Finding Cancer-Related Gene Combinations Using a Molecular Evolutionary Algorithm

Abstract

High-throughput data such as microarrays make it possible to investigate the molecular-level mechanism of cancer more efficiently. Computational methods boost the microarray analysis by managing large and complex data systematically. However, combinatorial interactions among genes have not been considered as a unit of the analysis since previous methods mainly focus on a whole gene or a single isolated gene. Here, we introduce a molecular evolutionary algorithm called probabilistic library model (PLM). In the PLM, library elements are generated from gene combinations. An evolutionary procedure is adopted to learn the probabilistic distribution of training samples. We apply the PLM to prostate cancer microarray data. The experimental results show that the PLM classifiers perform better than conventional methods such as neural networks and decision trees in accuracy. We also examine the evolved library to find cancer-related gene combinations.

Research on the Design of Parallel Hypernetworks Model Based on Hadoop Cloud Computing Platform

“…Hypernetworks is quite similar to mankind's cognitive learning process and can mimic mankind's cognition model. Indeed, Hypernetworks model has been successfully applied in plenty of fields, such as stock prediction [7], multimoding information retrieval [8], and prostatic cancer classification [9].…”

“…There are two typical methods of Hypernetworks in process of evolutionary learning, based on alternative evolutionary learning algorithm and evolutionary learning algorithm of gradient descent [4][5][6][7]. In this paper, based on alternative evolutionary learning algorithm, its advantage lies in exploring bigger solution space in learning process of Hypernetworks.…”

“…4) Calculating adaptive value of each hyperedge As for every data sample in collection X c , respectively calculate whether it matches every hyperedge ei or not (if the value of each attribute in data sample equals value of corresponding attribute in hyperedge, they match, otherwise they do not). If hyperedge matches train sample data and category of hyperedge equals train data sample, set adaptive value of hy-Similarly, as for each data sample in collection X w , respectively calculate whether it matches every hyperedge ei or not; if hyperedge matches train sample data and category of hyperedge equals train data sample, set adaptive value of hyperedge ei |Y| 1; if hyperedge matches train sample data yet category of hyperedge does not equal train data sample, set adaptive value of hyperedge ei 1, among which |Y| represents the number of classification.…”