SCOTCH: subtype A coreceptor tropism classification in HIV-1.

Motivation: The V3 loop of the gp120 glycoprotein of the Human Immunodeficiency Virus 1 (HIV-1) is considered to be responsible for viral coreceptor tropism. gp120 interacts with the CD4 receptor of the host cell and subsequently V3 binds either CCR5 or CXCR4. Due to the fact that the CCR5 coreceptor is targeted by entry inhibitors, a reliable prediction of the coreceptor usage of HIV-1 is of great interest for antiretroviral therapy. Although several methods for the prediction of coreceptor tropism are available, almost all of them have been developed based on only subtype B sequences, and it has been shown in several studies that the prediction of non-B sequences, in particular subtype A sequences, are less reliable. Thus, the aim of the current study was to develop a reliable prediction model for subtype A viruses. Results: Our new model SCOTCH is based on a stacking approach of classifier ensembles and shows a significantly better performance for subtype A sequences compared to other available models. In particular for low false positive rates (between 0.05 and 0.2, i.e. recommendation in the German and European Guidelines for tropism prediction), SCOTCH shows significantly better prediction performances in terms of partial area under the curves and diagnostic odds ratios compared to existing tools, and thus can be used to reliably predict coreceptor tropism for subtype A sequences. Availability and implementation: SCOTCH can be downloaded/accessed at http://www.heiderlab.de.

eccCL: parallelized GPU implementation of Ensemble Classifier Chains.

BACKGROUND: Multi-label classification has recently gained great attention in diverse fields of research, e.g., in biomedical application such as protein function prediction or drug resistance testing in HIV. In this context, the concept of Classifier Chains has been shown to improve prediction accuracy, especially when applied as Ensemble Classifier Chains. However, these techniques lack computational efficiency when applied on large amounts of data, e.g., derived from next-generation sequencing experiments. By adapting algorithms for the use of graphics processing units, computational efficiency can be greatly improved due to parallelization of computations. RESULTS: Here, we provide a parallelized and optimized graphics processing unit implementation (eccCL) of Classifier Chains and Ensemble Classifier Chains. Additionally to the OpenCL implementation, we provide an R-Package with an easy to use R-interface for parallelized graphics processing unit usage. CONCLUSION: eccCL is a handy implementation of Classifier Chains on GPUs, which is able to process up to over 25,000 instances per second, and thus can be used efficiently in high-throughput experiments. The software is available at http://www.heiderlab.de .

A systematic SNP selection approach to identify mechanisms underlying disease aetiology: linking height to post-menopausal breast and colorectal cancer risk.

Data from GWAS suggest that SNPs associated with complex diseases or traits tend to co-segregate in regions of low recombination, harbouring functionally linked gene clusters. This phenomenon allows for selecting a limited number of SNPs from GWAS repositories for large-scale studies investigating shared mechanisms between diseases. For example, we were interested in shared mechanisms between adult-attained height and post-menopausal breast cancer (BC) and colorectal cancer (CRC) risk, because height is a risk factor for these cancers, though likely not a causal factor. Using SNPs from public GWAS repositories at p-values < 1 × 10-5 and a genomic sliding window of 1 mega base pair, we identified SNP clusters including at least one SNP associated with height and one SNP associated with either post-menopausal BC or CRC risk (or both). SNPs were annotated to genes using HapMap and GRAIL and analysed for significantly overrepresented pathways using ConsensuspathDB. Twelve clusters including 56 SNPs annotated to 26 genes were prioritised because these included at least one height- and one BC risk- or CRC risk-associated SNP annotated to the same gene. Annotated genes were involved in Indian hedgehog signalling (p-value = 7.78 × 10-7) and several cancer site-specific pathways. This systematic approach identified a limited number of clustered SNPs, which pinpoint potential shared mechanisms linking together the complex phenotypes height, post-menopausal BC and CRC.

Rare genetic variants in SMAP1, B3GAT2, and RIMS1 contribute to pediatric venous thromboembolism.

Recent genome-wide association studies (GWAS) have confirmed known risk mutations for venous thromboembolism (VTE) and identified a number of novel susceptibility loci in adults. Here we present a GWAS in 212 nuclear families with pediatric VTE followed by targeted next-generation sequencing (NGS) to identify causative mutations contributing to the association. Three single nucleotide polymorphisms (SNPs) exceeded the threshold for genome-wide significance as determined by permutation testing using 100 000 bootstrap permutations (P < 10-5). These SNPs reside in a region on chromosome 6q13 comprising the genes small ARF GAP1 (SMAP1), an ARF6 guanosine triphosphatase-activating protein that functions in clathrin-dependent endocytosis, and ß-1,3-glucoronyltransferase 2 (B3GAT2), a member of the human natural killer 1 carbohydrate pathway. Rs1304029 and rs2748331 are associated with pediatric VTE with unpermuted/permuted values of P = 1.42 × 10-6/2.0 × 10-6 and P = 6.11 × 10-6/1.8 × 10-5, respectively. Rs2748331 was replicated (P = .00719) in an independent study sample coming from our GWAS on pediatric thromboembolic stroke (combined P = 7.88 × 10-7). Subsequent targeted NGS in 24 discordant sibling pairs identified 17 nonsynonymous coding variants, of which 1 located in SMAP1 and 3 in RIMS1, a member of the RIM family of active zone proteins, are predicted as damaging by Protein Variation Effect Analyzer and/or sorting intolerant from tolerant scores. Three SNPs curtly missed statistical significance in the transmission-disequilibrium test in the full cohort (rs112439957: P = .08326, SMAP1; rs767118962: P = .08326, RIMS1; and rs41265501: P = .05778, RIMS1). In conjunction, our data provide compelling evidence for SMAP1, B3GAT2, and RIMS1 as novel susceptibility loci for pediatric VTE and warrant future functional studies to unravel the underlying molecular mechanisms leading to VTE.

Compensation of feature selection biases accompanied with improved predictive performance for binary classification by using a novel ensemble feature selection approach.

MOTIVATION: Biomarker discovery methods are essential to identify a minimal subset of features (e.g., serum markers in predictive medicine) that are relevant to develop prediction models with high accuracy. By now, there exist diverse feature selection methods, which either are embedded, combined, or independent of predictive learning algorithms. Many preceding studies showed the defectiveness of single feature selection results, which cause difficulties for professionals in a variety of fields (e.g., medical practitioners) to analyze and interpret the obtained feature subsets. Whereas each of these methods is highly biased, an ensemble feature selection has the advantage to alleviate and compensate for such biases. Concerning the reliability, validity, and reproducibility of these methods, we examined eight different feature selection methods for binary classification datasets and developed an ensemble feature selection system. RESULTS: By using an ensemble of feature selection methods, a quantification of the importance of the features could be obtained. The prediction models that have been trained on the selected features showed improved prediction performance.

SHIVA - a web application for drug resistance and tropism testing in HIV.

BACKGROUND: Drug resistance testing is mandatory in antiretroviral therapy in human immunodeficiency virus (HIV) infected patients for successful treatment. The emergence of resistances against antiretroviral agents remains the major obstacle in inhibition of viral replication and thus to control infection. Due to the high mutation rate the virus is able to adapt rapidly under drug pressure leading to the evolution of resistant variants and finally to therapy failure. RESULTS: We developed a web service for drug resistance prediction of commonly used drugs in antiretroviral therapy, i.e., protease inhibitors (PIs), reverse transcriptase inhibitors (NRTIs and NNRTIs), and integrase inhibitors (INIs), but also for the novel drug class of maturation inhibitors. Furthermore, co-receptor tropism (CCR5 or CXCR4) can be predicted as well, which is essential for treatment with entry inhibitors, such as Maraviroc. Currently, SHIVA provides 24 prediction models for several drug classes. SHIVA can be used with single RNA/DNA or amino acid sequences, but also with large amounts of next-generation sequencing data and allows prediction of a user specified selection of drugs simultaneously. Prediction results are provided as clinical reports which are sent via email to the user. CONCLUSIONS: SHIVA represents a novel high performing alternative for hitherto developed drug resistance testing approaches able to process data derived from next-generation sequencing technologies. SHIVA is publicly available via a user-friendly web interface.

Genotypic Prediction of Co-receptor Tropism of HIV-1 Subtypes A and C.

