Numerous computational algorithms for predicting protein-coding genes from genomic sequences have been developed, and hidden Markov models (HMMs) have frequently been used to model gene structures. For eukaryotes, more complex gene structures such as introns make gene prediction much harder due to isoforms of transcripts by alternative splicing machinery. We develop a novel gene prediction method for eukaryote genomes that extends the traditional HMM-based gene prediction model by incorporating comprehensive evidence of transcripts by using RNA sequencing (RNA-seq) technology. We formulate gene prediction as an integer programming problem, and solve it by the dual decomposition technique. To confirm the utility of the proposed algorithm, computational experiments on benchmark datasets were conducted. The results show that our algorithm efficiently and effectively employs RNA-seq data in gene structure prediction.
Combinatorial optimization problem is a difficult class of problems from which to obtain exact solutions, but such problems often arise in biotechnology, for example, it is often necessary to find optimal combinations of genes in transgenics to improve production of a useful compound by microorganisms. In the cases of 20 candidate genes for introduction into cells, the number of possible combinations of introduced genes is approximately 106. Testing all of their combinations by experimental observation is impossible practically. A few combinations are observed experimentally for large numbers of possible combinations generally. We tested two methods for the prediction of effects of transgenes: multivariate linear regression and the RBF (Radial Basis Function) network, with a simulated and an unpublished experimentally observed dataset of transgenic yeast. Results show that RBF network can detect a special gene (introduced gene) at the five percent significance level when the gene causes production values that are 1.5 times greater than other genes for the simulated dataset. Prediction by RBF network causes over-learning for larger numbers of learning data, however, it is superior than that by the linear regression model at the best condition.
Temporal mental orientation is a brain function that enables us to roam from the memorized past to the imaginable future. Previous studies have reported that mental orientation in spatial dimension correlated with activation of multiple cortical areas, including the posterior medial portion of the parietal lobe and precuneus. In contrast, the neural correlates of temporal mental orientation remain unclear. The present study performed a verbal experiment to investigate the neurophysiological correlates of temporal mental orientation. Neurophysiological activities were recorded extracranially, as participants processed sentences with correct or incorrect temporal orientations. We conducted time-domain and signal source estimation analyses. We observed that right frontal positive and centro-parietal negative event-related brain potential amplitudes increased for the incorrect temporal orientation, compared to that for correct orientation. Signal source estimation analysis demonstrated that these neural activities originated from the superior parietal areas, including the right precuneus, which functionally connected with the left precentral or premotor areas. The present findings suggest that the fronto-parietal functional connection contributes to temporal mental orientation.
Random projection is a powerful method for dimensionality reduction while its applications in high-dimensional survival analysis is rather limited. In this research, we propose a novel survival ensemble model based on sparse random projection and survival trees. Supported by the proper statistical analysis, we show that the proposed model is comparable to or better than popular survival models such as random survival forest, regularized Cox proportional hazard and fast cocktail models on high-dimensional microarray gene expression right censored data.