Targeted serum proteomics of longitudinal samples from newly diagnosed youth with type 1 diabetes distinguishes markers of disease and C-peptide trajectory.

AIMS/HYPOTHESIS: There is a growing need for markers that could help indicate the decline in beta cell function and recognise the need and efficacy of intervention in type 1 diabetes. Measurements of suitably selected serum markers could potentially provide a non-invasive and easily applicable solution to this challenge. Accordingly, we evaluated a broad panel of proteins previously associated with type 1 diabetes in serum from newly diagnosed individuals during the first year from diagnosis. To uncover associations with beta cell function, comparisons were made between these targeted proteomics measurements and changes in fasting C-peptide levels. To further distinguish proteins linked with the disease status, comparisons were made with measurements of the protein targets in age- and sex-matched autoantibody-negative unaffected family members (UFMs). METHODS: Selected reaction monitoring (SRM) mass spectrometry analyses of serum, targeting 85 type 1 diabetes-associated proteins, were made. Sera from individuals diagnosed under 18 years (n=86) were drawn within 6 weeks of diagnosis and at 3, 6 and 12 months afterwards (288 samples in total). The SRM data were compared with fasting C-peptide/glucose data, which was interpreted as a measure of beta cell function. The protein data were further compared with cross-sectional SRM measurements from UFMs (n=194). RESULTS: Eleven proteins had statistically significant associations with fasting C-peptide/glucose. Of these, apolipoprotein L1 and glutathione peroxidase 3 (GPX3) displayed the strongest positive and inverse associations, respectively. Changes in GPX3 levels during the first year after diagnosis indicated future fasting C-peptide/glucose levels. In addition, differences in the levels of 13 proteins were observed between the individuals with type 1 diabetes and the matched UFMs. These included GPX3, transthyretin, prothrombin, apolipoprotein C1 and members of the IGF family. CONCLUSIONS/INTERPRETATION: The association of several targeted proteins with fasting C-peptide/glucose levels in the first year after diagnosis suggests their connection with the underlying changes accompanying alterations in beta cell function in type 1 diabetes. Moreover, the direction of change in GPX3 during the first year was indicative of subsequent fasting C-peptide/glucose levels, and supports further investigation of this and other serum protein measurements in future studies of beta cell function in type 1 diabetes.

DanMAC5: a browser of aggregated sequence variants from 8,671 whole genome sequenced Danish individuals.

OBJECTIVES: Allele counts of sequence variants obtained by whole genome sequencing (WGS) often play a central role in interpreting the results of genetic and genomic research. However, such variant counts are not readily available for individuals in the Danish population. Here, we present a dataset with allele counts for sequence variants (single nucleotide variants (SNVs) and indels) identified from WGS of 8,671 (5,418 females) individuals from the Danish population. The data resource is based on WGS data from three independent research projects aimed at assessing genetic risk factors for cardiovascular, psychiatric, and headache disorders. To enable the sharing of information on sequence variation in Danish individuals, we created summarized statistics on allele counts from anonymized data and made them available through the European Genome-phenome Archive (EGA, https://identifiers.org/ega. DATASET: EGAD00001009756 ) and in a dedicated browser, DanMAC5 (available at www.danmac5.dk ). The summary level data and the DanMAC5 browser provide insight into the allelic spectrum of sequence variants segregating in the Danish population, which is important in variant interpretation. DATA DESCRIPTION: Three WGS datasets with an average coverage of 30x were processed independently using the same quality control pipeline. Subsequently, we summarized, filtered, and merged allele counts to create a high-quality summary level dataset of sequence variants.

A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories.

