Network-induced classification kernels for gene expression profile analysis

Multi-level attention graph neural network based on co-expression gene modules for disease diagnosis and prognosis

MOTIVATION

Advanced deep learning techniques have been widely applied in disease diagnosis and prognosis with clinical omics, especially gene expression data. In the regulation of biological processes and disease progression, genes often work interactively rather than individually. Therefore, investigating gene association information and co-functional gene modules can facilitate disease state prediction.

RESULTS

To explore the gene modules and inter-gene relational information contained in the omics data, we propose a novel multi-level attention graph neural network (MLA-GNN) for disease diagnosis and prognosis. Specifically, we format omics data into co-expression graphs via weighted correlation network analysis, and then construct multi-level graph features, finally fuse them through a well-designed multi-level graph feature fully fusion module to conduct predictions. For model interpretation, a novel full-gradient graph saliency mechanism is developed to identify the disease-relevant genes. MLA-GNN achieves state-of-the-art performance on transcriptomic data from TCGA-LGG/TCGA-GBM and proteomic data from coronavirus disease 2019 (COVID-19)/non-COVID-19 patient sera. More importantly, the relevant genes selected by our model are interpretable and are consistent with the clinical understanding.

AVAILABILITYAND IMPLEMENTATION

The codes are available at https://github.com/TencentAILabHealthcare/MLA-GNN.

A Hierarchical Graph Convolution Network for Representation Learning of Gene Expression Data

The curse of dimensionality, which is caused by high-dimensionality and low-sample-size, is a major challenge in gene expression data analysis. However, the real situation is even worse: labelling data is laborious and time-consuming, so only a small part of the limited samples will be labelled. Having such few labelled samples further increases the difficulty of training deep learning models. Interpretability is an important requirement in biomedicine. Many existing deep learning methods are trying to provide interpretability, but rarely apply to gene expression data. Recent semi-supervised graph convolution network methods try to address these problems by smoothing the label information over a graph. However, to the best of our knowledge, these methods only utilize graphs in either the feature space or sample space, which restrict their performance. We propose a transductive semi-supervised representation learning method called a hierarchical graph convolution network (HiGCN) to aggregate the information of gene expression data in both feature and sample spaces. HiGCN first utilizes external knowledge to construct a feature graph and a similarity kernel to construct a sample graph. Then, two spatial-based GCNs are used to aggregate information on these graphs. To validate the model's performance, synthetic and real datasets are provided to lend empirical support. Compared with two recent models and three traditional models, HiGCN learns better representations of gene expression data, and these representations improve the performance of downstream tasks, especially when the model is trained on a few labelled samples. Important features can be extracted from our model to provide reliable interpretability.

forgeNet: a graph deep neural network model using tree-based ensemble classifiers for feature graph construction

MOTIVATION

A unique challenge in predictive model building for omics data has been the small number of samples (n) versus the large amount of features (p). This 'n≪p' property brings difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating known functional relationships between the biological units, such as the graph-embedded deep feedforward network (GEDFN) model, has been a solution to this issue. However, such methods require an existing feature graph, and potential mis-specification of the feature graph can be harmful on classification and feature selection.

RESULTS

To address this limitation and develop a robust classification model without relying on external knowledge, we propose a forest graph-embedded deep feedforward network (forgeNet) model, to integrate the GEDFN architecture with a forest feature graph extractor, so that the feature graph can be learned in a supervised manner and specifically constructed for a given prediction task. To validate the method's capability, we experimented the forgeNet model with both synthetic and real datasets. The resulting high classification accuracy suggests that the method is a valuable addition to sparse deep learning models for omics data.

AVAILABILITY AND IMPLEMENTATION

The method is available at https://github.com/yunchuankong/forgeNet.

CONTACT

tianwei.yu@emory.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prognostic prediction of carcinoma by a differential-regulatory-network-embedded deep neural network

The accurate prognostic prediction is essential for precise diagnosis and treatment of carcinoma. In addition to clinical survival prediction method, many computational methods based on transcriptomic data have been proposed to build the prediction models and study the prognosis of cancer patients. We propose a differential-regulatory-network-embedded deep neural network (DRE-DNN) method by integrating differential regulatory analysis based on gene co-expression network and deep neural network (DNN) method. From three public hepatocellular carcinoma (HCC) datasets, we derive differential regulatory network and embed regulatory information into DNN. By employing 1869 differential regulatory genes and survival data, we apply DRE-DNN to build a prediction model. We compare our method with the one which has all gene features in normal DNN, and results show that our method has better generalization ability and accuracy. We modify the normal DNN and develop an efficient method to predict prognosis of HCC from gene expression data. Our method decreases the inconsistence caused by the overfitting problem when the training sample size is small. DRE-DNN is also extendable for prognostic prediction of other cancers.

