当前位置: X-MOL 学术Mol. Divers. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A multimodal deep learning-based drug repurposing approach for treatment of COVID-19
Molecular Diversity ( IF 3.8 ) Pub Date : 2020-09-30 , DOI: 10.1007/s11030-020-10144-9
Seyed Aghil Hooshmand 1, 2 , Mohadeseh Zarei Ghobadi 2 , Seyyed Emad Hooshmand 3 , Sadegh Azimzadeh Jamalkandi 4 , Seyed Mehdi Alavi 5 , Ali Masoudi-Nejad 1, 2
Affiliation  

Abstract

Recently, various computational methods have been proposed to find new therapeutic applications of the existing drugs. The Multimodal Restricted Boltzmann Machine approach (MM-RBM), which has the capability to connect the information about the multiple modalities, can be applied to the problem of drug repurposing. The present study utilized MM-RBM to combine two types of data, including the chemical structures data of small molecules and differentially expressed genes as well as small molecules perturbations. In the proposed method, two separate RBMs were applied to find out the features and the specific probability distribution of each datum (modality). Besides, RBM was used to integrate the discovered features, resulting in the identification of the probability distribution of the combined data. The results demonstrated the significance of the clusters acquired by our model. These clusters were used to discover the medicines which were remarkably similar to the proposed medications to treat COVID-19. Moreover, the chemical structures of some small molecules as well as dysregulated genes’ effect led us to suggest using these molecules to treat COVID-19. The results also showed that the proposed method might prove useful in detecting the highly promising remedies for COVID-19 with minimum side effects. All the source codes are accessible using https://github.com/LBBSoft/Multimodal-Drug-Repurposing.git

Graphic abstract



中文翻译:

一种基于多模式深度学习的药物再利用方法治疗 COVID-19

摘要

最近,已经提出了各种计算方法来寻找现有药物的新治疗应用。多模态受限玻尔兹曼机方法 (MM-RBM) 具有连接多模态信息的能力,可应用于药物再利用问题。本研究利用 MM-RBM 结合两种类型的数据,包括小分子和差异表达基因的化学结构数据以及小分子扰动。在所提出的方法中,应用了两个独立的 RBM 来找出每个数据(模态)的特征和特定概率分布。此外,RBM用于整合发现的特征,从而识别组合数据的概率分布。结果证明了我们的模型获得的集群的重要性。这些集群用于发现与提议的治疗 COVID-19 的药物非常相似的药物。此外,一些小分子的化学结构以及失调基因的影响使我们建议使用这些分子来治疗 COVID-19。结果还表明,所提出的方法可能被证明有助于以最小的副作用检测 COVID-19 的极有希望的补救措施。所有源代码都可以使用 https://github.com/LBBSoft/Multimodal-Drug-Repurposing.git 访问 一些小分子的化学结构以及失调基因的影响使我们建议使用这些分子来治疗 COVID-19。结果还表明,所提出的方法可能被证明有助于以最小的副作用检测 COVID-19 的极有希望的补救措施。所有源代码都可以使用 https://github.com/LBBSoft/Multimodal-Drug-Repurposing.git 访问 一些小分子的化学结构以及失调基因的影响使我们建议使用这些分子来治疗 COVID-19。结果还表明,所提出的方法可能被证明有助于以最小的副作用检测 COVID-19 的极有希望的补救措施。所有源代码都可以使用 https://github.com/LBBSoft/Multimodal-Drug-Repurposing.git 访问

图形摘要

更新日期:2020-09-30
down
wechat
bug