodology addresses the issue of the chemical space of ‘in-house’ libraries being considerably wider than that of publicly available data which results in limited applicability of most third-party QSARs for analysis of ‘in-house’ data. The ‘Training engine‘ makes appropriate corrections for systematic deviations produced by the baseline QSAR model based on analysis of similar compounds from the experimental data library. Expansion of this Self-training Library with user-defined experimental data for new compounds leads to instant improvement of prediction accuracy for the respective compound classes. Moreover, addition of 'in-house' data allows adapting the existing model to the particular experimental protocol used in your company and avoiding potential issues related to discrepancies between different experimental methods used for determination of drug interactions with P-gp.		The presented method also forms the basis of model Trainability. 'Trainable model' methodology addresses the issue of the chemical space of ‘in-house’ libraries being considerably wider than that of publicly available data which results in limited applicability of most third-party QSARs for analysis of ‘in-house’ data. The ‘Training engine‘ makes appropriate corrections for systematic deviations produced by the baseline QSAR model based on analysis of similar compounds from the experimental data library. Expansion of this Self-training Library with user-defined experimental data for new compounds leads to instant improvement of prediction accuracy for the respective compound classes. Moreover, addition of 'in-house' data allows adapting the existing model to the particular experimental protocol used in your company and avoiding potential issues related to discrepancies between different experimental methods used for determination of drug interactions with P-gp.

Kristina: /* Features */

2012-05-25T10:21:20Z

Features

← Older revision		Revision as of 10:21, 25 May 2012
Line 11:		Line 11:
	* The P-gp Substrates prediction module uses two models to estimate the probability a compound is a P-gp substrate and if so, is it a high-affinity substrate?		* The P-gp Substrates prediction module uses two models to estimate the probability a compound is a P-gp substrate and if so, is it a high-affinity substrate?
	* Additional knowledge-based model classifies compounds as P-gp substrates/non-substrates using rules based on ionization, molecular size and biological class of compounds (analogs of peptides, alkaloids, anthracyclines, etc.)		* Additional knowledge-based model classifies compounds as P-gp substrates/non-substrates using rules based on ionization, molecular size and biological class of compounds (analogs of peptides, alkaloids, anthracyclines, etc.)
	* Statistical algorithms calculate estimate the reliability of every prediction by means of Reliability Index calculation ~~(see more information about [[Trainable_Models#Overview\|Trainable Models]])~~		* Statistical algorithms calculate estimate the reliability of every prediction by means of Reliability Index calculation
	* Displays experimental data for the 5 most similar compounds from '''P-gp DB'''		* Displays experimental data for the 5 most similar compounds from '''P-gp DB'''
	* Training set consisted of >1,000 compounds. Reference data were compiled from more than 800 original publications.		* Training set consisted of >1,000 compounds. Reference data were compiled from more than 800 original publications.

Kirilas: /* Interface */

2012-05-25T09:05:00Z

Interface

← Older revision		Revision as of 09:05, 25 May 2012
Line 23:		Line 23:

	# Classification of compounds as P-gp substrates or non-substrates		# Classification of compounds as P-gp substrates or non-substrates
	# ~~Description~~ of ~~P-gp substrate group~~		# Physicochemical reasoning of prediction
	# Reliability of calculation (low, medium, high)		# Reliability of calculation (low, medium, high)
	# Switch to the probabilistic model		# Switch to the probabilistic model
	# ~~Up to~~ 5 most similar structures with experimental values and references		# View 5 most similar structures from '''P-gp DB''' with experimental values and references
	<br />		<br />

