Refining Algorithms with Knowledge-Based Neural Networks: Improving the Chou-Fasman Algorithm for Protein Folding*
نویسندگان
چکیده
We describe a method for using machine learning to refine algorithms represented as generalized finite-state automata. The knowledge in an automaton is translated into a corresponding artificial neural network, and then refined by applying backpropagation to a set of examples. Our technique for translating an automaton into a network extends the KBANN algorithm, a system that translates a set of propositional, non-recursive rules into a corresponding neural network. The topology and weights of the neural network are set by KBANN so that the network represents the knowledge in the rules. We present the extended system, FSKBANN, which augments the KBANN algorithm to handle finite-state automata. We employ FSKBANN to refine the Chou-Fasman algorithm, a method for predicting how globular proteins fold. The Chou-Fasman algorithm cannot be elegantly formalized using non-recursive rules, but can be concisely described as a finite-state automaton. Empirical evidence shows that the refined algorithm FSKBANN produces is statistically significantly more accurate than both the original Chou-Fasman algorithm and a neural network trained using the standard approach. We also provide extensive statistics on the type of errors each of the three approaches makes and discuss the need for better definitions of solution quality for the protein-folding problem.
منابع مشابه
Using Knowledge-Based Neural Networks to Improve Algorithms: Re ning the Chou-Fasman Algorithm for Protein Folding
We describe a method for using machine learning to re ne algorithms represented as generalized nite-state automata. The knowledge in an automaton is translated into an arti cial neural network, and then re ned with backpropagation on a set of examples. Our technique for translating an automaton into a network extends kbann, a system that translates a set of propositional rules into a correspond...
متن کاملDesign and Implementation of a Neural Network For the Evaluation of Protein Secondary Structure Prediction Using the DSSP and Chou-Fasman Algorithms
Neural networks have conventionally been used to predict protein secondary structure. However, they have not been used to improve the predictions of existing methods. This paper presents the design and implementation of a neural network to refine secondary structure prediction using information obtained from the DSSP and Chou-Fasman algorithms. The network was trained with input patterns consis...
متن کاملProtein Folding: Symbolic Refinement Competes with Neural Networks
The Chou-Fasman Algorithm and its associated theory are non-learning methods to predict the secondary structure for proteins from the string of amino acids forming the protein. However, the overall accuracy of the predictions is not high and the predictions for the important structures are particularly low. Therefore, a range of methods have been used to improve the prediction of the secondary ...
متن کاملProtein Folding : Symbolic Re nement Competeswith Neural
The Chou-Fasman Algorithm and its associated theory are non-learning methods to predict the secondary structure for proteins from the string of amino acids forming the protein. However, the overall accuracy of the predictions is not high and the predictions for the important structures are particularly low. Therefore, a range of methods have been used to improve the prediction of the secondary ...
متن کاملA Differential Evolution and Spatial Distribution based Local Search for Training Fuzzy Wavelet Neural Network
Abstract Many parameter-tuning algorithms have been proposed for training Fuzzy Wavelet Neural Networks (FWNNs). Absence of appropriate structure, convergence to local optima and low speed in learning algorithms are deficiencies of FWNNs in previous studies. In this paper, a Memetic Algorithm (MA) is introduced to train FWNN for addressing aforementioned learning lacks. Differential Evolution...
متن کامل