Predicting clinical outcome of neuroblastoma patients using an integrative network-based approach

An integrated analysis of the cancer genome atlas data discovers a hierarchical association structure across thirty three cancer types

Cancer cells harbor molecular alterations at all levels of information processing. Genomic/epigenomic and transcriptomic alterations are inter-related between genes, within and across cancer types and may affect clinical phenotypes. Despite the abundant prior studies of integrating cancer multi-omics data, none of them organizes these associations in a hierarchical structure and validates the discoveries in extensive external data. We infer this Integrated Hierarchical Association Structure (IHAS) from the complete data of The Cancer Genome Atlas (TCGA) and compile a compendium of cancer multi-omics associations. Intriguingly, diverse alterations on genomes/epigenomes from multiple cancer types impact transcriptions of 18 Gene Groups. Half of them are further reduced to three Meta Gene Groups enriched with (1) immune and inflammatory responses, (2) embryonic development and neurogenesis, (3) cell cycle process and DNA repair. Over 80% of the clinical/molecular phenotypes reported in TCGA are aligned with the combinatorial expressions of Meta Gene Groups, Gene Groups, and other IHAS subunits. Furthermore, IHAS derived from TCGA is validated in more than 300 external datasets including multi-omics measurements and cellular responses upon drug treatments and gene perturbations in tumors, cancer cell lines, and normal tissues. To sum up, IHAS stratifies patients in terms of molecular signatures of its subunits, selects targeted genes or drugs for precision cancer therapy, and demonstrates that associations between survival times and transcriptional biomarkers may vary with cancer types. These rich information is critical for diagnosis and treatments of cancers.

Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma

Multi-omics data are increasingly being gathered for investigations of complex diseases such as cancer. However, high dimensionality, small sample size, and heterogeneity of different omics types pose huge challenges to integrated analysis. In this paper, we evaluate two network-based approaches for integration of multi-omics data in an application of clinical outcome prediction of neuroblastoma. We derive Patient Similarity Networks (PSN) as the first step for individual omics data by computing distances among patients from omics features. The fusion of different omics can be investigated in two ways: the network-level fusion is achieved using Similarity Network Fusion algorithm for fusing the PSNs derived for individual omics types; and the feature-level fusion is achieved by fusing the network features obtained from individual PSNs. We demonstrate our methods on two high-risk neuroblastoma datasets from SEQC project and TARGET project. We propose Deep Neural Network and Machine Learning methods with Recursive Feature Elimination as the predictor of survival status of neuroblastoma patients. Our results indicate that network-level fusion outperformed feature-level fusion for integration of different omics data whereas feature-level fusion is more suitable incorporating different feature types derived from same omics type. We conclude that the network-based methods are capable of handling heterogeneity and high dimensionality well in the integration of multi-omics.

Identification of Drug-Disease Associations by Using Multiple Drug and Disease Networks

Background:

Drug repositioning is a new research area in drug development. It aims to discover novel therapeutic uses of existing drugs. It could accelerate the process of designing novel drugs for some diseases and considerably decrease the cost. The traditional method to determine novel therapeutic uses of an existing drug is quite laborious. It is alternative to design computational methods to overcome such defect.

Objective:

This study aims to propose a novel model for the identification of drug–disease associations.

Method:

Twelve drug networks and three disease networks were built, which were fed into a powerful network-embedding algorithm called Mashup to produce informative drug and disease features. These features were combined to represent each drug–disease association. Classic classification algorithm, random forest, was used to build the model.

Results:

Tenfold cross-validation results indicated that the MCC, AUROC, and AUPR were 0.7156, 0.9280, and 0.9191, respectively.

Conclusion:

The proposed model showed good performance. Some tests indicated that a small dimension of drug features and a large dimension of disease features were beneficial for constructing the model. Moreover, the model was quite robust even if some drug or disease properties were not available.

