LogP - Revision history

Kirilas: Added new statistics

2024-09-23T13:35:39Z

Added new statistics

← Older revision		Revision as of 13:35, 23 September 2024
Line 156:		Line 156:

	* "LogP v. 1.4" library introduced in 2024 has been further expanded by ~4750 new compounds, resulting in a >25% increase over the previous version, and improving the prediction error for newly acquired compounds from ~1 to ~0.4 log units.		* "LogP v. 1.4" library introduced in 2024 has been further expanded by ~4750 new compounds, resulting in a >25% increase over the previous version, and improving the prediction error for newly acquired compounds from ~1 to ~0.4 log units.

			[[File:LogP_GALAS_v2023_vs_v2024.png\|frame\|none\|Improvement in accuracy of logP prediction for the new set of 4750 compounds with the logP GALAS prediction model]]

	===Description of ACD/LogP Classic Algorithm===		===Description of ACD/LogP Classic Algorithm===

Kirilas: Library upgrade warning

2024-09-23T13:04:21Z

Library upgrade warning

← Older revision		Revision as of 13:04, 23 September 2024
Line 10:		Line 10:
	* Train the model with experimental values to improve predictions for proprietary chemical space		* Train the model with experimental values to improve predictions for proprietary chemical space

	~~<!--~~<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>		<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>

	If you installed ~~ACD/~~Percepta as an upgrade over a previous version, the program will attempt to preserve any custom configuration of Self-training libraries used in ACD/LogP GALAS module. ~~If you are upgrading from a version earlier than v. 2018, this~~ configuration will not include the new, significantly extended built-in library that was introduced in ~~2018~~ release. In this case, to take advantage of the new library, you may need to click "Configure" and manually select the following entry: ''LogP v. 1.3 (read-only)''.		If you installed Percepta as an upgrade over a previous version, the program will attempt to preserve any custom configuration of Self-training libraries used in ACD/LogP GALAS module. This configuration will not include the new, significantly extended built-in library that was introduced in 2024 release. In this case, to take advantage of the new library, you may need to click "Configure" and manually select the following entry: ''LogP v. 1.4 (read-only)''.

	In case of a new installation~~, or an upgrade over ACD/Percepta v. 2018~~, the new library should be selected automatically with no further action required.~~-->~~		In case of a new installation, the new library should be selected automatically with no further action required.

	== Interface ==		== Interface ==
Line 148:		Line 148:
	\|}		\|}

	The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. ~~The current version uses an updated~~ "LogP v. 1.3" library ~~that~~ has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP ~~is now~~ predicted within 0.5 log units for 85 % of ~~those~~ compounds as demonstrated in the figures below:		The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. Since then the library has undergone several updates.
			* "LogP v. 1.3" library introduced in 2018 has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP was predicted within 0.5 log units for 85% of the novel compounds as demonstrated in the figures below:

	[[File:LogP_GALAS_v2017_vs_v2018.png\|frame\|none\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]		[[File:LogP_GALAS_v2017_vs_v2018.png\|frame\|none\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]

	[[File:LogP_GALAS_v2017_to_v2018.png\|frame\|none\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]		[[File:LogP_GALAS_v2017_to_v2018.png\|frame\|none\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]

			* "LogP v. 1.4" library introduced in 2024 has been further expanded by ~4750 new compounds, resulting in a >25% increase over the previous version, and improving the prediction error for newly acquired compounds from ~1 to ~0.4 log units.

	===Description of ACD/LogP Classic Algorithm===		===Description of ACD/LogP Classic Algorithm===

Kirilas: Removed the library upgrade note

2020-08-18T08:49:59Z

Removed the library upgrade note

← Older revision		Revision as of 08:49, 18 August 2020
Line 10:		Line 10:
	* Train the model with experimental values to improve predictions for proprietary chemical space		* Train the model with experimental values to improve predictions for proprietary chemical space

	<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>		<!--<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>

	If you installed ACD/Percepta as an upgrade over a previous version, the program will attempt to preserve any custom configuration of Self-training libraries used in ACD/LogP GALAS module. If you are upgrading from a version earlier than v. 2018, this configuration will not include the new, significantly extended built-in library that was introduced in 2018 release. In this case, to take advantage of the new library, you may need to click "Configure" and manually select the following entry: ''LogP v. 1.3 (read-only)''.		If you installed ACD/Percepta as an upgrade over a previous version, the program will attempt to preserve any custom configuration of Self-training libraries used in ACD/LogP GALAS module. If you are upgrading from a version earlier than v. 2018, this configuration will not include the new, significantly extended built-in library that was introduced in 2018 release. In this case, to take advantage of the new library, you may need to click "Configure" and manually select the following entry: ''LogP v. 1.3 (read-only)''.

