Publications (2)2.75 Total impact
-
Article: A new regularized least squares support vector regression for gene selection.
[show abstract] [hide abstract]
ABSTRACT: Selection of influential genes with microarray data often faces the difficulties of a large number of genes and a relatively small group of subjects. In addition to the curse of dimensionality, many gene selection methods weight the contribution from each individual subject equally. This equal-contribution assumption cannot account for the possible dependence among subjects who associate similarly to the disease, and may restrict the selection of influential genes. A novel approach to gene selection is proposed based on kernel similarities and kernel weights. We do not assume uniformity for subject contribution. Weights are calculated via regularized least squares support vector regression (RLS-SVR) of class levels on kernel similarities and are used to weight subject contribution. The cumulative sum of weighted expression levels are next ranked to select responsible genes. These procedures also work for multiclass classification. We demonstrate this algorithm on acute leukemia, colon cancer, small, round blue cell tumors of childhood, breast cancer, and lung cancer studies, using kernel Fisher discriminant analysis and support vector machines as classifiers. Other procedures are compared as well. This approach is easy to implement and fast in computation for both binary and multiclass problems. The gene set provided by the RLS-SVR weight-based approach contains a less number of genes, and achieves a higher accuracy than other procedures.BMC Bioinformatics 03/2009; 10:44. · 2.75 Impact Factor -
Article: Use of ecstasy and other psychoactive substances among school-attending adolescents in Taiwan: national surveys 2004–2006
[show abstract] [hide abstract]
ABSTRACT: Abstract Background With the backdrop of a global ecstasy epidemic, this study sought to examine the trend, correlates, and onset sequence of ecstasy use among adolescents in Taiwan, where a well-established gateway drug such as marijuana is much less popular. Methods A multistage probability survey of school-attending adolescents in grades 7, 9, 10, and 12, aged 11–19 years, was conducted in 2004, 2005, and 2006. A self-administered anonymous questionnaire elicited response rates ranging from 94.3% to 96.6%. The sample sizes were 18232 respondents in 2004, 17986 in 2005, and 17864 in 2006. Results In terms of lifetime prevalence and incidence, ecstasy and ketamine by and large appeared as the first and second commonly used illegal drugs, respectively, among middle (grades 7 and 9) and high school students (grades 10 and 12) during the 3-year survey period; however, this order was reversed in the middle school-aged students starting in 2006. Having sexual experience, tobacco use, and betel nut use were factors consistently associated with the onset of ecstasy use across years. The majority of ecstasy users had been involved in polydrug use, such as the use of ketamine (41.4%–53.5%), marijuana (12.7%–18.7%), and methamphetamine (4.2%–9.5%). Conclusion From 2004 to 2006, a decline was noted in the prevalence and incidence rate of ecstasy, a leading illegal drug used by school-attending adolescents in Taiwan since the early 2000s. The emerging ketamine use trend may warrant more attention in the future.BMC Public Health. 01/2009;
