Phthalate esters (PAEs) as plasticizers posed significant environmental and human health risks during the production and application processes. This study aims to investigate the synthesizability of previously designe...
详细信息
Phthalate esters (PAEs) as plasticizers posed significant environmental and human health risks during the production and application processes. This study aims to investigate the synthesizability of previously designed environmentally friendly PAEs alternatives by in silico approaches and explore the key factors influencing their synthesizability. Firstly, a novel approach combining positive and unlabeled (PU) machine learning (ML) and k Nearest Neighbor (kNN) models was utilized to screen three environmentally friendly PAEs alternatives with high synthesizability. Subsequently, the synthesizability and environmental friendliness of the selected PAEs alternatives were evaluated and confirmed using ADMETlab 2.0. Results demonstrated that all three PAEs alternatives exhibited high synthesizability and environmental friendliness. Finally, the SHapley Additive exPlanation (SHAP) method was employed to analyze the synthesis mechanisms of PAEs alternatives, revealing that the VE2_DzZ (molecular substitutability) and maxHCsats (molecular structure) could influence their synthesizability. Based on these findings, the synthesizability of the three PAEs alternatives was validated using density functional theory (DFT) and three-dimensional quantitative structure-activity relationship (3D-QSAR) methods. This cost-effective study provided the first evaluation of the synthesizability of PAEs alternatives and reduced the number of unlabeled samples by 95.83%. Moreover, these findings offered a theoretical foundation for developing environmentally friendly PAEs alternatives and provided new insights for substituting emerging pollutants and developing new materials.
positive and unlabeled (PU) learning is a learning method which can be applied to various field such as recommendation and big data analysis. A direct method to solve PU learning is transform it into a weighted classi...
详细信息
ISBN:
(纸本)9798400708534
positive and unlabeled (PU) learning is a learning method which can be applied to various field such as recommendation and big data analysis. A direct method to solve PU learning is transform it into a weighted classification problem. However, previously proposed methods assume a strict condition. In this paper, we first investigate if the condition can be satisfied in real world situations and then propose a normalized weighted method which can relax the difficultly of PU learning.
In the problem of learning with positive and unlabeled examples, existing research all assumes that positive examples P and the hidden positive examples in the unlabeled set U are generated from the same distribution....
详细信息
ISBN:
(纸本)9781581139129
In the problem of learning with positive and unlabeled examples, existing research all assumes that positive examples P and the hidden positive examples in the unlabeled set U are generated from the same distribution. This assumption may be violated in practice. In such cases, existing methods perform poorly. This paper proposes a novel technique A-EM to deal with the problem. Experimental results with product page classification demonstrate the effectiveness of the proposed technique.
暂无评论