Pancreatic cancer is an aggressive disease that typically presents late with poor outcomes, indicating a pronounced need for early detection. In this study, we applied artificial intelligence methods to clinical data from 6 million patients (24,000 pancreatic cancer cases) in Denmark (Danish National Patient Registry (DNPR)) and from 3 million patients (3,900 cases) in the United States (US Veterans Affairs (US-VA)). We trained machine learning models on the sequence of disease codes in clinical histories and tested prediction of cancer occurrence within incremental time windows (CancerRiskNet). For cancer occurrence within 36 months, the performance of the best DNPR model has area under the receiver operating characteristic (AUROC) curve = 0.88 and decreases to AUROC (3m) = 0.83 when disease events within 3 months before cancer diagnosis are excluded from training, with an estimated relative risk of 59 for 1,000 highest-risk patients older than age 50 years. Cross-application of the Danish model to US-VA data had lower performance (AUROC = 0.71), and retraining was needed to improve performance (AUROC = 0.78, AUROC (3m) = 0.76). These results improve the ability to design realistic surveillance programs for patients at elevated risk, potentially benefiting lifespan and quality of life by early detection of this aggressive cancer.

Gene expression signature predicts rate of type 1 diabetes progression.

BACKGROUND: Type 1 diabetes is a complex heterogenous autoimmune disease without therapeutic interventions available to prevent or reverse the disease. This study aimed to identify transcriptional changes associated with the disease progression in patients with recent-onset type 1 diabetes. METHODS: Whole-blood samples were collected as part of the INNODIA study at baseline and 12 months after diagnosis of type 1 diabetes. We used linear mixed-effects modelling on RNA-seq data to identify genes associated with age, sex, or disease progression. Cell-type proportions were estimated from the RNA-seq data using computational deconvolution. Associations to clinical variables were estimated using Pearson's or point-biserial correlation for continuous and dichotomous variables, respectively, using only complete pairs of observations. FINDINGS: We found that genes and pathways related to innate immunity were downregulated during the first year after diagnosis. Significant associations of the gene expression changes were found with ZnT8A autoantibody positivity. Rate of change in the expression of 16 genes between baseline and 12 months was found to predict the decline in C-peptide at 24 months. Interestingly and consistent with earlier reports, increased B cell levels and decreased neutrophil levels were associated with the rapid progression. INTERPRETATION: There is considerable individual variation in the rate of progression from appearance of type 1 diabetes-specific autoantibodies to clinical disease. Patient stratification and prediction of disease progression can help in developing more personalised therapeutic strategies for different disease endotypes. FUNDING: A full list of funding bodies can be found under Acknowledgments.

Discovery of drug-omics associations in type 2 diabetes with generative deep-learning models.

The application of multiple omics technologies in biomedical cohorts has the potential to reveal patient-level disease characteristics and individualized response to treatment. However, the scale and heterogeneous nature of multi-modal data makes integration and inference a non-trivial task. We developed a deep-learning-based framework, multi-omics variational autoencoders (MOVE), to integrate such data and applied it to a cohort of 789 people with newly diagnosed type 2 diabetes with deep multi-omics phenotyping from the DIRECT consortium. Using in silico perturbations, we identified drug-omics associations across the multi-modal datasets for the 20 most prevalent drugs given to people with type 2 diabetes with substantially higher sensitivity than univariate statistical tests. From these, we among others, identified novel associations between metformin and the gut microbiota as well as opposite molecular responses for the two statins, simvastatin and atorvastatin. We used the associations to quantify drug-drug similarities, assess the degree of polypharmacy and conclude that drug effects are distributed across the multi-omics modalities.

Discrete-time survival analysis in the critically ill: a deep learning approach using heterogeneous data.

Prediction of survival for patients in intensive care units (ICUs) has been subject to intense research. However, no models exist that embrace the multiverse of data in ICUs. It is an open question whether deep learning methods using automated data integration with minimal pre-processing of mixed data domains such as free text, medical history and high-frequency data can provide discrete-time survival estimates for individual ICU patients. We trained a deep learning model on data from patients admitted to ten ICUs in the Capital Region of Denmark and the Region of Southern Denmark between 2011 and 2018. Inspired by natural language processing we mapped the electronic patient record data to an embedded representation and fed the data to a recurrent neural network with a multi-label output layer representing the chance of survival at different follow-up times. We evaluated the performance using the time-dependent concordance index. In addition, we quantified and visualized the drivers of survival predictions using the SHAP methodology. We included 37,355 admissions of 29,417 patients in our study. Our deep learning models outperformed traditional Cox proportional-hazard models with concordance index in the ranges 0.72-0.73, 0.71-0.72, 0.71, and 0.69-0.70, for models applied at baseline 0, 24, 48, and 72 h, respectively. Deep learning models based on a combination of entity embeddings and survival modelling is a feasible approach to obtain individualized survival estimates in data-rich settings such as the ICU. The interpretable nature of the models enables us to understand the impact of the different data domains.

