Development of an expert system for establishment of threshold limit values of novel compounds
Grant-in-Aid for Scientific Research (A)
|Allocation Type||Single-year Grants |
|Research Institution||Akita University |
KOIZUMI Akio Akita Univ.School of Medicine, Professor, 医学部, 教授 (50124574)
NAKAAKI Kenji Azabu Univ.School of Environment & Health, Professor, 環境保健学部, 教授 (90072652)
TAKEUCHI Yasuhiro Nagoya Univ.School of Medicine, Professor, 大学院・医学研究科, 教授 (90022805)
SATO Hiroshi Tohoku Univ.School of Medicine, Professor, 大学院・医学系研究科, 教授 (40125571)
SATO Akio Yamanashi Medical University, Professor, 教授 (40020747)
SAKURAI Haruhiko National Institute of Industrial Health, Director, 産業医学総合研究所, (所長)研究職 (70051357)
|Project Period (FY)
1996 – 1998
Completed (Fiscal Year 1998)
|Budget Amount *help
¥13,900,000 (Direct Cost: ¥13,900,000)
Fiscal Year 1998: ¥1,600,000 (Direct Cost: ¥1,600,000)
Fiscal Year 1997: ¥3,800,000 (Direct Cost: ¥3,800,000)
Fiscal Year 1996: ¥8,500,000 (Direct Cost: ¥8,500,000)
|Keywords||threshold limit values / QSAR / prediction of hazard / expert system / metabolism / artificial intelligence / 有害性予測|
We have been trying to construct an expert system which predicts hazard of novel compounds.
1. A multi-purpose database of regulated compounds
We collected data of 1749 compounds which are registered at ACGJH, GFD, NIOSH, IARC, JSOH.Terms of the database are JUPAC name, physical characteristics, hazard, LD50, effects on the environment, usage, amount of production.
2. A database of metabolism.
We made a database of ways of metabolism of major drugs and industrial compounds. It was made with the IUIPAC name for purpose of searching.
3. A method to search known compounds which resemble novel one and to predict hazard.
We made rules to find similar compounds using above two databases by the JUPAC name. It was easy to use and predict hazard for many non-specialists of chemistry.
4. Hazard prediction using quantitative structure-activity relationships (QSAR).
We tried to predict sensitization and LD50 by QSAR.Accuracy of prediction of sensitization was different between compounds groups (acryls, amins, isocyanates, epoxides). Prediction of LD50 of alcohols and aromatic hydrocarbons was fairly good.
Report (4 results)
Research Products (15 results)