Prediction of the coupling specificity of GPCRs to four families of G-proteins using hidden Markov models and artificial neural networks
Prediction of the coupling specificity of GPCRs to four families of G-proteins using hidden Markov models and artificial neural networks
复制标题
DOI：
10.1093/bioinformatics/bti679
复制
发表时间：
2005-11-15
期刊：
影响因子：
5.8
通讯作者：
Hamodrakas, SJ
中科院分区：
文献类型：
--
作者：
Sgourakis, NG;Bagos, PG;Hamodrakas, SJ
动机：G蛋白偶联受体是一类主要的真核细胞表面受体。它们功能的一个非常重要的方面是与四个 G 蛋白家族成员的特异性相互作用（偶联）。单个 GPCR 可能与多个 G 蛋白家族的成员相互作用（混杂耦合）。迄今为止，所有已发表的预测 GPCR 耦合特异性的方法都仅限于三个主要耦合组 G(i/o)、G(q/11) 和 G(s)，不包括 G(12/13) 耦合或其他混杂受体。 结果：我们提出了一种结合隐马尔可夫模型和前馈人工神经网络的方法来克服这些限制，同时产生当前可用的最准确的预测。使用最新的精选数据集，我们的方法在 5 倍交叉验证测试中产生 94% 的正确分类率。该方法还预测混杂的耦合偏好，包括与 G(12/13) 的耦合，而与其他方法不同的是，当遇到非 GPCR 序列时，可以避免过度预测（误报）。
Motivation: G-protein coupled receptors are a major class of eukaryotic cell-surface receptors. A very important aspect of their function is the specific interaction (coupling) with members of four G-protein families. A single GPCR may interact with members of more than one G-protein families (promiscuous coupling). To date all published methods that predict the coupling specificity of GPCRs are restricted to three main coupling groups G(i/o), G(q/11) and G(s), not including G(12/13)-coupled or other promiscuous receptors.Results: We present a method that combines hidden Markov models and a feed-forward artificial neural network to overcome these limitations, while producing the most accurate predictions currently available. Using an up-to-date curated dataset, our method yields a 94% correct classification rate in a 5-fold cross-validation test. The method predicts also promiscuous coupling preferences, including coupling to G(12/13), whereas unlike other methods avoids overpredictions (false positives) when non-GPCR sequences are encountered.