	In case of a new installation, or an upgrade over ACD/Percepta v. 2018, the new library should be selected automatically with no further action required.		In case of a new installation, or an upgrade over ACD/Percepta v. 2018, the new library should be selected automatically with no further action required.-->

	== Interface ==		== Interface ==

Kirilas: Edited new library note

2019-09-24T12:18:30Z

Edited new library note

← Older revision		Revision as of 12:18, 24 September 2019
Line 12:		Line 12:
	<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>		<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>

	If you installed ACD/Percepta ~~v. 2018~~ as an ~~in-place~~ upgrade over ~~the~~ previous version, ~~ACD/LogP GALAS module~~ will ~~continue using the same set~~ of Self-training libraries ~~that was configured~~ in ~~your previous installation~~. ~~To take advantage of~~ the new, significantly extended built-in library that ~~comes with the current version~~ of the ~~software~~, you ~~will~~ need to click "Configure" and manually select the ~~folowing~~ entry: ''LogP v. 1.3 (read-only)''.		If you installed ACD/Percepta as an upgrade over a previous version, the program will attempt to preserve any custom configuration of Self-training libraries used in ACD/LogP GALAS module. If you are upgrading from a version earlier than v. 2018, this configuration will not include the new, significantly extended built-in library that was introduced in 2018 release. In this case, to take advantage of the new library, you may need to click "Configure" and manually select the following entry: ''LogP v. 1.3 (read-only)''.

	In case of a ~~clean~~ installation, ~~this~~ library is selected automatically~~, and~~ no further action is required.		In case of a new installation, or an upgrade over ACD/Percepta v. 2018, the new library should be selected automatically with no further action required.

	== Interface ==		== Interface ==

Kirilas at 10:56, 30 October 2018

2018-10-30T10:56:49Z

← Older revision		Revision as of 10:56, 30 October 2018
Line 9:		Line 9:
	* Offers color-coded representation of lipophilic and hydrophilic parts of the compound structure.		* Offers color-coded representation of lipophilic and hydrophilic parts of the compound structure.
	* Train the model with experimental values to improve predictions for proprietary chemical space		* Train the model with experimental values to improve predictions for proprietary chemical space
	<br />
			<span style="color:red; font-weight: bold;">IMPORTANT NOTE:</span>

			If you installed ACD/Percepta v. 2018 as an in-place upgrade over the previous version, ACD/LogP GALAS module will continue using the same set of Self-training libraries that was configured in your previous installation. To take advantage of the new, significantly extended built-in library that comes with the current version of the software, you will need to click "Configure" and manually select the folowing entry: ''LogP v. 1.3 (read-only)''.

			In case of a clean installation, this library is selected automatically, and no further action is required.

	== Interface ==		== Interface ==

Kirilas at 09:43, 8 August 2018

2018-08-08T09:43:00Z

← Older revision		Revision as of 09:43, 8 August 2018
Line 145:		Line 145:
	The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. The current version uses an updated "LogP v. 1.3" library that has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP is now predicted within 0.5 log units for 85 % of those compounds as demonstrated in the figures below:		The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. The current version uses an updated "LogP v. 1.3" library that has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP is now predicted within 0.5 log units for 85 % of those compounds as demonstrated in the figures below:

	[[File:LogP_GALAS_v2017_vs_v2018.png\|frame\|~~left~~\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]		[[File:LogP_GALAS_v2017_vs_v2018.png\|frame\|none\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]

	[[File:LogP_GALAS_v2017_to_v2018.png\|frame\|~~left~~\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]		[[File:LogP_GALAS_v2017_to_v2018.png\|frame\|none\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]

	===Description of ACD/LogP Classic Algorithm===		===Description of ACD/LogP Classic Algorithm===

Kirilas: /* Internal Validation */

2018-08-08T09:40:27Z

Internal Validation

← Older revision		Revision as of 09:40, 8 August 2018
Line 145:		Line 145:
	The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. The current version uses an updated "LogP v. 1.3" library that has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP is now predicted within 0.5 log units for 85 % of those compounds as demonstrated in the figures below:		The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. The current version uses an updated "LogP v. 1.3" library that has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP is now predicted within 0.5 log units for 85 % of those compounds as demonstrated in the figures below:

