Limits...
Interactive data mining for molecular graphs.

Yilmaz B, Göktürk M - J Autom Methods Manag Chem (2009)

Bottom Line: Using a pipelining structure, it enables experts to contribute to the solution with their expertise at different levels.In order to derive desired fragments, it combines histogram-based filtering and clustering methods in a novel way.This combination enables a flexible determination of frequent fragments that repeat in molecules exactly or with some variations.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Gebze Institute of Technology, 10141400 Kocaeli, Turkey. byilmaz@gyte.edu.tr

ABSTRACT
Designing new medical drugs for a specific disease requires extensive analysis of many molecules that have an activity for the disease. The main goal of these extensive analyses is to discover substructures (fragments) that account for the activity of these molecules. Once they are discovered, these fragments are used to understand the structure of new drugs and design new medicines for the disease. In this paper, we propose an interactive approach for visual molecule mining to discover fragments of molecules that are responsible for the desired activity with respect to a specific disease. Our approach visualizes molecular data in a form that can be interpreted by a human expert. Using a pipelining structure, it enables experts to contribute to the solution with their expertise at different levels. In order to derive desired fragments, it combines histogram-based filtering and clustering methods in a novel way. This combination enables a flexible determination of frequent fragments that repeat in molecules exactly or with some variations.

No MeSH data available.


Inactivity map.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC2801005&req=5

fig8: Inactivity map.

Mentions: An expert is first asked for the parameters Δx and Δy. Those parameters are selected as Δx = 0.12 and Δy = 0.07 by the expert. Using those parameters, activity and inactivity maps are created as in Figures 7 and 8, respectively. Using those activity and inactivity maps, the dataset is filtered using a threshold value, %40. This threshold value is decided by the expert in order to keep more information unfiltered. Although it may seem that using a 2D activity maps rather than a 3D representation may cause loss of data. It is important to note that these maps are only used in finding approximate locations of clusters where unfiltered data and the preliminary information about clusters are fully preserved. Lastly, using unfiltered data and preliminary information about the clusters, the system finds final active fragments. To visualize 3D topology of active fragments, an active template molecule that is selected by the expert is used. Graph-based representation of extracted active fragments on the template molecule is shown at Figure 9.


Interactive data mining for molecular graphs.

Yilmaz B, Göktürk M - J Autom Methods Manag Chem (2009)

Inactivity map.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC2801005&req=5

fig8: Inactivity map.
Mentions: An expert is first asked for the parameters Δx and Δy. Those parameters are selected as Δx = 0.12 and Δy = 0.07 by the expert. Using those parameters, activity and inactivity maps are created as in Figures 7 and 8, respectively. Using those activity and inactivity maps, the dataset is filtered using a threshold value, %40. This threshold value is decided by the expert in order to keep more information unfiltered. Although it may seem that using a 2D activity maps rather than a 3D representation may cause loss of data. It is important to note that these maps are only used in finding approximate locations of clusters where unfiltered data and the preliminary information about clusters are fully preserved. Lastly, using unfiltered data and preliminary information about the clusters, the system finds final active fragments. To visualize 3D topology of active fragments, an active template molecule that is selected by the expert is used. Graph-based representation of extracted active fragments on the template molecule is shown at Figure 9.

Bottom Line: Using a pipelining structure, it enables experts to contribute to the solution with their expertise at different levels.In order to derive desired fragments, it combines histogram-based filtering and clustering methods in a novel way.This combination enables a flexible determination of frequent fragments that repeat in molecules exactly or with some variations.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Engineering, Gebze Institute of Technology, 10141400 Kocaeli, Turkey. byilmaz@gyte.edu.tr

ABSTRACT
Designing new medical drugs for a specific disease requires extensive analysis of many molecules that have an activity for the disease. The main goal of these extensive analyses is to discover substructures (fragments) that account for the activity of these molecules. Once they are discovered, these fragments are used to understand the structure of new drugs and design new medicines for the disease. In this paper, we propose an interactive approach for visual molecule mining to discover fragments of molecules that are responsible for the desired activity with respect to a specific disease. Our approach visualizes molecular data in a form that can be interpreted by a human expert. Using a pipelining structure, it enables experts to contribute to the solution with their expertise at different levels. In order to derive desired fragments, it combines histogram-based filtering and clustering methods in a novel way. This combination enables a flexible determination of frequent fragments that repeat in molecules exactly or with some variations.

No MeSH data available.