ChemSpaceShuttle: A tool for data mining in drug discovery by classification, projection, and 3D visualization

An abundant amount of information is produced in the digital domain, and an effective information extraction (IE) system is required to surf through this sea of information. In this paper, we show that an interactive visualization system works effectively to complement an IE system. In particular, three-dimensional (3D) visualization can turn a data-centric system into a user-centric one by facilitating the human visual system as a powerful pattern recognizer to become a part of the IE cycle. Because information as data is multidimensional in nature, 2D visualization has been the preferred mode. However, we argue that the extra dimension available for us in a 3D mode provides a valuable space where we can pack an orthogonal aspect of the available information. As for candidates of this orthogonal information, we have considered the following two aspects: 1) abstraction of the unstructured source data, and 2) the history line of the discovery process. We have applied our proposal to text data mining in bioinformatics. Through case studies of data mining for molecular interaction in the yeast and mitogen-activated protein kinase pathways, we demonstrate the possibility of interpreting the extracted results with a 3D visualization system.

Download Full-text

3D VISUALIZATION AND VIRTUAL REALITY FOR VISUAL DATA MINING - A Survey

Proceedings of the International Conference on Imaging Theory and Applications and International Conference on Information Visualization Theory and Applications ◽

10.5220/0002850801400145 ◽

2010 ◽

Keyword(s):

Data Mining ◽

Virtual Reality ◽

3D Visualization ◽

Visual Data ◽

Visual Data Mining

Download Full-text

Computational chemistry, data mining, high-throughput synthesis and screening - informatics and integration in drug discovery

Journal of Automated Methods and Management in Chemistry ◽

10.1080/14639240110092521 ◽

2001 ◽

Vol 23 (6) ◽

pp. 191-192

Author(s):

Charles J. Manly

Keyword(s):

Data Mining ◽

Drug Discovery ◽

Computational Chemistry ◽

High Throughput ◽

Chemistry Data

Download Full-text

Multimodality Data Integration in Epilepsy

International Journal of Biomedical Imaging ◽

10.1155/2007/13963 ◽

2007 ◽

Vol 2007 ◽

pp. 1-12 ◽

Cited By ~ 34

Author(s):

Otto Muzik ◽

Diane C. Chugani ◽

Guangyu Zou ◽

Jing Hua ◽

Yi Lu ◽

...

Keyword(s):

Data Mining ◽

Pet Imaging ◽

3D Visualization ◽

Underlying Disease ◽

Spatial Proximity ◽

Software Environment ◽

Generic Level ◽

Efficient Data ◽

Quantitative Results ◽

The Relationship

An important goal of software development in the medical field is the design of methods which are able to integrate information obtained from various imaging and nonimaging modalities into a cohesive framework in order to understand the results of qualitatively different measurements in a larger context. Moreover, it is essential to assess the various features of the data quantitatively so that relationships in anatomical and functional domains between complementing modalities can be expressed mathematically. This paper presents a clinically feasible software environment for the quantitative assessment of the relationship among biochemical functions as assessed by PET imaging and electrophysiological parameters derived from intracranial EEG. Based on the developed software tools, quantitative results obtained from individual modalities can be merged into a data structure allowing a consistent framework for advanced data mining techniques and 3D visualization. Moreover, an effort was made to derive quantitative variables (such as the spatial proximity index, SPI) characterizing the relationship between complementing modalities on a more generic level as a prerequisite for efficient data mining strategies. We describe the implementation of this software environment in twelve children (mean age5.2±4.3years) with medically intractable partial epilepsy who underwent both high-resolution structural MR and functional PET imaging. Our experiments demonstrate that our approach will lead to a better understanding of the mechanisms of epileptogenesis and might ultimately have an impact on treatment. Moreover, our software environment holds promise to be useful in many other neurological disorders, where integration of multimodality data is crucial for a better understanding of the underlying disease mechanisms.

Download Full-text