abs

학술발표회초록보기

초록문의 abstract@kcsnet.or.kr

결제문의 member@kcsnet.or.kr

현재 가능한 작업은 아래와 같습니다.
  • 09월 04일 17시 이후 : 초록수정 불가능, 일정확인 및 검색만 가능

제114회 대한화학회 학술발표회, 총회 및 기기전시회 안내 Predicting human intestinal absorption and skin permeability of organic compounds using QSAR analysis

등록일
2014년 8월 28일 15시 54분 35초
접수번호
1162
발표코드
MEDI.P-971 이곳을 클릭하시면 발표코드에 대한 설명을 보실 수 있습니다.
발표시간
10월 15일 (수요일) 16:00~19:00
발표형식
포스터
발표분야
의약화학
저자 및
공동저자
송현주, 이성광*, 변나연
한남대학교 화학과, Korea
Human intestinal absorption(HIA) for oral drugs, and skin permeability for transdermal patch are one of most important properties in the modeling in the development of new drugs. As such data are not available for new candidate drug, and therefore must be estimated. In this study, we were tried to predict HIA and skin permeability by using quantitative structure-activity relationships(QSAR). Using the collected data for HIA and skin permeability, the molecular descriptors were calculated from PreADMET program and dataset was divided into traning and test set by using the sphere exclusion method. Multiple linear regression(MLR) and support vector machine(SVM) were used to develop the QSAR models. After several validating the model with bootstrap and y-scrambling method, the reliable prediction range will be set from applicability domain(AD) in the model. The performance of each model were compared with R2 , RMSE(root mean square error), and MAE(mean absolute error) for training and test set.

상단으로