Bioinformatics Mining and Modeling Methods for the Identification of Disease Mechanisms in Neurodegenerative Disorders

Explainable variational autoencoder (E-VAE) model using genome-wide SNPs to predict dementia

OBJECTIVE

Alzheimer's disease (AD) and AD related dementias (ADRD) are complex multifactorial neurodegenerative diseases. The associations between genetic variants obtained from genome wide association studies (GWAS) are the most widely available and well documented variants associated with ADRD. Application of deep learning methods to analyze large scale GWAS data may be a powerful approach to elucidate the biological mechanisms in ADRD compared to penalized regression models that may lead to over-fitting.

METHODS

We developed a deep learning frame work explainable variational autoencoder (E-VAE) classifier model using genotype (GWAS SNPs = 5474) data from 2714 study participants in the Health and Retirement Study (HRS) to classify ADRD. We validated the generalizability of this model among 234 participants in the Religious Orders Study and Memory and Aging Project (ROSMAP). Utilizing a linear decoder approach we have extracted the weights associated with latent features for biological interpretation.

RESULTS

We obtained a predictive accuracy of 0.71 (95 % CI [0.59, 0.84]) with an AUC of 0.69 in the HRS test dataset and got an accuracy of 0.62 (95 % CI [0.56, 0.68]) with an AUC of 0.63 in the ROSMAP dataset.

CONCLUSION

This is the first study showing the generalizability of a deep learning prediction model for dementia using genetic variants in an independent cohort. The latent features identified using E-VAE can help us understand the biology of AD/ ADRD and better characterize disease status.

Development of a 2D-QSAR Model for Tissue-to-Plasma Partition Coefficient Value with High Accuracy Using Machine Learning Method, Minimum Required Experimental Values, and Physicochemical Descriptors

BACKGROUND

The demand for physiologically based pharmacokinetic (PBPK) model is increasing currently. New drug application (NDA) of many compounds is submitted with PBPK models for efficient drug development. Tissue-to-plasma partition coefficient (K_p) is a key parameter for the PBPK model to describe differential equations. However, it is difficult to obtain the K_p value experimentally because the measurement of drug concentration in the tissue is much harder than that in plasma.

OBJECTIVE

Instead of experiments, many researchers have sought in silico methods. Today, most of the models for K_p prediction are using in vitro and in vivo parameters as explanatory variables. We thought of physicochemical descriptors that could improve the predictability. Therefore, we aimed to develop the two-dimensional quantitative structure-activity relationship (2D-QSAR) model for K_p using physicochemical descriptors instead of in vivo experimental data as explanatory variables.

METHODS

We compared our model with the conventional models using 20-fold cross-validation according to the published method (Yun et al. J Pharmacokinet Pharmacodyn 41:1-14, 2014). We used random forest algorithm, which is known to be one of the best predictors for the 2D-QSAR model. Finally, we combined minimum in vitro experimental values and physiochemical descriptors. Thus, the prediction method for K_p value using a few in vitro parameters and physicochemical descriptors was developed; this is a multimodal model.

RESULTS

Its accuracy was found to be superior to that of the conventional models. Results of this research suggest that multimodality is useful for the 2D-QSAR model [RMSE and % of two-fold error: 0.66 and 42.2% (Berezohkovsky), 0.52 and 52.2% (Rodgers), 0.65 and 34.6% (Schmitt), 0.44 and 61.1% (published model), 0.41 and 62.1% (traditional model), 0.39 and 64.5% (multimodal model)].

CONCLUSION

We could develop a 2D-QSAR model for K_p value with the highest accuracy using a few in vitro experimental data and physicochemical descriptors.

Deep neural network prediction of genome-wide transcriptome signatures - beyond the Black-box

Prediction algorithms for protein or gene structures, including transcription factor binding from sequence information, have been transformative in understanding gene regulation. Here we ask whether human transcriptomic profiles can be predicted solely from the expression of transcription factors (TFs). We find that the expression of 1600 TFs can explain >95% of the variance in 25,000 genes. Using the light-up technique to inspect the trained NN, we find an over-representation of known TF-gene regulations. Furthermore, the learned prediction network has a hierarchical organization. A smaller set of around 125 core TFs could explain close to 80% of the variance. Interestingly, reducing the number of TFs below 500 induces a rapid decline in prediction performance. Next, we evaluated the prediction model using transcriptional data from 22 human diseases. The TFs were sufficient to predict the dysregulation of the target genes (rho = 0.61, P < 10⁻²¹⁶). By inspecting the model, key causative TFs could be extracted for subsequent validation using disease-associated genetic variants. We demonstrate a methodology for constructing an interpretable neural network predictor, where analyses of the predictors identified key TFs that were inducing transcriptional changes during disease.

Construction of a knowledge graph for diabetes complications from expert-reviewed clinical evidences

A knowledge graph is a structured representation of data that can express entity and relational knowledge. More attention has been paid to the study of a clinical knowledge graph, especially in the field of chronic diseases. However, knowledge graph construction is based mainly on electronic medical records and other data sources, and the authority of the constructed knowledge graph presents some problems. Therefore, regarding the quality of evidence, this study, in combination with experimental research on system evaluation and meta-analysis presents some new information, On the basis of evidence-based medicine (EBM), the secondary results of systematic evaluation and meta-analyses of social, psychological, and behavioral aspects were extracted as data for the core nodes and edges of a knowledge graph to construct a graph of type 2 diabetes (T2D) and its complications. In this study, relevant life-style evidence that are factors for the risk of diabetic retinopathy (DR), diabetic nephropathy (DN), diabetic foot (DF), and diabetic depression (DD), and the results of several of the relevant clinical test, including bariatric surgery, myopia, lipid-lowering drugs, lipid-lowering drug duration, blood glucose control, disease course, glycosylated hemoglobin, fasting blood glucose, hypertension, sex, smoking and other common lifestyle characteristics were finally extracted. The evidence-based knowledge graph of the DM complications was constructed by extracting relevant disease, risk factors, risk outcomes, and other diabetes entities and the strength of the data for the odds ratio (OR) or relative risk (RR) correlations from clinical evidence. Moreover, the risk prediction models constructed using a logistic model were incorporated into the knowledge graph to visualize the risk score of DM complications for each user. In short, the EBM-powered construction of the knowledge graph could provide high-quality information to support decisions for the prevention and control of diabetes and its complications.

STATegra: Multi-Omics Data Integration - A Conceptual Scheme With a Bioinformatics Pipeline

Technologies for profiling samples using different omics platforms have been at the forefront since the human genome project. Large-scale multi-omics data hold the promise of deciphering different regulatory layers. Yet, while there is a myriad of bioinformatics tools, each multi-omics analysis appears to start from scratch with an arbitrary decision over which tools to use and how to combine them. Therefore, it is an unmet need to conceptualize how to integrate such data and implement and validate pipelines in different cases. We have designed a conceptual framework (STATegra), aiming it to be as generic as possible for multi-omics analysis, combining available multi-omic anlaysis tools (machine learning component analysis, non-parametric data combination, and a multi-omics exploratory analysis) in a step-wise manner. While in several studies, we have previously combined those integrative tools, here, we provide a systematic description of the STATegra framework and its validation using two The Cancer Genome Atlas (TCGA) case studies. For both, the Glioblastoma and the Skin Cutaneous Melanoma (SKCM) cases, we demonstrate an enhanced capacity of the framework (and beyond the individual tools) to identify features and pathways compared to single-omics analysis. Such an integrative multi-omics analysis framework for identifying features and components facilitates the discovery of new biology. Finally, we provide several options for applying the STATegra framework when parametric assumptions are fulfilled and for the case when not all the samples are profiled for all omics. The STATegra framework is built using several tools, which are being integrated step-by-step as OpenSource in the STATegRa Bioconductor package.

Road to effective data curation for translational research

Translational research today is data-intensive and requires multi-stakeholder collaborations to generate and pool data together for integrated analysis. This leads to the challenge of harmonization of data from different sources with different formats and standards, which is often overlooked during project planning and thus becomes a bottleneck of the research progress. We report on our experience and lessons learnt about data curation for translational research garnered over the course of the European Translational Research Infrastructure & Knowledge management Services (eTRIKS) program (https://www.etriks.org), a unique, 5-year, cross-organizational, cross-cultural collaboration project funded by the Innovative Medicines Initiative of the EU. Here, we discuss the obstacles and suggest what steps are needed for effective data curation in translational research, especially for projects involving multiple organizations from academia and industry.

Bayesian variable selection in logistic regression with application to whole-brain functional connectivity analysis for Parkinson's disease

Parkinson's disease is a progressive, chronic, and neurodegenerative disorder that is primarily diagnosed by clinical examinations and magnetic resonance imaging (MRI). In this paper, we propose a Bayesian model to predict Parkinson's disease employing a functional MRI (fMRI) based radiomics approach. We consider a spike and slab prior for variable selection in high-dimensional logistic regression models, and present an approximate Gibbs sampler by replacing a logistic distribution with a t-distribution. Under mild conditions, we establish model selection consistency of the induced posterior and illustrate the performance of the proposed method outperforms existing state-of-the-art methods through simulation studies. In fMRI analysis, 6216 whole-brain functional connectivity features are extracted for 50 healthy controls along with 70 Parkinson's disease patients. We apply our method to the resulting dataset and further show its benefits with a higher average prediction accuracy of 0.83 compared to other contenders based on 10 random splits. The model fitting procedure also reveals the most discriminative brain regions for Parkinson's disease. These findings demonstrate that the proposed Bayesian variable selection method has the potential to support radiological diagnosis for patients with Parkinson's disease.