Tissue-guided LASSO for prediction of clinical drug response using preclinical samples

Prediction of clinical drug response (CDR) of cancer patients, based on their clinical and molecular profiles obtained prior to administration of the drug, can play a significant role in individualized medicine. Machine learning models have the potential to address this issue but training them requires data from a large number of patients treated with each drug, limiting their feasibility. While large databases of drug response and molecular profiles of preclinical in-vitro cancer cell lines (CCLs) exist for many drugs, it is unclear whether preclinical samples can be used to predict CDR of real patients. We designed a systematic approach to evaluate how well different algorithms, trained on gene expression and drug response of CCLs, can predict CDR of patients. Using data from two large databases, we evaluated various linear and non-linear algorithms, some of which utilized information on gene interactions. Then, we developed a new algorithm called TG-LASSO that explicitly integrates information on samples' tissue of origin with gene expression profiles to improve prediction performance. Our results showed that regularized regression methods provide better prediction performance. However, including the network information or common methods of including information on the tissue of origin did not improve the results. On the other hand, TG-LASSO improved the predictions and distinguished resistant and sensitive patients for 7 out of 13 drugs. Additionally, TG-LASSO identified genes associated with the drug response, including known targets and pathways involved in the drugs' mechanism of action. Moreover, genes identified by TG-LASSO for multiple drugs in a tissue were associated with patient survival. In summary, our analysis suggests that preclinical samples can be used to predict CDR of patients and identify biomarkers of drug sensitivity and survival.

A Deep Neural Network Model using Random Forest to Extract Feature Representation for Gene Expression Data Classification

In predictive model development, gene expression data is associated with the unique challenge that the number of samples (n) is much smaller than the amount of features (p). This "n ≪ p" property has prevented classification of gene expression data from deep learning techniques, which have been proved powerful under "n > p" scenarios in other application fields, such as image classification. Further, the sparsity of effective features with unknown correlation structures in gene expression profiles brings more challenges for classification tasks. To tackle these problems, we propose a newly developed classifier named Forest Deep Neural Network (fDNN), to integrate the deep neural network architecture with a supervised forest feature detector. Using this built-in feature detector, the method is able to learn sparse feature representations and feed the representations into a neural network to mitigate the overfitting problem. Simulation experiments and real data analyses using two RNA-seq expression datasets are conducted to evaluate fDNN's capability. The method is demonstrated a useful addition to current predictive models with better classification performance and more meaningful selected features compared to ordinary random forests and deep neural networks.

A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data

Motivation

Gene expression data represents a unique challenge in predictive model building, because of the small number of samples (n) compared with the huge amount of features (p). This 'n≪p' property has hampered application of deep learning techniques for disease outcome classification. Sparse learning by incorporating external gene network information could be a potential solution to this issue. Still, the problem is very challenging because (i) there are tens of thousands of features and only hundreds of training samples, (ii) the scale-free structure of the gene network is unfriendly to the setup of convolutional neural networks.

Results

To address these issues and build a robust classification model, we propose the Graph-Embedded Deep Feedforward Networks (GEDFN), to integrate external relational information of features into the deep neural network architecture. The method is able to achieve sparse connection between network layers to prevent overfitting. To validate the method's capability, we conducted both simulation experiments and real data analysis using a breast invasive carcinoma RNA-seq dataset and a kidney renal clear cell carcinoma RNA-seq dataset from The Cancer Genome Atlas. The resulting high classification accuracy and easily interpretable feature selection results suggest the method is a useful addition to the current graph-guided classification models and feature selection procedures.

Availability and implementation

The method is available at https://github.com/yunchuankong/GEDFN.

Supplementary information

Supplementary data are available at Bioinformatics online.