Antiretroviral treatment of Human Immunodeficiency Virus type-1 (HIV-1) infections with CCR5-antagonists requires the co-receptor usage prediction of viral strains. Currently available tools are mostly designed based on subtype B strains and thus are in general not applicable to non-B subtypes. However, HIV-1 infections caused by subtype B only account for approximately 11% of infections worldwide. We evaluated the performance of several sequence-based algorithms for co-receptor usage prediction employed on subtype A V3 sequences including circulating recombinant forms (CRFs) and subtype C strains. We further analysed sequence profiles of gp120 regions of subtype A, B and C to explore functional relationships to entry phenotypes. Our analyses clearly demonstrate that state-of-the-art algorithms are not useful for predicting co-receptor tropism of subtype A and its CRFs. Sequence profile analysis of gp120 revealed molecular variability in subtype A viruses. Especially, the V2 loop region could be associated with co-receptor tropism, which might indicate a unique pattern that determines co-receptor tropism in subtype A strains compared to subtype B and C strains. Thus, our study demonstrates that there is a need for the development of novel algorithms facilitating tropism prediction of HIV-1 subtype A to improve effective antiretroviral treatment in patients.

Exploiting HIV-1 protease and reverse transcriptase cross-resistance information for improved drug resistance prediction by means of multi-label classification.

BACKGROUND: Antiretroviral therapy is essential for human immunodeficiency virus (HIV) infected patients to inhibit viral replication and therewith to slow progression of disease and prolong a patient's life. However, the high mutation rate of HIV can lead to a fast adaptation of the virus under drug pressure and thereby to the evolution of resistant variants. In turn, these variants will lead to the failure of antiretroviral treatment. Moreover, these mutations cannot only lead to resistance against single drugs, but also to cross-resistance, i.e., resistance against drugs that have not yet been applied. METHODS: 662 protease sequences and 715 reverse transcriptase sequences with complete resistance profiles were analyzed using machine learning techniques, namely binary relevance classifiers, classifier chains, and ensembles of classifier chains. RESULTS: In our study, we applied multi-label classification models incorporating cross-resistance information to predict drug resistance for two of the major drug classes used in antiretroviral therapy for HIV-1, namely protease inhibitors (PIs) and non-nucleoside reverse transcriptase inhibitors (NNRTIs). By means of multi-label learning, namely classifier chains (CCs) and ensembles of classifier chains (ECCs), we were able to improve overall prediction accuracy for all drugs compared to hitherto applied binary classification models. CONCLUSIONS: The development of fast and precise models to predict drug resistance in HIV-1 is highly important to enable a highly effective personalized therapy. Cross-resistance information can be exploited to improve prediction accuracy of computational drug resistance models.

Current Approaches in Computational Drug Resistance Prediction in HIV.

BACKGROUND: Today a broad range of antiretroviral drug regimens are applicable for the successful suppression of virus replication in human immunodeficiency virus (HIV) infected people. However, there still remains an obstacle in therapy: the high mutation rate of the HI virus under drug pressure leads to resistant variants causing failure of permanent and effective treatment. Therefore, resistance testing is therefore inevitable to administer appropriate antiviral drugs to infected patients. METHODS: By means of current high-throughput sequencing technologies, computational models have recently constituted important assistance in drug resistance prediction and can guide the choice of medical treatment. Several machine learning algorithms, e.g. support-vector machines, random forests, as well as statistical methods have been already applied to genotypic data and structural information to predict drug resistance. RESULTS: In this review, we provide an overview of existing approaches in computational drug resistance prediction in HIV. We further highlight the challenges and limitations of current methods, e.g. time complexity and prediction of non-B subtypes. CONCLUSION: Moreover, we give a perspective on multi-label and multi-instance classification techniques that potentially tackle the problem of cross-resistances among drugs.

In Acute Myocardial Infarction Liver Parameters Are Associated With Stenosis Diameter.

Detection of high-risk subjects in acute myocardial infarction (AMI) by noninvasive means would reduce the need for intracardiac catheterization and associated complications. Liver enzymes are associated with cardiovascular disease risk. A potential predictive value for liver serum markers for the severity of stenosis in AMI was analyzed.Patients with AMI undergoing percutaneous coronary intervention (PCI; n = 437) were retrospectively evaluated. Minimal lumen diameter (MLD) and percent stenosis diameter (SD) were determined from quantitative coronary angiography. Patients were classified according to the severity of stenosis (SD ≥ 50%, n = 357; SD < 50%, n = 80). Routine heart and liver parameters were associated with SD using random forests (RF). A prediction model (M10) was developed based on parameter importance analysis in RF.Age, alkaline phosphatase (AP), aspartate aminotransferase (AST), and MLD differed significantly between SD ≥ 50 and SD < 50. Age, AST, alanine aminotransferase (ALT), and troponin correlated significantly with SD, whereas MLD correlated inversely with SD. M10 (age, BMI, AP, AST, ALT, gamma-glutamyltransferase, creatinine, troponin) reached an AUC of 69.7% (CI 63.8-75.5%, P < 0.0001).Routine liver parameters are associated with SD in AMI. A small set of noninvasively determined parameters can identify SD in AMI, and might avoid unnecessary coronary angiography in patients with low risk. The model can be accessed via http://stenosis.heiderlab.de.

