Messenger RNA expression of Pabpnl1 and Mbd3l2 genes in oocytes and cleavage embryos

Objective: To identify genes specifically expressed in mammalian oocytes using an in silico subtraction, and to characterize the mRNA patterns of selected genes in oocytes, embryos, and adult tissues. Design: Comparison between oocyte groups and between early embryo stages. Setting: Laboratories of embryo manipulation and molecular biology from Departamento de Genetica (FMRP) and Departamento de Ciencias Basicas (FZEA) - University of Sao Paulo. Sample(s): Oocytes were collected from slaughtered cows for measurements, in vitro fertilization, and in vitro embryo culture. Somatic tissue, excluding gonad and uterus tissue, was collected from male and female cattle. Main Outcome Measure(s): Messenger RNA levels of poly(A)-binding protein nuclear-like 1 (Pabpnl1) and methyl-CpG-binding domain protein 3-like 2 (Mbd3l2). Result(s): Pabpnl1 mRNA was found to be expressed in oocytes, and Mbd3l2 transcripts were present in embryos. Quantification of Pabpnl1 transcripts showed no difference in levels between good-and bad-quality oocytes before in vitro maturation (IVM) or between good-quality oocytes before and after IVM. However, Pabpnl1 transcripts were not detected in bad-quality oocytes after IVM. Transcripts of the Mbd3l2 gene were found in 4-cell, 8-cell, and morula-stage embryos, with the highest level observed in 8-cell embryos. Conclusion(s): Pabpnl1 gene expression is restricted to oocytes and Mbd3l2 to embryos. Different Pabpnl1 mRNA levels in oocytes of varying viability suggest an important role in fertility involving the oocyte potential for embryo development. (Fertil Steril (R) 2010; 93: 2507-12. (C) 2010 by American Society for Reproductive Medicine.)

Poly-bagging predictors for classification modelling for credit scoring

Credit scoring modelling comprises one of the leading formal tools for supporting the granting of credit. Its core objective consists of the generation of a score by means of which potential clients can be listed in the order of the probability of default. A critical factor is whether a credit scoring model is accurate enough in order to provide correct classification of the client as a good or bad payer. In this context the concept of bootstraping aggregating (bagging) arises. The basic idea is to generate multiple classifiers by obtaining the predicted values from the fitted models to several replicated datasets and then combining them into a single predictive classification in order to improve the classification accuracy. In this paper we propose a new bagging-type variant procedure, which we call poly-bagging, consisting of combining predictors over a succession of resamplings. The study is derived by credit scoring modelling. The proposed poly-bagging procedure was applied to some different artificial datasets and to a real granting of credit dataset up to three successions of resamplings. We observed better classification accuracy for the two-bagged and the three-bagged models for all considered setups. These results lead to a strong indication that the poly-bagging approach may promote improvement on the modelling performance measures, while keeping a flexible and straightforward bagging-type structure easy to implement. (C) 2011 Elsevier Ltd. All rights reserved.