Robust phenotype prediction from gene expression data using differential shrinkage of co-regulated genes

Discovery of robust diagnostic or prognostic biomarkers is a key to optimizing therapeutic benefit for select patient cohorts - an idea commonly referred to as precision medicine. Most discovery studies to derive such markers from high-dimensional transcriptomics datasets are weakly powered with sample sizes in the tens of patients. Therefore, highly regularized statistical approaches are essential to making generalizable predictions. At the same time, prior knowledge-driven approaches have been successfully applied to the manual interpretation of high-dimensional transcriptomics datasets. In this work, we assess the impact of combining two orthogonal approaches for the discovery of biomarker signatures, namely (1) well-known lasso-based regression approaches and its more recent derivative, the group lasso, and (2) the discovery of significant upstream regulators in literature-derived biological networks. Our method integrates both approaches in a weighted group-lasso model and differentially weights gene sets based on inferred active regulatory mechanism. Using nested cross-validation as well as independent clinical datasets, we demonstrate that our approach leads to increased accuracy and generalizable results. We implement our approach in a computationally efficient, user-friendly R package called creNET. The package can be downloaded at https://github.com/kouroshz/creNethttps://github.com/kouroshz/creNet and is accompanied by a parsed version of the STRING DB data base.

Interpretable per case weighted ensemble method for cancer associations

BACKGROUND

Molecular measurements from cancer patients such as gene expression and DNA methylation can be influenced by several external factors. This makes it harder to reproduce the exact values of measurements coming from different laboratories. Furthermore, some cancer types are very heterogeneous, meaning that there might be different underlying causes for the same type of cancer among different individuals. If a model does not take potential biases in the data into account, this can lead to problems when trying to predict the stage of a certain cancer type. This is especially true when these biases differ between the training and test set.

RESULTS

We introduce a method that can estimate this bias on a per-feature level and incorporate calculated feature confidences into a weighted combination of classifiers with disjoint feature sets. In this way, the method provides a prediction that is adjusted for the potential biases on a per-patient basis, providing a personalized prediction for each test patient. The new method achieves state-of-the-art performance on many different cancer data sets with measured DNA methylation or gene expression. Moreover, we show how to visualize the learned classifiers to display interesting associations with the target label. Applied to a leukemia data set, our method finds several ribosomal proteins associated with the risk group, which might be interesting targets for follow-up studies. This discovery supports the hypothesis that the ribosomes are a new frontier in genadaptivelearninge regulation.

CONCLUSION

We introduce a new method for robust prediction of phenotypes from molecular measurements such as DNA methylation or gene expression. Furthermore, the visualization capabilities enable exploratory analysis on the learnt dependencies and pave the way for a personalized prediction of phenotypes. The software is available under GPL2+ from https://github.com/adrinjalali/Network-Classifier/tree/v1.0 .

DTW-MIC Coexpression Networks from Time-Course Data

When modeling coexpression networks from high-throughput time course data, Pearson Correlation Coefficient (PCC) is one of the most effective and popular similarity functions. However, its reliability is limited since it cannot capture non-linear interactions and time shifts. Here we propose to overcome these two issues by employing a novel similarity function, Dynamic Time Warping Maximal Information Coefficient (DTW-MIC), combining a measure taking care of functional interactions of signals (MIC) and a measure identifying time lag (DTW). By using the Hamming-Ipsen-Mikhailov (HIM) metric to quantify network differences, the effectiveness of the DTW-MIC approach is demonstrated on a set of four synthetic and one transcriptomic datasets, also in comparison to TimeDelay ARACNE and Transfer Entropy.

Pathway-Based Genomics Prediction using Generalized Elastic Net

We present a novel regularization scheme called The Generalized Elastic Net (GELnet) that incorporates gene pathway information into feature selection. The proposed formulation is applicable to a wide variety of problems in which the interpretation of predictive features using known molecular interactions is desired. The method naturally steers solutions toward sets of mechanistically interlinked genes. Using experiments on synthetic data, we demonstrate that pathway-guided results maintain, and often improve, the accuracy of predictors even in cases where the full gene network is unknown. We apply the method to predict the drug response of breast cancer cell lines. GELnet is able to reveal genetic determinants of sensitivity and resistance for several compounds. In particular, for an EGFR/HER2 inhibitor, it finds a possible trans-differentiation resistance mechanism missed by the corresponding pathway agnostic approach.