INNODIA Master Protocol for the evaluation of investigational medicinal products in children, adolescents and adults with newly diagnosed type 1 diabetes.

BACKGROUND: The INNODIA consortium has established a pan-European infrastructure using validated centres to prospectively evaluate clinical data from individuals with newly diagnosed type 1 diabetes combined with centralised collection of clinical samples to determine rates of decline in beta-cell function and identify novel biomarkers, which could be used for future stratification of phase 2 clinical trials. METHODS: In this context, we have developed a Master Protocol, based on the "backbone" of the INNODIA natural history study, which we believe could improve the delivery of phase 2 studies exploring the use of single or combinations of Investigational Medicinal Products (IMPs), designed to prevent or reverse declines in beta-cell function in individuals with newly diagnosed type 1 diabetes. Although many IMPs have demonstrated potential efficacy in phase 2 studies, few subsequent phase 3 studies have confirmed these benefits. Currently, phase 2 drug development for this indication is limited by poor evaluation of drug dosage and lack of mechanistic data to understand variable responses to the IMPs. Identification of biomarkers which might permit more robust stratification of participants at baseline has been slow. DISCUSSION: The Master Protocol provides (1) standardised assessment of efficacy and safety, (2) comparable collection of mechanistic data, (3) the opportunity to include adaptive designs and the use of shared control groups in the evaluation of combination therapies, and (4) benefits of greater understanding of endpoint variation to ensure more robust sample size calculations and future baseline stratification using existing and novel biomarkers.

Study protocol: Minimum effective low dose: anti-human thymocyte globulin (MELD-ATG): phase II, dose ranging, efficacy study of antithymocyte globulin (ATG) within 6 weeks of diagnosis of type 1 diabetes.

INTRODUCTION: Type 1 diabetes (T1D) is a chronic autoimmune disease, characterised by progressive destruction of the insulin-producing ß cells of the pancreas. One immunosuppressive agent that has recently shown promise in the treatment of new-onset T1D subjects aged 12-45 years is antithymocyte globulin (ATG), Thymoglobuline, encouraging further exploration in lower age groups. METHODS AND ANALYSIS: Minimal effective low dose (MELD)-ATG is a phase 2, multicentre, randomised, double-blind, placebo-controlled, multiarm parallel-group trial in participants 5-25 years diagnosed with T1D within 3-9 weeks of planned treatment day 1. A total of 114 participants will be recruited sequentially into seven different cohorts with the first cohort of 30 participants being randomised to placebo, 2.5 mg/kg, 1.5 mg/kg, 0.5 mg/kg and 0.1 mg/kg ATG total dose in a 1:1:1:1:1 allocation ratio. The next six cohorts of 12-15 participants will be randomised to placebo, 2.5 mg/kg, and one or two selected middle ATG total doses in a 1:1:1:1 or 1:1:1 allocation ratio, as dependent on the number of middle doses, given intravenously over two consecutive days. The primary objective will be to determine the changes in stimulated C-peptide response over the first 2 hours of a mixed meal tolerance test at 12 months for 2.5 mg/kg ATG arm vs the placebo. Conditional on finding a significant difference at 2.5 mg/kg, a minimally effective dose will be sought. Secondary objectives include the determination of the effects of a particular ATG treatment dose on (1) stimulated C-peptide, (2) glycated haemoglobin, (3) daily insulin dose, (4) time in range by intermittent continuous glucose monitoring measures, (5) fasting and stimulated dry blood spot (DBS) C-peptide measurements. ETHICS AND DISSEMINATION: MELD-ATG received first regulatory and ethical approvals in Belgium in September 2020 and from the German and UK regulators as of February 2021. The publication policy is set in the INNODIA (An innovative approach towards understanding and arresting Type 1 diabetes consortium) grant agreement (www.innodia.eu). TRIAL REGISTRATION NUMBER: NCT03936634; Pre-results.

biotoolsSchema: a formalized schema for bioinformatics software description.

