Kirilas at 10:03, 15 June 2017

2017-06-15T10:03:55Z

← Older revision		Revision as of 10:03, 15 June 2017
Line 22:		Line 22:


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

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

Kirilas at 09:36, 9 July 2013

2013-07-09T09:36:23Z

← Older revision		Revision as of 09:36, 9 July 2013
Line 6:		Line 6:
	===Features===		===Features===
	* PepT1 (oligopeptide transporter) and ASBT (bile acid transporter) substrate prediction		* PepT1 (oligopeptide transporter) and ASBT (bile acid transporter) substrate prediction
	* Similarity approach used for prediction of other possible active transport systems (monocarboxylic acid transporter		* Similarity approach used for prediction of other possible active transport systems (monocarboxylic acid transporter MCT1, amino acid carriers, etc.)
	* MCT1, amino acid carriers, etc.)
	* Provides reference data for similar structures		* Provides reference data for similar structures
	<br />		<br />

Kristina at 10:17, 8 July 2013

2013-07-08T10:17:40Z

← Older revision		Revision as of 10:17, 8 July 2013
Line 14:		Line 14:
	<br />		<br />

	[[Image:~~active_transport~~.png\|center]]		[[Image:Active_transport.png\|center]]
	<br />		<br />

Kristina: /* Interface */

2012-05-21T10:59:02Z

Interface

← Older revision		Revision as of 10:59, 21 May 2012
Line 14:		Line 14:
	<br />		<br />

	[[Image:~~bbb_logbb~~.png\|center]]		[[Image:active_transport.png\|center]]
	<br />		<br />

	~~[[Image:OralBio_AcTr_Screenshot.png\|center]]~~

	# Prediction of PepT1 and ASBT transport		# Prediction of PepT1 and ASBT transport

Kristina: Created page with "==Overview==
Active transport module offers classification methods for the prediction of the compound transport across intestinal membrane by oligopeptide transporter ..."

2012-05-21T10:58:22Z

Created page with "==Overview== Active transport module offers classification methods for the prediction of the compound transport across intestinal membrane by oligopeptide transporter ..."

New page

==Overview==
 

Active transport module offers classification methods for the prediction of the compound transport across intestinal membrane by oligopeptide transporter (PepT1) or bile acid transporter (ASBT) as well as the similarity based assessment of the likelihood of other most important active transport systems (monocarboxylic acid transporter (MCT1), amino acid carriers) involvement in compound's ability to penetrate intestinal barrier. 

===Features===
* PepT1 (oligopeptide transporter) and ASBT (bile acid transporter) substrate prediction
* Similarity approach used for prediction of other possible active transport systems (monocarboxylic acid transporter
* MCT1, amino acid carriers, etc.)
* Provides reference data for similar structures
 

== Interface ==
 

[[Image:bbb_logbb.png|center]]
 

[[Image:OralBio_AcTr_Screenshot.png|center]]

# Prediction of PepT1 and ASBT transport
# Prediction for other transport systems (MCT1, amino acid carriers, etc.)
# Up to 5 most similar structures in the training set with experimental values and references
 

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

==Technical information==
 

<div class="mw-collapsible-content">
'''Training set size:'''

{| cellpadding="0" cellspacing="0" align="left"
|-
| width="320" | Model || width="150" | Number of compounds
|-
| PepT1 || N/A*
|-
| ASBT || N/A*
|-
| Other transporters || N/A*
|}

 
 
 
 


<nowiki>*</nowiki> - All ACD/Active Transport models are knowledge based "expert-like" systems, therefore the concept of training set does not apply to the process of their development.


'''Validation set size:'''

{| cellpadding="0" cellspacing="0" align="left"
|-
| width="320" | Model || width="150" | Number of compounds
|-
| PepT1 || 330
|-
| ASBT || 173
|-
| Other transporters || N/A*
|}

 
 
 
 


<nowiki>*</nowiki> - The substrate specificity of the remaining transporters is very narrow. The compounds that can be transported by these enzymes are considered to be well known and documented. As a result any actual experimental measurements for new compounds are very rare and no adequate validation sets could be compiled to test the accuracy of the classification models in question.


'''Main sources of experimental data:'''
* Various articles from peer-reviewed scientific journals*

<nowiki>*</nowiki> - Both articles reporting corresponding Active Transport models by other authors (i.e. with larger collections of experimental data per article) and dealing with detailed experimental pharmacokinetic characterization (i.e. usually only several compounds per article) were available for the validation set construction.


