Neural network packing

M. Vieth, A. Kolinsky, J. Skolnicek, and A. Sikorski, Prediction of protein secondary structure by neural networks, encoding short and long range patterns of amino acid packing. Acta Biochim. Pol., 39 (1992) 369-392. 

Table 10.1 summarizes neural network applications for protein structure prediction. Protein secondary structure prediction is often used as the first step toward understanding and predicting tertiary structure because secondary structure elements constitute the building blocks of the folding units. An estimated 90% or so of the residues in most proteins are involved in three classes of secondary structures, the a-helices, p-strands or reverse turns. Related to the secondary structure prediction are also the prediction of solvent accessibility, transmembrane helices, and secondary structure content (10.2). Neural networks have also been applied to protein tertiary structure prediction, such as the prediction of the backbones or side-chain packing, and to structural class prediction (10.3). 

Milik et al. (1995) developed a neural network system to evaluate side-chain packing in protein structures. Instead of using protein sequence as input to the neural network as in most other studies, protein structure represented by a side-chain-side-chain contact map was used. Contact maps of globular protein structures in the Protein Data Bank were scanned using 7x7 windows, and converted to 49 binary numbers for the neural network input. One output unit was used to determine whether the contact pattern is popular in... 

Milik, M., Kolinski, A. Skolnick, J. (1995). Neural network system for the evaluation of side-chain packing in protein structures. Protein Eng 8,225-36. 

Key words irregular object packing, evolutionary strategies, neural network. 

Lotei, T. and Bagheri Shouraki, S., 2004, Active learning method to solve Bin Packing problem. In Proc. of Neural Networks and Computational Intelligence (NCI 2004), 23-25 February 2004, Grindelwald, Switzerland, Paper No. 413-009. 

Analyses of large sets of structures have shown that the packing energy correlates reasonably with the molecular volume and also with the number of valence electrons in the molecule. In another approach, neural network techniques have been used to identify a correlation between molecular composition and sublimation enthalpy based on 60 compounds . The correlation is based on a 3-parameter model involving the number of carbon atoms C, the number of hydrogen bond donors HBD and hydrogen bond acceptors HBA (Eq. 8-2). 

MacMuixay, J.C. and Hhmnelblau, D.M. (1995). Modeling and control of a packed distillation column using artificial neural networks. Comp. Chem. Eng., 19,1077-1088. 

Charlton, M. H., Docherty, R., and Hutchings, M. G., Quantitative structure-sublimation enthalpy relationships studied by neural networks, theoretical crystal packing calculations and multilinear regression analysis, J. Chem. Soc. Perkin Trans. 2, 2203, 1995. 

The brain contains grey matter and white matter substances that are easily distinguished upon gross examination. Grey matter contains a densely packed network of neural cell bodies and associated glial cells, whereas white matter contains myelinated axonal tracts, relatively few neuronal cell bodies, and a supporting environment of glial cells. The entire brain is surrounded by cerebrospinal fluid contained within an extensive ventricular system that occupies approximately one-tenth of the total brain volume. The ventricular system supports the brain as well as the spinal cord, and provides nutrients to and removes waste products from the central nervous system. 

---