AI reveals insights into link between CD33 and cognitive impairment in Alzheimer's Disease.

Modeling biological mechanisms is a key for disease understanding and drug-target identification. However, formulating quantitative models in the field of Alzheimer's Disease is challenged by a lack of detailed knowledge of relevant biochemical processes. Additionally, fitting differential equation systems usually requires time resolved data and the possibility to perform intervention experiments, which is difficult in neurological disorders. This work addresses these challenges by employing the recently published Variational Autoencoder Modular Bayesian Networks (VAMBN) method, which we here trained on combined clinical and patient level gene expression data while incorporating a disease focused knowledge graph. Our approach, called iVAMBN, resulted in a quantitative model that allowed us to simulate a down-expression of the putative drug target CD33, including potential impact on cognitive impairment and brain pathophysiology. Experimental validation demonstrated a high overlap of molecular mechanism predicted to be altered by CD33 perturbation with cell line data. Altogether, our modeling approach may help to select promising drug targets.

Transformer models in biomedicine.

Deep neural networks (DNN) have fundamentally revolutionized the artificial intelligence (AI) field. The transformer model is a type of DNN that was originally used for the natural language processing tasks and has since gained more and more attention for processing various kinds of sequential data, including biological sequences and structured electronic health records. Along with this development, transformer-based models such as BioBERT, MedBERT, and MassGenie have been trained and deployed by researchers to answer various scientific questions originating in the biomedical domain. In this paper, we review the development and application of transformer models for analyzing various biomedical-related datasets such as biomedical textual data, protein sequences, medical structured-longitudinal data, and biomedical images as well as graphs. Also, we look at explainable AI strategies that help to comprehend the predictions of transformer-based models. Finally, we discuss the limitations and challenges of current models, and point out emerging novel research directions.

GenRisk: a tool for comprehensive genetic risk modeling.

SUMMARY: The genetic architecture of complex traits can be influenced by both many common regulatory variants with small effect sizes and rare deleterious variants in coding regions with larger effect sizes. However, the two kinds of genetic contributions are typically analyzed independently. Here, we present GenRisk, a python package for the computation and the integration of gene scores based on the burden of rare deleterious variants and common-variants-based polygenic risk scores. The derived scores can be analyzed within GenRisk to perform association tests or to derive phenotype prediction models by testing multiple classification and regression approaches. GenRisk is compatible with VCF input file formats. AVAILABILITY AND IMPLEMENTATION: GenRisk is an open source publicly available python package that can be downloaded or installed from Github (https://github.com/AldisiRana/GenRisk). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SEEDS: data driven inference of structural model errors and unknown inputs for dynamic systems biology.

SUMMARY: Dynamic models formulated as ordinary differential equations can provide information about the mechanistic and causal interactions in biological systems to guide targeted interventions and to design further experiments. Inaccurate knowledge about the structure, functional form and parameters of interactions is a major obstacle to mechanistic modeling. A further challenge is the open nature of biological systems which receive unknown inputs from their environment. The R-package SEEDS implements two recently developed algorithms to infer structural model errors and unknown inputs from output measurements. This information can facilitate efficient model recalibration as well as experimental design in the case of misfits between the initial model and data. AVAILABILITY AND IMPLEMENTATION: For the R-package seeds, see the CRAN server https://cran.r-project.org/package=seeds.

Towards realizing the vision of precision medicine: AI based prediction of clinical drug response.

Accurate and individualized prediction of response to therapies is central to precision medicine. However, because of the generally complex and multifaceted nature of clinical drug response, realizing this vision is highly challenging, requiring integrating different data types from the same individual into one prediction model. We used the anti-epileptic drug brivaracetam as a case study and combine a hybrid data/knowledge-driven feature extraction with machine learning to systematically integrate clinical and genetic data from a clinical discovery dataset (n = 235 patients). We constructed a model that successfully predicts clinical drug response [area under the curve (AUC) = 0.76] and show that even with limited sample size, integrating high-dimensional genetics data with clinical data can inform drug response prediction. After further validation on data collected from an independently conducted clinical study (AUC = 0.75), we extensively explore our model to gain insights into the determinants of drug response, and identify various clinical and genetic characteristics predisposing to poor response. Finally, we assess the potential impact of our model on clinical trial design and demonstrate that, by enriching for probable responders, significant reductions in clinical study sizes may be achieved. To our knowledge, our model represents the first retrospectively validated machine learning model linking drug mechanism of action and the genetic, clinical and demographic background in epilepsy patients to clinical drug response. Hence, it provides a blueprint for how machine learning-based multimodal data integration can act as a driver in achieving the goals of precision medicine in fields such as neurology.