 
====Internal Validation====
 

{| cellpadding="2" cellspacing="0" style="border-top:2px solid black; border-bottom:2px solid black"
|+ Table 1. Classification accuracy of the knowledge based ACD/Active transport (PepT1) model.
|-
! style="border-bottom:1px solid black; background:#EAEAEA" width="250" rowspan="2" | Subset
! style="border-bottom:1px solid black; background:#EAEAEA" width="200" rowspan="2" | Coverage of the entire internal validation set (N=330)
! style="border-bottom:1px solid black; background:#EAEAEA" width="100" rowspan="2" | Observed
! style="border-bottom:1px solid black; background:#EAEAEA" width="300" colspan="2" | Assigned class
|-
! style="border-bottom:1px solid black; background:#EAEAEA" width="150" | Transported
! style="border-bottom:1px solid black; background:#EAEAEA" width="150" | Not-transported
|-
| style="border-bottom:1px solid black" align="center" rowspan="2" | Compounds receiving definite model predictions N = 311*

| rowspan="2" align="center" style="border-bottom:1px solid black" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:40px"
| style="color:white; background:#B9CDE5" align="right" width="94.2%" | 94.2%  || style="background:#EDF2F9" width="5.8%" |  
|}

| style="border-bottom:1px solid black" | True || align="center" style="border-bottom:1px solid black; background:#E1FFE1" | 121 (38.9%) || align="center" style="border-bottom:1px solid black; background:#FFE1E1" | 10 (3.2%)
|-
| style="border-bottom:1px solid black" | False || align="center" style="border-bottom:1px solid black; background:#FFE1E1" | 13 (4.2%) || align="center" style="border-bottom:1px solid black; background:#E1FFE1" | 167 (53.7%)
|-
| style="height:30px" colspan="2" |   || Accuracy
| colspan="2" align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:20px"
| style="color:white; background:#B9CDE5" align="right" width="92.6%" | 92.6%  || style="background:#EDF2F9" width="7.4%" |  
|}

|-
| style="height:30px" colspan="2" |   || Sensitivity
| colspan="2" align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:20px"
| style="color:white; background:#B9CDE5" align="right" width="92.4%" | 92.4%  || style="background:#EDF2F9" width="7.6%" |  
|}

|-
| style="height:30px" colspan="2" |   || Specificity
| colspan="2" align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:20px"
| style="color:white; background:#B9CDE5" align="right" width="92.8%" | 92.8%  || style="background:#EDF2F9" width="7.2%" |  
|}

|}
* - 'No predcition' is one of the possible outputs of the classification model, meaning that it cannot make an unambiguous judgment based on available rules. Obviously such compounds cannot be included in the accuracy assessment. As a result not all compounds fall into the applicability domain of the model even with no additional parameters (i.e., RI) available to filter out unreliable predictions as in GALAS models. Analysis of experimental data for similar compounds can still be used as a source of information regarding active influx via PepT1 transporter for the compounds which cannot be classified by the model.


{| cellpadding="2" cellspacing="0" style="border-top:2px solid black; border-bottom:2px solid black"
|+ Table 2. Classification accuracy of the knowledge based ACD/Active transport (ASBT) model.
|-
! style="border-bottom:1px solid black; background:#EAEAEA" width="250" rowspan="2" | Subset
! style="border-bottom:1px solid black; background:#EAEAEA" width="100" rowspan="2" | Observed
! style="border-bottom:1px solid black; background:#EAEAEA" width="300" colspan="2" | Assigned class
|-
! style="border-bottom:1px solid black; background:#EAEAEA" width="150" | Transported
! style="border-bottom:1px solid black; background:#EAEAEA" width="150" | Not-transported
|-
| style="border-bottom:1px solid black" align="center" rowspan="2" | Entire internal validation set N = 173*
| style="border-bottom:1px solid black" | True || align="center" style="border-bottom:1px solid black; background:#E1FFE1" | 22 (12.7%) || align="center" style="border-bottom:1px solid black; background:#FFE1E1" | 8 (4.6%)
|-
| style="border-bottom:1px solid black" | False || align="center" style="border-bottom:1px solid black; background:#FFE1E1" | 7 (4.0%) || align="center" style="border-bottom:1px solid black; background:#E1FFE1" | 136 (78.6%)
|-
| style="height:30px" |   || Accuracy
| colspan="2" align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:20px"
| style="color:white; background:#B9CDE5" align="right" width="91.3%" | 91.3%  || style="background:#EDF2F9" width="8.7%" |  
|}

|-
| style="height:30px" |   || Sensitivity
| colspan="2" align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:20px"
| style="color:white; background:#B9CDE5" align="right" width="73.3%" | 73.3%  || style="background:#EDF2F9" width="26.7%" |  
|}

|-
| style="height:30px" |   || Specificity
| colspan="2" align="center" |
{| cellpadding="0" cellspacing="0" style="width:80%; height:20px"
| style="color:white; background:#B9CDE5" align="right" width="95.1%" | 95.1%  || style="background:#EDF2F9" width="4.9%" |  
|}

|}
* - There are no inconclusive predictions produced by the model. Moreover, since ACD/Active Transport models do not utilize GALAS modeling methodology, no additional parameters (i.e., RI) are available to enable additional filtering of more reliable predictions.

</div>
</div>

Active Transport - Revision history

Kirilas at 10:03, 15 June 2017

Kirilas at 09:36, 9 July 2013

Kristina at 10:17, 8 July 2013

Kristina: /* Interface */

Kristina: Created page with "==Overview== Active transport module offers classification methods for the prediction of the compound transport across intestinal membrane by oligopeptide transporter ..."

Kristina: Created page with "==Overview==
Active transport module offers classification methods for the prediction of the compound transport across intestinal membrane by oligopeptide transporter ..."