arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.08019q-bio.QMcs.LGphysics.chem-ph
收藏

通过通用物理信息神经网络学习化疗药物作用

Learning Chemotherapy Drug Action via Universal Physics-Informed Neural Networks

Cheriton School of Computer Science(查尔顿计算机科学学院);University of Waterloo(滑铁卢大学);Department of Applied Mathematics(应用数学系)

Lena Podina, Ali Ghodsi, Mohammad Kohandel

AI总结:

针对定量系统药理学模型构建需大量人工提炼文献、拟合参数的问题,本研究将通用物理信息神经网络用于学习化疗药效动力学微分方程的未知组分,验证了其在该领域的应用潜力。

摘要:

定量系统药理学(QSP)被广泛用于药物进入临床试验前评估药物疗效和毒性。然而,构建QSP模型需要对大量文献进行人工提炼,还需要拟合参数,并对模型做出简化假设。本研究中,我们将通用物理信息神经网络(UPINNs)应用于学习各类化疗药效动力学微分方程模型中的未知组分。我们从合成数据中学习了三种常用化疗药物作用机制(log-kill、Norton-Simon和E_max)。随后,我们使用UPINN方法同时拟合多个合成数据集的参数。最后,我们在多柔比星(一种化疗药物)的药效动力学模型中学习了净增殖率。尽管这些仅为示例研究,我们仍凸显了UPINNs在学习药效动力学和药代动力学模型未知项方面的实用性。

英文摘要:

Quantitative systems pharmacology (QSP) is widely used to assess drug effects and toxicity before the drug goes to clinical trial. However, significant manual distillation of the literature is needed in order to construct a QSP model. Parameters may need to be fit, and simplifying assumptions of the model need to be made. In this work, we apply Universal Physics-Informed Neural Networks (UPINNs) to learn unknown components of various differential equations that model chemotherapy pharmacodynamics. We learn three commonly employed chemotherapeutic drug actions (log-kill, Norton-Simon, and E_max) from synthetic data. Then, we use the UPINN method to fit the parameters for several synthetic datasets simultaneously. Finally, we learn the net proliferation rate in a model of doxorubicin (a chemotherapeutic) pharmacodynamics. As these are only toy examples, we highlight the usefulness of UPINNs in learning unknown terms in pharmacodynamic and pharmacokinetic models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