Interpreting Neural Network Models for Toxicity Prediction by Extracting Learned Chemical Features

人工神经网络 Nexus(标准) 人工智能 计算机科学 机器学习 特征(语言学) 哲学 语言学 嵌入式系统
作者
Moritz Walter,Samuel J. Webb,Valerie J. Gillet
出处
期刊:Journal of Chemical Information and Modeling [American Chemical Society]
标识
DOI:10.1021/acs.jcim.4c00127
摘要

Neural network models have become a popular machine-learning technique for the toxicity prediction of chemicals. However, due to their complex structure, it is difficult to understand predictions made by these models which limits confidence. Current techniques to tackle this problem such as SHAP or integrated gradients provide insights by attributing importance to the input features of individual compounds. While these methods have produced promising results in some cases, they do not shed light on how representations of compounds are transformed in hidden layers, which constitute how neural networks learn. We present a novel technique to interpret neural networks which identifies chemical substructures in training data found to be responsible for the activation of hidden neurons. For individual test compounds, the importance of hidden neurons is determined, and the associated substructures are leveraged to explain the model prediction. Using structural alerts for mutagenicity from the Derek Nexus expert system as ground truth, we demonstrate the validity of the approach and show that model explanations are competitive with and complementary to explanations obtained from an established feature attribution method.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
悦耳静枫发布了新的文献求助10
3秒前
烟花应助果粒多采纳,获得10
3秒前
潘善若发布了新的文献求助10
4秒前
廉凌波发布了新的文献求助10
4秒前
赘婿应助crazy采纳,获得10
4秒前
喻义梅关注了科研通微信公众号
5秒前
精明寻梅完成签到,获得积分10
5秒前
行远完成签到,获得积分10
6秒前
科目三应助感动黄豆采纳,获得10
7秒前
xueyu发布了新的文献求助10
7秒前
钱宇成完成签到,获得积分20
8秒前
修道院的豌豆完成签到,获得积分10
8秒前
廉凌波完成签到,获得积分10
9秒前
Rondab应助行远采纳,获得10
11秒前
11秒前
SYLH应助showmaker采纳,获得20
12秒前
12秒前
领导范儿应助FXQ123_范采纳,获得10
12秒前
Afaq完成签到,获得积分20
13秒前
油饼发布了新的文献求助30
15秒前
潘善若发布了新的文献求助10
15秒前
ganxinran发布了新的文献求助10
15秒前
17秒前
17秒前
19秒前
果粒多发布了新的文献求助10
22秒前
可爱的函函应助大刘采纳,获得10
23秒前
Rondab应助q792309106采纳,获得10
23秒前
23秒前
momo发布了新的文献求助10
24秒前
潘善若发布了新的文献求助10
25秒前
26秒前
斯文败类应助baronge采纳,获得10
27秒前
赘婿应助要减肥笑阳采纳,获得10
27秒前
27秒前
ganxinran完成签到,获得积分10
28秒前
xiaoyangchun完成签到,获得积分10
28秒前
小二郎应助阿航采纳,获得30
30秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989263
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253814
捐赠科研通 3270066
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882084
科研通“疑难数据库(出版商)”最低求助积分说明 809136