DNA methylation in an engineered heart tissue model of cardiac hypertrophy: common signatures and effects of DNA methylation inhibitors.

DNA methylation affects transcriptional regulation and constitutes a drug target in cancer biology. In cardiac hypertrophy, DNA methylation may control the fetal gene program. We therefore investigated DNA methylation signatures and their dynamics in an in vitro model of cardiac hypertrophy based on engineered heart tissue (EHT). We exposed EHTs from neonatal rat cardiomyocytes to a 12-fold increased afterload (AE) or to phenylephrine (PE 20 µM) and compared DNA methylation signatures to control EHT by pull-down assay and DNA methylation microarray. A 7-day intervention sufficed to induce contractile dysfunction and significantly decrease promoter methylation of hypertrophy-associated upregulated genes such as Nppa (encoding ANP) and Acta1 (α-skeletal actin) in both intervention groups. To evaluate whether pathological consequences of AE are affected by inhibiting de novo DNA methylation we applied AE in the absence and presence of DNA methyltransferase (DNMT) inhibitors: 5-aza-2'-deoxycytidine (aza, 100 µM, nucleosidic inhibitor), RG108 (60 µM, non-nucleosidic) or methylene disalicylic acid (MDSA, 25 µM, non-nucleosidic). Aza had no effect on EHT function, but RG108 and MDSA partially prevented the detrimental consequences of AE on force, contraction and relaxation velocity. RG108 reduced AE-induced Atp2a2 (SERCA2a) promoter methylation. The results provide evidence for dynamic DNA methylation in cardiac hypertrophy and warrant further investigation of the potential of DNA methylation in the treatment of cardiac hypertrophy.

Fetal-adult cardiac transcriptome analysis in rats with contrasting left ventricular mass reveals new candidates for cardiac hypertrophy.

Reactivation of fetal gene expression patterns has been implicated in common cardiac diseases in adult life including left ventricular (LV) hypertrophy (LVH) in arterial hypertension. Thus, increased wall stress and neurohumoral activation are discussed to induce the return to expression of fetal genes after birth in LVH. We therefore aimed to identify novel potential candidates for LVH by analyzing fetal-adult cardiac gene expression in a genetic rat model of hypertension, i.e. the stroke-prone spontaneously hypertensive rat (SHRSP). To this end we performed genome-wide transcriptome analysis in SHRSP to identify differences in expression patterns between day 20 of fetal development (E20) and adult animals in week 14 in comparison to a normotensive rat strain with contrasting low LV mass, i.e. Fischer (F344). 15232 probes were detected as expressed in LV tissue obtained from rats at E20 and week 14 (p < 0.05) and subsequently screened for differential expression. We identified 24 genes with SHRSP specific up-regulation and 21 genes with down-regulation as compared to F344. Further bioinformatic analysis presented Efcab6 as a new candidate for LVH that showed only in the hypertensive SHRSP rat differential expression during development (logFC = 2.41, p < 0.001) and was significantly higher expressed in adult SHRSP rats compared with adult F344 (+ 76%) and adult normotensive Wistar-Kyoto rats (+ 82%). Thus, it represents an interesting new target for further functional analyses and the elucidation of mechanisms leading to LVH. Here we report a new approach to identify candidate genes for cardiac hypertrophy by combining the analysis of gene expression differences between strains with a contrasting cardiac phenotype with a comparison of fetal-adult cardiac expression patterns.

Transcriptome assessment reveals a dominant role for TLR4 in the activation of human monocytes by the alarmin MRP8.

