Network algorithms

Freeman, J. A., Skapura, D. M. Neural Networks Algorithms, Applications and Programming Techniques, Computation and Neural systems Series. Addison Wesley Publishing Company, 1991... 

Description of function and network algorithms used for gene network visualization... 

J.A. Freeman and D.M. Skapura, Neural Networks, Algorithms, Applications and Programming Techniques. Addison-Wesley, Reading, MA, 1991. 

The specificity determinants surrounding the tyrosine phospho-acceptor sites have been determined by various procedures. In PTK assays using various substrates, it was determined that glutamic residues of the N-terminal or C-terminal side of the acceptor are often preferred. The substrate specificity of PTK catalytic domains has been analyzed by peptide library screening for prediction of the optimal peptide substrates. Finally, bioinformatics has been applied to identify phospho-acceptor sites in proteins of PTKs by application of a neural network algorithm. 

MacKay s textbook [114] offers not only a comprehensive coverage of Shannon s theory of information but also probabilistic data modeling and the mathematical theory of neural networks. Artificial NN can be applied when problems appear with processing and analyzing the data, with their prediction and classification (data mining). The wide range of applications of NN also comprises optimization issues. The information-theoretic capabilities of some neural network algorithms are examined and neural networks are motivated as statistical models [114]. 

MetaBase is a curated database of human protein-protein and protein-DNA interactions, transcriptional factors, signaling, metabolism and bioactive molecules. MetaCore provides intuitive tools for data visualization, mapping and exchange, multiple networking algorithms and data mining. 

R. J. H. Waddell, N. NicDaeid and D. Littlejohn, Classification of ecstasy tablets using trace metal analysis with the application of chemometric procedures and artificial neural networks algorithms. Analyst, 129(3), 2004, 235-240. 

Case (a) may lead to parallel computations of the independent subproblems. Case (b) allows the use of special-purpose algorithms (e.g., generalized network algorithms), while case (c) invokes special structure from the convexity point of view that can be useful for the decomposition of non-convex optimization problems Floudas et al. (1989). 

Mian S, Ball G, Hornbuckle J, et al. A prototype methodology combining surface-enhanced laser desorption/ionization protein chip technology and artificial neural network algorithms to predict the chemoresponsiveness of breast cancer cell lines exposed to Paclitaxel and Doxorubicin under in vitro conditions. Proteomics 2003 3(9) 1725-1737. 

Fig. 2. Phylogenetics of fS2-AR haplotypes. Each circle represents a haplotype with an area that correlates with its frequency in the test population. Sections within each circle show the distribution by race. Connecting lines solid black, single-site differences solid blue, two-site differences dashed, more than two-site differences. Analysis was by the minimum spanning network algorithm. (See Color Plate 5 following p. 148 reprinted, with permission, from ref. 3.)...

Products/technologies Has delivered various applications, including combinatorial chemistry predictions, by use of five neural network algorithms for building predictive models. 

Yang, Honig [204] PrISM Multiple structures are aligned, and the most appropriate template is used for each segment of the target to be built. Loops are built ah initio and side chains are built using the template or based on mainchain torsions and a neural network algorithm. 

An automated FTP service was used to obtain the predictions for all of our 168 integral membrane proteins by using the Rost et al. method [9]. A total of 11870 residues were correctly predicted in the TMH conformations, 2436 residues were overpredicted, 2512 residues were underpredicted, while 50335 residues were correctly predicted not to be in the TMH conformation. One of many different performance parameter that can be constructed by using these data is the Aj] parameter (Methods). Its value is A m = 0.656, which is inferior to our value of 0.712 (Table 9) for the same parameter. However, when tested on the subset of 63 proteins used by Rost et al. [9] the Ajj parameter, calculated from predictions returned by automated service, becomes 0.733, which is comparable to our value of Ajj = 0.740 for the same subset of proteins (Table 9). Similar test on the subset of 105 proteins, never before seen in the training process for the neural network algorithm, gave quite a low value of Ajj = 0.610 for the Rost et al. method [9]. That value is lower than our value of Ajj = 0.682 for the same subset of 105 proteins (Table 9). All of 63 proteins selected by Rost et al. [9] are also predicted as membrane proteins, but their method does not recognize 2 out of 105 membrane proteins selected by us. Underprediction of membrane proteins is due to serious underprediction of transmembrane helices 50 of observed 419 TMH are underpredicted and 11 overpredicted by Rost et al. [9]. For comparison our Table 9 results (row f) for Aj are obtained for the case of 21 underpredicted and 25 overpredicted TMH in the same test set of 105 proteins. 

It is much less expensive in computer time than a neural network algorithm. 

---