abs

학술발표회초록보기

초록문의 abstract@kcsnet.or.kr

결제문의 member@kcsnet.or.kr

현재 가능한 작업은 아래와 같습니다.
  • 08월 28일 16시 이후 : 초록수정 불가능, 일정확인 및 검색만 가능

Insilico hERG toxicity model by decision tree

등록일
2008년 8월 12일 09시 27분 47초
접수번호
0991
발표코드
35P313포 이곳을 클릭하시면 발표코드에 대한 설명을 보실 수 있습니다.
발표시간
목 <발표Ⅰ>
발표형식
포스터
발표분야
의약화학
저자 및
공동저자
장재완, 추현아1, 조용서2, 배애님2
과학기술연합 대학원, Korea
1한국과학기술연구원 생체과학연구부, Korea
2한국과학기술연구원 생체과학연구본부, Korea
hERG related cardiotoxicity is a major pharmacological safety concern facing the pharmaceutical industry and the health regulatory authorities. Our goal is to build a insilico model using T-type calcium channel blockers(TCCB) for predicting this recently issued hERG related side effect in an early stage of drug development. Studies showed that T-type calcium channel and hERG potassium channel are similar each other, which renders TCCB development more difficult. Among several in silico modeling methods, classification method using ‘Decision Tree’ based on CART algorithm is our approach to make a model. This method attempts to bin compounds by their hERG inhibition activities according to specific descriptors. Several important descriptors were identified and applied to make a model. Furthermore, not only compounds that we synthesized, but compounds that were synthesized by other laboratories and already marketed were also used to improve our models. Selecting best models based on several criteria like enrichment factor and validating our model by test set were also considered deeply.

상단으로