Unraveling the heterogeneity in Alzheimer's disease progression across multiple cohorts and the implications for data-driven disease modeling.

INTRODUCTION: Given study-specific inclusion and exclusion criteria, Alzheimer's disease (AD) cohort studies effectively sample from different statistical distributions. This heterogeneity can propagate into cohort-specific signals and subsequently bias data-driven investigations of disease progression patterns. METHODS: We built multi-state models for six independent AD cohort datasets to statistically compare disease progression patterns across them. Additionally, we propose a novel method for clustering cohorts with regard to their progression signals. RESULTS: We identified significant differences in progression patterns across cohorts. Models trained on cohort data learned cohort-specific effects that bias their estimations. We demonstrated how six cohorts relate to each other regarding their disease progression. DISCUSSION: Heterogeneity in cohort datasets impedes the reproducibility of data-driven results and validation of progression models generated on single cohorts. To ensure robust scientific insights, it is advisable to externally validate results in independent cohort datasets. The proposed clustering assesses the comparability of cohorts in an unbiased, data-driven manner.

PathME: pathway based multi-modal sparse autoencoders for clustering of patient-level multi-omics data.

BACKGROUND: Recent years have witnessed an increasing interest in multi-omics data, because these data allow for better understanding complex diseases such as cancer on a molecular system level. In addition, multi-omics data increase the chance to robustly identify molecular patient sub-groups and hence open the door towards a better personalized treatment of diseases. Several methods have been proposed for unsupervised clustering of multi-omics data. However, a number of challenges remain, such as the magnitude of features and the large difference in dimensionality across different omics data sources. RESULTS: We propose a multi-modal sparse denoising autoencoder framework coupled with sparse non-negative matrix factorization to robustly cluster patients based on multi-omics data. The proposed model specifically leverages pathway information to effectively reduce the dimensionality of omics data into a pathway and patient specific score profile. In consequence, our method allows us to understand, which pathway is a feature of which particular patient cluster. Moreover, recently proposed machine learning techniques allow us to disentangle the specific impact of each individual omics feature on a pathway score. We applied our method to cluster patients in several cancer datasets using gene expression, miRNA expression, DNA methylation and CNVs, demonstrating the possibility to obtain biologically plausible disease subtypes characterized by specific molecular features. Comparison against several competing methods showed a competitive clustering performance. In addition, post-hoc analysis of somatic mutations and clinical data provided supporting evidence and interpretation of the identified clusters. CONCLUSIONS: Our suggested multi-modal sparse denoising autoencoder approach allows for an effective and interpretable integration of multi-omics data on pathway level while addressing the high dimensional character of omics data. Patient specific pathway score profiles derived from our model allow for a robust identification of disease subgroups.

The EMT transcription factor Zeb2 controls adult murine hematopoietic differentiation by regulating cytokine signaling.

Epithelial-to-mesenchymal-transition (EMT) is critical for normal embryogenesis and effective postnatal wound healing, but is also associated with cancer metastasis. SNAIL, ZEB, and TWIST families of transcription factors are key modulators of the EMT process, but their precise roles in adult hematopoietic development and homeostasis remain unclear. Here we report that genetic inactivation of Zeb2 results in increased frequency of stem and progenitor subpopulations within the bone marrow (BM) and spleen and that these changes accompany differentiation defects in multiple hematopoietic cell lineages. We found no evidence that Zeb2 is critical for hematopoietic stem cell self-renewal capacity. However, knocking out Zeb2 in the BM promoted a phenotype with several features that resemble human myeloproliferative disorders, such as BM fibrosis, splenomegaly, and extramedullary hematopoiesis. Global gene expression and intracellular signal transduction analysis revealed perturbations in specific cytokine and cytokine receptor-related signaling pathways following Zeb2 loss, especially the JAK-STAT and extracellular signal-regulated kinase pathways. Moreover, we detected some previously unknown mutations within the human Zeb2 gene (ZFX1B locus) from patients with myeloid disease. Collectively, our results demonstrate that Zeb2 controls adult hematopoietic differentiation and lineage fidelity through widespread modulation of dominant signaling pathways that may contribute to blood disorders.