BACKGROUND: Life scientists routinely face massive and heterogeneous data analysis tasks and must find and access the most suitable databases or software in a jungle of web-accessible resources. The diversity of information used to describe life-scientific digital resources presents an obstacle to their utilization. Although several standardization efforts are emerging, no information schema has been sufficiently detailed to enable uniform semantic and syntactic description-and cataloguing-of bioinformatics resources. FINDINGS: Here we describe biotoolsSchema, a formalized information model that balances the needs of conciseness for rapid adoption against the provision of rich technical information and scientific context. biotoolsSchema results from a series of community-driven workshops and is deployed in the bio.tools registry, providing the scientific community with >17,000 machine-readable and human-understandable descriptions of software and other digital life-science resources. We compare our approach to related initiatives and provide alignments to foster interoperability and reusability. CONCLUSIONS: biotoolsSchema supports the formalized, rigorous, and consistent specification of the syntax and semantics of bioinformatics resources, and enables cataloguing efforts such as bio.tools that help scientists to find, comprehend, and compare resources. The use of biotoolsSchema in bio.tools promotes the FAIRness of research software, a key element of open and reproducible developments for data-intensive sciences.

Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records.

BACKGROUND: Many mortality prediction models have been developed for patients in intensive care units (ICUs); most are based on data available at ICU admission. We investigated whether machine learning methods using analyses of time-series data improved mortality prognostication for patients in the ICU by providing real-time predictions of 90-day mortality. In addition, we examined to what extent such a dynamic model could be made interpretable by quantifying and visualising the features that drive the predictions at different timepoints. METHODS: Based on the Simplified Acute Physiology Score (SAPS) III variables, we trained a machine learning model on longitudinal data from patients admitted to four ICUs in the Capital Region, Denmark, between 2011 and 2016. We included all patients older than 16 years of age, with an ICU stay lasting more than 1 h, and who had a Danish civil registration number to enable 90-day follow-up. We leveraged static data and physiological time-series data from electronic health records and the Danish National Patient Registry. A recurrent neural network was trained with a temporal resolution of 1 h. The model was internally validated using the holdout method with 20% of the training dataset and externally validated using previously unseen data from a fifth hospital in Denmark. Its performance was assessed with the Matthews correlation coefficient (MCC) and area under the receiver operating characteristic curve (AUROC) as metrics, using bootstrapping with 1000 samples with replacement to construct 95% CIs. A Shapley additive explanations algorithm was applied to the prediction model to obtain explanations of the features that drive patient-specific predictions, and the contributions of each of the 44 features in the model were analysed and compared with the variables in the original SAPS III model. FINDINGS: From a dataset containing 15 615 ICU admissions of 12 616 patients, we included 14 190 admissions of 11 492 patients in our analysis. Overall, 90-day mortality was 33·1% (3802 patients). The deep learning model showed a predictive performance on the holdout testing dataset that improved over the timecourse of an ICU stay: MCC 0·29 (95% CI 0·25-0·33) and AUROC 0·73 (0·71-0·74) at admission, 0·43 (0·40-0·47) and 0·82 (0·80-0·84) after 24 h, 0·50 (0·46-0·53) and 0·85 (0·84-0·87) after 72 h, and 0·57 (0·54-0·60) and 0·88 (0·87-0·89) at the time of discharge. The model exhibited good calibration properties. These results were validated in an external validation cohort of 5827 patients with 6748 admissions: MCC 0·29 (95% CI 0·27-0·32) and AUROC 0·75 (0·73-0·76) at admission, 0·41 (0·39-0·44) and 0·80 (0·79-0·81) after 24 h, 0·46 (0·43-0·48) and 0·82 (0·81-0·83) after 72 h, and 0·47 (0·44-0·49) and 0·83 (0·82-0·84) at the time of discharge. INTERPRETATION: The prediction of 90-day mortality improved with 1-h sampling intervals during the ICU stay. The dynamic risk prediction can also be explained for an individual patient, visualising the features contributing to the prediction at any point in time. This explanation allows the clinician to determine whether there are elements in the current patient state and care that are potentially actionable, thus making the model suitable for further validation as a clinical tool. FUNDING: Novo Nordisk Foundation and the Innovation Fund Denmark.

