Neural network activation similarity: a new measure to assist decision making in chemical toxicology
Author:
Affiliation:
1. MRC Toxicology Unit
2. University of Cambridge
3. Leicester
4. UK
5. Centre for Molecular Informatics
6. Department of Chemistry
7. Cambridge
8. Unilever Safety and Environmental Assurance Centre
9. Colworth Science Park
10. Bedfordshire
Abstract
Deep learning neural networks, constructed for the prediction of chemical binding at 79 pharmacologically important human biological targets, show extremely high performance on test data (accuracy 92.2 ± 4.2%, MCC 0.814 ± 0.093, ROC-AUC 0.96 ± 0.04).
Funder
Unilever
Publisher
Royal Society of Chemistry (RSC)
Subject
General Chemistry
Link
http://pubs.rsc.org/en/content/articlepdf/2020/SC/D0SC01637C
Reference52 articles.
1. The development and application of in silico models for drug induced liver injury
2. In silico prediction of chemical genotoxicity using machine learning methods and structural alerts
3. In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods
4. Development of novel in silico model for developmental toxicity assessment by using naïve Bayes classifier method
Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A Graph Neural Network Model with a Transparent Decision-Making Process Defines the Applicability Domain for Environmental Estrogen Screening;Environmental Science & Technology;2023-09-25
2. FP-MAP: an extensive library of fingerprint-based molecular activity prediction tools;Frontiers in Chemistry;2023-08-15
3. The role of computational toxicology in the risk assessment of food products;Present Knowledge in Food Safety;2023
4. The Efficiency of Background Data Visualization of College Smart Education System Integrating Social Management Information Platform;2022 International Conference on Edge Computing and Applications (ICECAA);2022-10-13
5. Uncertainty quantification: Can we trust artificial intelligence in drug discovery?;iScience;2022-08
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3