“bound drug/molecule”or “unbound drug/molecule” For clarity, the following terms will be used throughout this study: “bound drug/molecule” (or “unbound drug/molecule”) refers to the drug/molecule th
多限制分子采样分子优化 Multi-constraint Molecule Sampling for Molecule Optimization 摘要 挑战:face difficulties in simultaneously optimizing multiple drug properties. 方法:To address such challenges, we propose
A Deep Generative Model for Molecule Optimization via One FragmentModification 利用变分自编码器的生成模型 训练:输入两个对比的分子,生成断点,需要删除增加的片段 生成:从隐向量空间中采样 z , 和Mx一起计算出断点,和需要删除或添加的片段。 We first quantified the difference
Modof:A Deep Generative Model for Molecule Optimization via One FragmentModification 基于单片段修改的分子优化深度生成模型 paper and supplement metrics : A deep generative model for molecule optimization via one fragm
论文题目:Generating focused molecule libraries for drug discovery with recurrent neural networks scholar 引用:203 页数:12 发表时间:2017.12 发表刊物:ASC(American Chemical Society) Central Science 作者:Marwin H. S.
Decoder整体流程: DSP预测在哪个节点应该断开,并预测在该断开位点 n d n_d nd 是否应该有一个child node 或者多个 child node n c n_c nc 再预测这些child node的类型 x c x_c xc连接断开位点 n ∗ ( t ) n^{*}(t) n∗(t) 和这些 child node n c n_c nc【连接的键的选择、连接