首页>
外国专利>
A METHOD AND APPARATUS FOR MODELING A COMPUTATIONAL TOXICOLOGY BASED ON DEEP NEURAL NETWORK FOR EVALUATING AN EFFECT OF ENDOCRINE DISRUPTING CHEMICALS ON HUMAN HEALTH
A METHOD AND APPARATUS FOR MODELING A COMPUTATIONAL TOXICOLOGY BASED ON DEEP NEURAL NETWORK FOR EVALUATING AN EFFECT OF ENDOCRINE DISRUPTING CHEMICALS ON HUMAN HEALTH
展开▼
机译：一种基于深神经网络建模计算毒理学的方法和装置，用于评估内分泌扰动化学品对人体健康的影响
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present specification comprises the steps of selecting a chemical substance having endocrine disrupting risk; Generating a reduced set of molecular presenters by removing at least one molecular presenter from the set of molecular presenters representing the chemical substance; And generating a learning model for analyzing the risk of chemical substances using an artificial neural network algorithm based on the reduced set of molecular representations. In one embodiment, the user selects important molecular expressions using the VIP score based on the partial least squares method and the LASSO regression method among the molecular expressions of chemical substances and develops a computational toxicology model based on a deep artificial neural network to efficiently reduce the risk of endocrine disruptors Can be evaluated as.
展开▼
