Artificial neural network classifier predicts neuroblastoma patients' outcome

Predicting Neuroblastoma Patient Risk Groups, Outcomes, and Treatment Response Using Machine Learning Methods: A Review

Neuroblastoma, a paediatric malignancy with high rates of cancer-related morbidity and mortality, is of significant interest to the field of paediatric cancers. High-risk NB tumours are usually metastatic and result in survival rates of less than 50%. Machine learning approaches have been applied to various neuroblastoma patient data to retrieve relevant clinical and biological information and develop predictive models. Given this background, this study will catalogue and summarise the literature that has used machine learning and statistical methods to analyse data such as multi-omics, histological sections, and medical images to make clinical predictions. Furthermore, the question will be turned on its head, and the use of machine learning to accurately stratify NB patients by risk groups and to predict outcomes, including survival and treatment response, will be summarised. Overall, this study aims to catalogue and summarise the important work conducted to date on the subject of expression-based predictor models and machine learning in neuroblastoma for risk stratification and patient outcomes including survival, and treatment response which may assist and direct future diagnostic and therapeutic efforts.

Development and validation of a 21-gene prognostic signature in neuroblastoma

Survival outcomes for patients with neuroblastoma vary markedly and reliable prognostic markers and risk stratification tools are lacking. We sought to identify and validate a transcriptomic signature capable of predicting risk of mortality in patients with neuroblastoma. The TARGET NBL dataset (n = 243) was used to develop the model and two independent cohorts, E-MTAB-179 (n = 478) and GSE85047 (n = 240) were used as validation sets. EFS was the primary outcome and OS was the secondary outcome of interest for all analysis. We identified a 21-gene signature capable of stratifying neuroblastoma patients into high and low risk groups in the E-MTAB-179 (HR 5.87 [3.83-9.01], p < 0.0001, 5 year AUC 0.827) and GSE85047 (HR 3.74 [2.36-5.92], p < 0.0001, 5 year AUC 0.815) validation cohorts. Moreover, the signature remained independent of known clinicopathological variables, and remained prognostic within clinically important subgroups. Further, the signature was effectively incorporated into a risk model with clinicopathological variables to improve prognostic performance across validation cohorts (Pooled Validation HR 6.93 [4.89-9.83], p < 0.0001, 5 year AUC 0.839). Similar prognostic utility was also demonstrated with OS. The identified signature is a robust independent predictor of EFS and OS outcomes in neuroblastoma patients and can be combined with clinically utilized clinicopathological variables to improve prognostic performance.

Machine Learning as a Support for the Diagnosis of Type 2 Diabetes

Diabetes is a chronic, metabolic disease characterized by high blood sugar levels. Among the main types of diabetes, type 2 is the most common. Early diagnosis and treatment can prevent or delay the onset of complications. Previous studies examined the application of machine learning techniques for prediction of the pathology, and here an artificial neural network shows very promising results as a possible valuable aid in the management and prevention of diabetes. Additionally, its superior ability for long-term predictions makes it an ideal choice for this field of study. We utilized machine learning methods to uncover previously undiscovered associations between an individual’s health status and the development of type 2 diabetes, with the goal of accurately predicting its onset or determining the individual’s risk level. Our study employed a binary classifier, trained on scratch, to identify potential nonlinear relationships between the onset of type 2 diabetes and a set of parameters obtained from patient measurements. Three datasets were utilized, i.e., the National Center for Health Statistics’ (NHANES) biennial survey, MIMIC-III and MIMIC-IV. These datasets were then combined to create a single dataset with the same number of individuals with and without type 2 diabetes. Since the dataset was balanced, the primary evaluation metric for the model was accuracy. The outcomes of this study were encouraging, with the model achieving accuracy levels of up to 86% and a ROC AUC value of 0.934. Further investigation is needed to improve the reliability of the model by considering multiple measurements from the same patient over time.

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.

Artificial Intelligence in Pediatric Pathology: The Extinction of a Medical Profession or the Key to a Bright Future?