The study protocol: Neuroendocrinology and (epi-) genetics of female reproductive transition phase mood disorder - an observational, longitudinal study from pregnancy to postpartum

BACKGROUND

Postpartum depression is considered to be one of the most common health threats during pregnancy and postpartum, affecting not only the woman herself but also the offspring and the whole family system. Evidence for a conclusive etiopathological model with distinct risk and resilience factors is still broadly lacking. Therefore, the aim of the present study is to investigate numerous health-related markers to obtain greater insight into which biopsychosocial profiles render women more vulnerable to PPD or facilitate a healthy transition from pregnancy to postpartum.

METHODS

The observational, longitudinal study aims to include a total of 288 physically healthy women, aged 20-45 years. A multitude of relevant parameters, of an (epi-) genetic, endocrinological, physiological and psychological nature, will be assessed over a period of 5 months, following the participants from the 3rd trimester until three months postpartum.

DISCUSSION

The ultimate goal of the present study is to ameliorate mental health care during pregnancy and postpartum, by gaining a better understanding of the underlying biopsychosocial mechanisms that women undergo during the transition from pregnancy to postpartum.

A Radiomics Approach to Predicting Parkinson's Disease by Incorporating Whole-Brain Functional Activity and Gray Matter Structure

Parkinson's disease (PD) is a progressive, chronic, and neurodegenerative disorder that is primarily diagnosed by clinical examinations and magnetic resonance imaging (MRI). In this study, we proposed a machine learning based radiomics method to predict PD. Fifty healthy controls (HC) along with 70 PD patients underwent resting-state magnetic resonance imaging (rs-fMRI). For all subjects, we extracted five types of 6664 features, including mean amplitude of low-frequency fluctuation (mALFF), mean regional homogeneity (mReHo), resting-state functional connectivity (RSFC), voxel-mirrored homotopic connectivity (VMHC) and gray matter (GM) volume. After conducting dimension reduction utilizing Least absolute shrinkage and selection operator (LASSO), fifty-three radiomic features including 46 RSFCs, 1 mALFF, 3 mReHos, 1 VMHC, 2 GM volumes and 1 clinical factor were retained. The selected features also indicated the most discriminative regions for PD. We further conducted model fitting procedure for classifying subjects in the training set employing random forest and support volume machine (SVM) to evaluate the performance of the two methods. After cross-validation, both methods achieved 100% accuracy and area under curve (AUC) for distinguishing between PD and HC in the training set. In the testing set, SVM performed better than random forest with the accuracy, true positive rate (TPR) and AUC being 85%, 1 and 0.97, respectively. These findings demonstrate the radiomics technique has the potential to support radiological diagnosis and to achieve high classification accuracy for clinical diagnostic systems for patients with PD.

Improving predictive models for Alzheimer's disease using GWAS data by incorporating misclassified samples modeling

Late-onset Alzheimer’s Disease (LOAD) is the most common form of dementia in the elderly. Genome-wide association studies (GWAS) for LOAD have open new avenues to identify genetic causes and to provide diagnostic tools for early detection. Although several predictive models have been proposed using the few detected GWAS markers, there is still a need for improvement and identification of potential markers. Commonly, polygenic risk scores are being used for prediction. Nevertheless, other methods to generate predictive models have been suggested. In this research, we compared three machine learning methods that have been proved to construct powerful predictive models (genetic algorithms, LASSO, and step-wise) and propose the inclusion of markers from misclassified samples to improve overall prediction accuracy. Our results show that the addition of markers from an initial model plus the markers of the model fitted to misclassified samples improves the area under the receiving operative curve by around 5%, reaching ~0.84, which is highly competitive using only genetic information. The computational strategy used here can help to devise better methods to improve classification models for AD. Our results could have a positive impact on the early diagnosis of Alzheimer’s disease.

New Frontiers in Parkinson's Disease: From Genetics to the Clinic

The greatest unmet therapeutic need in Parkinson's disease (PD) is a treatment that slows the relentless progression of the symptoms and the neurodegenerative process. This review highlights the utility of genetics to understand the pathogenic mechanisms and develop novel therapeutic approaches for PD. The focus is on strategies provided by genetic studies: notably via the reduction and clearance of α-synuclein, inhibition of LRRK2 kinase activity, and modulation of glucocerebrosidase-related substrates. In addition, the critical role of precompetitive public-private partnerships in supporting trial design optimization, overall drug development, and regulatory approvals is illustrated. With these great advances, the promise of developing transformative therapies that halt or slow disease progression is a tangible goal.

