IEEE/ACM Trans Comput Biol Bioinform. 2023 May-Jun;20(3):1761-1773. doi: 10.1109/TCBB.2022.3215645. Epub 2023 Jun 5.
In silico machine learning based prediction of drug functions considering the drug properties would substantially enhance the speed and reduce the cost of identifying promising drug leads. The drug function prediction capability of different drug properties happens to be different. So assessing these is advantageous in drug discovery. The task of drug function prediction is multi-label in nature reason being, in case of several drugs, multiple functions are associated with a drug. A number of existing works have ignored this inherent multi-label nature of the problem in context of addressing the issue of class imbalance. In the present work, a computational framework named as BRMCF has been proposed for analysing the prediction capability of chemical and biological properties of drugs toward drug functions in view of multi-label nature of problem. It employs Binary Relevance (BR) approach along with five base classifiers for handling the multi-label prediction task and MLSMOTE for addressing the issue of class imbalance. The proposed framework has been validated and compared with BR, Classifier Chains (CC) and Deep Neural Network (DNN) method on four drug properties datasets: SMILES Strings (SS) dataset, 17 Molecular Descriptors (17MD) dataset, Protein Sequences (PS) dataset and drug perturbed Gene EXpression Profiles (GEX) dataset. The analysis of results shows that the proposed framework BRMCF has outperformed BR, CC and DNN method in terms of exact match ratio, precision, recall, F1-score, ROC-AUC which signifies the effectiveness of MLSMOTE. Further, assessment of prediction capability of different drug properties is done and they are ranked as SS GEX PS 17MD. Additionally, the visualization and analysis of drug function co-occurrences signify the appropriateness of the proposed framework for drug function co-occurrence detection and in signaling the new possible drug leads where the detection rate varies from 94.34% to 99.61%.
基于药物特性的基于计算机的机器学习药物功能预测将大大提高识别有前途药物先导的速度和降低成本。不同药物特性的药物功能预测能力碰巧有所不同。因此，评估这些特性在药物发现中是有利的。药物功能预测任务本质上是多标签的，因为在几种药物的情况下，一种药物与多种功能相关。许多现有的工作在解决类不平衡问题时忽略了这个问题的固有多标签性质。在本工作中，提出了一个名为 BRMCF 的计算框架，用于分析药物的化学和生物学性质对药物功能的预测能力，考虑到问题的多标签性质。它采用二元相关性（BR）方法和五个基本分类器来处理多标签预测任务，并使用 MLSMOTE 来解决类不平衡问题。在四个药物特性数据集（SMILES 字符串（SS）数据集、17 个分子描述符（17MD）数据集、蛋白质序列（PS）数据集和药物扰动基因表达谱（GEX）数据集）上验证并比较了所提出的框架与 BR、分类器链（CC）和深度神经网络（DNN）方法。结果分析表明，所提出的框架 BRMCF 在精确匹配率、精度、召回率、F1 得分、ROC-AUC 方面均优于 BR、CC 和 DNN 方法，这表明了 MLSMOTE 的有效性。此外，对不同药物特性的预测能力进行了评估，并对它们进行了排序，结果为 SS > GEX > PS > 17MD。此外，药物功能共现的可视化和分析表明，该框架适用于药物功能共现检测和信号新的可能药物先导，检测率从 94.34%到 99.61%不等。