Artificial Intelligence (AI) has become of increasing interest over the past decade. While digital image analysis (DIA) is already being used in radiology, it is still in its infancy in pathology. One of the reasons is that large-scale digitization of glass slides has only recently become available. With the advent of digital slide scanners, that digitize glass slides into whole slide images, many labs are now in a transition phase towards digital pathology. However, only few departments worldwide are currently fully digital. Digital pathology provides the ability to annotate large datasets and train computers to develop and validate robust algorithms, similar to radiology. In this opinionated overview, we will give a brief introduction into AI in pathology, discuss the potential positive and negative implications and speculate about the future role of AI in the field of pediatric pathology.

Potential for Machine Learning in Burn Care

INTRODUCTION

Burn-related injuries are a leading cause of morbidity across the globe. Accurate assessment and treatment have been demonstrated to reduce the morbidity and mortality. This essay explores the forms of artificial intelligence to be implemented the field of burns management to optimise the care we deliver in the National Health Service (NHS) in the UK.

METHODS

Machine Learning methods which predict or classify are explored. This includes linear and logistic regression, artificial neural networks, deep learning, and decision tree analysis.

DISCUSSION

Utilizing Machine Learning in burns care holds potential from prevention, burns assessment, predicting mortality and critical care monitoring to healing time. Establishing a regional or national Machine Learning group would be the first step towards the development of these essential technologies.

CONCLUSION

The implementation of machine learning technologies will require buy-in from the NHS health boards, with significant implications with cost of investment, implementation, employment of machine learning teams and provision of training to medical professionals.

Connectivity Map Analysis Indicates PI3K/Akt/mTOR Inhibitors as Potential Anti-Hypoxia Drugs in Neuroblastoma

Neuroblastoma (NB) is one of the deadliest pediatric cancers, accounting for 15% of deaths in childhood. Hypoxia is a condition of low oxygen tension occurring in solid tumors and has an unfavorable prognostic factor for NB. In the present study, we aimed to identify novel promising drugs for NB treatment. Connectivity Map (CMap), an online resource for drug repurposing, was used to identify connections between hypoxia-modulated genes in NB tumors and compounds. Two sets of 34 and 21 genes up- and down-regulated between hypoxic and normoxic primary NB tumors, respectively, were analyzed with CMap. The analysis reported a significant negative connectivity score across nine cell lines for 19 compounds mainly belonging to the class of PI3K/Akt/mTOR inhibitors. The gene expression profiles of NB cells cultured under hypoxic conditions and treated with the mTORC complex inhibitor PP242, referred to as the Mohlin dataset, was used to validate the CMap findings. A heat map representation of hypoxia-modulated genes in the Mohlin dataset and the gene set enrichment analysis (GSEA) showed an opposite regulation of these genes in the set of NB cells treated with the mTORC inhibitor PP242. In conclusion, our analysis identified inhibitors of the PI3K/Akt/mTOR signaling pathway as novel candidate compounds to treat NB patients with hypoxic tumors and a poor prognosis.

Data analytics and clinical feature ranking of medical records of patients with sepsis

Background

Sepsis is a life-threatening clinical condition that happens when the patient’s body has an excessive reaction to an infection, and should be treated in one hour. Due to the urgency of sepsis, doctors and physicians often do not have enough time to perform laboratory tests and analyses to help them forecast the consequences of the sepsis episode. In this context, machine learning can provide a fast computational prediction of sepsis severity, patient survival, and sequential organ failure by just analyzing the electronic health records of the patients. Also, machine learning can be employed to understand which features in the medical records are more predictive of sepsis severity, of patient survival, and of sequential organ failure in a fast and non-invasive way.

Dataset and methods

In this study, we analyzed a dataset of electronic health records of 364 patients collected between 2014 and 2016. The medical record of each patient has 29 clinical features, and includes a binary value for survival, a binary value for septic shock, and a numerical value for the sequential organ failure assessment (SOFA) score. We disjointly utilized each of these three factors as an independent target, and employed several machine learning methods to predict it (binary classifiers for survival and septic shock, and regression analysis for the SOFA score). Afterwards, we used a data mining approach to identify the most important dataset features in relation to each of the three targets separately, and compared these results with the results achieved through a standard biostatistics approach.