Integrated analysis of numerous heterogeneous gene expression profiles for detecting robust disease-specific biomarkers and proposing drug targets

Genome-wide expression profiling has revolutionized biomedical research; vast amounts of expression data from numerous studies of many diseases are now available. Making the best use of this resource in order to better understand disease processes and treatment remains an open challenge. In particular, disease biomarkers detected in case-control studies suffer from low reliability and are only weakly reproducible. Here, we present a systematic integrative analysis methodology to overcome these shortcomings. We assembled and manually curated more than 14,000 expression profiles spanning 48 diseases and 18 expression platforms. We show that when studying a particular disease, judicious utilization of profiles from other diseases and information on disease hierarchy improves classification quality, avoids overoptimistic evaluation of that quality, and enhances disease-specific biomarker discovery. This approach yielded specific biomarkers for 24 of the analyzed diseases. We demonstrate how to combine these biomarkers with large-scale interaction, mutation and drug target data, forming a highly valuable disease summary that suggests novel directions in disease understanding and drug repurposing. Our analysis also estimates the number of samples required to reach a desired level of biomarker stability. This methodology can greatly improve the exploitation of the mountain of expression profiles for better disease analysis.

Pathway Relevance Ranking for Tumor Samples through Network-Based Data Integration

The study of cancer, a highly heterogeneous disease with different causes and clinical outcomes, requires a multi-angle approach and the collection of large multi-omics datasets that, ideally, should be analyzed simultaneously. We present a new pathway relevance ranking method that is able to prioritize pathways according to the information contained in any combination of tumor related omics datasets. Key to the method is the conversion of all available data into a single comprehensive network representation containing not only genes but also individual patient samples. Additionally, all data are linked through a network of previously identified molecular interactions. We demonstrate the performance of the new method by applying it to breast and ovarian cancer datasets from The Cancer Genome Atlas. By integrating gene expression, copy number, mutation and methylation data, the method's potential to identify key pathways involved in breast cancer development shared by different molecular subtypes is illustrated. Interestingly, certain pathways were ranked equally important for different subtypes, even when the underlying (epi)-genetic disturbances were diverse. Next to prioritizing universally high-scoring pathways, the pathway ranking method was able to identify subtype-specific pathways. Often the score of a pathway could not be motivated by a single mutation, copy number or methylation alteration, but rather by a combination of genetic and epi-genetic disturbances, stressing the need for a network-based data integration approach. The analysis of ovarian tumors, as a function of survival-based subtypes, demonstrated the method's ability to correctly identify key pathways, irrespective of tumor subtype. A differential analysis of survival-based subtypes revealed several pathways with higher importance for the bad-outcome patient group than for the good-outcome patient group. Many of the pathways exhibiting higher importance for the bad-outcome patient group could be related to ovarian tumor proliferation and survival.

A null model for Pearson coexpression networks

Gene coexpression networks inferred by correlation from high-throughput profiling such as microarray data represent simple but effective structures for discovering and interpreting linear gene relationships. In recent years, several approaches have been proposed to tackle the problem of deciding when the resulting correlation values are statistically significant. This is most crucial when the number of samples is small, yielding a non-negligible chance that even high correlation values are due to random effects. Here we introduce a novel hard thresholding solution based on the assumption that a coexpression network inferred by randomly generated data is expected to be empty. The threshold is theoretically derived by means of an analytic approach and, as a deterministic independent null model, it depends only on the dimensions of the starting data matrix, with assumptions on the skewness of the data distribution compatible with the structure of gene expression levels data. We show, on synthetic and array datasets, that the proposed threshold is effective in eliminating all false positive links, with an offsetting cost in terms of false negative detected edges.

Network-constrained forest for regularized classification of omics data

Contemporary molecular biology deals with wide and heterogeneous sets of measurements to model and understand underlying biological processes including complex diseases. Machine learning provides a frequent approach to build such models. However, the models built solely from measured data often suffer from overfitting, as the sample size is typically much smaller than the number of measured features. In this paper, we propose a random forest-based classifier that reduces this overfitting with the aid of prior knowledge in the form of a feature interaction network. We illustrate the proposed method in the task of disease classification based on measured mRNA and miRNA profiles complemented by the interaction network composed of the miRNA-mRNA target relations and mRNA-mRNA interactions corresponding to the interactions between their encoded proteins. We demonstrate that the proposed network-constrained forest employs prior knowledge to increase learning bias and consequently to improve classification accuracy, stability and comprehensibility of the resulting model. The experiments are carried out in the domain of myelodysplastic syndrome that we are concerned about in the long term. We validate our approach in the public domain of ovarian carcinoma, with the same data form. We believe that the idea of a network-constrained forest can straightforwardly be generalized towards arbitrary omics data with an available and non-trivial feature interaction network. The proposed method is publicly available in terms of miXGENE system (http://mixgene.felk.cvut.cz), the workflow that implements the myelodysplastic syndrome experiments is presented as a dedicated case study.

