Baldi P, Chauvin Y
Division of Biology and JPL California Institute of Technology, Pasadena 91125, USA.
Proc Int Conf Intell Syst Mol Biol. 1995;3:39-47.
Hidden Markov Models (HMMs) are useful in a number of tasks in computational molecular biology, and in particular to model and align protein families. We argue that HMMs are somewhat optimal within a certain modeling hierarchy. Single first order HMMs, however, have two potential limitations: a large number of unstructured parameters, and a built-in inability to deal with long-range dependencies. Hybrid HMM/Neural Network (NN) architectures attempt to overcome these limitations. In hybrid HMM/NN, the HMM parameters are computed by a NN. This provides a reparametrization that allows for flexible control of model complexity, and incorporation of constraints. The approach is tested on the immunoglobulin family. A hybrid model is trained, and a multiple alignment derived, with less than a fourth of the number of parameters used with previous single HMMs. To capture dependencies, however, one must resort to a larger hybrid model class, where the data is modeled by multiple HMMs. The parameters of the HMMs, and their modulation as a function of input or context, is again calculated by a NN.
隐马尔可夫模型（HMM）在计算分子生物学的许多任务中都很有用，尤其适用于对蛋白质家族进行建模和比对。我们认为，在特定的建模层次结构中，HMM在某种程度上是最优的。然而，单一的一阶HMM有两个潜在的局限性：大量无结构的参数，以及内在的处理长程依赖关系的能力不足。混合HMM/神经网络（NN）架构试图克服这些局限性。在混合HMM/NN中，HMM参数由NN计算得出。这提供了一种重新参数化方式，允许灵活控制模型复杂度并纳入约束条件。该方法在免疫球蛋白家族上进行了测试。训练了一个混合模型，并得出了一个多重比对结果，所使用的参数数量不到先前单一HMM的四分之一。然而，为了捕捉依赖关系，必须采用更大的混合模型类别，其中数据由多个HMM建模。HMM的参数及其作为输入或上下文函数的调制再次由NN计算得出。