Results and conclusions

Our results showed that machine learning can be employed efficiently to predict septic shock, SOFA score, and survival of patients diagnoses with sepsis, from their electronic health records data. And regarding clinical feature ranking, our results showed that Random Forests feature selection identified several unexpected symptoms and clinical components as relevant for septic shock, SOFA score, and survival. These discoveries can help doctors and physicians in understanding and predicting septic shock. We made the analyzed dataset and our developed software code publicly available online.

Supplementary Information

The online version contains supplementary material available at (10.1186/s13040-021-00235-0).

Siamese Neural Networks: An Overview

Similarity has always been a key aspect in computer science and statistics. Any time two element vectors are compared, many different similarity approaches can be used, depending on the final goal of the comparison (Euclidean distance, Pearson correlation coefficient, Spearman's rank correlation coefficient, and others). But if the comparison has to be applied to more complex data samples, with features having different dimensionality and types which might need compression before processing, these measures would be unsuitable. In these cases, a siamese neural network may be the best choice: it consists of two identical artificial neural networks each capable of learning the hidden representation of an input vector. The two neural networks are both feedforward perceptrons, and employ error back-propagation during training; they work parallelly in tandem and compare their outputs at the end, usually through a cosine distance. The output generated by a siamese neural network execution can be considered the semantic similarity between the projected representation of the two input vectors. In this overview we first describe the siamese neural network architecture, and then we outline its main applications in a number of computational fields since its appearance in 1994. Additionally, we list the programming languages, software packages, tutorials, and guides that can be practically used by readers to implement this powerful machine learning model.

Artificial neural network-based models used for predicting 28- and 90-day mortality of patients with hepatitis B-associated acute-on-chronic liver failure

Background

This study aimed to develop prognostic models for predicting 28- and 90-day mortality rates of hepatitis B virus (HBV)-associated acute-on-chronic liver failure (HBV-ACLF) through artificial neural network (ANN) systems.

Methods

Six hundred and eight-four cases of consecutive HBV-ACLF patients were retrospectively reviewed. Four hundred and twenty-three cases were used for training and constructing ANN models, and the remaining 261 cases were for validating the established models. Predictors associated with mortality were determined by univariate analysis and were then included in ANN models for predicting prognosis of mortality. The receiver operating characteristic curve analysis was used to evaluate the predictive performance of the ANN models in comparison with various current prognostic models.

Results

Variables with statistically significant difference or important clinical characteristics were input in the ANN training process, and eight independent risk factors, including age, hepatic encephalopathy, serum sodium, prothrombin activity, γ-glutamyltransferase, hepatitis B e antigen, alkaline phosphatase and total bilirubin, were eventually used to establish ANN models. For 28-day mortality in the training cohort, the model’s predictive accuracy (AUR 0.948, 95% CI 0.925–0.970) was significantly higher than that of the Model for End-stage Liver Disease (MELD), MELD-sodium (MELD-Na), Chronic Liver Failure-ACLF (CLIF-ACLF), and Child-Turcotte-Pugh (CTP) (all p < 0.001). In the validation cohorts the predictive accuracy of ANN model (AUR 0.748, 95% CI: 0.673–0.822) was significantly higher than that of MELD (p = 0.0099) and insignificantly higher than that of MELD-Na, CTP and CLIF-ACLF (p > 0.05). For 90-day mortality in the training cohort, the model’s predictive accuracy (AUR 0.913, 95% CI 0.887–0.938) was significantly higher than that of MELD, MELD-Na, CTP and CLIF-ACLF (all p < 0.001). In the validation cohorts, the prediction accuracy of the ANN model (AUR 0.754, 95% CI: 0.697–0.812 was significantly higher than that of MELD (p = 0.019) and insignificantly higher than MELD-Na, CTP and CLIF-ACLF (p > 0.05).

Conclusions

The established ANN models can more accurately predict short-term mortality risk in patients with HBV- ACLF.

The main content has been postered as an abstract at the AASLD Hepatology Conference (10.1002/hep.30257).

