Butt Ahmad Hassan, Alkhalifah Tamim, Alturise Fahad, Khan Yaser Daanial
Department of Computer Science, Faculty of Computing & Information Technology, University of the Punjab, Lahore 54000, Pakistan.
Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass 51921, Qassim, Saudi Arabia.
Diagnostics (Basel). 2023 Jun 1;13(11):1940. doi: 10.3390/diagnostics13111940.
Hormone-binding proteins (HBPs) are specific carrier proteins that bind to a given hormone. A soluble carrier hormone binding protein (HBP), which can interact non-covalently and specifically with growth hormone, modulates or inhibits hormone signaling. HBP is essential for the growth of life, despite still being poorly understood. Several diseases, according to some data, are caused by HBPs that express themselves abnormally. Accurate identification of these molecules is the first step in investigating the roles of HBPs and understanding their biological mechanisms. For a better understanding of cell development and cellular mechanisms, accurate HBP determination from a given protein sequence is essential. Using traditional biochemical experiments, it is difficult to correctly separate HBPs from an increasing number of proteins because of the high experimental costs and lengthy experiment periods. The abundance of protein sequence data that has been gathered in the post-genomic era necessitates a computational method that is automated and enables quick and accurate identification of putative HBPs within a large number of candidate proteins. A brand-new machine-learning-based predictor is suggested as the HBP identification method. To produce the desirable feature set for the method proposed, statistical moment-based features and amino acids were combined, and the random forest was used to train the feature set. During 5-fold cross validation experiments, the suggested method achieved 94.37% accuracy and 0.9438 F1-scores, respectively, demonstrating the importance of the Hahn moment-based features.
激素结合蛋白（HBPs）是一类与特定激素结合的特异性载体蛋白。一种可溶性载体激素结合蛋白（HBP），它能与生长激素进行非共价且特异性的相互作用，从而调节或抑制激素信号传导。尽管人们对HBP的了解仍然有限，但它对生命的生长至关重要。根据一些数据，几种疾病是由异常表达的HBP引起的。准确识别这些分子是研究HBP的作用及其生物学机制的第一步。为了更好地理解细胞发育和细胞机制，从给定的蛋白质序列中准确测定HBP至关重要。使用传统的生化实验，由于实验成本高和实验周期长，很难从越来越多的蛋白质中正确分离出HBP。在后基因组时代积累的大量蛋白质序列数据需要一种自动化的计算方法，以便能够在大量候选蛋白质中快速准确地识别出假定的HBP。一种全新的基于机器学习的预测器被建议作为HBP的识别方法。为了为所提出的方法生成理想的特征集，将基于统计矩的特征和氨基酸相结合，并使用随机森林对该特征集进行训练。在5折交叉验证实验中，所提出的方法分别达到了94.37%的准确率和0.9438的F1分数，证明了基于哈恩矩的特征的重要性。
