Protein Secondary Structure Modelling with Probabilistic Networks

In this paper we study the performance of probabilistic networks in the context of protein sequence analysis in molecular biology. Speci cally, we report the results of our initial experiments applying this framework to the problem of protein secondary structure prediction. One of the main advantages of the probabilistic approach we describe here is our ability to perform detailed experiments where we can experiment with di erent models. We can easily perform local substitutions (mutations) and measure (probabilistically) their e ect on the global structure. Window-based methods do not support such experimentation as readily. Our method is e cient both during training and during prediction, which is important in order to be able to perform many experiments with di erent networks. We believe that probabilistic methods are comparable to other methods in prediction quality. In addition, the predictions generated by our methods have precise quantitative semantics which is not shared by other classi cation methods. Speci cally, all the causal and statistical independence assumptions are made explicit in our networks thereby allowing biologists to study and experiment with di erent causal models in a convenient manner.