Hypoxia in the Initiation and Progression of Neuroblastoma Tumours

Neuroblastoma is the most frequent extracranial solid tumour in children, causing 10% of all paediatric oncology deaths. It arises in the embryonic neural crest due to an uncontrolled behaviour of sympathetic nervous system progenitors, giving rise to heterogeneous tumours. Low local or systemic tissue oxygen concentration has emerged as a cellular stimulus with important consequences for tumour initiation, evolution and progression. In neuroblastoma, several evidences point towards a role of hypoxia in tumour initiation during development, tumour cell differentiation, survival and metastatic spreading. However, the heterogeneous nature of the disease, its developmental origin and the lack of suitable experimental models have complicated a clear understanding of the effect of hypoxia in neuroblastoma tumour progression and the molecular mechanisms implicated. In this review, we have compiled available evidences to try to shed light onto this important field. In particular, we explore the effect of hypoxia in neuroblastoma cell transformation and differentiation. We also discuss the experimental models available and the emerging alternatives to study this problem, and we present hypoxia-related therapeutic avenues being explored in the field.

Cumulative Risk and Impact Modeling on Environmental Chemical and Social Stressors

PURPOSE OF REVIEW

The goal of this review is to identify cumulative modeling methods used to evaluate combined effects of exposures to environmental chemicals and social stressors. The specific review question is: What are the existing quantitative methods used to examine the cumulative impacts of exposures to environmental chemical and social stressors on health?

RECENT FINDINGS

There has been an increase in literature that evaluates combined effects of exposures to environmental chemicals and social stressors on health using regression models; very few studies applied other data mining and machine learning techniques to this problem. The majority of studies we identified used regression models to evaluate combined effects of multiple environmental and social stressors. With proper study design and appropriate modeling assumptions, additional data mining methods may be useful to examine combined effects of environmental and social stressors.

Computational prediction of diagnosis and feature selection on mesothelioma patient health records

BACKGROUND

Mesothelioma is a lung cancer that kills thousands of people worldwide annually, especially those with exposure to asbestos. Diagnosis of mesothelioma in patients often requires time-consuming imaging techniques and biopsies. Machine learning can provide for a more effective, cheaper, and faster patient diagnosis and feature selection from clinical data in patient records.

METHODS AND FINDINGS

We analyzed a dataset of health records of 324 patients having mesothelioma symptoms from Turkey. The patients had prior asbestos exposure and displayed symptoms consistent with mesothelioma. We compared probabilistic neural network, perceptron-based neural network, random forest, one rule, and decision tree classifiers to predict diagnosis of the patient records. We measured classifiers' performance through standard confusion matrix scores such as Matthews correlation coefficient (MCC). Random forest outperformed all models tried, obtaining MCC = +0.37 on the complete imbalanced dataset and MCC = +0.64 on the under-sampled balanced dataset. We then employed random forest feature selection to identify the two most relevant dataset traits associated with mesothelioma: lung side and platelet count. These two risk factors resulted so predictive, that decision tree focusing on them achieved the second top accuracy on the complete dataset diagnosis prediction (MCC = +0.28), outperforming all other methods and even decision tree itself applied to all features.

CONCLUSIONS

Our results show that machine learning can predict diagnoses of patients having mesothelioma symptoms with high accuracy, sensitivity, and specificity, in few minutes. Additionally, random forest can efficiently select the most important features of this clinical dataset (lung side and platelet count) in few seconds. The importance of pleural plaques in lung sides and blood platelets in mesothelioma diagnosis indicates that physicians should focus on these two features when reading records of patients with mesothelioma symptoms. Moreover, doctors can exploit our machinery to predict patient diagnosis when only lung side and platelet data are available.

Distillation of the clinical algorithm improves prognosis by multi-task deep learning in high-risk Neuroblastoma

