Real-Time Gene-Expression Extraction with Fast Classification (FC) Networks

Fast Classification (FC) networks were inspired by a biologically plausible mechanism for short term memory where learning occurs instantaneously. Both weights and the topology for an FC network are mapped directly from the training samples by using a prescriptive training scheme. Only two presentations of the training data are required to train an FC network. Compared with iterative learning algorithms such as Back-propagation (which may require many hundreds of presentations of the training data), the training of FC networks is extremely fast and learning convergence is always guaranteed. Thus FC networks may be suitable for applications where real-time classification is needed. In this paper, the FC networks are applied for the real-time extraction of gene expressions for Chlamydia microarray data. Both the classification performance and learning time of the FC networks are compared with the Multi-Layer Proceptron (MLP) networks and support-vector-machines (SVM) in the same classification task. The FC networks are shown to have extremely fast learning time and comparable classification accuracy.

Genes and gene expression in human alcoholic brain

Chronic alcoholism leads to localized brain damage, which is prominent in superior frontal cortex but mild in motor cortex. The likelihood of developing alcohol dependence is associated with genetic markers. GABA-A receptor expression differs between alcoholics and controls, whereas glutamate receptor differences are muted. We determined whether genotype differentiated the localized expression of glutamate N-methyl-D-aspartate (NMDA) and GABA-A receptors to influence the severity of alcohol-induced brain damage. Cerebral cortex tissue was obtained at autopsy from alcoholics without disease comorbid with alcoholics, alcoholics with cirrhosis, and matched controls. DRD2A, DRD2B, GABRB2, SLC1A2, and 5HTT genotypes did not divide alcoholic cases and controls on NMDA receptor parameters. In contrast, a specific alcohol dehydrogenase (ADHIC) genotype interacted significantly with NMDA efficacy and affinity in a region-specific manner SLC1A2 (glutamate transporter-2) genotype interacted significantly with local GABAA receptor b subunit mRNA expression, and ADHIC, DRD2B, SLC1A2, and APOE genotypes with b subunit isoform protein expression. In the latter instance, possession of the alcoholism- associated allele altered b isoform protein expression patterns toward a less-efficacious form of the GABA-A receptor in the pathologically vulnerable region. GABRB2 and GRIN2B (NMDA receptor 2B subunit} Genotypes were associated with significant regional difference in the pattern of b subunit protein isoform expression, but this was not influenced by alcoholism status. Genotype may modulate amino acid transmission locally so as to mediate neuronal vulnerability. This has implications for the effectiveness of pharmacological interventions aimed at ameliorating brain damage and, possibly, dependence.