Line 32:		Line 32:
	<br />		<br />

	# Probability~~, ranging from 0 (definite non~~-substrate~~) to 1 (definite substrate)~~		# Probability of the compound being a P-gp substrate
	# Indication of the ~~probability~~ prediction reliability ~~along with the~~ Reliability Index value		# Indication of the prediction reliability (Reliability Index value)
	# Probability ~~between 0 (definitely not~~ a high-~~affinity~~ substrate) and ~~1 (definitely a high-affinity substrate)~~		# "Configure" and "Train" buttons provide the means to select the training library for use in calculations and to add new data to that library. The name of the currently selected library is indicated with italic font.
	# Switch to the knowledge based ~~C-SAR~~ model		# Probability that the compound is a high P-gp substrate and exhibits significant efflux ''in vivo''
	# ~~Up to~~ 5 most similar structures with experimental values and references		# Switch to the knowledge based classification model
			# View 5 most similar structures from '''P-gp DB''' with experimental values and references
	<br />		<br />

Kirilas: /* Features */

2012-05-25T09:01:52Z

Features

← Older revision		Revision as of 09:01, 25 May 2012
Line 9:		Line 9:

	===Features===		===Features===
	* ~~Calculates probabilities of the analyzed compound being a~~ P-gp ~~substrate or inhibitor.~~		* The P-gp Substrates prediction module uses two models to estimate the probability a compound is a P-gp substrate and if so, is it a high-affinity substrate?
	* Calculates Reliability Index (RI values) of predictions that show whether tested compounds belong to ~~Applicability Domain of predictive model?~~		* Additional knowledge-based model classifies compounds as P-gp substrates/non-substrates using rules based on ionization, molecular size and biological class of compounds (analogs of peptides, alkaloids, anthracyclines, etc.)
	* In some cases the ~~explanation why tested~~ compound ~~can be~~ P-gp substrate ~~or inhibitor~~ is ~~added (supplementary classification P~~-~~gp specificity models).~~		* Statistical algorithms calculate estimate the reliability of every prediction by means of Reliability Index calculation (see more information about [[Trainable_Models#Overview\|Trainable Models]])
	* ~~Training set of >1,000 compounds for P~~-~~gp substrate algorithm, and of >1,500~~ compounds ~~for P-gp inhibitor algorithm was used~~		* Displays experimental data for the 5 most similar compounds from '''P-gp DB'''
	* Two models of P-gp ~~substrate and inhibitor specificity were build~~ - ~~classification and probabilistic~~		* Training set consisted of >1,000 compounds. Reference data were compiled from more than 800 original publications.
	* The classification models, used P-gp substrate and inhibitor specificity rules, based on ionization, molecular size and biological class of compounds (analogs of peptides, alkaloids, anthracyclines, etc.)
	* Statistical algorithms calculate ~~the probabilities of compound being P-gp substrate or inhibitor and~~ estimate the reliability of every prediction by means of Reliability Index calculation (see more information about [[Trainable_Models#Overview\|Trainable Models]])
	* ~~Classification based on the~~ experimental data ~~is presented~~ for similar ~~structures~~
	* Reference data were compiled from more than 800 original publications
	<br />		<br />


	== Interface ==		== Interface ==

Kristina: /* Interface */

2012-05-22T08:36:46Z

Interface

← Older revision		Revision as of 08:36, 22 May 2012
Line 27:		Line 27:
	<br />		<br />

	# Classification of compounds as ~~inhibitors~~ or non-~~inhibitors~~		# Classification of compounds as P-gp substrates or non-substrates
	# Description of ~~prediction~~		# Description of P-gp substrate group
	# Reliability of ~~prediction~~ (low, medium, high)		# Reliability of calculation (low, medium, high)
	# Switch to the probabilistic model		# Switch to the probabilistic model
	# Up to 5 most similar structures ~~in the P-gp DB~~ and references		# Up to 5 most similar structures with experimental values and references
	<br />		<br />

Line 37:		Line 37:
	<br />		<br />

	# Probability, ranging from 0 (definite non-~~inhibitor~~) to 1 (definite ~~inhibitor~~)		# Probability, ranging from 0 (definite non-substrate) to 1 (definite substrate)
	# Indication of the ~~P-gp Inhibitor~~ probability prediction reliability along with the Reliability Index value		# Indication of the probability prediction reliability along with the Reliability Index value
	# Probability between 0 (definitely not a high-affinity ~~inhibitor~~) and 1 (definitely a high-affinity ~~inhibitor~~)		# Probability between 0 (definitely not a high-affinity substrate) and 1 (definitely a high-affinity substrate)
	~~# Indication of the potent P-gp inhibition probability prediction reliability along with the Reliability Index value~~
	# Switch to the knowledge based C-SAR model		# Switch to the knowledge based C-SAR model
	# Up to 5 most similar structures ~~in the P-gp DB~~ and references		# Up to 5 most similar structures with experimental values and references
	<br />		<br />

