DNA-Stabilized Silver Nanocluster Design via Regularized Variational Autoencoders
DNA-Stabilized Silver Nanocluster Design via Regularized Variational Autoencoders
复制标题
通过正则化变分自动编码器设计 DNA 稳定的银纳米簇
DOI：
10.1145/3534678.3539032
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Bogdanov, Petko
中科院分区：
文献类型：
--
作者：
Moomtaheen, Fariha;Killeen, Matthew;Oswald, James;Gonzàlez-Rosell, Anna;Mastracco, Peter;Gorovits, Alexander;Copp, Stacy M.;Bogdanov, Petko
DNA稳定的银纳米团簇（AgN-DNA）是一类由10-30个银原子通过短的合成DNA模板链结合在一起组成的纳米材料。AgN-DNA具有体积小、与DNA天然相容、荧光亮（吸收光并重新发射不同颜色的光）等优点，是一种很有前途的生物传感器和荧光团。DNA模板的序列充当AgN-DNA的“基因组”，调节封装的银纳米团簇的大小，从而调节其荧光颜色。然而，目前对AgN-DNA基因组的了解仍然有限。只有少数DNA序列产生高荧光AgN-DNA，庞大的DNA链和复杂的DNA-银相互作用使得使用第一原理化学计算来理解和设计AgN-DNA具有挑战性。因此，研究这些纳米材料的研究人员面临的一个主要挑战是开发方法，采用观测数据研究AgN-DNAs设计新的nanoclusters为目标application.In这项工作中，我们提出了一种方法来设计AgN-DNAs采用变分自编码器（VAE）作为生成模型。具体来说，我们采用了基于LSTM的β-VAE架构，并将其潜在空间正则化，以与AgN-DNA属性（如颜色和亮度）相关联。正则化是自适应的倾斜样本分布的可用观测数据沿着我们的设计轴的属性。我们采用我们的模型设计的AgN-DNA在近红外（NIR）波段，其中相对较少的AgN-DNA已被观察到。湿实验室实验验证，当用于设计新的AgN-DNA时，我们的模型显着地将AgN-DNA颜色的分布向NIR方向移动，同时实现明亮的荧光。这项工作表明，基于VAE的生成模型非常适合设计具有多种目标特性的AgN-DNA，具有显著的潜力，可以推动这些纳米材料在生物成像，生物传感和其他关键技术方面的应用。
DNA-stabilized silver nanoclusters (AgN-DNAs) are a class of nanomaterials comprised of 10-30 silver atoms held together by short synthetic DNA template strands. AgN-DNAs are promising biosensors and fluorophores due to their small sizes, natural compatibility with DNA, and bright fluorescence---the property of absorbing light and re-emitting light of a different color. The sequence of the DNA template acts as a "genome" for AgN-DNAs, tuning the size of the encapsulated silver nanocluster, and thus its fluorescence color. However, current understanding of the AgN-DNA genome is still limited. Only a minority of DNA sequences produce highly fluorescent AgN-DNAs, and the bulky DNA strands and complex DNA-silver interactions make it challenging to use first principles chemical calculations to understand and design AgN-DNAs. Thus, a major challenge for researchers studying these nanomaterials is to develop methods to employ observational data about studied AgN-DNAs to design new nanoclusters for targeted applications.In this work, we present an approach to design AgN-DNAs by employing variational autoencoders (VAEs) as generative models. Specifically, we employ an LSTM-based β-VAE architecture and regularize its latent space to correlate with AgN-DNA properties such as color and brightness. The regularization is adaptive to skewed sample distributions of available observational data along our design axes of properties. We employ our model for design of AgN-DNAs in the near-infrared (NIR) band, where relatively few AgN-DNAs have been observed to date. Wet lab experiments validate that when employed for designing new AgN-DNAs, our model significantly shifts the distribution of AgN-DNA colors towards the NIR while simultaneously achieving bright fluorescence. This work shows that VAE-based generative models are well-suited for the design of AgN-DNAs with multiple targeted properties, with significant potential to advance the promising applications of these nanomaterials for bioimaging, biosensing, and other critical technologies.
登录
查看更多内容
DNA稳定的荧光银簇中的魔术数字导致魔术色。
DOI：
10.1021/jz500146q
发表时间：
2014-03-20
期刊：
The journal of physical chemistry letters
影响因子：
--
作者：
Copp SM;Schultz D;Swasey S;Pavlovich J;Debord M;Chiu A;Olsson K;Gwinn E
通讯作者：
Gwinn E
DOI：
--
发表时间：
2021-09
期刊：
--
影响因子：
--
作者：
Gabriele Corso;Rex Ying;Michal P'andy;Petar Velivckovi'c;J. Leskovec;P. Lio’
通讯作者：
Gabriele Corso;Rex Ying;Michal P'andy;Petar Velivckovi'c;J. Leskovec;P. Lio’
影响因子：
4.7
作者：
通讯作者：
--
影响因子：
4.3
作者：
Stephen Woloszynek;Zhengqiao Zhao;Jian Chen;G. Rosen
通讯作者：
Stephen Woloszynek;Zhengqiao Zhao;Jian Chen;G. Rosen