자료유형 | 학위논문 |
---|---|
서명/저자사항 | Integrating Genetic and Structural Features: Building a Hybrid Physical-Statistical Classifier for Variants Related to Protein-Drug Interactions. |
개인저자 | Wang, Bo. |
단체저자명 | Yale University. Chemistry. |
발행사항 | [S.l.]: Yale University., 2019. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
형태사항 | 99 p. |
기본자료 저록 | Dissertations Abstracts International 81-03B. Dissertation Abstract International |
ISBN | 9781088315019 |
학위논문주기 | Thesis (Ph.D.)--Yale University, 2019. |
일반주기 |
Source: Dissertations Abstracts International, Volume: 81-03, Section: B.
Advisor: Gerstein, Mark B. |
이용제한사항 | This item must not be sold to any third party vendors.This item must not be added to any third party search indexes. |
요약 | A key issue in drug design is understanding how population variation affects drug efficacy by altering binding affinity (BA) in different individuals -- an important consideration for pharmaceutical regulators. Ideally, we would like to evaluate millions of single-nucleotide variants (SNVs) in relation to BA. However, only hundreds of protein-drug complexes with BA and mutations are available, constituting too small a gold-standard for straightforward statistical model training. Thus, we take a hybrid approach using physically-based calculations to bootstrap the parameterization of a full statistical model. In particular, we do 3D-structure-based docking calculations on ~10,000 SNVs modifying known protein-drug complexes to construct a pseudo-gold-standard dataset of BAs. Then we develop a complete statistical model combining structure, ligand and sequence features and show how it can be applied to score millions of SNVs. Finally, we show our model has good performance in cross-validated testing (AUROC of 97%) and can also be validated by orthogonal ligand-binding data. |
일반주제명 | Bioinformatics. Biophysics. Statistics. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |