골격기반 분자 그래프 생성모델 (scaffold-based molecular generative model)
- 여러 물성을 만족하는 분자를 만들기위해 기본 골격을 유지하면서 분자를 추가하고 분석하여 생성.
3D linker design model
- DeLinker : 2개 fragment의 3차원 배양을 고려하여 최적의 liner를 디자인하는 모델
- Deep Generative Models for 3D Linker Design, https://doi.org/10.1021/acs.jcim.9b01120
- https://github.com/oxpig/DeLinker
- 기존의 데이터베이스 기반 방법들보다 실제와 유사한 분자들을 생성함.
- Docking 계산시 더 안정한 구조들이 만들어짐.
- 실험으로 검증된 분자를 실제로 디자인함.
Reference
- Graph기반 deep generative model을 이용한 분자 디자인2ㅣ임재창, https://youtu.be/XGbNtPZK82U
- https://blog.naver.com/hits_inc/222415287818
- Scaffold-based molecular design with a graph generative model, https://pubs.rsc.org/en/content/articlelanding/2020/sc/c9sc04503a
- DeepScaffold: A Comprehensive Tool for Scaffold-Based De Novo Drug Discovery Using Deep Learning, https://doi.org/10.1021/acs.jcim.9b00727
- DRUG DESIGN – Fragment-Based Drug Design: Delivering Drugs That Hit Multiple targets, Leveraging Insights From Systems Biology, https://drug-dev.com/fragment-based-drug-design-delivering-drugs-that-hit-multiple-targets-leveraging-insights-from-systems-biology/
- AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings, https://doi.org/10.1021/acs.jcim.1c00203
- Semi-supervised learning 방법론 소개, https://blog.est.ai/2020/11/ssl/
'Drug' 카테고리의 다른 글
ZINC database (0) | 2022.01.10 |
---|---|
Molecule design using Deep generative models (0) | 2022.01.04 |
Molecule design using Graph model 1 (0) | 2022.01.04 |
Molecule design using SMILES (0) | 2022.01.04 |
[Company] Standigm (0) | 2021.12.30 |
댓글