Deep-learning
图卷积网络在药物研发中的应用综述
尽管深度学习在很多领域在过去的几年取得了一定的成功,但是在分子信息和药物发现领域成功的应用依然有限。
适用于深层架构的结构化数据方面的最新进展为药物研究开辟了新的范例。
该篇从四个角度阐述了图神经网络在药物发现和分子信息领域的应用。1)分子属性和活性预测;2)相互作用预测;3)合成预测;4)从头药物设计。
最后总结了药物相关问题的代表性应用。讨论将图卷积网络应用于药物发现领域的当前挑战和未来可能性。
https://zhuanlan.zhihu.com/p/196763461
AI医药方向论文总结(包含DDI和DDS,重点分析药物联合预测)
https://blog.csdn.net/xiao_muyu/article/details/121786199
Deep learning 相互作用的深层预测模型
https://zhuanlan.zhihu.com/p/193649160
参考文献
[1] A multimodal deep learning framework for predicting drug-drug interaction events.
[2] Graph embedding on biomedical networks: methods, applications and evaluations.
BioSNAP: network
https://snap.stanford.edu/biodata/datasets/10001/10001-ChCh-Miner.html
https://github.com/topics/drug-similarity
Drug–drug similarity studies aim to find drugs which display similar pharmacological characteristics to the drug of interest and are driven by the hypothesis that similar drugs should be similar in mechanism of action, have similar side effect and be useful in treating a similar constellation of diseases.
https://www.sciencedirect.com/science/article/pii/S1386505618305963#:~:text=Drug–drug%20similarity%20studies%20aim%20to%20find%20drugs%20which,a%20similar%20constellation%20of%20diseases%20%5B%201%20%5D.