We introduce the CDRP (Concatenated Diagnostic-Relapse Prognostic) architecture for multi-task deep learning that incorporates a clinical algorithm, e.g., a risk stratification schema to improve prognostic profiling. We present the first application to survival prediction in High-Risk (HR) Neuroblastoma from transcriptomics data, a task that studies from the MAQC consortium have shown to remain the hardest among multiple diagnostic and prognostic endpoints predictable from the same dataset. To obtain a more accurate risk stratification needed for appropriate treatment strategies, CDRP combines a first component (CDRP-A) synthesizing a diagnostic task and a second component (CDRP-N) dedicated to one or more prognostic tasks. The approach leverages the advent of semi-supervised deep learning structures that can flexibly integrate multimodal data or internally create multiple processing paths. CDRP-A is an autoencoder trained on gene expression on the HR/non-HR risk stratification by the Children’s Oncology Group, obtaining a 64-node representation in the bottleneck layer. CDRP-N is a multi-task classifier for two prognostic endpoints, i.e., Event-Free Survival (EFS) and Overall Survival (OS). CDRP-A provides the HR embedding input to the CDRP-N shared layer, from which two branches depart to model EFS and OS, respectively. To control for selection bias, CDRP is trained and evaluated using a Data Analysis Protocol (DAP) developed within the MAQC initiative. CDRP was applied on Illumina RNA-Seq of 498 Neuroblastoma patients (HR: 176) from the SEQC study (12,464 Entrez genes) and on Affymetrix Human Exon Array expression profiles (17,450 genes) of 247 primary diagnostic Neuroblastoma of the TARGET NBL cohort. On the SEQC HR patients, CDRP achieves Matthews Correlation Coefficient (MCC) 0.38 for EFS and MCC = 0.19 for OS in external validation, improving over published SEQC models. We show that a CDRP-N embedding is indeed parametrically associated to increasing severity and the embedding can be used to better stratify patients’ survival.

Hypoxia Modifies the Transcriptome of Human NK Cells, Modulates Their Immunoregulatory Profile, and Influences NK Cell Subset Migration

Hypoxia, which characterizes most tumor tissues, can alter the function of different immune cell types, favoring tumor escape mechanisms. In this study, we show that hypoxia profoundly acts on NK cells by influencing their transcriptome, affecting their immunoregulatory functions, and changing the chemotactic responses of different NK cell subsets. Exposure of human peripheral blood NK cells to hypoxia for 16 or 96 h caused significant changes in the expression of 729 or 1,100 genes, respectively. Gene Set Enrichment Analysis demonstrated that these changes followed a consensus hypoxia transcriptional profile. As assessed by Gene Ontology annotation, hypoxia-targeted genes were implicated in several biological processes: metabolism, cell cycle, differentiation, apoptosis, cell stress, and cytoskeleton organization. The hypoxic transcriptome also showed changes in genes with immunological relevance including those coding for proinflammatory cytokines, chemokines, and chemokine-receptors. Quantitative RT-PCR analysis confirmed the modulation of several immune-related genes, prompting further immunophenotypic and functional studies. Multiplex ELISA demonstrated that hypoxia could variably reduce NK cell ability to release IFNγ, TNFα, GM-CSF, CCL3, and CCL5 following PMA+Ionomycin or IL15+IL18 stimulation, while it poorly affected the response to IL12+IL18. Cytofluorimetric analysis showed that hypoxia could influence NK chemokine receptor pattern by sustaining the expression of CCR7 and CXCR4. Remarkably, this effect occurred selectively (CCR7) or preferentially (CXCR4) on CD56^bright NK cells, which indeed showed higher chemotaxis to CCL19, CCL21, or CXCL12. Collectively, our data suggest that the hypoxic environment may profoundly influence the nature of the NK cell infiltrate and its effects on immune-mediated responses within tumor tissues.

Prognostic significance of microsatellite instability‑associated pathways and genes in gastric cancer

The aim of the present study was to reveal the potential molecular mechanisms of microsatellite instability (MSI) on the prognosis of gastric cancer (GC). The investigation was performed based on an RNAseq expression profiling dataset downloaded from The Cancer Genome Atlas, including 64 high‑level MSI (MSI‑H) GC samples, 44 low‑level MSI (MSI‑L) GC samples and 187 stable microsatellite (MSI‑S) GC samples. Differentially expressed genes (DEGs) were identified between the MSI‑H, MSI‑L and MSI‑S samples. Pathway enrichment analysis was performed for the identified DEGs and the pathway deviation scores of the significant enrichment pathways were calculated. A Multi‑Layer Perceptron (MLP) classifier, based on the different pathways associated with the MSI statuses was constructed for predicting the outcome of patients with GC, which was validated in another independent dataset. A total of 190 DEGs were selected between the MSI‑H, MSI‑L and MSI‑S samples. The MLP classifier was established based on the deviation scores of 10 significant pathways, among which antigen processing and presentation, and inflammatory bowel disease pathways were significantly enriched with HLA‑DRB5, HLA‑DMA, HLA‑DQA1 and HLA‑DRA; the measles, toxoplasmosis and herpes simplex infection pathways were significantly enriched with Janus kinase 2 (JAK2), caspase‑8 (CASP8) and Fas. The classifier performed well on an independent validation set with 100 GC samples. Taken together, the results indicated that MSI status may affect GC prognosis, partly through the antigen processing and presentation, inflammatory bowel disease, measles, toxoplasmosis and herpes simplex infection pathways. HLA‑DRB5, HLA‑DMA, HLA‑DQA1, HLA‑DRA, JAK2, CASP8 and Fas may be predictive factors for prognosis in GC.