Non-parametric combination analysis of multiple data types enables detection of novel regulatory mechanisms in T cells of multiple sclerosis patients

Multiple Sclerosis (MS) is an autoimmune disease of the central nervous system with prominent neurodegenerative components. The triggering and progression of MS is associated with transcriptional and epigenetic alterations in several tissues, including peripheral blood. The combined influence of transcriptional and epigenetic changes associated with MS has not been assessed in the same individuals. Here we generated paired transcriptomic (RNA-seq) and DNA methylation (Illumina 450 K array) profiles of CD4+ and CD8+ T cells (CD4, CD8), using clinically accessible blood from healthy donors and MS patients in the initial relapsing-remitting and subsequent secondary-progressive stage. By integrating the output of a differential expression test with a permutation-based non-parametric combination methodology, we identified 149 differentially expressed (DE) genes in both CD4 and CD8 cells collected from MS patients. Moreover, by leveraging the methylation-dependent regulation of gene expression, we identified the gene SH3YL1, which displayed significant correlated expression and methylation changes in MS patients. Importantly, silencing of SH3YL1 in primary human CD4 cells demonstrated its influence on T cell activation. Collectively, our strategy based on paired sampling of several cell-types provides a novel approach to increase sensitivity for identifying shared mechanisms altered in CD4 and CD8 cells of relevance in MS in small sized clinical materials.

Quantitative System Pharmacology (QSP): An Integrative Framework for paradigm change in the treatment of the first-episode schizophrenia

Despite the lack of progress in the curative treatment of mental illness, especially schizophrenia, the accumulation of neuroscience data over the past decade suggests the re-conceptualization of schizophrenia. With the advent of new biomarkers and cognitive tools, new neuroscience technologies such as functional dynamic connectivity and the identification of subtle clinical features; it is now possible to detect early stages at risk or prodromes of a first psychotic episode. Current concepts reconceptualizes schizophrenia as a neurodevelopmental disorder at early onset, with polygenic risk and only symptomatic treatment for positive symptoms at this time. The use of such technologies in the future suggests new diagnostic and therapeutic options. Next steps include new pharmacological perspectives and potential contributions of new technologies such as quantitative system pharmacology brain computational modeling approach.

Navigating the disease landscape: knowledge representations for contextualizing molecular signatures

Large amounts of data emerging from experiments in molecular medicine are leading to the identification of molecular signatures associated with disease subtypes. The contextualization of these patterns is important for obtaining mechanistic insight into the aberrant processes associated with a disease, and this typically involves the integration of multiple heterogeneous types of data. In this review, we discuss knowledge representations that can be useful to explore the biological context of molecular signatures, in particular three main approaches, namely, pathway mapping approaches, molecular network centric approaches and approaches that represent biological statements as knowledge graphs. We discuss the utility of each of these paradigms, illustrate how they can be leveraged with selected practical examples and identify ongoing challenges for this field of research.

Re-curation and rational enrichment of knowledge graphs in Biological Expression Language

The rapid accumulation of new biomedical literature not only causes curated knowledge graphs (KGs) to become outdated and incomplete, but also makes manual curation an impractical and unsustainable solution. Automated or semi-automated workflows are necessary to assist in prioritizing and curating the literature to update and enrich KGs. We have developed two workflows: one for re-curating a given KG to assure its syntactic and semantic quality and another for rationally enriching it by manually revising automatically extracted relations for nodes with low information density. We applied these workflows to the KGs encoded in Biological Expression Language from the NeuroMMSig database using content that was pre-extracted from MEDLINE abstracts and PubMed Central full-text articles using text mining output integrated by INDRA. We have made this workflow freely available at https://github.com/bel-enrichment/bel-enrichment.

Report: NIA workshop on translating genetic variants associated with longevity into drug targets

To date, candidate gene and genome-wide association studies (GWAS) have led to the discovery of longevity-associated variants (LAVs) in genes such as FOXO3A and APOE. Unfortunately, translating variants into drug targets is challenging for any trait, and longevity is no exception. Interdisciplinary and integrative multi-omics approaches are needed to understand how LAVs affect longevity-related phenotypes at the molecular physiologic level in order to leverage their discovery to identify new drug targets. The NIA convened a workshop in August 2017 on emerging and novel in silico (i.e., bioinformatics and computational) approaches to the translation of LAVs into drug targets. The goal of the workshop was to identify ways of enabling, enhancing, and facilitating interactions among researchers from different disciplines whose research considers either the identification of LAVs or the mechanistic or causal pathway(s) and protective factors they influence for discovering drug targets. Discussions among the workshop participants resulted in the identification of critical needs for enabling the translation of LAVs into drug targets in several areas. These included (1) the initiation and better use of cohorts with multi-omics profiling on the participants; (2) the generation of longitudinal information on multiple individuals; (3) the collection of data from non-human species (both long and short-lived) for comparative biology studies; (4) the refinement of computational tools for integrative analyses; (5) the development of novel computational and statistical inference techniques for assessing the potential of a drug target; (6) the identification of available drugs that could modulate a target in a way that could potentially provide protection against age-related diseases and/or enhance longevity; and (7) the development or enhancement of databases and repositories of relevant information, such as the Longevity Genomics website ( https://www.longevitygenomics.org ), to enhance and help motivate future interdisciplinary studies. Integrative approaches that examine the influence of LAVs on molecular physiologic phenotypes that might be amenable to pharmacological modulation are necessary for translating LAVs into drugs to enhance health and life span.