JIB.tools 2.0 - A Bioinformatics Registry for Journal Published Tools with Interoperability to bio.tools.

JIB.tools 2.0 is a new approach to more closely embed the curation process in the publication process. This website hosts the tools, software applications, databases and workflow systems published in the Journal of Integrative Bioinformatics (JIB). As soon as a new tool-related publication is published in JIB, the tool is posted to JIB.tools and can afterwards be easily transferred to bio.tools, a large information repository of software tools, databases and services for bioinformatics and the life sciences. In this way, an easily-accessible list of tools is provided which were published in JIB a well as status information regarding the underlying service. With newer registries like bio.tools providing these information on a bigger scale, JIB.tools 2.0 closes the gap between journal publications and registry publication. (Reference: https://jib.tools).

Community curation of bioinformatics software and data resources.

The corpus of bioinformatics resources is huge and expanding rapidly, presenting life scientists with a growing challenge in selecting tools that fit the desired purpose. To address this, the European Infrastructure for Biological Information is supporting a systematic approach towards a comprehensive registry of tools and databases for all domains of bioinformatics, provided under a single portal (https://bio.tools). We describe here the practical means by which scientific communities, including individual developers and projects, through major service providers and research infrastructures, can describe their own bioinformatics resources and share these via bio.tools.

The bio.tools registry of software tools and data resources for the life sciences.

Bioinformaticians and biologists rely increasingly upon workflows for the flexible utilization of the many life science tools that are needed to optimally convert data into knowledge. We outline a pan-European enterprise to provide a catalogue ( https://bio.tools ) of tools and databases that can be used in these workflows. bio.tools not only lists where to find resources, but also provides a wide variety of practical information.

DBDS Genomic Cohort, a prospective and comprehensive resource for integrative and temporal analysis of genetic, environmental and lifestyle factors affecting health of blood donors.

PURPOSE: To establish a cohort that enables identification of genomic factors that influence human health and empower increased blood donor health and safe blood transfusions. Human health is complex and involves several factors, a major one being the genomic aspect. The genomic era has resulted in many consortia encompassing large samples sizes, which has proven successful for identifying genetic factors associated with specific traits. However, it remains a big challenge to establish large cohorts that facilitate studies of the interaction between genetic factors, environmental and life-style factors as these change over the course of life. A major obstacle to such endeavours is that it is difficult to revisit participants to retrieve additional information and obtain longitudinal, consecutive measurements. PARTICIPANTS: Blood donors (n=110 000) have given consent to participate in the Danish Blood Donor Study. The study uses the infrastructure of the Danish blood banks. FINDINGS TO DATE: The cohort comprises extensive phenotype data and whole genome genotyping data. Further, it is possible to retrieve additional phenotype data from national registries as well as from the donors at future visits, including consecutive measurements. FUTURE PLANS: To provide new knowledge on factors influencing our health and thus provide a platform for studying the influence of genomic factors on human health, in particular the interaction between environmental and genetic factors.

Survival prediction in intensive-care units based on aggregation of long-term disease history and acute physiology: a retrospective study of the Danish National Patient Registry and electronic patient records.