Kristina: Created page with "==Overview==
P-glycoprotein (P-gp) is a clinically relevant efflux transporter that extrudes compounds from a large variety of cells. Its function has been associated ..."

2012-05-22T08:31:46Z

Created page with "==Overview== <br /> P-glycoprotein (P-gp) is a clinically relevant efflux transporter that extrudes compounds from a large variety of cells. Its function has been associated ..."

New page

==Overview==
<br />

P-glycoprotein (P-gp) is a clinically relevant efflux transporter that extrudes compounds from a large variety of cells. Its function has been associated with the drugs’ absorption, distribution, excretion, CNS effects, multidrug resistance (MDR). P-gp transports a variety of natural compounds and drugs of different therapeutic areas.

Rapid identification of drug candidates that are P-gp substrates and/or inhibitors is possible using P-gp specificity module. Filtering and exclusion of P-gp substrates/inhibitors from huge ‘in-house’ libraries of synthesized compounds or virtual libraries is possible, followed by exclusion of such compounds from further development. P-gp specificity module may serve as an initial screen that could replace screening test based on P-gp ATPase activity measurements and partially replace expensive experiments with P-gp expressing cell monolayers and P-gp knock-out animals.

Training of P-gp specificity models with ‘in-house’ data allows producing reliable predictions of P-gp interaction with compounds synthesized in your company.<br />

===Features===
* Calculates probabilities of the analyzed compound being a P-gp substrate or inhibitor.
* Calculates Reliability Index (RI values) of predictions that show whether tested compounds belong to Applicability Domain of predictive model?
* In some cases the explanation why tested compound can be P-gp substrate or inhibitor is added (supplementary classification P-gp specificity models).
* Training set of >1,000 compounds for P-gp substrate algorithm, and of >1,500 compounds for P-gp inhibitor algorithm was used
* Two models of P-gp substrate and inhibitor specificity were build - classification and probabilistic
* The classification models, used P-gp substrate and inhibitor specificity rules, based on ionization, molecular size and biological class of compounds (analogs of peptides, alkaloids, anthracyclines, etc.)
* Statistical algorithms calculate the probabilities of compound being P-gp substrate or inhibitor and estimate the reliability of every prediction by means of Reliability Index calculation (see more information about [[Trainable_Models#Overview|Trainable Models]])
* Classification based on the experimental data is presented for similar structures
* Reference data were compiled from more than 800 original publications
<br />

== Interface ==
<br />

[[Image:Pgp_Substrate_Classification.png|center]]
<br />

# Classification of compounds as inhibitors or non-inhibitors
# Description of prediction
# Reliability of prediction (low, medium, high)
# Switch to the probabilistic model
# Up to 5 most similar structures in the P-gp DB and references
<br />

[[Image:Pgp_Substrate_Probability.png|center]]
<br />

# Probability, ranging from 0 (definite non-inhibitor) to 1 (definite inhibitor)
# Indication of the P-gp Inhibitor probability prediction reliability along with the Reliability Index value
# Probability between 0 (definitely not a high-affinity inhibitor) and 1 (definitely a high-affinity inhibitor)
# Indication of the potent P-gp inhibition probability prediction reliability along with the Reliability Index value
# Switch to the knowledge based C-SAR model
# Up to 5 most similar structures in the P-gp DB and references
<br />

'''Note''': Prediction reliability classification according to Reliability Index (RI) values:
* RI < 0.3 – Not Reliable,
* RI in range 0.3-0.5 – Borderline Reliability,
* RI in range 0.5-0.75 – Moderate Reliability,
* RI >= 0.75 – High Reliability
<br />

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

==Technical information==
<br />

<div class="mw-collapsible-content">
===Experimental data===
There are many ''in vitro'' and ''in vivo'' tests used in P-gp specificity studies that often produce contradictive results. P-gp specificity model is based on the data collected from scientific literature. The following assays for substrates were considered:
* ''In vitro'' polarized transport across P-gp expressing cell monolayers
* ''In vivo'' BBB models with P-gp knock-out animals, P-gp mediated drug resistance.

