Motivation: Although numerous methods have been developed to better capture biological information from microarray data, commonly used single gene-based methods neglect interactions among genes and leave room for other novel approaches. For example, most classification and regression methods for microarray data are based on the whole set of genes and have not made use of pathway information. Pathway-based analysis in microarray studies may lead to more informative and relevant knowledge for biological researchers.
Results: In this paper, we describe a pathway-based classification and regression method using Random Forests to analyze gene expression data. The proposed methods allow researchers to rank important pathways from externally available databases, discover important genes, find pathway-based outlying cases and make full use of a continuous outcome variable in the regression setting. We also compared Random Forests with other machine learning methods using several datasets and found that Random Forests classification error rates were either the lowest or the second-lowest. By combining pathway information and novel statistical methods, this procedure represents a promising computational strategy in dissecting pathways and can provide biological insight into the study of microarray data.
Availability: Source code written in R is available from
Contact: hongyu.zhao@yale.edu
Supplementary Information: Supplementary Data are available at
USPIO, a macromolecular particulate MR imaging contrast agent, can be applied successfully to characterize tumor microvessels in animals. USPIO-derived K(PS) correlated strongly with histopathologic tumor grade, MVD, and K(PS) values derived by using albumin-(Gd-DTPA)(30) in the same tumors.
A new contrast medium, MS-325, was compared to albumin-(Gd-DTPA) 30 in 18 chemically induced rat breast tumors based on quantitative estimates of microvascular permeability (K PS ) and fractional plasma volume (fPV) using a two-compartment bidirectional model. No significant correlation was found between MS-325-enhanced microvascular assays with either tumor grade or with microvascular counts (MVCs). In comparison, the correlation coefficient between K PS and histologic tumor grade using albumin-(Gd-DTPA) 30 (r ؍ .58) was statistically significant (P < .01). Also, using albumin-(Gd-DTPA) 30 , a significant correlation (r ؍ .55, P < .05) was observed between the K PS and MVC, a biomarker of angiogenesis. Correlations between fPV and MVC were not statistically significant for either contrast medium. In conclusion, using MS-325, no significant correlations between the MR-estimated permeability values or plasma volumes were observed in experimental breast tumors with either the histologic tumor grade or MVC. This analysis confirms our previous determination that capillary permeability estimates, using a prototype large molecular contrast medium, albumin-(Gd-DTPA) 30
The aim of this study was to evaluate the potential of dynamic magnetic resonance imaging (MRI) enhanced by macromolecular contrast agents to monitor noninvasively the therapeutic effect of an anti-angiogenesis VEGF receptor kinase inhibitor in an experimental cancer model. MDA-MB-435, a poorly differentiated human breast cancer cell line, was implanted into the mammary fat pad in 20 female homozygous athymic rats. Animals were assigned randomly to a control (n=10) or drug treatment group (n=10). Baseline dynamic MRI was performed on sequential days using albumin-(GdDTPA)30 (6.0 nm diameter) and ultrasmall superparamagnetic iron oxide (USPIO) particles (approximately 30 nm diameter). Subjects were treated either with PTK787/ZK 222584, a VEGF receptor tyrosine kinase inhibitor, or saline given orally twice daily for 1 week followed by repeat MRI examinations serially using each contrast agent. Employing a unidirectional kinetic model comprising the plasma and interstitial water compartments, tumor microvessel characteristics including fractional plasma volume and transendothelial permeability (K(PS)) were estimated for each contrast medium. Tumor growth and the microvascular density, a histologic surrogate of angiogenesis, were also measured. Control tumors significantly increased (P<0.05) in size and in microvascular permeability (K(PS)) based on MRI assays using both macromolecular contrast media. In contrast, tumor growth was significantly reduced (P<0.05) in rats treated with PTK787/ZK 222584 and K(PS) values declined slightly. Estimated values for the fractional plasma volume did not differ significantly between treatment groups or contrast agents. Microvascular density counts correlated fairly with the tumor growth rate (r=0.64) and were statistically significant higher (P<0.05) in the control than in the drug-treated group. MRI measurements of tumor microvascular response, particularly transendothelial permeability (K(PS)), using either of two macromolecular contrast media, were able to detect effects of treatment with a VEGF receptor tyrosine kinase inhibitor on tumor vascular permeability. In a clinical setting such quantitative MRI measurements could be used to monitor tumor anti-angiogenesis therapy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.