Presentation | 2003/3/8 Risk Report Based on Structural Similarity of Chemicals Yoshimasa TAKAHASHI, Satoshi FUJISIMA, Kyoko YOKOE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The applicability of the Topological Fragment Spectra (TFS) method, which was reported in our preceding work, was validated in discriminating active classes of pharmaceutical drugs. Dopamine antagonists of 1,227 that interact with different type of receptors (D1, D2, D3 and D4) were used for training an artificial neural network(ANN) with their TFS to classify the type of action. The ANN classified 88% of the drugs into their own classes correctly. Then, the trained ANN model was used for predicting class unknown compounds. For other 137 compounds the active classes of 81% of all the compounds were correctly predicted. Beside, to validate an instance-based chemical risk report approach based on structural similarity, TFS-based similar structure searching was employed for identification of active molecular analogues with different activities. The TFS successfully identified structurally similar molecular analogues of our interest. In addition, a desktop software tool, called MolSpace, was also developed for visualizing massive molecular data space or TFS space. It makes us easy to compare an object molecule with neighbors in the same region of data space. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Structural Similarity / TFS, Pattern Classification / Data mining / Structural Feature Analysis / Risk Assessment |
Paper # | AI2002-87 |
Date of Issue |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2003/3/8(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Risk Report Based on Structural Similarity of Chemicals |
Sub Title (in English) | |
Keyword(1) | Structural Similarity |
Keyword(2) | TFS, Pattern Classification |
Keyword(3) | Data mining |
Keyword(4) | Structural Feature Analysis |
Keyword(5) | Risk Assessment |
1st Author's Name | Yoshimasa TAKAHASHI |
1st Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology() |
2nd Author's Name | Satoshi FUJISIMA |
2nd Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology |
3rd Author's Name | Kyoko YOKOE |
3rd Author's Affiliation | Department of Knowledge-based Information Engineering, Toyohashi University of Technology |
Date | 2003/3/8 |
Paper # | AI2002-87 |
Volume (vol) | vol.102 |
Number (no) | 711 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |