JCDSA: a joint covariate detection tool for survival analysis on tumor expression profiles

Abstract

BackgroundSurvival analysis on tumor expression profiles has always been a key issue for subsequent biological experimental validation. It is crucial how to select features which closely correspond to survival time. Furthermore, it is important how to select features which best discriminate between low-risk and high-risk group of patients. Common features derived from the two aspects may provide variable candidates for prognosis of cancer.ResultsBased on the provided two-step feature selection strategy, we develop a joint covariate detection tool for survival analysis on tumor expression profiles. Significant features, which are not only consistent with survival time but also associated with the categories of patients with different survival risks, are chosen. Using the miRNA expression data (Level 3) of 548 patients with glioblastoma multiforme (GBM) as an example, miRNA candidates for prognosis of cancer are selected. The reliability of selected miRNAs using this tool is demonstrated by 100 simulations. Furthermore, It is discovered that significant covariates are not directly composed of individually significant variables.ConclusionsJoint covariate detection provides a viewpoint for selecting variables which are not individually but jointly significant. Besides, it helps to select features which are not only consistent with survival time but also associated with prognosis risk. The software is available at http://bio-nefu.com/resource/jcdsa.

Stepwise detection and evaluation reveal miR-10b and miR-222 as a remarkable prognostic pair for glioblastoma

“…As a result, 9 individuals, 26 pairs, and 68 triples of miRNAs were selected. More details about how the p- values were obtained could be seen in the method part of our previous work [12, 13].…”

“…Furthermore, we more stringently controlled the threshold of p -value to be 0.0005, and ultimately selected the pair miR-222 and miR-10b for further analysis. More details about how the p -values were obtained could be seen in the method part of our previous work [12, 13].…”

“…We have presented a method named as joint covariate detection [12] for selection of features by bottom-up enumeration of variables, and have provided a tool named as JCDSA, i.e., a joint covariate detection tool for survival analysis [13]. Joint covariate detection resolved the problem of partial or local feature selection by variable enumeration.…”

“…In Fig. 1, the main diagonal two parts refer to JCDSA-based feature selection, as has been expressed in our previous work [12, 13]; while, the accessory diagonal two parts correspond to its evaluation.

Fig. 1A framework indicating the strategy containing not only JCDSA-based feature selection but also the corresponding evaluations

…”

FeatureSelect: a software for feature selection based on machine learning approaches

“…These methods are combination of four above categories. For example, some related works use two-step feature selection methods [17,18]. In these methods, a number of features are reduced by the first method, and the second method is then used for further reduction [19].…”