Prediction of organismal viability upon exposure to a nanoparticle in varying environments─as fully specified at the molecular scale─has emerged as a useful figure of merit in the design of engineered nanoparticles. We build on our earlier finding that a bag of artificial neural networks (ANNs) can provide such a prediction when such machines are trained with a relatively small data set (with ca. 200 examples). Therein, viabilities were predicted by consensus using the weighted means of the predictions from the bags. Here, we confirm the accuracy and precision of the prediction of nanoparticle viabilities using an optimized bag of ANNs over sets of data examples that had not previously been used in the training and validation process. We also introduce the viability strip, rather than a single value, as the prediction and construct it from the viability probability distribution of an ensemble of ANNs compatible with the data set. Specifically, the ensemble consists of the ANNs arising from subsets of the data set corresponding to different splittings between training and validation, and the different bags (k-folds). A k−1k$\frac{k-1}{k}$ machine uses a single partition (or bag) of k – 1 ANNs each trained on 1/k of the data to obtain a consensus prediction, and a k-bag machine quorum samples the k possible k−1k$\frac{k-1}{k}$ machines available for a given partition. We find that with increasing k in the k-bag or k−1k$\frac{k-1}{k}$ machines, the viability strips become more normally distributed and their predictions become more precise. Benchmark comparisons between ensembles of 4-bag machines and 34$\frac{3}{4}$ fraction machines suggest that the 34$\frac{3}{4}$ fraction machine has similar accuracy while overcoming some of the challenges arising from divergent ANNs in the 4-bag machines.

中文翻译：

---

优化的人工神经网络袋可以预测暴露于纳米颗粒的生物体的生存能力

在不同环境中暴露于纳米颗粒时预测生物体的活力（在分子尺度上完全指定）已成为工程纳米颗粒设计中有用的品质因数。我们基于之前的发现，即当使用相对较小的数据集（大约 200 个示例）训练此类机器时，一包人工神经网络 (ANN) 可以提供此类预测。其中，使用袋子预测的加权平均值通过共识预测生存力。在这里，我们使用优化的 ANN 包对之前未在训练和验证过程中使用过的数据示例集来确认纳米颗粒活力预测的准确性和精确度。我们还引入了可行性条带，而不是单个值作为预测，并根据与数据集兼容的 ANN 集合的可行性概率分布来构建它。具体来说，该集合由来自数据集子集的 ANN 组成，这些子集对应于训练和验证之间的不同划分以及不同的包（k倍）。 Ak − 1k$\frac{k-1}{k}$机器使用k – 1 个 ANN的单个分区（或袋），每个 ANN 在 1/ k的数据上进行训练以获得一致预测，并且k袋机器群体对k 个可能的样本进行采样k − 1k$\frac{k-1}{k}$可用于给定分区的机器。我们发现随着k -bag中k 的增加或k − 1k$\frac{k-1}{k}$机器的存在，活力条变得更加正态分布，并且它们的预测变得更加精确。 4 袋机和 4 袋机组合之间的基准比较34$\frac{3}{4}$分数机表明34$\frac{3}{4}$分数机具有类似的精度，同时克服了 4 袋机中不同的 ANN 带来的一些挑战。