The l1-l2 regularization framework unmasks the hypoxia signature hidden in the transcriptome of a set of heterogeneous neuroblastoma cell lines

Comparative epigenomics by machine learning approach for neuroblastoma

BACKGROUND

Neuroblastoma (NB) is the second most common pediatric solid tumor. Because the number of genetic mutations found in tumors are small, even in some patients with unfavorable NB, epigenetic variation is expected to play an important role in NB progression. DNA methylation is a major epigenetic mechanism, and its relationship with NB prognosis has been a concern. One limitation with the analysis of variation in DNA methylation is the lack of a suitable analytical model. Therefore, in this study, we performed a random forest (RF) analysis of the DNA methylome data of NB from multiple databases.

RESULTS

RF is a popular machine learning model owing to its simplicity, intuitiveness, and computational cost. RF analysis identified novel intermediate-risk patient groups with characteristic DNA methylation patterns within the low-risk group. Feature selection analysis based on probe annotation revealed that enhancer-annotated regions had strong predictive power, particularly for MYCN-amplified NBs. We developed a gene-based analytical model to identify candidate genes related to disease progression, such as PRDM8 and FAM13A-AS1. RF analysis revealed sufficient predictive power compared to other machine learning models.

CONCLUSIONS

RF is a useful tool for DNA methylome analysis in cancer epigenetic studies, and has potential to identify a novel cancer-related genes.

Molecular Genetics in Neuroblastoma Prognosis

In recent years, much research has been carried out to identify the biological and genetic characteristics of the neuroblastoma (NB) tumor in order to precisely define the prognostic subgroups for improving treatment stratification. This review will describe the major genetic features and the recent scientific advances, focusing on their impact on diagnosis, prognosis, and therapeutic solutions in NB clinical management.

Development and validation of a robotic multifactorial fall-risk predictive model: A one-year prospective study in community-dwelling older adults

BACKGROUND

Falls in the elderly are a major public health concern because of their high incidence, the involvement of many risk factors, the considerable post-fall morbidity and mortality, and the health-related and social costs. Given that many falls are preventable, the early identification of older adults at risk of falling is crucial in order to develop tailored interventions to prevent such falls. To date, however, the fall-risk assessment tools currently used in the elderly have not shown sufficiently high predictive validity to distinguish between subjects at high and low fall risk. Consequently, predicting the risk of falling remains an unsolved issue in geriatric medicine. This one-year prospective study aims to develop and validate, by means of a cross-validation method, a multifactorial fall-risk model based on clinical and robotic parameters in older adults.

METHODS

Community-dwelling subjects aged ≥ 65 years were enrolled. At the baseline, all subjects were evaluated for history of falling and number of drugs taken daily, and their gait and balance were evaluated by means of the Timed "Up & Go" test (TUG), Gait Speed (GS), Short Physical Performance Battery (SPPB) and Performance-Oriented Mobility Assessment (POMA). They also underwent robotic assessment by means of the hunova robotic device to evaluate the various components of balance. All subjects were followed up for one-year and the number of falls was recorded. The models that best predicted falls-on the basis of: i) only clinical parameters; ii) only robotic parameters; iii) clinical plus robotic parameters-were identified by means of a cross-validation method.

RESULTS

Of the 100 subjects initially enrolled, 96 (62 females, mean age 77.17±.49 years) completed the follow-up and were included. Within one year, 32 participants (33%) experienced at least one fall ("fallers"), while 64 (67%) did not ("non-fallers"). The best classifier model to emerge from cross-validated fall-risk estimation included eight clinical variables (age, sex, history of falling in the previous 12 months, TUG, Tinetti, SPPB, Low GS, number of drugs) and 20 robotic parameters, and displayed an area under the receiver operator characteristic (ROC) curve of 0.81 (95% CI: 0.72-0.90). Notably, the model that included only three of these clinical variables (age, history of falls and low GS) plus the robotic parameters showed similar accuracy (ROC AUC 0.80, 95% CI: 0.71-0.89). In comparison with the best classifier model that comprised only clinical parameters (ROC AUC: 0.67; 95% CI: 0.55-0.79), both models performed better in predicting fall risk, with an estimated Net Reclassification Improvement (NRI) of 0.30 and 0.31 (p = 0.02), respectively, and an estimated Integrated Discrimination Improvement (IDI) of 0.32 and 0.27 (p<0.001), respectively. The best model that comprised only robotic parameters (the 20 parameters identified in the final model) achieved a better performance than the clinical parameters alone, but worse than the combination of both clinical and robotic variables (ROC AUC: 0.73, 95% CI 0.63-0.83).