The respective assays for inhibitors were as follows:
* Drug efflux inhibition across/out of P-gp expressing cells
* MDR reversion.

Overall data set for P-gp substrates contains >1000 compounds, for inhibitors >1500 compounds.

===Reference database===
P-gp Specificity\P-gp DB module contains a browsable database of 2,290 compounds with experimental data related to their interactions with P-gp. Each compound in the DB is classified as a P-gp substrate or non-substrate (inconclusive or contradictive data are marked as Yes/No or No/Yes in the ''''Substrate''' field) and efficiency of P-gp mediated transport is provided for substrates. '''High efficiency''' describes compounds that are transported with the rate similar to the best substrates (vinblastine, daunorubicin, paclitaxel). Similarly, drugs comprising the database are classified according to their '''Inhibitor''' liability. '''Potency''' field denotes effectivity of P-gp inhibition, '''High potency''' representing compounds that inhibit P-gp as good as standard inhibitor verapamil or even better.

In the '''Assays''' section, the methods that were used in the analysis of P-gp substrate/inhibitor specificity are listed:
* '''Substrate (''in vitro'' transport assay)''' – polarized transport of drugs across P-gp expressing cell monolayers or decreased drug accumulation in MDR cells
* '''Substrate (''in vivo'' BBB models)''' – increased distribution of drugs to the brain in P-gp deficient (mdr1a/b(-/-)) mice
* '''P-gp mediated resistance''' – P-gp overexpressing (MDR) cells demonstrate resistance to the drug
* '''Drug efflux inhibition''' – inhibition of drug efflux in P-gp expressing cells.
* '''MDR reversion''' – sensitization of P-gp expressing cells to “MDR profile” drugs (taxanes, anthracyclines, vinca alkaloids)
* '''P-gp ATPase modulation''' – activation or inhibition of P-gp ATPase. This assay does not differentiate P-gp substrates and inhibitors.

===Model features & prediction accuracy===
The model was developed with Algorithm Builder using a novel methodology consisting of two parts:
* Global baseline statistical model employing binomial PLS with multiple bootstrapping using a predefined set of fragmental descriptors.
* Local correction to baseline prediction based on analysis of experimental data for similar compounds.
The underlying methodology enables obtaining an intrinsic evaluation of prediction confidence by the means of Reliability Index (RI) values calculated for each prediction. RI ranging from 0 to 1 serves as an indication whether a submitted compound falls within the Model Applicability Domain. Two criteria influence the calculation of Reliability Index of a prediction:
* Similarity of the analyzed molecule to compounds in the Self-training Library (prediction is unreliable if no similar compounds have been found in the Library).
* Consistency of experimental data for similar compounds (discrepant data for similar molecules lead to lower RI values).

The presented method also forms the basis of model Trainability. 'Trainable model' methodology addresses the issue of the chemical space of ‘in-house’ libraries being considerably wider than that of publicly available data which results in limited applicability of most third-party QSARs for analysis of ‘in-house’ data. The ‘Training engine‘ makes appropriate corrections for systematic deviations produced by the baseline QSAR model based on analysis of similar compounds from the experimental data library. Expansion of this Self-training Library with user-defined experimental data for new compounds leads to instant improvement of prediction accuracy for the respective compound classes. Moreover, addition of 'in-house' data allows adapting the existing model to the particular experimental protocol used in your company and avoiding potential issues related to discrepancies between different experimental methods used for determination of drug interactions with P-gp.

If the compound is within model Applicability Domain (acceptable Reliability Index) accuracy and sensitivity of classification is close to 90% for both models.
</div>
</div>