| Project/Area Number |
18K14987
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 47060:Clinical pharmacy-related
|
|---|
| Research Institution | Nagoya City University |
|---|
Principal Investigator |
Ambe Kaori 名古屋市立大学, 医薬学総合研究院(薬学), 助教 (70440625)
|
|---|
| Project Period (FY) |
2018-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2019: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2018: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 薬物性肝障害 / JADER / インシリコ予測 / 機械学習 / 副作用 / ビッグデータ / 人工知能 / 機械学習法 |
|---|
| Outline of Final Research Achievements |
The purpose of this study was to utilize JADER as spontaneous adverse event reporting database and to predict drug-induced liver injury from chemical structure information of drugs using machine learning. The positive drugs and negative drugs for drug-induced liver injury were defined using the signal detection method and the number of reports. Using a random forest with molecular descriptors of drugs as a feature value, in silico prediction model that classify the posirive or negative of drug-induced liver injury was constructed, and the performance of sensitivity 0.90 and AUC 0.66 was obtained. Furthermore, combining JADER and literature information, AUC was improved to 0.84. It was suggested that drug-induced liver injury could be predicted by appropriately utilizing large-scale adverse event information and machine learning.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究の学術的意義として、開発した予測モデルは対象とする副作用に対して柔軟性があり、入手しやすい医薬品の化学構造情報を用いて適切に大規模な副作用情報を活用することで、様々な副作用の予測に応用することが可能である。薬物性肝障害の予測モデルを活用すればヒトでの臨床試験や市販後のリスク軽減が可能となり、本研究から得られた知見は新薬開発において候補化合物のスクリーニングを効率化することも期待されるなど社会的意義も大きい。
|