CONCLUSION

A multifactorial fall-risk assessment that includes clinical and hunova robotic variables significantly improves the accuracy of predicting the risk of falling in community-dwelling older people. Our data suggest that combining clinical and robotic assessments can more accurately identify older people at high risk of falls, thereby enabling personalized fall-prevention interventions to be undertaken.

Metabolic Regulation of the Epigenome Drives Lethal Infantile Ependymoma

Posterior fossa A (PFA) ependymomas are lethal malignancies of the hindbrain in infants and toddlers. Lacking highly recurrent somatic mutations, PFA ependymomas are proposed to be epigenetically driven tumors for which model systems are lacking. Here we demonstrate that PFA ependymomas are maintained under hypoxia, associated with restricted availability of specific metabolites to diminish histone methylation, and increase histone demethylation and acetylation at histone 3 lysine 27 (H3K27). PFA ependymomas initiate from a cell lineage in the first trimester of human development that resides in restricted oxygen. Unlike other ependymomas, transient exposure of PFA cells to ambient oxygen induces irreversible cellular toxicity. PFA tumors exhibit a low basal level of H3K27me3, and, paradoxically, inhibition of H3K27 methylation specifically disrupts PFA tumor growth. Targeting metabolism and/or the epigenome presents a unique opportunity for rational therapy for infants with PFA ependymoma.

Transplantation Induces Profound Changes in the Transcriptional Asset of Hematopoietic Stem Cells: Identification of Specific Signatures Using Machine Learning Techniques

During the phase of proliferation needed for hematopoietic reconstitution following transplantation, hematopoietic stem/progenitor cells (HSPC) must express genes involved in stem cell self-renewal. We investigated the expression of genes relevant for self-renewal and expansion of HSPC (operationally defined as CD34+ cells) in steady state and after transplantation. Specifically, we evaluated the expression of ninety-one genes that were analyzed by real-time PCR in CD34+ cells isolated from (i) 12 samples from umbilical cord blood (UCB); (ii) 15 samples from bone marrow healthy donors; (iii) 13 samples from bone marrow after umbilical cord blood transplant (UCBT); and (iv) 29 samples from patients after transplantation with adult hematopoietic cells. The results show that transplanted CD34+ cells from adult cells acquire an asset very different from transplanted CD34+ cells from cord blood. Multivariate machine learning analysis (MMLA) showed that four specific gene signatures can be obtained by comparing the four types of CD34+ cells. In several, but not all cases, transplanted HSPC from UCB overexpress reprogramming genes. However, these remarkable changes do not alter the commitment to hematopoietic lineage. Overall, these results reveal undisclosed aspects of transplantation biology.

Perturbation-response genes reveal signaling footprints in cancer gene expression

Aberrant cell signaling can cause cancer and other diseases and is a focal point of drug research. A common approach is to infer signaling activity of pathways from gene expression. However, mapping gene expression to pathway components disregards the effect of post-translational modifications, and downstream signatures represent very specific experimental conditions. Here we present PROGENy, a method that overcomes both limitations by leveraging a large compendium of publicly available perturbation experiments to yield a common core of Pathway RespOnsive GENes. Unlike pathway mapping methods, PROGENy can (i) recover the effect of known driver mutations, (ii) provide or improve strong markers for drug indications, and (iii) distinguish between oncogenic and tumor suppressor pathways for patient survival. Collectively, these results show that PROGENy accurately infers pathway activity from gene expression in a wide range of conditions.

Immunohistochemical analysis of PDK1, PHD3 and HIF-1α expression defines the hypoxic status of neuroblastoma tumors