	[[File:LogP_GALAS_v2017_vs_v2018.png\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]		[[File:LogP_GALAS_v2017_vs_v2018.png\|frame\|left\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]

	[[File:LogP_GALAS_v2017_to_v2018.png\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]		[[File:LogP_GALAS_v2017_to_v2018.png\|frame\|left\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]

	===Description of ACD/LogP Classic Algorithm===		===Description of ACD/LogP Classic Algorithm===

Kirilas at 09:37, 8 August 2018

2018-08-08T09:37:11Z

← Older revision		Revision as of 09:37, 8 August 2018
Line 142:		Line 142:
	\| align="center" \| 0.96 \|\| align="center" \| 0.36		\| align="center" \| 0.96 \|\| align="center" \| 0.36
	\|}		\|}

			The statistics above apply to ACD/LogP GALAS algorithm with built-in "LogP v. 1.2" self-training library. The current version uses an updated "LogP v. 1.3" library that has been expanded by >1700 drug-like compounds from novel congeneric series (representing a 12% increase in size) resulting in improved accuracy and reliability of prediction for novel entities: LogP is now predicted within 0.5 log units for 85 % of those compounds as demonstrated in the figures below:

			[[File:LogP_GALAS_v2017_vs_v2018.png\|Improvement in accuracy of logP prediction for the new set of 1724 compounds with the logP GALAS prediction model]]

			[[File:LogP_GALAS_v2017_to_v2018.png\|Improvements in logP prediction accuracy for the new set of 1724 compound from v2017.1 to v2018.1—less than 2% compounds have a prediction error greater than 1 logP unit in v 2018.1 compared to 30% in v2017.1]]

	===Description of ACD/LogP Classic Algorithm===		===Description of ACD/LogP Classic Algorithm===

Kirilas at 09:19, 8 August 2018

2018-08-08T09:19:58Z

← Older revision		Revision as of 09:19, 8 August 2018
Line 155:		Line 155:

	The algorithm estimates the probability of tautomeric and ionic equilibria, the calculation error, and displays the results.		The algorithm estimates the probability of tautomeric and ionic equilibria, the calculation error, and displays the results.

			====Limitations====

			ACD/LogP Classic algorithm does not calculate the logP values for the following chemical structures:
			* Charged structures other than the zwitterionic alpha-amino acids and their peptide derivatives, and other than the non-ionic derivatives of IV-valent Nitrogen (+) bonded to Oxygen (–) or bonded to Nitrogen (–) with double bond (note that such compounds can be calculated, if their logP values are included in the user database that is used for system training)
			* Structures containing atoms other than C, H, O, S, N, or F in possible chemical surroundings or structures containing atoms P, Cl, Br, I, Se, Si, Ge, Pb, Sn, As, or B that are not within the chemical surroundings shown below (note that A denotes any atom out of C, O, S, N, F, or any group listed below):
			[[File:Classic_Algorithm_Limitations.png]]
			* Structures that contain elements in their non-typical valence
			* Structures with coordinating bonds
			* Structures containing more than 255 atoms excluding hydrogen.

			'''Note:''' The groups from the table except sp<sup>3</sup>-hybridized selene cannot be a part of a cycle.

			The program does not take into account the specific features of different geometric isomers, stereoisomers, conformers, isotopes, and structures with non-covalent bonds.

			It predicts logP values so that in most cases the reliable experimental measurements lie within the calculated ±logP interval. However, it is still possible that some new chemical structures might possess new specific structural features, such as far-range non-covalent bonding, intra-molecular shielding, or inter-molecular association. In such cases, the discrepancy between a newly measured experimental value and the calculated ±logP interval might occur.

			'''Note:''' There certainly exist some structures that formally meet the aforementioned limitations, but cannot be calculated by the current algorithm.

	===Example of Structure-Fragment Approach===		===Example of Structure-Fragment Approach===

Kirilas at 10:02, 15 June 2017

2017-06-15T10:02:26Z

← Older revision		Revision as of 10:02, 15 June 2017
Line 52:		Line 52:

	<div id="Expand" style="display:inline;"></div>		<div id="Expand" style="display:inline;"></div>
	<div class="mw-collapsible ~~mw-collapsed~~">		<div class="mw-collapsible">

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