Session Details
[GS01]Prediction of drug toxicity by data-driven approach
Mon. Mar 28, 2022 9:30 AM - 11:30 AM JST
Mon. Mar 28, 2022 12:30 AM - 2:30 AM UTC
Mon. Mar 28, 2022 12:30 AM - 2:30 AM UTC
[Room B] Conference Room 131+132 Bldg. 1: 3F
Organizer: Saki Katayama (Nagoya City Univ.), Masaya Ieda (Nagoya City Univ.)
We aim to gather researchers in the fields related to drug toxicity prediction by in silico methods, and to activate information exchanges for a research in this field in this symposium.
Adverse drug reactions are serious factors for new drug candidates to drop out from the developing process. It is desired to control the risk of adverse drug reactions as well as the basic properties of drugs such as drug efficacy and physical in the early stages of drug development because the adverse drug reactions are the chemical toxic aspect of drugs. Therefore, it has been remarkable to use in silico method in recent years for quick and efficient evaluating of the risk of adverse drug reactions.
In this symposium, we will introduce the developments of in silico methods for evaluating the toxicity and risk of adverse drug reactions, such as a machine learning and statistics prediction models using the existing databases related to pharmaceuticals or the in-house databases.
Furthermore, we will discuss future prospects of studies in this field to establish evidences that the use of in silico methods is useful in accelerating drug development.
Adverse drug reactions are serious factors for new drug candidates to drop out from the developing process. It is desired to control the risk of adverse drug reactions as well as the basic properties of drugs such as drug efficacy and physical in the early stages of drug development because the adverse drug reactions are the chemical toxic aspect of drugs. Therefore, it has been remarkable to use in silico method in recent years for quick and efficient evaluating of the risk of adverse drug reactions.
In this symposium, we will introduce the developments of in silico methods for evaluating the toxicity and risk of adverse drug reactions, such as a machine learning and statistics prediction models using the existing databases related to pharmaceuticals or the in-house databases.
Furthermore, we will discuss future prospects of studies in this field to establish evidences that the use of in silico methods is useful in accelerating drug development.
オーガナイザー挨拶：家田 維哉（名市大院薬）
[GS01-1]Investigation on suicide-related adverse events associated with perampanel treatment utilizing adverse event reporting databases
○Tasuku Irei1, Yukihiro Shibata2, Hiromi Sato1, Akihiro Hisaka1 (1. Chiba Univ., 2. Nagoya City Univ.)
[GS01-2]Development of prediction models for drug-induced liver marlignant tumors using a large scale self-reporting adverse drug event database
○Kota Kurosaki1, Yoshihiro Uesawa1 (1. Meiji Pharm. Univ.)
[GS01-3]The development of in silico method to predict the inhibitory activity of drug-metabolizing enzyme
○Mizuki Nakamori1, Riku Tohno1, Kaori Ambe1, Masahiro Tohkin1, Takamitsu Sasaki2, Kouichi Yoshinari2 (1. Nagoya City Univ., 2. University of Shizuoka)
[GS01-4]Extracting drug-drug interactions from texts using heterogeneous information on drug databases
○Masaki Asada1, Makoto Miwa1, Yutaka Sasaki1 (1. Toyota Technological Institute)