Limits...
A ranking method for the concurrent learning of compounds with various activity profiles.

Dörr A, Rosenbaum L, Zell A - J Cheminform (2015)

Bottom Line: We compared the method with several state-of-the-art SVM classification techniques that are capable of inferring multi-target screening models on three chemical data sets (cytochrome P450s, dehydrogenases, and a trypsin-like protease data set) containing three different biological targets each.The experiments show that ranking-based algorithms show an increased performance for single- and multi-target virtual screening.SVM-based ranking methods constitute a valuable approach for virtual screening in multi-target drug design.

View Article: PubMed Central - PubMed

Affiliation: Center for Bioinformatics Tübingen (ZBIT), University of Tuebingen, Sand 1, Tübingen, 72076 Germany.

ABSTRACT

Background: In this study, we present a SVM-based ranking algorithm for the concurrent learning of compounds with different activity profiles and their varying prioritization. To this end, a specific labeling of each compound was elaborated in order to infer virtual screening models against multiple targets. We compared the method with several state-of-the-art SVM classification techniques that are capable of inferring multi-target screening models on three chemical data sets (cytochrome P450s, dehydrogenases, and a trypsin-like protease data set) containing three different biological targets each.

Results: The experiments show that ranking-based algorithms show an increased performance for single- and multi-target virtual screening. Moreover, compounds that do not completely fulfill the desired activity profile are still ranked higher than decoys or compounds with an entirely undesired profile, compared to other multi-target SVM methods.

Conclusions: SVM-based ranking methods constitute a valuable approach for virtual screening in multi-target drug design. The utilization of such methods is most helpful when dealing with compounds with various activity profiles and the finding of many ligands with an already perfectly matching activity profile is not to be expected.

No MeSH data available.


Related in: MedlinePlus

Performance of the cytochrome P450 and dehydrogenase single-target data sets with binary test sets. Each boxplot depicts the mean ranking error on the 20 randomly generated test sets for each target. The given ranking error is equal to 1−AUC.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4306736&req=5

Fig8: Performance of the cytochrome P450 and dehydrogenase single-target data sets with binary test sets. Each boxplot depicts the mean ranking error on the 20 randomly generated test sets for each target. The given ranking error is equal to 1−AUC.

Mentions: Figure 8 shows the results of the training sets for single-target activity with the setup from Table 1 and a binary labeling of the test sets for the cytochrome P450s and dehydrogenases. The results show an overall better performance of the multi-target ranking method (MT RANK) compared to SVM with linear combinations (SVM LC). Furthermore, the higher ranking error of the selectivity ranking (S RANK) shows that this method has a negative influence on the recognition of single-target ligands. This method was originally applied to data sets with two targets only. A data sets with three or more targets contains also more non-selective activity profiles. Therefore, grading non-selective molecules lower than decoys can have an adverse effect. As said before, even non-selective ligands still contain activity information which can be utilized for a finely graduated ranking.Figure 8


A ranking method for the concurrent learning of compounds with various activity profiles.

Dörr A, Rosenbaum L, Zell A - J Cheminform (2015)

Performance of the cytochrome P450 and dehydrogenase single-target data sets with binary test sets. Each boxplot depicts the mean ranking error on the 20 randomly generated test sets for each target. The given ranking error is equal to 1−AUC.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4306736&req=5

Fig8: Performance of the cytochrome P450 and dehydrogenase single-target data sets with binary test sets. Each boxplot depicts the mean ranking error on the 20 randomly generated test sets for each target. The given ranking error is equal to 1−AUC.
Mentions: Figure 8 shows the results of the training sets for single-target activity with the setup from Table 1 and a binary labeling of the test sets for the cytochrome P450s and dehydrogenases. The results show an overall better performance of the multi-target ranking method (MT RANK) compared to SVM with linear combinations (SVM LC). Furthermore, the higher ranking error of the selectivity ranking (S RANK) shows that this method has a negative influence on the recognition of single-target ligands. This method was originally applied to data sets with two targets only. A data sets with three or more targets contains also more non-selective activity profiles. Therefore, grading non-selective molecules lower than decoys can have an adverse effect. As said before, even non-selective ligands still contain activity information which can be utilized for a finely graduated ranking.Figure 8

Bottom Line: We compared the method with several state-of-the-art SVM classification techniques that are capable of inferring multi-target screening models on three chemical data sets (cytochrome P450s, dehydrogenases, and a trypsin-like protease data set) containing three different biological targets each.The experiments show that ranking-based algorithms show an increased performance for single- and multi-target virtual screening.SVM-based ranking methods constitute a valuable approach for virtual screening in multi-target drug design.

View Article: PubMed Central - PubMed

Affiliation: Center for Bioinformatics Tübingen (ZBIT), University of Tuebingen, Sand 1, Tübingen, 72076 Germany.

ABSTRACT

Background: In this study, we present a SVM-based ranking algorithm for the concurrent learning of compounds with different activity profiles and their varying prioritization. To this end, a specific labeling of each compound was elaborated in order to infer virtual screening models against multiple targets. We compared the method with several state-of-the-art SVM classification techniques that are capable of inferring multi-target screening models on three chemical data sets (cytochrome P450s, dehydrogenases, and a trypsin-like protease data set) containing three different biological targets each.

Results: The experiments show that ranking-based algorithms show an increased performance for single- and multi-target virtual screening. Moreover, compounds that do not completely fulfill the desired activity profile are still ranked higher than decoys or compounds with an entirely undesired profile, compared to other multi-target SVM methods.

Conclusions: SVM-based ranking methods constitute a valuable approach for virtual screening in multi-target drug design. The utilization of such methods is most helpful when dealing with compounds with various activity profiles and the finding of many ligands with an already perfectly matching activity profile is not to be expected.

No MeSH data available.


Related in: MedlinePlus