Molecular Mechanisms and Function of the p53 Protein Family Member - p73

Over 20 years after identification of p53 and its crucial function in cancer progression, two members of the same protein family were identified, namely p63 and p73. Since then, a body of information has been accumulated on each of these genes and their interrelations. Biological role of p73 has been elucidated thanks to four distinct knockout mice models: (i) with deletion of the entire TP73 gene, (ii) with deletion of exons encoding the full length TAp73 isoforms, (iii) with deletions of exons encoding the shorter DNp73 isoform, and (iv) with deletion of exons encoding C-terminal of the alpha isoform. This work, as well as expression studies in cancer and overwhelming body of molecular studies, allowed establishing major role of TP73 both in cancer and in neuro-development, as well as ciliogenesis, and metabolism. Here, we recapitulate the major milestones of this endeavor.

iMPTCE-Hnetwork: A Multilabel Classifier for Identifying Metabolic Pathway Types of Chemicals and Enzymes with a Heterogeneous Network

Metabolic pathway is an important type of biological pathways. It produces essential molecules and energies to maintain the life of living organisms. Each metabolic pathway consists of a chain of chemical reactions, which always need enzymes to participate in. Thus, chemicals and enzymes are two major components for each metabolic pathway. Although several metabolic pathways have been uncovered, the metabolic pathway system is still far from complete. Some hidden chemicals or enzymes are not discovered in a certain metabolic pathway. Besides the traditional experiments to detect hidden chemicals or enzymes, an alternative pipeline is to design efficient computational methods. In this study, we proposed a powerful multilabel classifier, called iMPTCE-Hnetwork, to uniformly assign chemicals and enzymes to metabolic pathway types reported in KEGG. Such classifier adopted the embedding features derived from a heterogeneous network, which defined chemicals and enzymes as nodes and the interactions between chemicals and enzymes as edges, through a powerful network embedding algorithm, Mashup. The popular RAndom k-labELsets (RAKEL) algorithm was employed to construct the classifier, which incorporated the support vector machine (polynomial kernel) as the basic classifier. The ten-fold cross-validation results indicated that such a classifier had good performance with accuracy higher than 0.800 and exact match higher than 0.750. Several comparisons were done to indicate the superiority of the iMPTCE-Hnetwork.

The ZNF750-RAC1 axis as potential prognostic factor for breast cancer

The human zinc finger (C2H2-type) protein ZNF750 is a transcription factor regulated by p63 that plays a critical role in epithelial tissues homoeostasis, as well as being involved in the pathogenesis of cancer. Indeed, missense mutations, truncation and genomic deletion have been found in oesophageal squamous cell carcinoma. In keeping, we showed that ZNF750 negatively regulates cell migration and invasion in breast cancer cells; in particular, ZNF750 binds and recruits KDM1A and HDAC1 on the LAMB3 and CTNNAL1 promoters. This interaction, in turn, represses the transcription of LAMB3 and CTNNAL1 genes, which are involved in cell migration and invasion. Given that ZNF750 is emerging as a crucial transcription factor that acts as tumour suppressor gene, here, we show that ZNF750 represses the expression of the small GTPase, Ras-related C3 botulinum toxin substrate 1 (RAC1) in breast cancer cell lines, by directly binding its promoter region. In keeping with ZNF750 controlling RAC1 expression, we found an inverse correlation between ZNF750 and RAC1 in human breast cancer datasets. More importantly, we found a significant upregulation of RAC1 in human breast cancer datasets and we identified a direct correlation between RAC1 expression and the survival rate of breast cancer patient. Overall, our findings provide a novel molecular mechanism by which ZNF750 acts as tumour suppressor gene. Hence, we report a potential clinical relevance of ZNF750/RAC1 axis in breast cancer.

Liquid biopsies and cancer omics

The development of the sequencing technologies allowed the generation of huge amounts of molecular data from a single cancer specimen, allowing the clinical oncology to enter the era of the precision medicine. This massive amount of data is highlighting new details on cancer pathogenesis but still relies on tissue biopsies, which are unable to capture the dynamic nature of cancer through its evolution. This assumption led to the exploration of non-tissue sources of tumoral material opening the field of liquid biopsies. Blood, together with body fluids such as urines, or stool, from cancer patients, are analyzed applying the techniques used for the generation of omics data. With blood, this approach would allow to take into account tumor heterogeneity (since the circulating components such as CTCs, ctDNA, or ECVs derive from each cancer clone) in a time dependent manner, resulting in a somehow "real-time" understanding of cancer evolution. Liquid biopsies are beginning nowdays to be applied in many cancer contexts and are at the basis of many clinical trials in oncology.

