arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.12368q-bio.BMcs.LG
收藏

利用条件生成模型生成具有目标性质的新分子

Generate Novel Molecules With Target Properties Using Conditional Generative Models

Abhinav Sagar

摘要:

最近,使用深度学习的药物发现吸引了很多关注,因为它具有明显的优势,如更高的效率,更少的人工猜测和更快的处理时间。在本文中,我们提出了一种新的神经网络产生的小分子类似的训练集。我们的网络由一个由bi-GRU层组成的编码器组成,用于将输入样本转换为潜在空间,预测器用于增强由1D-CNN层组成的编码器的能力,以及由uni-GRU层组成的解码器,用于从潜在空间表示重建样本。在潜在空间中的条件向量用于生成具有所需性质的分子。我们提出了用于训练我们的网络,实验细节和属性预测指标的损失函数。我们的网络优于以前的方法,使用分子量,LogP和药物相似性的定量估计作为评估指标。

英文摘要:

Drug discovery using deep learning has attracted a lot of attention of late as it has obvious advantages like higher efficiency, less manual guessing and faster process time. In this paper, we present a novel neural network for generating small molecules similar to the ones in the training set. Our network consists of an encoder made up of bi-GRU layers for converting the input samples to a latent space, predictor for enhancing the capability of encoder made up of 1D-CNN layers and a decoder comprised of uni-GRU layers for reconstructing the samples from the latent space representation. Condition vector in latent space is used for generating molecules with the desired properties. We present the loss functions used for training our network, experimental details and property prediction metrics. Our network outperforms previous methods using Molecular weight, LogP and Quantitative Estimation of Drug-likeness as the evaluation metrics.

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。

↑