State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University, 100191 Beijing, P. R. China.
Stonewise, No. 19 Zhongguancun Street, Haidian District, 100080 Beijing, P. R. China.
J Chem Inf Model. 2021 Jan 25;61(1):1-6. doi: 10.1021/acs.jcim.0c00867. Epub 2020 Dec 28.
Molecular scaffolds are widely used in drug design. Many methods and tools have been developed to utilize the information in scaffolds. Scaffold diversification is frequently used by medicinal chemists in tasks such as lead compound optimization, but tools for scaffold diversification are still lacking. Here, we propose AIScaffold (https://iaidrug.stonewise.cn), a web-based tool for scaffold diversification using the deep generative model. This tool can perform large-scale (up to 500,000 molecules) diversification in several minutes and recommend the top 500 (top 0.1%) molecules. Features such as site-specific diversification are also supported. This tool can facilitate the scaffold diversification process for medicinal chemists, thereby accelerating drug design.
分子骨架在药物设计中被广泛应用。许多方法和工具已经被开发出来，以利用骨架中的信息。骨架多样化经常被药物化学家用于先导化合物优化等任务，但骨架多样化的工具仍然缺乏。在这里，我们提出了 AIScaffold（https://iaidrug.stonewise.cn），这是一个使用深度生成模型进行骨架多样化的基于网络的工具。这个工具可以在几分钟内对大规模（高达 50 万个分子）进行多样化，并推荐前 500 个（前 0.1%）分子。还支持特定部位的多样化等功能。这个工具可以为药物化学家提供便利，从而加速药物设计。