Precision pharmacotherapy: psychiatry's future direction in preventing, diagnosing, and treating mental disorders

Mental disorders account for around one-third of disability worldwide and cause enormous personal and societal burden. Current pharmacotherapies and nonpharmacotherapies do help many patients, but there are still high rates of partial or no response, delayed effect, and unfavorable adverse effects. The current diagnostic taxonomy of mental disorders by the Diagnostic and Statistical Manual of Mental Disorders and the International Classification of Diseases relies on presenting signs and symptoms, but does not reflect evidence from neurobiological and behavioral systems. However, in the last decades, the understanding of biological mechanisms underlying mental disorders has grown and can be used for the development of precision medicine, that is, to deliver a patient-tailored individual treatment. Precision medicine may incorporate genetic variants contributing to the mental disorder and the response to pharmacotherapies, but also consider gene ¥ environment interactions, blood-based markers, neuropsychological tests, data from electronic health records, early life adversity, stressful life events, and very proximal factors such as lifestyle, nutrition, and sport. Methods such as artificial intelligence and the underlying machine learning and deep learning approaches provide the framework to stratify patients, initiate specific tailored treatments and thus increase response rates, reduce adverse effects and medical errors. In conclusion, precision medicine uses measurable health parameters to identify individuals at risk of a mental disorder, to improve the diagnostic process and to deliver a patient-tailored treatment.

Using predicate and provenance information from a knowledge graph for drug efficacy screening

Background

Biomedical knowledge graphs have become important tools to computationally analyse the comprehensive body of biomedical knowledge. They represent knowledge as subject-predicate-object triples, in which the predicate indicates the relationship between subject and object. A triple can also contain provenance information, which consists of references to the sources of the triple (e.g. scientific publications or database entries). Knowledge graphs have been used to classify drug-disease pairs for drug efficacy screening, but existing computational methods have often ignored predicate and provenance information. Using this information, we aimed to develop a supervised machine learning classifier and determine the added value of predicate and provenance information for drug efficacy screening. To ensure the biological plausibility of our method we performed our research on the protein level, where drugs are represented by their drug target proteins, and diseases by their disease proteins.

Results

Using random forests with repeated 10-fold cross-validation, our method achieved an area under the ROC curve (AUC) of 78.1% and 74.3% for two reference sets. We benchmarked against a state-of-the-art knowledge-graph technique that does not use predicate and provenance information, obtaining AUCs of 65.6% and 64.6%, respectively. Classifiers that only used predicate information performed superior to classifiers that only used provenance information, but using both performed best.

Conclusion

We conclude that both predicate and provenance information provide added value for drug efficacy screening.

Electronic supplementary material

The online version of this article (10.1186/s13326-018-0189-6) contains supplementary material, which is available to authorized users.

Multimodal mechanistic signatures for neurodegenerative diseases (NeuroMMSig): a web server for mechanism enrichment

Motivation

The concept of a 'mechanism-based taxonomy of human disease' is currently replacing the outdated paradigm of diseases classified by clinical appearance. We have tackled the paradigm of mechanism-based patient subgroup identification in the challenging area of research on neurodegenerative diseases.

Results

We have developed a knowledge base representing essential pathophysiology mechanisms of neurodegenerative diseases. Together with dedicated algorithms, this knowledge base forms the basis for a 'mechanism-enrichment server' that supports the mechanistic interpretation of multiscale, multimodal clinical data.

Availability and implementation

NeuroMMSig is available at http://neurommsig.scai.fraunhofer.de/.

Contact

martin.hofmann-apitius@scai.fraunhofer.de.

Supplementary information

Supplementary data are available at Bioinformatics online.

