Department of Computer and Systems Sciences, Stockholm University, Box 7003, SE-164 07 Kista, Sweden.
Department of Pharmaceutical Biosciences, Uppsala University, Box 591, SE-75124 Uppsala, Sweden.
J Chem Inf Model. 2020 Jun 22;60(6):2830-2837. doi: 10.1021/acs.jcim.0c00250. Epub 2020 May 15.
Predictive modeling is a cornerstone in early drug development. Using information for multiple domains or across prediction tasks has the potential to improve the performance of predictive modeling. However, aggregating data often leads to incomplete data matrices that might be limiting for modeling. In line with previous studies, we show that by generating predicted bioactivity profiles, and using these as additional features, prediction accuracy of biological endpoints can be improved. Using conformal prediction, a type of confidence predictor, we present a robust framework for the calculation of these profiles and the evaluation of their impact. We report on the outcomes from several approaches to generate the predicted profiles on 16 datasets in cytotoxicity and bioactivity and show that efficiency is improved the most when including the -values from conformal prediction as bioactivity profiles.
预测建模是药物早期开发的基石。利用来自多个领域或跨预测任务的信息，有可能提高预测建模的性能。然而，聚合数据通常会导致数据矩阵不完整，这可能会限制建模。与之前的研究一致，我们表明，通过生成预测的生物活性谱，并将其用作附加特征，可以提高生物终点预测的准确性。使用一致性预测（一种置信度预测器），我们提出了一种稳健的框架来计算这些谱并评估它们的影响。我们报告了在细胞毒性和生物活性的 16 个数据集上生成预测谱的几种方法的结果，并表明当将一致性预测的 - 值作为生物活性谱包含在内时，效率的提高最为显著。