Neuroblastoma (NB) is the most common solid tumor during infancy and the first cause of death among the preschool age diseases. The availability of several NB genomic profiles improves the prognostic ability, but the outcome prediction for this pathology remains imperfect. We previously produced a novel prognostic gene signature based on the response of NB cells to hypoxia, a condition of tumor microenvironment strictly connected with cancer aggressiveness. Here we attempted to further define the expression of hypoxia-modulated specific genes, looking at their protein level in NB specimens, considering in particular the hypoxia inducible factor-1α (HIF-1α), the mitochondrial pyruvate dehydrogenase kinase 1 (PDK1), and the HIF-prolyl hydroxylase domain 3 (PHD3). The evaluation of expression was performed by Western blot and immunocytochemistry on NB cell lines and by immunohistochemistry on tumor specimens. Stimulation of both HIF-1α and PDK1 and inhibition of PHD3 expression were observed in NB cell lines cultured under prolonged hypoxic conditions as well as in most of the tumors with poor outcome. Our results indicate that the immunohistochemistry analysis of the protein expression of PDK1, PHD3, and HIF-1α defines the hypoxic status of NB tumors and can be used as a simple and relevant tool to stratify high-risk patients.

Artificial neural network classifier predicts neuroblastoma patients' outcome

Background

More than fifty percent of neuroblastoma (NB) patients with adverse prognosis do not benefit from treatment making the identification of new potential targets mandatory. Hypoxia is a condition of low oxygen tension, occurring in poorly vascularized tissues, which activates specific genes and contributes to the acquisition of the tumor aggressive phenotype. We defined a gene expression signature (NB-hypo), which measures the hypoxic status of the neuroblastoma tumor. We aimed at developing a classifier predicting neuroblastoma patients’ outcome based on the assessment of the adverse effects of tumor hypoxia on the progression of the disease.

Methods

Multi-layer perceptron (MLP) was trained on the expression values of the 62 probe sets constituting NB-hypo signature to develop a predictive model for neuroblastoma patients’ outcome. We utilized the expression data of 100 tumors in a leave-one-out analysis to select and construct the classifier and the expression data of the remaining 82 tumors to test the classifier performance in an external dataset. We utilized the Gene set enrichment analysis (GSEA) to evaluate the enrichment of hypoxia related gene sets in patients predicted with “Poor” or “Good” outcome.

Results

We utilized the expression of the 62 probe sets of the NB-Hypo signature in 182 neuroblastoma tumors to develop a MLP classifier predicting patients’ outcome (NB-hypo classifier). We trained and validated the classifier in a leave-one-out cross-validation analysis on 100 tumor gene expression profiles. We externally tested the resulting NB-hypo classifier on an independent 82 tumors’ set. The NB-hypo classifier predicted the patients’ outcome with the remarkable accuracy of 87 %. NB-hypo classifier prediction resulted in 2 % classification error when applied to clinically defined low-intermediate risk neuroblastoma patients. The prediction was 100 % accurate in assessing the death of five low/intermediated risk patients. GSEA of tumor gene expression profile demonstrated the hypoxic status of the tumor in patients with poor prognosis.

Conclusions

We developed a robust classifier predicting neuroblastoma patients’ outcome with a very low error rate and we provided independent evidence that the poor outcome patients had hypoxic tumors, supporting the potential of using hypoxia as target for neuroblastoma treatment.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1194-3) contains supplementary material, which is available to authorized users.

Enhancing Interpretability of Gene Signatures with Prior Biological Knowledge

Biological interpretability is a key requirement for the output of microarray data analysis pipelines. The most used pipeline first identifies a gene signature from the acquired measurements and then uses gene enrichment analysis as a tool for functionally characterizing the obtained results. Recently Knowledge Driven Variable Selection (KDVS), an alternative approach which performs both steps at the same time, has been proposed. In this paper, we assess the effectiveness of KDVS against standard approaches on a Parkinson’s Disease (PD) dataset. The presented quantitative analysis is made possible by the construction of a reference list of genes and gene groups associated to PD. Our work shows that KDVS is much more effective than the standard approach in enhancing the interpretability of the obtained results.

Gene Expression Signatures as Biomarkers of Tumour Hypoxia

Hypoxia is a feature of most solid tumours and is associated with a poor prognosis. The hypoxic environment can reduce the efficacy of radiotherapy and some chemotherapeutics, and has been investigated extensively as a therapeutic target. The clinical use of hypoxia-targeting treatment will benefit from the development of a biomarker to assess tumour hypoxia. There are several possible techniques that measure either the level of oxygen or the tumour molecular response to hypoxia. The latter includes gene expression profiling, which measures the transcriptional response of a tumour to its hypoxic microenvironment. A systematic review identified 32 published hypoxia gene expression signatures. The methods used for their derivation varied, but are broadly classified as: (i) identifying genes with significantly higher or lower expression in cancer cells cultured under hypoxic versus normoxic conditions; (ii) using either previously characterised hypoxia-regulated genes/biomarkers to define hypoxic tumours and then identifying other genes that are over- or under-expressed in the hypoxic tumours. Both generated gene signatures useful in furthering our understanding of hypoxia biology. However, signatures derived using the second method seem to be superior in terms of providing prognostic information. Here we summarise all 32 published hypoxia signatures, discuss their commonalities and differences, and highlight their strengths and limitations. This review also highlights the importance of reproducibility and gene annotation, which must be accounted for to transfer signatures robustly for clinical application as biomarkers.

