数量结构-活动关系
背景(考古学)
计算机科学
领域(数学)
预测建模
预测能力
机器学习
模型验证
统计模型
人工智能
数据挖掘
数学
数据科学
地理
哲学
考古
纯数学
认识论
标识
DOI:10.1007/978-1-62703-059-5_21
摘要
The fundamental and more critical steps that are necessary for the development and validation of QSAR models are presented in this chapter as best practices in the field. These procedures are discussed in the context of predictive QSAR modelling that is focused on achieving models of the highest statistical quality and with external predictive power. The most important and most used statistical parameters needed to verify the real performances of QSAR models (of both linear regression and classification) are presented. Special emphasis is placed on the validation of models, both internally and externally, as well as on the need to define model applicability domains, which should be done when models are employed for the prediction of new external compounds.
科研通智能强力驱动
Strongly Powered by AbleSci AI