Gene Golden Age paradox and its partial solution

The prevalence of purifying selection in the nature suggests that larger organisms bear a higher number of slightly deleterious mutations because of smaller populations and therefore weaker selection. In this work redistribution of purifying selection in favor of information genes, pathways and processes was found in primates compared with treeshrew and rodents on the ground of genome-wide analysis. The genes which are more favored in primates belong mainly to regulation of gene expression and development, in treeshrew and rodents, to metabolism, transport, energetics, reproduction and olfaction. The former occur predominantly in the nucleus, the latter, in the cytoplasm and membranes. Thus, although purifying selection is on average weaker in the primates, it is stronger concentrated on the "information technology" of life (regulation of gene expression and development). Increased accuracy of information processes probably allows escaping "error catastrophes" in spite of more complex organization, larger body size and higher longevity.

Identification of differentially expressed genes and regulatory relationships in Huntington's disease by bioinformatics analysis

Huntington's disease (HD) is an inherited, progressive neurodegenerative disease caused by a CAG expansion in the huntingtin (HTT) gene; various dysfunctions of biological processes in HD have been proposed. However, at present the exact pathogenesis of HD is not fully understood. The present study aimed to explore the pathogenesis of HD using a computational bioinformatics analysis of gene expression. GSE11358 was downloaded from the Gene Expression Omnibus andthe differentially expressed genes (DEGs) in the mutant HTT knock-in cell model STHdhQ111/Q111 were predicted. DEGs between the HD and control samples were screened using the limma package in R. Functional and pathway enrichment analyses were conducted using the database for annotation, visualization and integrated discovery software. A protein-protein interaction (PPI) network was established by the search tool for the retrieval of interacting genes and visualized by Cytoscape. Module analysis of the PPI network was performed utilizing MCODE. A total of 471 DEGs were identified, including ribonuclease A family member 4 (RNASE4). In addition, 41 significantly enriched Kyoto Encyclopedia of Genes and Genomes pathways, as well as several significant Gene Ontology terms (including cytokine-cytokine receptor interaction and cytosolic DNA-sensing) were identified. A total of 18 significant modules were identified from the PPI network. Furthermore, a novel transcriptional regulatory relationship was identified, namely signal transducer and activator of transcription 3 (STAT3), which is regulated by miRNA-124 in HD. In conclusion, deregulation of 18 critical genes may contribute to the occurrence of HD. RNASE4, STAT3, and miRNA-124 may have a regulatory association with the pathological mechanisms in HD.

Specific protein biomarker patterns for Alzheimer's disease: improved diagnostics in progress

This short review looks at Alzheimer's disease (AD) diagnosis through my own point of view, going from imaging through cerebrospinal fluid to blood proteins. Over the last couple of years, we have published two papers targeted at Alzheimer's diagnosis. In one paper, we took an approach of selecting a specific target, namely, activity-dependent neuroprotective protein (ADNP), and our results tightened the association of ADNP blood expression with intelligence. In another paper, we took an unbiased approach of analysis of all genes expressed in lymphoblastoid cells lines and discovered changes in expression of the regulator of G-protein signaling 2 (RGS2) as a potential AD predictor. This review will assess our data in comparison to selected independent studies focusing on blood protein biomarkers as well as assessing saliva and urine samples with potential predictive value for AD. Furthermore, the review will provide directions for a combination of innovative markers, stratifying the population toward disease prevention and personalized medicine.

Towards the virtual human patient. Quantitative Systems Pharmacology in Alzheimer's disease

Development of successful therapeutic interventions in Central Nervous Systems (CNS) disorders is a daunting challenge with a low success rate. Probable reasons include the lack of translation from preclinical animal models, the individual variability of many pathological processes converging upon the same clinical phenotype, the pharmacodynamical interaction of various comedications and last but not least the complexity of the human brain. This paper argues for a re-engineering of the pharmaceutical CNS Research & Development strategy using ideas focused on advanced computer modeling and simulation from adjacent engineering-based industries. We provide examples that such a Quantitative Systems Pharmacology approach based on computer simulation of biological processes and that combines the best of preclinical research with actual clinical outcomes can enhance translation to the clinical situation. We will expand upon (1) the need to go from Big Data to Smart Data and develop predictive and quantitative algorithms that are actionable for the pharma industry, (2) using this platform as a "knowledge machine" that captures community-wide expertise in an active hypothesis-testing approach, (3) learning from failed clinical trials and (4) the need to go beyond simple linear hypotheses and embrace complex non-linear hypotheses. We will propose a strategy for applying these concepts to the substantial individual variability of AD patient subgroups and the treatment of neuropsychiatric problems in AD. Quantitative Systems Pharmacology is a new 'humanized' tool for supporting drug discovery and development in general and CNS disorders in particular.

Automated extraction of potential migraine biomarkers using a semantic graph

PROBLEM

Biomedical literature and databases contain important clues for the identification of potential disease biomarkers. However, searching these enormous knowledge reservoirs and integrating findings across heterogeneous sources is costly and difficult. Here we demonstrate how semantically integrated knowledge, extracted from biomedical literature and structured databases, can be used to automatically identify potential migraine biomarkers.