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

BACKGROUND

Cancer 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.

RESULTS

We 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.

CONCLUSIONS

Our 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.

Molecular fingerprinting reflects different histotypes and brain region in low grade gliomas

BACKGROUND

Paediatric low-grade gliomas (LGGs) encompass a heterogeneous set of tumours of different histologies, site of lesion, age and gender distribution, growth potential, morphological features, tendency to progression and clinical course. Among LGGs, Pilocytic astrocytomas (PAs) are the most common central nervous system (CNS) tumours in children. They are typically well-circumscribed, classified as grade I by the World Health Organization (WHO), but recurrence or progressive disease occurs in about 10-20% of cases. Despite radiological and neuropathological features deemed as classic are acknowledged, PA may present a bewildering variety of microscopic features. Indeed, tumours containing both neoplastic ganglion and astrocytic cells occur at a lower frequency.

METHODS

Gene expression profiling on 40 primary LGGs including PAs and mixed glial-neuronal tumours comprising gangliogliomas (GG) and desmoplastic infantile gangliogliomas (DIG) using Affymetrix array platform was performed. A biologically validated machine learning workflow for the identification of microarray-based gene signatures was devised. The method is based on a sparsity inducing regularization algorithm l₁l₂ that selects relevant variables and takes into account their correlation. The most significant genetic signatures emerging from gene-chip analysis were confirmed and validated by qPCR.

RESULTS

We identified an expression signature composed by a biologically validated list of 15 genes, able to distinguish infratentorial from supratentorial LGGs. In addition, a specific molecular fingerprinting distinguishes the supratentorial PAs from those originating in the posterior fossa. Lastly, within supratentorial tumours, we also identified a gene expression pattern composed by neurogenesis, cell motility and cell growth genes which dichotomize mixed glial-neuronal tumours versus PAs. Our results reinforce previous observations about aberrant activation of the mitogen-activated protein kinase (MAPK) pathway in LGGs, but still point to an active involvement of TGF-beta signaling pathway in the PA development and pick out some hitherto unreported genes worthy of further investigation for the mixed glial-neuronal tumours.

CONCLUSIONS

The identification of a brain region-specific gene signature suggests that LGGs, with similar pathological features but located at different sites, may be distinguishable on the basis of cancer genetics. Molecular fingerprinting seems to be able to better sub-classify such morphologically heterogeneous tumours and it is remarkable that mixed glial-neuronal tumours are strikingly separated from PAs.

Logic Learning Machine creates explicit and stable rules stratifying neuroblastoma patients

BACKGROUND

Neuroblastoma 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.

RESULTS

Shadow 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.

CONCLUSIONS

The 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.

Knowledge Driven Variable Selection (KDVS) - a new approach to enrichment analysis of gene signatures obtained from high-throughput data

Background

High–throughput (HT) technologies provide huge amount of gene expression data that can be used to identify biomarkers useful in the clinical practice. The most frequently used approaches first select a set of genes (i.e. gene signature) able to characterize differences between two or more phenotypical conditions, and then provide a functional assessment of the selected genes with an a posteriori enrichment analysis, based on biological knowledge. However, this approach comes with some drawbacks. First, gene selection procedure often requires tunable parameters that affect the outcome, typically producing many false hits. Second, a posteriori enrichment analysis is based on mapping between biological concepts and gene expression measurements, which is hard to compute because of constant changes in biological knowledge and genome analysis. Third, such mapping is typically used in the assessment of the coverage of gene signature by biological concepts, that is either score–based or requires tunable parameters as well, limiting its power.

