...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Computer-Aided Molecular Design >Multitask machine learning models for predicting lipophilicity (logP) in the SAMPL7 challenge
【24h】

Multitask machine learning models for predicting lipophilicity (logP) in the SAMPL7 challenge

机译：用于预测 SAMPL7 挑战中亲脂性 （logP） 的多任务机器学习模型

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Accurate prediction of lipophilicity-logP-based on molecular structures is a well-established field. Predictions of logP are often used to drive forward drug discovery projects. Driven by the SAMPL7 challenge, in this manuscript we describe the steps that were taken to construct a novel machine learning model that can predict and generalize well. This model is based on the recently described Directed-Message Passing Neural Networks (D-MPNNs). Further enhancements included: both the inclusion of additional datasets from ChEMBL (RMSE improvement of 0.03), and the addition of helper tasks (RMSE improvement of 0.04). To the best of our knowledge, the concept of adding predictions from other models (Simulations Plus logP and logD@pH7.4, respectively) as helper tasks is novel and could be applied in a broader context. The final model that we constructed and used to participate in the challenge ranked 2/17 ranked submissions with an RMSE of 0.66, and an MAE of 0.48 (submission: Chemprop). On other datasets the model also works well, especially retrospectively applied to the SAMPL6 challenge where it would have ranked number one out of all submissions (RMSE of 0.35). Despite the fact that our model works well, we conclude with suggestions that are expected to improve the model even further.
机译：基于分子结构的亲脂性logP-的准确预测是一个成熟的领域。logP的预测通常用于推动药物发现项目。在 SAMPL7 挑战的推动下，在这篇手稿中，我们描述了为构建一种可以很好地预测和泛化的新型机器学习模型所采取的步骤。该模型基于最近描述的定向消息传递神经网络 （D-MPNN）。进一步的增强功能包括：包含来自 ChEMBL 的其他数据集（RMSE 改进 0.03）和添加辅助任务（RMSE 改进 0.04）。据我们所知，将来自其他模型（分别为 Simulations Plus logP 和 logD@pH7.4）的预测添加为辅助任务的概念是新颖的，可以应用于更广泛的上下文中。我们构建并用于参与挑战的最终模型以 0.66 的 RMSE 和 0.48 的 MAE 排名 2/17 排名提交（提交：Chemprop）。在其他数据集上，该模型也运行良好，特别是回顾性地应用于 SAMPL6 挑战，它将在所有提交中排名第一（RMSE 为 0.35）。尽管我们的模型运行良好，但我们最后提出了一些建议，这些建议有望进一步改进模型。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号