BACKGROUND: Intensive-care units (ICUs) treat the most critically ill patients, which is complicated by the heterogeneity of the diseases that they encounter. Severity scores based mainly on acute physiology measures collected at ICU admission are used to predict mortality, but are non-specific, and predictions for individual patients can be inaccurate. We investigated whether inclusion of long-term disease history before ICU admission improves mortality predictions. METHODS: Registry data for long-term disease histories for more than 230 000 Danish ICU patients were used in a neural network to develop an ICU mortality prediction model. Long-term disease histories and acute physiology measures were aggregated to predict mortality risk for patients for whom both registry and ICU electronic patient record data were available. We compared mortality predictions with admission scores on the Simplified Acute Physiology Score (SAPS) II, the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE) II, and the best available multimorbidity score, the Multimorbidity Index. An external validation set from an additional hospital was acquired after model construction to confirm the validity of our model. During initial model development data were split into a training set (85%) and an independent test set (15%), and a five-fold cross-validation was done during training to avoid overfitting. Neural networks were trained for datasets with disease history of 1 month, 3 months, 6 months, 1 year, 2·5 years, 5 years, 7·5 years, 10 years, and 23 years before ICU admission. FINDINGS: Mortality predictions with a model based solely on disease history outperformed the Multimorbidity Index (Matthews correlation coefficient 0·265 vs 0·065), and performed similarly to SAPS II and APACHE II (Matthews correlation coefficient with disease history, age, and sex 0·326 vs 0·347 and 0·300 for SAPS II and APACHE II, respectively). Diagnoses up to 10 years before ICU admission affected current mortality prediction. Aggregation of previous disease history and acute physiology measures in a neural network yielded the most precise predictions of in-hospital mortality (Matthews correlation coefficient 0·391 for in-hospital mortality compared with 0·347 with SAPS II and 0·300 with APACHE II). These results for the aggregated model were validated in an external independent dataset of 1528 patients (Matthews correlation coefficient for prediction of in-hospital mortality 0·341). INTERPRETATION: Longitudinal disease-spectrum-wide data available before ICU admission are useful for mortality prediction. Disease history can be used to differentiate mortality risk between patients with similar vital signs with more precision than SAPS II and APACHE II scores. Machine learning models can be deconvoluted to generate novel understandings of how ICU patient features from long-term and short-term events interact with each other. Explainable machine learning models are key in clinical settings, and our results emphasise how to progress towards the transformation of advanced models into actionable, transparent, and trustworthy clinical tools. FUNDING: Novo Nordisk Foundation and Innovation Fund Denmark.

The governance structure for data access in the DIRECT consortium: an innovative medicines initiative (IMI) project.

Biomedical research projects involving multiple partners from public and private sectors require coherent internal governance mechanisms to engender good working relationships. The DIRECT project is an example of such a venture, funded by the Innovative Medicines Initiative Joint Undertaking (IMI JU). This paper describes the data access policy that was developed within DIRECT to support data access and sharing, via the establishment of a 3-tiered Data Access Committee. The process was intended to allow quick access to data, whilst enabling strong oversight of how data were being accessed and by whom, and any subsequent analyses, to contribute to the overall objectives of the consortium.

Tools and data services registry: a community effort to document bioinformatics resources.

Life sciences are yielding huge data sets that underpin scientific discoveries fundamental to improvement in human health, agriculture and the environment. In support of these discoveries, a plethora of databases and tools are deployed, in technically complex and diverse implementations, across a spectrum of scientific disciplines. The corpus of documentation of these resources is fragmented across the Web, with much redundancy, and has lacked a common standard of information. The outcome is that scientists must often struggle to find, understand, compare and use the best resources for the task at hand.Here we present a community-driven curation effort, supported by ELIXIR-the European infrastructure for biological information-that aspires to a comprehensive and consistent registry of information about bioinformatics resources. The sustainable upkeep of this Tools and Data Services Registry is assured by a curation effort driven by and tailored to local needs, and shared amongst a network of engaged partners.As of November 2015, the registry includes 1785 resources, with depositions from 126 individual registrations including 52 institutional providers and 74 individuals. With community support, the registry can become a standard for dissemination of information about bioinformatics resources: we welcome everyone to join us in this common endeavour. The registry is freely available at https://bio.tools.

Novel variation and de novo mutation rates in population-wide de novo assembled Danish trios.

Building a population-specific catalogue of single nucleotide variants (SNVs), indels and structural variants (SVs) with frequencies, termed a national pan-genome, is critical for further advancing clinical and public health genetics in large cohorts. Here we report a Danish pan-genome obtained from sequencing 10 trios to high depth (50 × ). We report 536k novel SNVs and 283k novel short indels from mapping approaches and develop a population-wide de novo assembly approach to identify 132k novel indels larger than 10 nucleotides with low false discovery rates. We identify a higher proportion of indels and SVs than previous efforts showing the merits of high coverage and de novo assembly approaches. In addition, we use trio information to identify de novo mutations and use a probabilistic method to provide direct estimates of 1.27e-8 and 1.5e-9 per nucleotide per generation for SNVs and indels, respectively.