From hype to reality: data science enabling personalized medicine.

BACKGROUND: Personalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of 'big data' and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In this paper, we review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future. CONCLUSIONS: There is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies, and health insurance organizations. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.

Towards clinically more relevant dissection of patient heterogeneity via survival-based Bayesian clustering.

MOTIVATION: Discovery of clinically relevant disease sub-types is of prime importance in personalized medicine. Disease sub-type identification has in the past often been explored in an unsupervised machine learning paradigm which involves clustering of patients based on available-omics data, such as gene expression. A follow-up analysis involves determining the clinical relevance of the molecular sub-types such as that reflected by comparing their disease progressions. The above methodology, however, fails to guarantee the separability of the sub-types based on their subtype-specific survival curves. RESULTS: We propose a new algorithm, Survival-based Bayesian Clustering (SBC) which simultaneously clusters heterogeneous-omics and clinical end point data (time to event) in order to discover clinically relevant disease subtypes. For this purpose we formulate a novel Hierarchical Bayesian Graphical Model which combines a Dirichlet Process Gaussian Mixture Model with an Accelerated Failure Time model. In this way we make sure that patients are grouped in the same cluster only when they show similar characteristics with respect to molecular features across data types (e.g. gene expression, mi-RNA) as well as survival times. We extensively test our model in simulation studies and apply it to cancer patient data from the Breast Cancer dataset and The Cancer Genome Atlas repository. Notably, our method is not only able to find clinically relevant sub-groups, but is also able to predict cluster membership and survival on test data in a better way than other competing methods. AVAILABILITY AND IMPLEMENTATION: Our R-code can be accessed as https://github.com/ashar799/SBC. CONTACT: ashar@bit.uni-bonn.de. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Linking metabolic network features to phenotypes using sparse group lasso.

MOTIVATION: Integration of metabolic networks with '-omics' data has been a subject of recent research in order to better understand the behaviour of such networks with respect to differences between biological and clinical phenotypes. Under the conditions of steady state of the reaction network and the non-negativity of fluxes, metabolic networks can be algebraically decomposed into a set of sub-pathways often referred to as extreme currents (ECs). Our objective is to find the statistical association of such sub-pathways with given clinical outcomes, resulting in a particular instance of a self-contained gene set analysis method. In this direction, we propose a method based on sparse group lasso (SGL) to identify phenotype associated ECs based on gene expression data. SGL selects a sparse set of feature groups and also introduces sparsity within each group. Features in our model are clusters of ECs, and feature groups are defined based on correlations among these features. RESULTS: We apply our method to metabolic networks from KEGG database and study the association of network features to prostate cancer (where the outcome is tumor and normal, respectively) as well as glioblastoma multiforme (where the outcome is survival time). In addition, simulations show the superior performance of our method compared to global test, which is an existing self-contained gene set analysis method. AVAILABILITY AND IMPLEMENTATION: R code (compatible with version 3.2.5) is available from http://www.abi.bit.uni-bonn.de/index.php?id=17. CONTACT: samal@combine.rwth-aachen.de or frohlich@bit.uni-bonn.de. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Single nucleotide polymorphisms in the angiogenic and lymphangiogenic pathways are associated with lymphedema caused by Wuchereria bancrofti.

