相关实验视频
Updated: Jun 12, 2025
06:35
Basics of Multivariate Analysis in Neuroimaging Data
Published on: July 24, 2010
16.8K
基于神经指纹模型的不确定性分析
Christian W Feldmann1, Jochen Sieg1, Miriam Mathea1
1BASF SE, Ludwigshafen, Germany. miriam.mathea@basf.com.
Faraday discussions
|September 25, 2024
概括
神经指纹增强了机器学习模型中的不确定性估计,用于分子性质预测. 将它们与随机森林等经典方法相结合,可以提供可靠的预测和强大的不确定性量化.
科学领域:
- 计算化学和化学信息学
- 机器学习在药物发现中的应用.
- 定量结构-活动关系 (QSAR) 建模.
背景情况:
- 机器学习模型越来越多地用于预测分子性质.
- 准确的不确定性估计对于现实应用至关重要,特别是在药物发现和化学安全方面.
- 图形神经网络 (GNN) 为学习分子表示提供了一个强大的方法.
研究的目的:
- 评估基于神经指纹的机器学习模型的不确定性估计.
- 将纯图形神经网络 (GNN) 与用神经指纹增强的经典机器学习算法进行比较.
- 研究将GNN提取的神经指纹集成到已知的更好的概率校准模型中.
主要方法:
- 纯GNN (Chemprop) 与使用神经指纹的经典方法 (随机森林,支持矢量分类器) 的比较.
- 利用了19个Toxcast数据集,代表了现实世界的化学预测挑战.
- 探索不同的分子表示和概率校准技术.
主要成果:
- 使用古典方法的神经指纹显示,与本地Chemprop.com相比,预测性能略有下降.
- 这些混合模型提供了显著改善的不确定性估计.
- 对于分布外的分子,不确定性估计仍然很强.
- 支持矢量分类器 (SVC) 与神经或指纹计数相结合,显示出有希望的性能.
结论:
- 神经指纹与经典机器学习相结合,特别是随机森林和SVC,为可靠的分子性质预测提供了一种可行的方法,可靠的不确定性估计.
- 这些方法适用于工业应用,要求准确性和可靠的不确定性量化.
- 校准的Chemprop和神经指纹增强的经典模型在考虑预测准确性和不确定性时提供了可比的性能.
相关概念视频
00:59Uncertainty: Overview
529
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
529
00:59Propagation of Uncertainty from Random Error
656
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
656