Network tuned multiple rank aggregation and applications to gene ranking

With the development of various high throughput technologies and analysis methods, researchers can study different aspects of a biological phenomenon simultaneously or one aspect repeatedly with different experimental techniques and analysis methods. The output from each study is a rank list of components of interest. Aggregation of the rank lists of components, such as proteins, genes and single nucleotide variants (SNV), produced by these experiments has been proven to be helpful in both filtering the noise and bringing forth a more complete understanding of the biological problems. Current available rank aggregation methods do not consider the network information that has been observed to provide vital contributions in many data integration studies. We developed network tuned rank aggregation methods incorporating network information and demonstrated its superior performance over aggregation methods without network information.

The methods are tested on predicting the Gene Ontology function of yeast proteins. We validate the methods using combinations of three gene expression data sets and three protein interaction networks as well as an integrated network by combining the three networks. Results show that the aggregated rank lists are more meaningful if protein interaction network is incorporated. Among the methods compared, CGI_RRA and CGI_Endeavour, which integrate rank lists with networks using CGI [1] followed by rank aggregation using either robust rank aggregation (RRA) [2] or Endeavour [3] perform the best. Finally, we use the methods to locate target genes of transcription factors.

Pathway mapping and development of disease-specific biomarkers: protein-based network biomarkers

It is known that a disease is rarely a consequence of an abnormality of a single gene, but reflects the interactions of various processes in a complex network. Annotated molecular networks offer new opportunities to understand diseases within a systems biology framework and provide an excellent substrate for network-based identification of biomarkers. The network biomarkers and dynamic network biomarkers (DNBs) represent new types of biomarkers with protein-protein or gene-gene interactions that can be monitored and evaluated at different stages and time-points during development of disease. Clinical bioinformatics as a new way to combine clinical measurements and signs with human tissue-generated bioinformatics is crucial to translate biomarkers into clinical application, validate the disease specificity, and understand the role of biomarkers in clinical settings. In this article, the recent advances and developments on network biomarkers and DNBs are comprehensively reviewed. How network biomarkers help a better understanding of molecular mechanism of diseases, the advantages and constraints of network biomarkers for clinical application, clinical bioinformatics as a bridge to the development of diseases-specific, stage-specific, severity-specific and therapy predictive biomarkers, and the potentials of network biomarkers are also discussed.

Elucidation of epithelial–mesenchymal transition-related pathways in a triple-negative breast cancer cell line model by multi-omics interactome analysis

Network features discriminate between epithelial and mesenchymal phenotype in a triple-negative breast cancer cell line model.

Broad spectrum detection and "barcoding" of water pollutants by a genome-wide bacterial sensor array

An approach for the rapid detection and classification of a broad spectrum of water pollutants, based on a genome-wide reporter bacterial live cell array, is proposed and demonstrated. An array of ca. 2000 Escherichia coli fluorescent transcriptional reporters was exposed to 25 toxic compounds as well as to unpolluted water, and its responses were recorded after 3 h. The 25 toxic compounds represented 5 pollutant classes: genotoxicants, metals, detergents, alcohols, and monoaromatic hydrocarbons. Identifying unique gene expression patterns, a nearest neighbour-based model detected pollutant presence and predicted class attribution with an estimated accuracy of 87%. Sensitivity and positive predictive values varied among classes, being higher for pollutant classes that were defined by mode of action than for those defined by structure only. Sensitivity for unpolluted water was 0.90 and the positive predictive value was 0.79. All pollutant classes induced the transcription of a statistically significant proportion of membrane associated genes; in addition, the sets of genes responsive to genotoxicants, detergents and alcohols were enriched with genes involved in DNA repair, iron utilization and the translation machinery, respectively. Following further development, a methodology of the type described herein may be suitable for integration in water monitoring schemes in conjunction with existing analytical and biological detection techniques.

