Large-Scale Modeling of Multispecies Acute Toxicity End Points Using Consensus of Multitask Deep Learning Methods.
Large-Scale Modeling of Multispecies Acute Toxicity End Points Using Consensus of Multitask Deep Learning Methods.
复制标题
DOI：
10.1021/acs.jcim.0c01164
复制
发表时间：
2021-02-22
影响因子：
5.6
通讯作者：
Zakharov AV
中科院分区：
文献类型：
--
作者：
Jain S;Siramshetty VB;Alves VM;Muratov EN;Kleinstreuer N;Tropsha A;Nicklaus MC;Simeonov A;Zakharov AV
预测有关安全性和毒理学的分子特性的计算方法代表了加快药物开发、筛选环境化学品的替代方法，从而显着减少相关时间和成本。人们对开发能够产生可靠的毒性预测的计算方法有强烈的需求和兴趣，并且许多方法，包括最近引入的深度神经网络，都已被用于实现这一目标。在此，我们报告了公共数据集数据的收集、管理和整合，这些数据集是 ChemIDplus 全身急性毒性数据库的来源。这些努力产生了最大的公开可用的此类数据集，其中包含针对总共 59 个急性全身毒性终点进行测量的超过 80,000 种化合物。这些数据用于利用随机森林、深度神经网络、卷积和图卷积神经网络方法开发多个单任务和多任务模型。我们还首次报告了基于不同多任务方法的共识模型。据我们所知，59 个端点中有 36 个的预测模型以前从未发布过。此外，我们的结果表明，从三种多任务学习方法获得的共识模型的性能明显更好，特别是比研究中开发的其他模型更好地预测了 29 个较小的任务（少于 300 种化合物）。策划的数据集和开发的模型已在 https://github.com/ncats/ld50-multitask、https://predictor.ncats.io/ 和 https://cactus.nci.nih.gov/download/acute-toothity-db（仅数据集）公开提供，以支持监管和研究应用。
Computational methods to predict molecular properties regarding safety and toxicology represent alternative approaches to expedite drug development, screen environmental chemicals, and thus significantly reduce associated time and costs. There is a strong need and interest in the development of computational methods that yield reliable predictions of toxicity, and many approaches, including the recently introduced deep neural networks, have been leveraged towards this goal. Herein, we report on the collection, curation, and integration of data from the public datasets that were the source of the ChemIDplus database for systemic acute toxicity. These efforts generated the largest publicly available such dataset comprising > 80,000 compounds measured against a total of 59 acute systemic toxicity endpoints. This data was used for developing multiple single- and multi-task models utilizing Random Forest, deep neural networks, convolutional and graph convolutional neural network approaches. For the first time, we also reported the consensus models based on different multi-task approaches. To the best of our knowledge, prediction models for 36 out of the 59 endpoints have never been published before. Furthermore, our results demonstrated a significantly better performance of the consensus model obtained from three multi-task learning approaches that particularly predicted the 29 smaller tasks (less than 300 compounds) better than other models developed in the study. The curated dataset and the developed models have been made publicly available at https://github.com/ncats/ld50-multitask, https://predictor.ncats.io/ and https://cactus.nci.nih.gov/download/acute-toxicity-db (dataset only) to support regulatory and research applications.
登录
查看更多内容
药物发现的迁移学习
影响因子：
7.3
作者：
Cai, Chenjing;Wang, Shiwei;Pei, Jianfeng
通讯作者：
Pei, Jianfeng
DOI：
10.1016/j.gpb.2017.07.003
发表时间：
2018-03
期刊：
Genomics, proteomics & bioinformatics
影响因子：
--
作者：
Cao C;Liu F;Tan H;Song D;Shu W;Li W;Zhou Y;Bo X;Xie Z
通讯作者：
Xie Z
使用随机森林学习器对不平衡数据的酚类毒性作用机制进行计算机预测
影响因子：
2.9
作者：
Chen, Jing;Tang, Yuan Yan;Guo, Chang
通讯作者：
Guo, Chang
影响因子：
5.6
作者：
Fourches D;Muratov E;Tropsha A
通讯作者：
Tropsha A
影响因子：
5.6
作者：
Fourches D;Muratov E;Tropsha A
通讯作者：
Tropsha A