METHOD

We used a knowledge graph containing more than 3.5 million biomedical concepts and 68.4 million relationships. Biochemical compound concepts were filtered and ranked by their potential as biomarkers based on their connections to a subgraph of migraine-related concepts. The ranked results were evaluated against the results of a systematic literature review that was performed manually by migraine researchers. Weight points were assigned to these reference compounds to indicate their relative importance.

RESULTS

Ranked results automatically generated by the knowledge graph were highly consistent with results from the manual literature review. Out of 222 reference compounds, 163 (73%) ranked in the top 2000, with 547 out of the 644 (85%) weight points assigned to the reference compounds. For reference compounds that were not in the top of the list, an extensive error analysis has been performed. When evaluating the overall performance, we obtained a ROC-AUC of 0.974.

DISCUSSION

Semantic knowledge graphs composed of information integrated from multiple and varying sources can assist researchers in identifying potential disease biomarkers.

The Necessity of Data Mining in Clinical Emergency Medicine; A Narrative Review of the Current Literatrue

Clinical databases can be categorized as big data, include large quantities of information about patients and their medical conditions. Analyzing the quantitative and qualitative clinical data in addition with discovering relationships among huge number of samples using data mining techniques could unveil hidden medical knowledge in terms of correlation and association of apparently independent variables. The aim of this research is using predictive algorithm for prediction of trauma patients on admission to hospital to be able to predict the necessary treatment for patients and provided the necessary measures for the trauma patients who are before entering the critical situation. This study provides a review on data mining in clinical medicine. The relevant, recently-published studies of data mining on medical data with a focus on emergency medicine were investigated to tackle pros and cons of such approaches. The results of this study can be used in prediction of trauma patient’s status at six hours after admission to hospital.

Predictive analytics in mental health: applications, guidelines, challenges and perspectives

The emerging field of 'predictive analytics in mental health' has recently generated tremendous interest with the bold promise to revolutionize clinical practice in psychiatry paralleling similar developments in personalized and precision medicine. Here, we provide an overview of the key questions and challenges in the field, aiming to (1) propose general guidelines for predictive analytics projects in psychiatry, (2) provide a conceptual introduction to core aspects of predictive modeling technology, and (3) foster a broad and informed discussion involving all stakeholders including researchers, clinicians, patients, funding bodies and policymakers.

Genes of susceptibility to early neurodegenerative changes in the rat retina and brain: analysis by means of congenic strains

BACKGROUND

There has been considerable interest in discovery of the genetic architecture of complex traits, particularly age-related neurodegenerative disorders. To predict disease risk and to understand its genetic basis in humans, it is necessary to study animal models. Our previous research on the accelerated-senescence OXYS strain has revealed two quantitative trait loci (QTLs) on rat chromosome 1 that are associated with early cataract and/or retinopathy as well as with behavioral abnormalities. Each locus was partially mapped within the introgressed segments in a certain congenic strain: WAG/OXYS-1.1 or WAG/OXYS-1.2. Retinal transcriptome profiling of 20-day-old congenic and OXYS rats by high-throughput RNA sequencing uncovered relevant candidate genes and pathways. Nonetheless, the question remained open whether the same genetic components simultaneously have effects on various manifestations of the accelerated-senescence phenotype in OXYS rats. The present study was designed to analyze the genes of susceptibility to early neurodegenerative processes taking place in the OXYS rat retina and brain and to assess their potential functional clustering. The study was based on the findings from recent publications (including mapping of quantitative trait loci) and on comparative phenotyping of congenic rat strains.

RESULTS

The backcrossing of Wistar Albino Glaxo (WAG) and OXYS strains to generate the congenics resulted in two congenic strains with high susceptibility to cataract and retinopathy but with no obvious signs of Alzheimer's disease-like brain pathology that are specific for OXYS rats. Thus, the genes of susceptibility to brain neurodegeneration were not introgressed into the congenic strains or there is a strong effect of the genetic background on the disease phenotype. Moreover, the progression of retinopathy with age was relatively less severe in the WAG background compared to the OXYS background. A comparative analysis of previously defined QTLs and congenic segments led to identification of candidate genes with a suspected effect on brain neurodegeneration including the genes showing differential expression in the congenic strains.

CONCLUSION

Overall, our findings suggest that the cause of the cataract and the cause of retinopathy phenotypes in OXYS rats may be genetically linked to each other within the introgressed segments in the WAG/OXYS-1.1 and/or WAG/OXYS-1.2 congenic strains.

