Protein-based neural networks

Combining the above properties of the protein repertoire of a cell strongly suggests that they behave as a nanoscale neural network. Indeed, the relatively simple reaction characteristic of proteins means that mathematical models of neural networks can describe the protein network more closely than one made of real neurons. 

Bray has demonstrated that a system consisting of just two transmembrane receptors sharing a ligand molecule on one side and a target protein which may be phosphorylated on the other side of the membrane, can in computer simulations be trained like a neural network (Fig. 2.5). The neural network analogy can also be used to explain how regulatory proteins often cluster to form functional units. 

---

Rost, B. (1996). PHD predicting one-dimensional protein structure by profile based neural networks. Method Enzymol. 266, 525-539. 

Maclin, R., and Shavlik J.W. (1993). Using knowledge-based neural network to improve algorithms Refining the Chou-Fasman algorithm for protein folding. Machine Learning 11, 195-215. 

Analysis, Vol. 266, R. F. Doolittle, Ed., Academic Press, San Diego, California, 1996, pp. 525-539. PHD Predicting One-Dimensional Protein Structure by Profile-Based Neural Networks. Available http //cubic.bioc.columbia.edu/predictprotein/. 

Figure 4 PHDsec profile-based neural network system for secondary structure prediction. From the multiple alignment (here guide sequence SH3 plus four other proteins al -a4, note lower case letters indicate deletions in the aligned sequence) a profile of amino acid occurrences is compiled. To the resulting 20 values at one particular position p in the protein (one column) three values are added the number of deletions and insertions, and the conservation weight (CW). 13 adjacent columns are used as input. The whole network system for. secondary structure prediction consists of three layers two network layers and one layer averaging over independently trained networks...

Neural networks have been applied to IR spectrum interpreting systems in many variations and applications. Anand [108] introduced a neural network approach to analyze the presence of amino acids in protein molecules with a reliability of nearly 90%. Robb and Munk [109] used a linear neural network model for interpreting IR spectra for routine analysis purposes, with a similar performance. Ehrentreich et al. [110] used a counterpropagation network based on a strategy of Novic and Zupan [111] to model the correlation of structures and IR spectra. Penchev and co-workers [112] compared three types of spectral features derived from IR peak tables for their ability to be used in automatic classification of IR spectra. 

Classification of Protein Structures Based on Convex Hull Representation by Integrated Neural Network. 

Emanuelsson, O., Nielsen, H., and von Heijne, G. (1999). ChloroP, a neural network-based method for predicting chloroplast transit peptides and their cleavage sites. Protein Sd. 8, 978—984. 

Fariselli, P. Casadio, R. (1996). HTP a neural network-based method for predicting the topology of helical transmembrane domains in proteins. Comput Appl Biosci 12,41-8. 

Ferran, E. A. Pflugfelder, B. (1993). A hybrid method to cluster protein sequences based on statistics and artificial neural networks. ComputAppl Biosci 9,671-80. 

Sun, Z., Rao, X., Peng, L. Xu, D. (1997). Prediction of protein supersecondary structures based on the artificial neural network method. Protein Eng 10,763-9. 

How have neural networks been used in genome informatics applications In Part II, we have summarized them based on the types of applications for DNA sequence analysis, protein structure prediction and protein sequence analysis. Indeed, the development of neural network applications over the years has resulted in many successful and widely used systems. Current state-of-the-art systems include those for gene recognition, secondary structure prediction, protein classification, signal peptide recognition, and peptide design, to name just a few. 

Jacoboni, I., Martelli, P. L., Fariselli, P., de Pinto, V., and Casadio, R. (2001). Prediction of the transmembrane regions of /3-barrel membrane proteins with a neural network-based predictor. Protein Sci. 10, 779-787. 

---