Department of Biochemistry, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, 492001, India.
Department of Genetics, Department of Cell Developmental and Integrative Biology, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA.
BMC Bioinformatics. 2020 Oct 31;21(1):493. doi: 10.1186/s12859-020-03835-5.
Cytokines act by binding to specific receptors in the plasma membrane of target cells. Knowledge of cytokine-receptor interaction (CRI) is very important for understanding the pathogenesis of various human diseases-notably autoimmune, inflammatory and infectious diseases-and identifying potential therapeutic targets. Recently, machine learning algorithms have been used to predict CRIs. "Gold Standard" negative datasets are still lacking and strong biases in negative datasets can significantly affect the training of learning algorithms and their evaluation. To mitigate the unrepresentativeness and bias inherent in the negative sample selection (non-interacting proteins), we propose a clustering-based approach for representative negative sample selection.
We used deep autoencoders to investigate the effect of different sampling approaches for non-interacting pairs on the training and the performance of machine learning classifiers. By using the anomaly detection capabilities of deep autoencoders we deduced the effects of different categories of negative samples on the training of learning algorithms. Random sampling for selecting non-interacting pairs results in either over- or under-representation of hard or easy to classify instances. When K-means based sampling of negative datasets is applied to mitigate the inadequacies of random sampling, random forest (RF) together with the combined feature set of atomic composition, physicochemical-2grams and two different representations of evolutionary information performs best. Average model performances based on leave-one-out cross validation (loocv) over ten different negative sample sets that each model was trained with, show that RF models significantly outperform the previous best CRI predictor in terms of accuracy (+ 5.1%), specificity (+ 13%), mcc (+ 0.1) and g-means value (+ 5.1). Evaluations using tenfold cv and training/testing splits confirm the competitive performance.
A comparative analysis was performed to assess the effect of three different sampling methods (random, K-means and uniform sampling) on the training of learning algorithms using different evaluation methods. Models trained on K-means sampled datasets generally show a significantly improved performance compared to those trained on random selections-with RF seemingly benefiting most in our particular setting. Our findings on the sampling are highly relevant and apply to many applications of supervised learning approaches in bioinformatics.
细胞因子通过与靶细胞质膜上的特定受体结合而发挥作用。细胞因子-受体相互作用（CRI）的知识对于理解各种人类疾病的发病机制非常重要，特别是自身免疫、炎症和传染病，并确定潜在的治疗靶点。最近，机器学习算法已被用于预测 CRI。“金标准”阴性数据集仍然缺乏，而阴性数据集的强烈偏差会显著影响学习算法的训练及其评估。为了减轻阴性样本选择（非相互作用蛋白）中固有的代表性不足和偏差，我们提出了一种基于聚类的代表性阴性样本选择方法。
我们使用深度自动编码器来研究不同的采样方法对非相互作用对的训练和机器学习分类器性能的影响。通过使用深度自动编码器的异常检测能力，我们推断出不同类别的阴性样本对学习算法训练的影响。随机采样选择非相互作用对会导致难以或易于分类的实例过度或不足代表。当应用基于 K-均值的阴性数据集采样来减轻随机采样的不足时，随机森林（RF）与原子组成、物理化学-2 克和两种不同进化信息表示形式的组合特征集相结合，表现最佳。基于 10 个不同的阴性样本集的留一交叉验证（loocv）的平均模型性能，每个模型都用其进行训练，表明 RF 模型在准确性（+5.1%）、特异性（+13%）、mcc（+0.1）和 g-均值值（+5.1%）方面明显优于以前最好的 CRI 预测器。使用 10 倍 cv 和训练/测试分割的评估确认了竞争性能。
进行了比较分析，以使用不同的评估方法评估三种不同采样方法（随机、K-均值和均匀采样）对学习算法训练的影响。与随机选择相比，在 K-均值采样数据集上训练的模型通常表现出显著提高的性能-似乎在我们的特定环境中 RF 受益最大。我们对采样的发现非常相关，并且适用于生物信息学中许多监督学习方法的应用。