BACKGROUND: Lymphedema (LE) is a chronic clinical manifestation of filarial nematode infections characterized by lymphatic dysfunction and subsequent accumulation of protein-rich fluid in the interstitial space-lymphatic filariasis. A number of studies have identified single nucleotide polymorphisms (SNPs) associated with primary and secondary LE. To assess SNPs associated with LE caused by lymphatic filariasis, a cross-sectional study of unrelated Ghanaian volunteers was designed to genotype SNPs in 285 LE patients as cases and 682 infected patients without pathology as controls. One hundred thirty-one SNPs in 64 genes were genotyped. The genes were selected based on their roles in inflammatory processes, angiogenesis/lymphangiogenesis, and cell differentiation during tumorigenesis. RESULTS: Genetic associations with nominal significance were identified for five SNPs in three genes: vascular endothelial growth factor receptor-3 (VEGFR-3) rs75614493, two SNPs in matrix metalloprotease-2 (MMP-2) rs1030868 and rs2241145, and two SNPs in carcinoembryonic antigen-related cell adhesion molecule-1 (CEACAM-1) rs8110904 and rs8111171. Pathway analysis revealed an interplay of genes in the angiogenic/lymphangiogenic pathways. Plasma levels of both MMP-2 and CEACAM-1 were significantly higher in LE cases compared to controls. Functional characterization of the associated SNPs identified genotype GG of CEACAM-1 as the variant influencing the expression of plasma concentration, a novel finding observed in this study. CONCLUSION: The SNP associations found in the MMP-2, CEACAM-1, and VEGFR-3 genes indicate that angiogenic/lymphangiogenic pathways are important in LE clinical development.

Inferring modulators of genetic interactions with epistatic nested effects models.

Maps of genetic interactions can dissect functional redundancies in cellular networks. Gene expression profiles as high-dimensional molecular readouts of combinatorial perturbations provide a detailed view of genetic interactions, but can be hard to interpret if different gene sets respond in different ways (called mixed epistasis). Here we test the hypothesis that mixed epistasis between a gene pair can be explained by the action of a third gene that modulates the interaction. We have extended the framework of Nested Effects Models (NEMs), a type of graphical model specifically tailored to analyze high-dimensional gene perturbation data, to incorporate logical functions that describe interactions between regulators on downstream genes and proteins. We benchmark our approach in the controlled setting of a simulation study and show high accuracy in inferring the correct model. In an application to data from deletion mutants of kinases and phosphatases in S. cerevisiae we show that epistatic NEMs can point to modulators of genetic interactions. Our approach is implemented in the R-package 'epiNEM' available from https://github.com/cbg-ethz/epiNEM and https://bioconductor.org/packages/epiNEM/.

Key Players of Cisplatin Resistance: Towards a Systems Pharmacology Approach.

The major obstacle in the clinical use of the antitumor drug cisplatin is inherent and acquired resistance. Typically, cisplatin resistance is not restricted to a single mechanism demanding for a systems pharmacology approach to understand a whole cell's reaction to the drug. In this study, the cellular transcriptome of untreated and cisplatin-treated A549 non-small cell lung cancer cells and their cisplatin-resistant sub-line A549rCDDP2000 was screened with a whole genome array for relevant gene candidates. By combining statistical methods with available gene annotations and without a previously defined hypothesis HRas, MAPK14 (p38), CCL2, DOK1 and PTK2B were identified as genes possibly relevant for cisplatin resistance. These and related genes were further validated on transcriptome (qRT-PCR) and proteome (Western blot) level to select candidates contributing to resistance. HRas, p38, CCL2, DOK1, PTK2B and JNK3 were integrated into a model of resistance-associated signalling alterations describing differential gene and protein expression between cisplatin-sensitive and -resistant cells in reaction to cisplatin exposure.

Epigenome-wide DNA methylation analysis in siblings and monozygotic twins discordant for sporadic Parkinson's disease revealed different epigenetic patterns in peripheral blood mononuclear cells.

Numerous studies have elucidated the genetics of Parkinson's disease; however, the aetiology of the majority of sporadic cases has not yet been resolved. We hypothesized that epigenetic variations could be associated with PD and evaluated the DNA methylation pattern in PD patients compared to brothers or twins without PD. The methylation of DNA from peripheral blood mononuclear cells of 62 discordant siblings including 24 monozygotic twins was characterized with Illumina DNA Methylation 450K bead arrays and subsequently validated in two independent cohorts: 221 PD vs. 227 healthy individuals (cohort 1) applying Illumina's VeraCode and 472 PD patients vs. 487 controls (cohort 2) using pyrosequencing. We choose a delta beta of >15 % and selected 62 differentially methylated CpGs in 51 genes from the discordant siblings. Among them, three displayed multiple CpGs per gene: microRNA 886 (MIR886, 10 CpGs), phosphodiesterase 4D (PDE4D, 2 CpGs) and tripartite motif-containing 34 (TRIM34, 2 CpGs). PDE4D was confirmed in both cohorts (p value 2.44e-05). In addition, for biomarker construction, we used the penalized logistic regression model, resulting in a signature of eight CpGs with an AUC of 0.77. Our findings suggest that a distinct level of PD susceptibility stems from individual, epigenetic modifications of specific genes. We identified a signature of CpGs in blood cells that could separate control from disease with a reasonable discriminatory power, holding promise for future epigenetically based biomarker development.

