Faculty of Information Technology, Macau University of Science and Technology, Macau (SAR), China.
State Key Laboratory of Quality Research in Chinese Medicine/Macau Institute for Applied Research in Medicine and Health, Macau University of Science and Technology, Macau (SAR), China.
Pharmacol Res. 2020 Oct;160:105037. doi: 10.1016/j.phrs.2020.105037. Epub 2020 Jun 23.
In personalized medicine, many factors influence the choice of compounds. Hence, the selection of suitable medicine for patients with non-small-cell lung cancer (NSCLC) is expensive. To shorten the decision-making process for compounds, we propose a computationally efficient and cost-effective collaborative filtering method with ensemble learning. The ensemble learning is used to handle small-sample sizes in drug response datasets as the typical number of patients in a cancer dataset is very small. Moreover, the proposed method can be used to identify the most suitable compounds for patients without genetic data. To the best of our knowledge, this is the first method to provide effective recommendations without genetic data. We also constructed a reliable dataset that includes eight NSCLC cell lines and ten compounds that have been approved by the Food and Drug Administration. With the new dataset, the experimental results demonstrated that the dataset shift phenomenon that commonly occurs in practical biomedical data does not occur in this problem. The experimental results demonstrated that our proposed method can outperform two state-of-the-art recommender system techniques on both the NCI60 dataset and our new dataset. Our model can be applied to the prediction of drug sensitivity with less labor-intensive experiments in the future.
在个性化医疗中，许多因素会影响化合物的选择。因此，为非小细胞肺癌（NSCLC）患者选择合适的药物是昂贵的。为了缩短化合物的决策过程，我们提出了一种具有集成学习的计算高效且具有成本效益的协同过滤方法。集成学习用于处理药物反应数据集中的小样本量，因为癌症数据集中的典型患者数量非常少。此外，该方法可用于确定没有遗传数据的患者最适合的化合物。据我们所知，这是第一个在没有遗传数据的情况下提供有效建议的方法。我们还构建了一个可靠的数据集，其中包括八个 NSCLC 细胞系和十种已获得美国食品和药物管理局批准的化合物。使用新数据集，实验结果表明，在这个问题中不会出现实际生物医学数据中常见的数据集偏移现象。实验结果表明，我们的方法在 NCI60 数据集和我们的新数据集上均优于两种最先进的推荐系统技术。我们的模型可以应用于未来需要更少劳动密集型实验的药物敏感性预测。
