通过集成图形卷积网络和多任务学习来推进水生持久性,移动性和有毒物质的选
Yang Chen1, Rui Qiu2, Jin Yin3
1State Key Laboratory of Intelligent Construction and Healthy Operation and Maintenance of Deep Underground Engineering, College of Architecture and Environment, Sichuan University, Chengdu, 610065, China; Business School, Sichuan University, Chengdu, 610065, China.
这项研究开发了一种多任务学习图形卷积网络模型,以准确识别水中的持久,移动和有毒物质 (PMT). 该模型增强了对新出现的污染物的水质监测和风险评估.
科学领域:
- 环境化学环境化学
- 计算化学计算化学
- 评估水质水质的评估.
背景情况:
- 新出现的污染物,特别是持久性,移动性和有毒物质 (PMT),对水生生态系统和饮用水构成风险.
- 准确识别PMT物质对于环境风险评估和水安全至关重要.
- 在预测污染物特性时,单任务机器学习模型可能会过度适应.
研究的目的:
- 开发一个准确的机器学习模型来识别持久,移动和有毒物质 (PMT).
- 利用图形卷积网络 (GCNs) 和分子描述器 (MDs) 的多任务学习 (MTL) 来提高预测准确度并减少过拟合.
- 为水质监测和新出现的污染物管理提供一个实用的工具.
主要方法:
- 集成的分子图形与分子描述符 (MDs) 创建一个图形卷积网络 (GCN) 模型.
- 采用多任务学习 (MTL) 来同时对持久性,移动性和毒性进行二进制分类.
- 使用6820种物质的数据集进行模型培训和验证.
主要成果:
- 与单任务 GCN 和传统机器学习模型相比,开发的 MTL-GCN-MD 模型表现出更高的性能.
- 在测试套件上,在所有三个识别任务 (持久性,移动性,毒性) 中,达到超过0.81的平衡精度.
- 使用特征分布可视化和原子注意力权重对预测机制的系统分析.
结论:
- MTL-GCN-MD模型有效地减少了过,并改善了PMT物质的识别.
- 开发了一个在线服务器,用于可访问的预测,帮助研究人员和水务当局.
- 该研究为早期预警,查和监管管理水系统中危险化学品提供了宝贵的工具.
更多相关视频
07:25High-throughput Screening of Chemical Compounds to Elucidate Their Effects on Bacterial Persistence
Published on: February 23, 2021
06:19Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
Published on: August 16, 2024
相关概念视频
Convolution Properties II
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
Convolution Properties I
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
Ogive Graph
Graphing Antiderivatives
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Bar Graph