Cancer predictive studies

The identification of individual or clusters of predictive genetic alterations might help in defining the outcome of cancer treatment, allowing for the stratification of patients into distinct cohorts for selective therapeutic protocols. Neuroblastoma (NB) is the most common extracranial childhood tumour, clinically defined in five distinct stages (1–4 & 4S), where stages 3–4 define chemotherapy-resistant, highly aggressive disease phases. NB is a model for geneticists and molecular biologists to classify genetic abnormalities and identify causative disease genes. Despite highly intensive basic research, improvements on clinical outcome have been predominantly observed for less aggressive cancers, that is stages 1,2 and 4S. Therefore, stages 3–4 NB are still complicated at the therapeutic level and require more intense fundamental research. Using neuroblastoma as a model system, here we herein outline how cancer prediction studies can help at steering preclinical and clinical research toward the identification and exploitation of specific genetic landscape. This might result in maximising the therapeutic success and minimizing harmful effects in cancer patients.

Drug Target Group Prediction with Multiple Drug Networks

Background:

Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments.

Methods:

In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model.

Results and Conclusion:

Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

Background

The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the “small n large p” problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.

Methods

We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients’ omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers.

Results

We apply this strategy to four neuroblastoma datasets and observe that models based on neural networks are more accurate than state of the art models (DNN: 85%-87%, SVM/RF: 75%-82%). We explore how different parameters and configurations are selected in order to overcome the effects of the small data problem as well as the curse of dimensionality.

Conclusions

Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes.

Predicting Drug Side Effects with Compact Integration of Heterogeneous Networks

Background:

The side effects of drugs are not only harmful to humans but also the major reasons for withdrawing approved drugs, bringing greater risks for pharmaceutical companies. However, detecting the side effects for a given drug via traditional experiments is time- consuming and expensive. In recent years, several computational methods have been proposed to predict the side effects of drugs. However, most of the methods cannot effectively integrate the heterogeneous properties of drugs.

Methods:

In this study, we adopted a network embedding method, Mashup, to extract essential and informative drug features from several drug heterogeneous networks, representing different properties of drugs. For side effects, a network was also built, from where side effect features were extracted. These features can capture essential information about drugs and side effects in a network level. Drug and side effect features were combined together to represent each pair of drug and side effect, which was deemed as a sample in this study. Furthermore, they were fed into a random forest (RF) algorithm to construct the prediction model, called the RF network model.

Results:

The RF network model was evaluated by several tests. The average of Matthews correlation coefficients on the balanced and unbalanced datasets was 0.640 and 0.641, respectively.

Conclusion:

The RF network model was superior to the models incorporating other machine learning algorithms and one previous model. Finally, we also investigated the influence of two feature dimension parameters on the RF network model and found that our model was not very sensitive to these parameters.

A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models

Background

Recently high-throughput technologies have been massively used alongside clinical tests to study various types of cancer. Data generated in such large-scale studies are heterogeneous, of different types and formats. With lack of effective integration strategies novel models are necessary for efficient and operative data integration, where both clinical and molecular information can be effectively joined for storage, access and ease of use. Such models, combined with machine learning methods for accurate prediction of survival time in cancer studies, can yield novel insights into disease development and lead to precise personalized therapies.

Results

We developed an approach for intelligent data integration of two cancer datasets (breast cancer and neuroblastoma) − provided in the CAMDA 2018 ‘Cancer Data Integration Challenge’, and compared models for prediction of survival time. We developed a novel semantic network-based data integration framework that utilizes NoSQL databases, where we combined clinical and expression profile data, using both raw data records and external knowledge sources. Utilizing the integrated data we introduced Tumor Integrated Clinical Feature (TICF) − a new feature for accurate prediction of patient survival time. Finally, we applied and validated several machine learning models for survival time prediction.

Conclusion

We developed a framework for semantic integration of clinical and omics data that can borrow information across multiple cancer studies. By linking data with external domain knowledge sources our approach facilitates enrichment of the studied data by discovery of internal relations. The proposed and validated machine learning models for survival time prediction yielded accurate results.

Reviewers

This article was reviewed by Eran Elhaik, Wenzhong Xiao and Carlos Loucera.