CHL1 gene acts as a tumor suppressor in human neuroblastoma

Neuroblastoma is an aggressive, relapse-prone childhood tumor of the sympathetic nervous system that accounts for 15% of pediatric cancer deaths. A distal portion of human chromosome 3p is often deleted in neuroblastoma, this region may contain one or more putative tumor suppressor genes. A 2.54 Mb region at 3p26.3 encompassing the smallest region of deletion pinpointed CHL1 gene, the locus for neuronal cell adhesion molecule close homolog of L1. We found that low CHL1 expression predicted poor outcome in neuroblastoma patients. Here we have used two inducible cell models to analyze the impact of CHL1 on neuroblastoma biology. Over-expression of CHL1 induced neurite-like outgrowth and markers of neuronal differentiation in neuroblastoma cells, halted tumor progression, inhibited anchorage-independent colony formation, and suppressed the growth of human tumor xenografts. Conversely, knock-down of CHL1 induced neurite retraction and activation of Rho GTPases, enhanced cell proliferation and migration, triggered colony formation and anchorage-independent growth, accelerated growth in orthotopic xenografts mouse model. Our findings demonstrate unambiguously that CHL1 acts as a regulator of proliferation and differentiation of neuroblastoma cells through inhibition of the MAPKs and Akt pathways. CHL1 is a novel candidate tumor suppressor in neuroblastoma, and its associated pathways may represent a promising target for future therapeutic interventions.

A review of machine learning in obesity

Rich sources of obesity-related data arising from sensors, smartphone apps, electronic medical health records and insurance data can bring new insights for understanding, preventing and treating obesity. For such large datasets, machine learning provides sophisticated and elegant tools to describe, classify and predict obesity-related risks and outcomes. Here, we review machine learning methods that predict and/or classify such as linear and logistic regression, artificial neural networks, deep learning and decision tree analysis. We also review methods that describe and characterize data such as cluster analysis, principal component analysis, network science and topological data analysis. We introduce each method with a high-level overview followed by examples of successful applications. The algorithms were then applied to National Health and Nutrition Examination Survey to demonstrate methodology, utility and outcomes. The strengths and limitations of each method were also evaluated. This summary of machine learning algorithms provides a unique overview of the state of data analysis applied specifically to obesity.

Supervised deep learning embeddings for the prediction of cervical cancer diagnosis

Cervical cancer remains a significant cause of mortality all around the world, even if it can be prevented and cured by removing affected tissues in early stages. Providing universal and efficient access to cervical screening programs is a challenge that requires identifying vulnerable individuals in the population, among other steps. In this work, we present a computationally automated strategy for predicting the outcome of the patient biopsy, given risk patterns from individual medical records. We propose a machine learning technique that allows a joint and fully supervised optimization of dimensionality reduction and classification models. We also build a model able to highlight relevant properties in the low dimensional space, to ease the classification of patients. We instantiated the proposed approach with deep learning architectures, and achieved accurate prediction results (top area under the curve AUC = 0.6875) which outperform previously developed methods, such as denoising autoencoders. Additionally, we explored some clinical findings from the embedding spaces, and we validated them through the medical literature, making them reliable for physicians and biomedical researchers.

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.

BITS 2015: the annual meeting of the Italian Society of Bioinformatics

This preface introduces the content of the BioMed Central journal Supplements related to the BITS 2015 meeting, held in Milan, Italy, from the 3^th to the 5^th of June, 2015.