Towards a 21st-century roadmap for biomedical research and drug discovery: consensus report and recommendations

Decades of costly failures in translating drug candidates from preclinical disease models to human therapeutic use warrant reconsideration of the priority placed on animal models in biomedical research. Following an international workshop attended by experts from academia, government institutions, research funding bodies, and the corporate and non-governmental organisation (NGO) sectors, in this consensus report, we analyse, as case studies, five disease areas with major unmet needs for new treatments. In view of the scientifically driven transition towards a human pathways-based paradigm in toxicology, a similar paradigm shift appears to be justified in biomedical research. There is a pressing need for an approach that strategically implements advanced, human biology-based models and tools to understand disease pathways at multiple biological scales. We present recommendations to help achieve this.

MINERVA-a platform for visualization and curation of molecular interaction networks

Our growing knowledge about various molecular mechanisms is becoming increasingly more structured and accessible. Different repositories of molecular interactions and available literature enable construction of focused and high-quality molecular interaction networks. Novel tools for curation and exploration of such networks are needed, in order to foster the development of a systems biology environment. In particular, solutions for visualization, annotation and data cross-linking will facilitate usage of network-encoded knowledge in biomedical research. To this end we developed the MINERVA (Molecular Interaction NEtwoRks VisuAlization) platform, a standalone webservice supporting curation, annotation and visualization of molecular interaction networks in Systems Biology Graphical Notation (SBGN)-compliant format. MINERVA provides automated content annotation and verification for improved quality control. The end users can explore and interact with hosted networks, and provide direct feedback to content curators. MINERVA enables mapping drug targets or overlaying experimental data on the visualized networks. Extensive export functions enable downloading areas of the visualized networks as SBGN-compliant models for efficient reuse of hosted networks. The software is available under Affero GPL 3.0 as a Virtual Machine snapshot, Debian package and Docker instance at http://r3lab.uni.lu/web/minerva-website/. We believe that MINERVA is an important contribution to systems biology community, as its architecture enables set-up of locally or globally accessible SBGN-oriented repositories of molecular interaction networks. Its functionalities allow overlay of multiple information layers, facilitating exploration of content and interpretation of data. Moreover, annotation and verification workflows of MINERVA improve the efficiency of curation of networks, allowing life-science researchers to better engage in development and use of biomedical knowledge repositories.

Making sense of big data in health research: Towards an EU action plan

Medicine and healthcare are undergoing profound changes. Whole-genome sequencing and high-resolution imaging technologies are key drivers of this rapid and crucial transformation. Technological innovation combined with automation and miniaturization has triggered an explosion in data production that will soon reach exabyte proportions. How are we going to deal with this exponential increase in data production? The potential of "big data" for improving health is enormous but, at the same time, we face a wide range of challenges to overcome urgently. Europe is very proud of its cultural diversity; however, exploitation of the data made available through advances in genomic medicine, imaging, and a wide range of mobile health applications or connected devices is hampered by numerous historical, technical, legal, and political barriers. European health systems and databases are diverse and fragmented. There is a lack of harmonization of data formats, processing, analysis, and data transfer, which leads to incompatibilities and lost opportunities. Legal frameworks for data sharing are evolving. Clinicians, researchers, and citizens need improved methods, tools, and training to generate, analyze, and query data effectively. Addressing these barriers will contribute to creating the European Single Market for health, which will improve health and healthcare for all Europeans.

Integration and Visualization of Translational Medicine Data for Better Understanding of Human Diseases

Translational medicine is a domain turning results of basic life science research into new tools and methods in a clinical environment, for example, as new diagnostics or therapies. Nowadays, the process of translation is supported by large amounts of heterogeneous data ranging from medical data to a whole range of -omics data. It is not only a great opportunity but also a great challenge, as translational medicine big data is difficult to integrate and analyze, and requires the involvement of biomedical experts for the data processing. We show here that visualization and interoperable workflows, combining multiple complex steps, can address at least parts of the challenge. In this article, we present an integrated workflow for exploring, analysis, and interpretation of translational medicine data in the context of human health. Three Web services-tranSMART, a Galaxy Server, and a MINERVA platform-are combined into one big data pipeline. Native visualization capabilities enable the biomedical experts to get a comprehensive overview and control over separate steps of the workflow. The capabilities of tranSMART enable a flexible filtering of multidimensional integrated data sets to create subsets suitable for downstream processing. A Galaxy Server offers visually aided construction of analytical pipelines, with the use of existing or custom components. A MINERVA platform supports the exploration of health and disease-related mechanisms in a contextualized analytical visualization system. We demonstrate the utility of our workflow by illustrating its subsequent steps using an existing data set, for which we propose a filtering scheme, an analytical pipeline, and a corresponding visualization of analytical results. The workflow is available as a sandbox environment, where readers can work with the described setup themselves. Overall, our work shows how visualization and interfacing of big data processing services facilitate exploration, analysis, and interpretation of translational medicine data.