Topology-enhanced molecular graph representation for anti-breast cancer drug selection.
Topology-enhanced molecular graph representation for anti-breast cancer drug selection.
复制标题
DOI：
10.1186/s12859-022-04913-6
复制
发表时间：
2022-09-19
影响因子：
3
通讯作者：
中科院分区：
文献类型：
--
作者：
乳腺癌是目前世界上死亡率较高的癌症之一。抗乳腺癌药物的生物学研究主要集中在雌激素受体α（ER）的活性、药代动力学特性和化合物的安全性上，然而，这是一个昂贵且耗时的过程。深度学习的发展带来了有效促进乳腺癌候选药物选择的潜力。在本文中，我们提出了一种抗乳腺癌药物选择方法，利用门控图神经网络（ABCD-GGNN）拓扑增强候选药物的分子表示。通过为每个不同的化合物构建原子级图，ABCD-GGNN可以拓扑地学习候选药物的隐式结构和子结构特征，然后将表示与显式离散分子描述符整合以生成分子级表示。因此，ABCD-GGNN的代表性可以归纳地预测每个候选药物的ER、药代动力学特性和安全性。最后，我们设计了一个排序算子，其输入是预测的属性，以便统计选择合适的药物治疗乳腺癌。在我们收集的抗乳腺癌候选药物数据集上进行的大量实验表明，我们提出的方法在预测ER以及化合物的药代动力学特性和安全性方面优于所有其他代表性方法。扩展的结果分析表明，我们设计的算子的效率和生物合理性，计算候选药物的排名从预测的属性。在本文中，我们提出了ABCD-GGNN表示方法，有效地集成了分子的拓扑结构和亚结构特征与离散分子描述符。应用排序算子，预测的性质有效地促进了针对乳腺癌的候选药物选择。在线版本包含补充材料，可通过10.1186/s12859-022-04913-6获得。
Breast cancer is currently one of the cancers with a higher mortality rate in the world. The biological research on anti-breast cancer drugs focuses on the activity of estrogen receptors alpha (ER), the pharmacokinetic properties and the safety of the compounds, which, however, is an expensive and time-consuming process. Developments of deep learning bring potential to efficiently facilitate the candidate drug selection against breast cancer. In this paper, we propose an Anti-Breast Cancer Drug selection method utilizing Gated Graph Neural Networks (ABCD-GGNN) to topologically enhance the molecular representation of candidate drugs. By constructing atom-level graphs through atomic descriptors for each distinct compound, ABCD-GGNN can topologically learn both the implicit structure and substructure characteristics of a candidate drug and then integrate the representation with explicit discrete molecular descriptors to generate a molecule-level representation. As a result, the representation of ABCD-GGNN can inductively predict the ER, the pharmacokinetic properties and the safety of each candidate drug. Finally, we design a ranking operator whose inputs are the predicted properties so as to statistically select the appropriate drugs against breast cancer. Extensive experiments conducted on our collected anti-breast cancer candidate drug dataset demonstrate that our proposed method outperform all the other representative methods in the tasks of predicting ER, and the pharmacokinetic properties and safety of the compounds. Extended result analysis demonstrates the efficiency and biological rationality of the operator we design to calculate the candidate drug ranking from the predicted properties. In this paper, we propose the ABCD-GGNN representation method to efficiently integrate the topological structure and substructure features of the molecules with the discrete molecular descriptors. With a ranking operator applied, the predicted properties efficiently facilitate the candidate drug selection against breast cancer. The online version contains supplementary material available at 10.1186/s12859-022-04913-6.
登录
查看更多内容
影响因子：
4.5
作者：
Haneczok J;Delijewski M
通讯作者：
Delijewski M
影响因子：
3.9
作者：
Gao, Yue;Fu, Xiangling;Wang, Yi
通讯作者：
Wang, Yi
揭示 microRNA/lncRNA 在表征乳腺癌亚型和预后中的作用
影响因子：
3
作者：
Li X;Truong B;Xu T;Liu L;Li J;Le TD
通讯作者：
Le TD
影响因子：
3
作者：
Hajiloo M;Damavandi B;Hooshsadat M;Sangi F;Mackey JR;Cass CE;Greiner R;Damaraju S
通讯作者：
Damaraju S
影响因子：
5.6
作者：
Li, Xinhao;Fourches, Denis
通讯作者：
Fourches, Denis