Changes in serum miRNAs following generalized convulsive seizures in human mesial temporal lobe epilepsy.

MicroRNAs (miRNAs) are key regulators of gene expression and are involved in the pathomechanisms of epilepsy. MiRNAs may also serve as peripheral biomarkers of epilepsy. We investigated the miRNA profile in the blood serum of patients suffering from mesial temporal lobe epilepsy (mTLE) following a single focal seizure evolving to a bilateral convulsive seizure (BCS) during video-EEG monitoring. Data of 15 patients were included in the final analysis. MiRNA expression was determined using Real Time-PCR followed by thorough bioinformatical analysis of expression levels. We found that more than 200 miRNAs were differentially expressed in the serum of patients within 30 min after a single seizure. Validation of the 20 top miRNA candidates confirmed that 4 miRNAs (miR-143, miR-145, miR-532, miR-365a) were significantly deregulated. Interestingly, in a sub-group of patients with seizures occurring during sleep, we found 10 miRNAs to be deregulated up to 20-28 h after the seizure. In this group of patients, miR-663b was significantly deregulated. We conclude that single seizures are associated with detectable transient miRNA alterations in blood serum in the early postictal phase. The significant upregulation of miR-663b following BCS arising during sleep indicates potential suitability of this miRNA as a potential biomarker for seizure diagnostics.

biRte: Bayesian inference of context-specific regulator activities and transcriptional networks.

UNLABELLED: In the last years there has been an increasing effort to computationally model and predict the influence of regulators (transcription factors, miRNAs) on gene expression. Here we introduce biRte as a computationally attractive approach combining Bayesian inference of regulator activities with network reverse engineering. biRte integrates target gene predictions with different omics data entities (e.g. miRNA and mRNA data) into a joint probabilistic framework. The utility of our method is tested in extensive simulation studies and demonstrated with applications from prostate cancer and Escherichia coli growth control. The resulting regulatory networks generally show a good agreement with the biological literature. AVAILABILITY AND IMPLEMENTATION: biRte is available on Bioconductor (http://bioconductor.org). CONTACT: frohlich@bit.uni-bonn.de SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

NEMix: single-cell nested effects models for probabilistic pathway stimulation.

Nested effects models have been used successfully for learning subcellular networks from high-dimensional perturbation effects that result from RNA interference (RNAi) experiments. Here, we further develop the basic nested effects model using high-content single-cell imaging data from RNAi screens of cultured cells infected with human rhinovirus. RNAi screens with single-cell readouts are becoming increasingly common, and they often reveal high cell-to-cell variation. As a consequence of this cellular heterogeneity, knock-downs result in variable effects among cells and lead to weak average phenotypes on the cell population level. To address this confounding factor in network inference, we explicitly model the stimulation status of a signaling pathway in individual cells. We extend the framework of nested effects models to probabilistic combinatorial knock-downs and propose NEMix, a nested effects mixture model that accounts for unobserved pathway activation. We analyzed the identifiability of NEMix and developed a parameter inference scheme based on the Expectation Maximization algorithm. In an extensive simulation study, we show that NEMix improves learning of pathway structures over classical NEMs significantly in the presence of hidden pathway stimulation. We applied our model to single-cell imaging data from RNAi screens monitoring human rhinovirus infection, where limited infection efficiency of the assay results in uncertain pathway stimulation. Using a subset of genes with known interactions, we show that the inferred NEMix network has high accuracy and outperforms the classical nested effects model without hidden pathway activity. NEMix is implemented as part of the R/Bioconductor package 'nem' and available at www.cbg.ethz.ch/software/NEMix.

Crowdsourced estimation of cognitive decline and resilience in Alzheimer's disease.

Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer's disease. The Alzheimer's disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer's disease based on high dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for prediction of cognitive performance.