Early diagnosis of complex diseases by molecular biomarkers, network biomarkers, and dynamical network biomarkers

Many studies have been carried out for early diagnosis of complex diseases by finding accurate and robust biomarkers specific to respective diseases. In particular, recent rapid advance of high-throughput technologies provides unprecedented rich information to characterize various disease genotypes and phenotypes in a global and also dynamical manner, which significantly accelerates the study of biomarkers from both theoretical and clinical perspectives. Traditionally, molecular biomarkers that distinguish disease samples from normal samples are widely adopted in clinical practices due to their ease of data measurement. However, many of them suffer from low coverage and high false-positive rates or high false-negative rates, which seriously limit their further clinical applications. To overcome those difficulties, network biomarkers (or module biomarkers) attract much attention and also achieve better performance because a network (or subnetwork) is considered to be a more robust form to characterize diseases than individual molecules. But, both molecular biomarkers and network biomarkers mainly distinguish disease samples from normal samples, and they generally cannot ensure to identify predisease samples due to their static nature, thereby lacking ability to early diagnosis. Based on nonlinear dynamical theory and complex network theory, a new concept of dynamical network biomarkers (DNBs, or a dynamical network of biomarkers) has been developed, which is different from traditional static approaches, and the DNB is able to distinguish a predisease state from normal and disease states by even a small number of samples, and therefore has great potential to achieve "real" early diagnosis of complex diseases. In this paper, we comprehensively review the recent advances and developments on molecular biomarkers, network biomarkers, and DNBs in particular, focusing on the biomarkers for early diagnosis of complex diseases considering a small number of samples and high-throughput data (or big data). Detailed comparisons of various types of biomarkers as well as their applications are also discussed.

Breaking free from the chains of pathway annotation: de novo pathway discovery for the analysis of disease processes

Interpreting the biological implications of high-throughput experiments such as gene-expression studies, genome-wide association studies and large-scale sequencing studies is not trivial. Gene-set and pathway analyses are useful tools to support the interpretation of such experiments, but rely on curated pathways or gene sets. The recent development of de novo pathway discovery methods aims to overcome this limitation. This article provides an overview of the methods currently available and reviews the advantages and challenges of this approach. In detail, it highlights the particular issues of de novo pathway discovery based on genome-wide association studies data, for which multiple different strategies have been proposed.

EPSILON: an eQTL prioritization framework using similarity measures derived from local networks

MOTIVATION

When genomic data are associated with gene expression data, the resulting expression quantitative trait loci (eQTL) will likely span multiple genes. eQTL prioritization techniques can be used to select the most likely causal gene affecting the expression of a target gene from a list of candidates. As an input, these techniques use physical interaction networks that often contain highly connected genes and unreliable or irrelevant interactions that can interfere with the prioritization process. We present EPSILON, an extendable framework for eQTL prioritization, which mitigates the effect of highly connected genes and unreliable interactions by constructing a local network before a network-based similarity measure is applied to select the true causal gene.

RESULTS

We tested the new method on three eQTL datasets derived from yeast data using three different association techniques. A physical interaction network was constructed, and each eQTL in each dataset was prioritized using the EPSILON approach: first, a local network was constructed using a k-trials shortest path algorithm, followed by the calculation of a network-based similarity measure. Three similarity measures were evaluated: random walks, the Laplacian Exponential Diffusion kernel and the Regularized Commute-Time kernel. The aim was to predict knockout interactions from a yeast knockout compendium. EPSILON outperformed two reference prioritization methods, random assignment and shortest path prioritization. Next, we found that using a local network significantly increased prioritization performance in terms of predicted knockout pairs when compared with using exactly the same network similarity measures on the global network, with an average increase in prioritization performance of 8 percentage points (P < 10(-5)).

AVAILABILITY

The physical interaction network and the source code (Matlab/C++) of our implementation can be downloaded from http://bioinformatics.intec.ugent.be/epsilon.

CONTACT

lieven.verbeke@intec.ugent.be, kamar@psb.ugent.be, jan.fostier@intec.ugent.be

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Genetic variants and their interactions in disease risk prediction - machine learning and network perspectives

A central challenge in systems biology and medical genetics is to understand how interactions among genetic loci contribute to complex phenotypic traits and human diseases. While most studies have so far relied on statistical modeling and association testing procedures, machine learning and predictive modeling approaches are increasingly being applied to mining genotype-phenotype relationships, also among those associations that do not necessarily meet statistical significance at the level of individual variants, yet still contributing to the combined predictive power at the level of variant panels. Network-based analysis of genetic variants and their interaction partners is another emerging trend by which to explore how sub-network level features contribute to complex disease processes and related phenotypes. In this review, we describe the basic concepts and algorithms behind machine learning-based genetic feature selection approaches, their potential benefits and limitations in genome-wide setting, and how physical or genetic interaction networks could be used as a priori information for providing improved predictive power and mechanistic insights into the disease networks. These developments are geared toward explaining a part of the missing heritability, and when combined with individual genomic profiling, such systems medicine approaches may also provide a principled means for tailoring personalized treatment strategies in the future.