Logic Learning Machine creates explicit and stable rules stratifying neuroblastoma patients

Abstract

BackgroundNeuroblastoma is the most common pediatric solid tumor. About fifty percent of high risk patients die despite treatment making the exploration of new and more effective strategies for improving stratification mandatory. Hypoxia is a condition of low oxygen tension occurring in poorly vascularized areas of the tumor associated with poor prognosis. We had previously defined a robust gene expression signature measuring the hypoxic component of neuroblastoma tumors (NB-hypo) which is a molecular risk factor. We wanted to develop a prognostic classifier of neuroblastoma patients' outcome blending existing knowledge on clinical and molecular risk factors with the prognostic NB-hypo signature. Furthermore, we were interested in classifiers outputting explicit rules that could be easily translated into the clinical setting.ResultsShadow Clustering (SC) technique, which leads to final models called Logic Learning Machine (LLM), exhibits a good accuracy and promises to fulfill the aims of the work. We utilized this algorithm to classify NB-patients on the bases of the following risk factors: Age at diagnosis, INSS stage, MYCN amplification and NB-hypo. The algorithm generated explicit classification rules in good agreement with existing clinical knowledge. Through an iterative procedure we identified and removed from the dataset those examples which caused instability in the rules. This workflow generated a stable classifier very accurate in predicting good and poor outcome patients. The good performance of the classifier was validated in an independent dataset. NB-hypo was an important component of the rules with a strength similar to that of tumor staging.ConclusionsThe novelty of our work is to identify stability, explicit rules and blending of molecular and clinical risk factors as the key features to generate classification rules for NB patients to be conveyed to the clinic and to be used to design new therapies. We derived, through LLM, a set of four stable rules identifying a new class of poor outcome patients that could benefit from new therapies potentially targeting tumor hypoxia or its consequences.

Artificial neural network classifier predicts neuroblastoma patients’ outcome

“…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]. However, the feature selection system of LLM reshaped the feature space definition for optimizing the rule construction and only a fraction of the NB-hypo probe sets was tested in these studies.…”

“…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].…”

Machine learning for bioinformatics and neuroimaging

“…Finally, only significant rules, containing miRNAs with highly correlated expression profiles, are retained. Other applications of rule induction in bioinformatics include the description of gene sets (Gruca & Sikora, 2017) and disease subtyping (Cangelosi et al, 2013;Huang, Huang, Lee, & Weng, 2015).…”

Bioinformatics in Italy: BITS2012, the ninth annual meeting of the Italian Society of Bioinformatics

“…In the paper "Logic Learning Machine creates explicit and stable rules stratifying neuroblastoma patients" [15], Cangelosi et al develop a novel prognostic classifier of neuroblastoma patients' outcome blending existing knowledge on clinical and molecular risk factors with the prognostic NB-hypo signature. In particular, the proposed model is capable to give explicit rules that could be easily translated into the clinical setting.…”