Use of Attribute Driven Incremental Discretization and Logic Learning Machine to build a prognostic classifier for neuroblastoma patients

Abstract

BackgroundCancer patient's outcome is written, in part, in the gene expression profile of the tumor. We previously identified a 62-probe sets signature (NB-hypo) to identify tissue hypoxia in neuroblastoma tumors and showed that NB-hypo stratified neuroblastoma patients in good and poor outcome [1]. It was important to develop a prognostic classifier to cluster patients into risk groups benefiting of defined therapeutic approaches. Novel classification and data discretization approaches can be instrumental for the generation of accurate predictors and robust tools for clinical decision support. We explored the application to gene expression data of Rulex, a novel software suite including the Attribute Driven Incremental Discretization technique for transforming continuous variables into simplified discrete ones and the Logic Learning Machine model for intelligible rule generation.ResultsWe applied Rulex components to the problem of predicting the outcome of neuroblastoma patients on the bases of 62 probe sets NB-hypo gene expression signature. The resulting classifier consisted in 9 rules utilizing mainly two conditions of the relative expression of 11 probe sets. These rules were very effective predictors, as shown in an independent validation set, demonstrating the validity of the LLM algorithm applied to microarray data and patients' classification. The LLM performed as efficiently as Prediction Analysis of Microarray and Support Vector Machine, and outperformed other learning algorithms such as C4.5. Rulex carried out a feature selection by selecting a new signature (NB-hypo-II) of 11 probe sets that turned out to be the most relevant in predicting outcome among the 62 of the NB-hypo signature. Rules are easily interpretable as they involve only few conditions.Furthermore, we demonstrate that the application of a weighted classification associated with the rules improves the classification of poorly represented classes.ConclusionsOur findings provided evidence that the application of Rulex to the expression values of NB-hypo signature created a set of accurate, high quality, consistent and interpretable rules for the prediction of neuroblastoma patients' outcome. We identified the Rulex weighted classification as a flexible tool that can support clinical decisions. For these reasons, we consider Rulex to be a useful tool for cancer classification from microarray gene expression data.

Artificial neural network classifier predicts neuroblastoma patients’ outcome

“…These values are better than what can be achieved with other available risk factors (MYCN amplification, age at diagnosis and INSS stage) on the same cohort. These findings extend and complement previous work on NB patients’ classifiers based on Logic Learning machine (LLM) [11, 66] trained through an optimized version of the Shadow Clustering algorithm [67]. These studies were instrumental to demonstrate that hypoxia based predictors could generate intelligible rules translatable into the clinical settings [66].…”

“…Several groups have used gene expression-based approaches to stratify neuroblastoma patients and prognostic gene signatures have been described [11, 13–22]. The performance of our NB-hypo classifier is comparable with that of the other prognostic gene expression signatures proposed for neuroblastoma [68].…”

“…Several groups have developed gene expression-based approaches to stratify neuroblastoma patients [11–28] and described prognostic gene signatures. We studied outcome prediction in neuroblastoma patients utilizing a biology-driven approach, in which the gene expression profile under investigation is associated to “a priori” knowledge of a biological process that has a major impact on tumor growth [29].…”

Transcriptome analysis defines myocardium gene signatures in children with ToF and ASD and reveals disease-specific molecular reprogramming in response to surgery with cardiopulmonary bypass

“…We filtered out probe sets having a coefficient of variation (CV) lower than 0.7, because they did not substantially change between the two diseases under consideration, and those having an expression value lower than 100 in at least 20% of the samples because they were not sufficiently expressed in our data set to provide a reliable transcriptional level. Filtering was carried out by 'GeneFilter' R package, as described [18,19]. We converted the Affymetrix probe sets into the corresponding gene symbol by Netaffix tool.…”

“…We converted the Affymetrix probe sets into the corresponding gene symbol by Netaffix tool. When multiple probe sets were associated with the same gene symbol, the probe set with the highest expression signal was considered [19]. The full set of data from each microarray experiment has been deposited at the Gene Expression Omnibus (GEO) public repository at NCBI (http:// www.ncbi.nlm.nih.gov) and can be accessed to through GEO Series accession number GSE132176.…”