Results

We present Knowledge Driven Variable Selection (KDVS), a framework that uses a priori biological knowledge in HT data analysis. The expression data matrix is transformed, according to prior knowledge, into smaller matrices, easier to analyze and to interpret from both computational and biological viewpoints. Therefore KDVS, unlike most approaches, does not exclude a priori any function or process potentially relevant for the biological question under investigation. Differently from the standard approach where gene selection and functional assessment are applied independently, KDVS embeds these two steps into a unified statistical framework, decreasing the variability derived from the threshold–dependent selection, the mapping to the biological concepts, and the signature coverage. We present three case studies to assess the usefulness of the method.

Conclusions

We showed that KDVS not only enables the selection of known biological functionalities with accuracy, but also identification of new ones. An efficient implementation of KDVS was devised to obtain results in a fast and robust way. Computing time is drastically reduced by the effective use of distributed resources. Finally, integrated visualization techniques immediately increase the interpretability of results. Overall, KDVS approach can be considered as a viable alternative to enrichment–based approaches.

Design of a multi-signature ensemble classifier predicting neuroblastoma patients' outcome

Background

Neuroblastoma is the most common pediatric solid tumor of the sympathetic nervous system. Development of improved predictive tools for patients stratification is a crucial requirement for neuroblastoma therapy. Several studies utilized gene expression-based signatures to stratify neuroblastoma patients and demonstrated a clear advantage of adding genomic analysis to risk assessment. There is little overlapping among signatures and merging their prognostic potential would be advantageous. Here, we describe a new strategy to merge published neuroblastoma related gene signatures into a single, highly accurate, Multi-Signature Ensemble (MuSE)-classifier of neuroblastoma (NB) patients outcome.

Methods

Gene expression profiles of 182 neuroblastoma tumors, subdivided into three independent datasets, were used in the various phases of development and validation of neuroblastoma NB-MuSE-classifier. Thirty three signatures were evaluated for patients' outcome prediction using 22 classification algorithms each and generating 726 classifiers and prediction results. The best-performing algorithm for each signature was selected, validated on an independent dataset and the 20 signatures performing with an accuracy > = 80% were retained.

Results

We combined the 20 predictions associated to the corresponding signatures through the selection of the best performing algorithm into a single outcome predictor. The best performance was obtained by the Decision Table algorithm that produced the NB-MuSE-classifier characterized by an external validation accuracy of 94%. Kaplan-Meier curves and log-rank test demonstrated that patients with good and poor outcome prediction by the NB-MuSE-classifier have a significantly different survival (p < 0.0001). Survival curves constructed on subgroups of patients divided on the bases of known prognostic marker suggested an excellent stratification of localized and stage 4s tumors but more data are needed to prove this point.

Conclusions

The NB-MuSE-classifier is based on an ensemble approach that merges twenty heterogeneous, neuroblastoma-related gene signatures to blend their discriminating power, rather than numeric values, into a single, highly accurate patients' outcome predictor. The novelty of our approach derives from the way to integrate the gene expression signatures, by optimally associating them with a single paradigm ultimately integrated into a single classifier. This model can be exported to other types of cancer and to diseases for which dedicated databases exist.

A computational procedure for functional characterization of potential marker genes from molecular data: Alzheimer's as a case study

BACKGROUND

A molecular characterization of Alzheimer's Disease (AD) is the key to the identification of altered gene sets that lead to AD progression. We rely on the assumption that candidate marker genes for a given disease belong to specific pathogenic pathways, and we aim at unveiling those pathways stable across tissues, treatments and measurement systems. In this context, we analyzed three heterogeneous datasets, two microarray gene expression sets and one protein abundance set, applying a recently proposed feature selection method based on regularization.

RESULTS

For each dataset we identified a signature that was successively evaluated both from the computational and functional characterization viewpoints, estimating the classification error and retrieving the most relevant biological knowledge from different repositories. Each signature includes genes already known to be related to AD and genes that are likely to be involved in the pathogenesis or in the disease progression. The integrated analysis revealed a meaningful overlap at the functional level.

CONCLUSIONS

The identification of three gene signatures showing a relevant overlap of pathways and ontologies, increases the likelihood of finding potential marker genes for AD.