The alarmins myeloid-related protein (MRP)8 and MRP14 are the most prevalent cytoplasmic proteins in phagocytes. When released from activated or necrotic phagocytes, extracellular MRP8/MRP14 promote inflammation in many diseases, including infections, allergies, autoimmune diseases, rheumatoid arthritis, and inflammatory bowel disease. The involvement of TLR4 and the multiligand receptor for advanced glycation end products as receptors during MRP8-mediated effects on inflammation remains controversial. By comparative bioinformatic analysis of genome-wide response patterns of human monocytes to MRP8, endotoxins, and various cytokines, we have developed a model in which TLR4 is the dominant receptor for MRP8-mediated phagocyte activation. The relevance of the TLR4 signaling pathway was experimentally validated using human and murine models of TLR4- and receptor for advanced glycation end products-dependent signaling. Furthermore, our systems biology approach has uncovered an antiapoptotic role for MRP8 in monocytes, which was corroborated by independent functional experiments. Our data confirm the primary importance of the TLR4/MRP8 axis in the activation of human monocytes, representing a novel and attractive target for modulation of the overwhelming innate immune response.

MANIA-a pattern classification toolbox for neuroimaging data.

Conventional univariate statistics are common and widespread in neuroimaging research. However, functional and structural MRI data reveal a multivariate nature, since neighboring voxels are highly correlated and different localized brain regions activate interdependently. Multivariate pattern classification techniques are capable of overcoming shortcomings of univariate statistics. A rising interest in such approaches on neuroimaging data leads to an increasing demand of appropriate software and tools in this field. Here, we introduce and release MANIA-Machine learning Application for NeuroImaging Analyses. MANIA is a Matlab based software toolbox enabling easy pattern classification of neuroimaging data and offering a broad assortment of machine learning algorithms and feature selection methods. Between groups classifications are the main scope of this software, for instance the differentiation between patients and controls. A special emphasis was placed on an intuitive and easy to use graphical user interface allowing quick implementation and guidance also for clinically oriented researchers. MANIA is free and open source, published under GPL3 license. This work will give an overview regarding the functionality and the modular software architecture as well as a comparison between other software packages.

Evolutionary dynamics of co-segregating gene clusters associated with complex diseases.

BACKGROUND: The distribution of human disease-associated mutations is not random across the human genome. Despite the fact that natural selection continually removes disease-associated mutations, an enrichment of these variants can be observed in regions of low recombination. There are a number of mechanisms by which such a clustering could occur, including genetic perturbations or demographic effects within different populations. Recent genome-wide association studies (GWAS) suggest that single nucleotide polymorphisms (SNPs) associated with complex disease traits are not randomly distributed throughout the genome, but tend to cluster in regions of low recombination. PRINCIPAL FINDINGS: Here we investigated whether deleterious mutations have accumulated in regions of low recombination due to the impact of recent positive selection and genetic hitchhiking. Using publicly available data on common complex diseases and population demography, we observed an enrichment of hitchhiked disease associations in conserved gene clusters subject to selection pressure. Evolutionary analysis revealed that these conserved gene clusters arose by multiple concerted rearrangements events across the vertebrate lineage. We observed distinct clustering of disease-associated SNPs in evolutionary rearranged regions of low recombination and high gene density, which harbor genes involved in immunity, that is, the interleukin cluster on 5q31 or RhoA on 3p21. CONCLUSIONS: Our results suggest that multiple lineage specific rearrangements led to a physical clustering of functionally related and linked genes exhibiting an enrichment of susceptibility loci for complex traits. This implies that besides recent evolutionary adaptations other evolutionary dynamics have played a role in the formation of linked gene clusters associated with complex disease traits.

Improved Bevirimat resistance prediction by combination of structural and sequence-based classifiers.

BACKGROUND: Maturation inhibitors such as Bevirimat are a new class of antiretroviral drugs that hamper the cleavage of HIV-1 proteins into their functional active forms. They bind to these preproteins and inhibit their cleavage by the HIV-1 protease, resulting in non-functional virus particles. Nevertheless, there exist mutations in this region leading to resistance against Bevirimat. Highly specific and accurate tools to predict resistance to maturation inhibitors can help to identify patients, who might benefit from the usage of these new drugs. RESULTS: We tested several methods to improve Bevirimat resistance prediction in HIV-1. It turned out that combining structural and sequence-based information in classifier ensembles led to accurate and reliable predictions. Moreover, we were able to identify the most crucial regions for Bevirimat resistance computationally, which are in line with experimental results from other studies. CONCLUSIONS: Our analysis demonstrated the use of machine learning techniques to predict HIV-1 resistance against maturation inhibitors such as Bevirimat. New maturation inhibitors are already under development and might enlarge the arsenal of antiretroviral drugs in the future. Thus, accurate prediction tools are very useful to enable a personalized therapy.