Modeling Colon Cancer Gene Logic Network With mRNA Microarray Data / 生物化学与生物物理进展

Analysis of cellular pathways and networks in terms of logic relations is important to decipher the networks of molecular interactions that underlie cellular function.A computational approach for identifying lower and higher order gene logic associations was presented on the base of graph coloring theory and applied it to the colon cancer mRNA microarray data.Then the logic relationships of 51 oncogenes and cancer suppressor genes are analyzed and the logic association network of them was constructed.The signal pathway of TGF? from the network model was found and verified by the colon cancer pathway of KEGG.The model reveals many higher order logic relationships of cancer genes.These relationships illustrate the complexities that arise in cancer cellular networks because of interacting pathways.The results show that this method is feasible and is expected to give a reference to the medical molecular biologist.

Research on EEG classification with evolving cascade neural networks / 生物医学工程学杂志

To correctly classify EEG with different mental tasks, a new learning algorithm for Evolving Cascade Neural Networks (ECNNs) is described to avoid over-fitting of a neural network due to noise and redundant features. The learning algorithm calculates the value of a fitness function on validate set and accordingly updates the connection weights on training set. The learning algorithm uses the regularity criterion for selecting the neurons with relevant connection. If the value Cr calculated for the rth neuron is less than the value Cr-1 calculated for the previous (r-1) neuron, the features that feed the rth neuron are relevant, else they are irrelevant. An ECNN starts to learn with one input node and then, adding new inputs as well as new hidden neurons, evolves it. The trained ECNN has a nearly minimal number of input and hidden neurons as well as connections. The algorithm is applied to classify EEG with two mental tasks. The trained ECNN has correctly classified 83.1% of the testing segments. It shows a better result, compared with a standard BP network.

A logistic cellular automaton for simulating tumor growth / 生物医学工程学杂志

This paper focuses on a differential equation logistic model simulating tumor growth. We design a kind of tumor dynamic growth model with one-dimensional cellular automata. A discrete logistic model is developed from the continuous logistic model. Based on others' work, we design discrete mathematical growth dynamic model with cellular automaton. In terms of discrete model, we design stochastic evolving rules of cellular automaton. And this paper simulates the tumor growth dynamic model with cellular automata. The theoretic analysis and results of cellular automaton model are in agreement with data from the ideal differential equation logistic growth of cancer.