A machine learning pipeline for quantitative phenotype prediction from genotype data

Background

Quantitative phenotypes emerge everywhere in systems biology and biomedicine due to a direct interest for quantitative traits, or to high individual variability that makes hard or impossible to classify samples into distinct categories, often the case with complex common diseases. Machine learning approaches to genotype-phenotype mapping may significantly improve Genome-Wide Association Studies (GWAS) results by explicitly focusing on predictivity and optimal feature selection in a multivariate setting. It is however essential that stringent and well documented Data Analysis Protocols (DAP) are used to control sources of variability and ensure reproducibility of results. We present a genome-to-phenotype pipeline of machine learning modules for quantitative phenotype prediction. The pipeline can be applied for the direct use of whole-genome information in functional studies. As a realistic example, the problem of fitting complex phenotypic traits in heterogeneous stock mice from single nucleotide polymorphims (SNPs) is here considered.

Methods

The core element in the pipeline is the L1L2 regularization method based on the naïve elastic net. The method gives at the same time a regression model and a dimensionality reduction procedure suitable for correlated features. Model and SNP markers are selected through a DAP originally developed in the MAQC-II collaborative initiative of the U.S. FDA for the identification of clinical biomarkers from microarray data. The L1L2 approach is compared with standard Support Vector Regression (SVR) and with Recursive Jump Monte Carlo Markov Chain (MCMC). Algebraic indicators of stability of partial lists are used for model selection; the final panel of markers is obtained by a procedure at the chromosome scale, termed ’saturation’, to recover SNPs in Linkage Disequilibrium with those selected.

Results

With respect to both MCMC and SVR, comparable accuracies are obtained by the L1L2 pipeline. Good agreement is also found between SNPs selected by the L1L2 algorithms and candidate loci previously identified by a standard GWAS. The combination of L1L2-based feature selection with a saturation procedure tackles the issue of neglecting highly correlated features that affects many feature selection algorithms.

Conclusions

The L1L2 pipeline has proven effective in terms of marker selection and prediction accuracy. This study indicates that machine learning techniques may support quantitative phenotype prediction, provided that adequate DAPs are employed to control bias in model selection.

A biology-driven approach identifies the hypoxia gene signature as a predictor of the outcome of neuroblastoma patients

BACKGROUND

Hypoxia is a condition of low oxygen tension occurring in the tumor microenvironment and it is related to poor prognosis in human cancer. To examine the relationship between hypoxia and neuroblastoma, we generated and tested an in vitro derived hypoxia gene signature for its ability to predict patients' outcome.

RESULTS

We obtained the gene expression profile of 11 hypoxic neuroblastoma cell lines and we derived a robust 62 probesets signature (NB-hypo) taking advantage of the strong discriminating power of the l1-l2 feature selection technique combined with the analysis of differential gene expression. We profiled gene expression of the tumors of 88 neuroblastoma patients and divided them according to the NB-hypo expression values by K-means clustering. The NB-hypo successfully stratifies the neuroblastoma patients into good and poor prognosis groups. Multivariate Cox analysis revealed that the NB-hypo is a significant independent predictor after controlling for commonly used risk factors including the amplification of MYCN oncogene. NB-hypo increases the resolution of the MYCN stratification by dividing patients with MYCN not amplified tumors in good and poor outcome suggesting that hypoxia is associated with the aggressiveness of neuroblastoma tumor independently from MYCN amplification.

CONCLUSIONS

Our results demonstrate that the NB-hypo is a novel and independent prognostic factor for neuroblastoma and support the view that hypoxia is negatively correlated with tumors' outcome. We show the power of the biology-driven approach in defining hypoxia as a critical molecular program in neuroblastoma and the potential for improvement in the current criteria for risk stratification.

Identification of multiple hypoxia signatures in neuroblastoma cell lines by l1-l2 regularization and data reduction

Hypoxia is a condition of low oxygen tension occurring in the tumor and negatively correlated with the progression of the disease. We studied the gene expression profiles of nine neuroblastoma cell lines grown under hypoxic conditions to define gene signatures that characterize hypoxic neuroblastoma. The l(1)-l(2) regularization applied to the entire transcriptome identified a single signature of 11 probesets discriminating the hypoxic state. We demonstrate that new hypoxia signatures, with similar discriminatory power, can be generated by a prior knowledge-based filtering in which a much smaller number of probesets, characterizing hypoxia-related biochemical pathways, are analyzed. l(1)-l(2) regularization identified novel and robust hypoxia signatures within apoptosis, glycolysis, and oxidative phosphorylation Gene Ontology classes. We conclude that the filtering approach overcomes the noisy nature of the microarray data and allows generating robust signatures suitable for biomarker discovery and patients risk assessment in a fraction of computer time.