Machine learning prediction of malaria vaccine efficacy based on antibody profiles.

Immunization through repeated direct venous inoculation of Plasmodium falciparum (Pf) sporozoites (PfSPZ) under chloroquine chemoprophylaxis, using the PfSPZ Chemoprophylaxis Vaccine (PfSPZ-CVac), induces high-level protection against controlled human malaria infection (CHMI). Humoral and cellular immunity contribute to vaccine efficacy but only limited information about the implicated Pf-specific antigens is available. Here, we examined Pf-specific antibody profiles, measured by protein arrays representing the full Pf proteome, of 40 placebo- and PfSPZ-immunized malaria-naïve volunteers from an earlier published PfSPZ-CVac dose-escalation trial. For this purpose, we both utilized and adapted supervised machine learning methods to identify predictive antibody profiles at two different time points: after immunization and before CHMI. We developed an adapted multitask support vector machine (SVM) approach and compared it to standard methods, i.e. single-task SVM, regularized logistic regression and random forests. Our results show, that the multitask SVM approach improved the classification performance to discriminate the protection status based on the underlying antibody-profiles while combining time- and dose-dependent data in the prediction model. Additionally, we developed the new fEature diStance exPlainabilitY (ESPY) method to quantify the impact of single antigens on the non-linear multitask SVM model and make it more interpretable. In conclusion, our multitask SVM model outperforms the studied standard approaches in regard of classification performance. Moreover, with our new explanation method ESPY, we were able to interpret the impact of Pf-specific antigen antibody responses that predict sterile protective immunity against CHMI after immunization. The identified Pf-specific antigens may contribute to a better understanding of immunity against human malaria and may foster vaccine development.

A study on interoperability between two Personal Health Train infrastructures in leukodystrophy data analysis.

The development of platforms for distributed analytics has been driven by a growing need to comply with various governance-related or legal constraints. Among these platforms, the so-called Personal Health Train (PHT) is one representative that has emerged over the recent years. However, in projects that require data from sites featuring different PHT infrastructures, institutions are facing challenges emerging from the combination of multiple PHT ecosystems, including data governance, regulatory compliance, or the modification of existing workflows. In these scenarios, the interoperability of the platforms is preferable. In this work, we introduce a conceptual framework for the technical interoperability of the PHT covering five essential requirements: Data integration, unified station identifiers, mutual metadata, aligned security protocols, and business logic. We evaluated our concept in a feasibility study that involves two distinct PHT infrastructures: PHT-meDIC and PADME. We analyzed data on leukodystrophy from patients in the University Hospitals of Tübingen and Leipzig, and patients with differential diagnoses at the University Hospital Aachen. The results of our study demonstrate the technical interoperability between these two PHT infrastructures, allowing researchers to perform analyses across the participating institutions. Our method is more space-efficient compared to the multi-homing strategy, and it shows only a minimal time overhead.

App-based assessment of patient-reported outcomes in the Molecular Tumor Board in the Center for Personalized Medicine-(TRACE).

Background: Biomarker-based therapies are increasingly used in cancer patients outside clinical trials. Systematic assessment of patient-reported outcomes (PRO) is warranted to take patients' perspectives during biomarker-based therapies into consideration. We assessed the feasibility of an electronic PRO assessment via a smartphone application. Methods: An interdisciplinary expert panel developed a smartphone application based on symptom burden and health-related quality of life (HRQoL) metrics reported in a retrospective analysis of 292 neuro-oncological patients. The app included validated assessments of health-related quality of life (HRQoL), the burden of symptoms, and psychological stress. Feasibility and usability were tested in a pilot study. Semi-structured interviews with patients and health care professionals (HCP) were conducted, transcribed, and analyzed according to Mayring´s qualitative content analysis. Furthermore, we assessed compliance and descriptive data of ePROs. Results: A total of 14 patients have been enrolled, (9 female, 5 male). A total of 4 HCPs, 9 patients, and 1 caregiver were interviewed regarding usability/feasibility. The main advantages were the possibility to complete questionnaires at home and comfortable implementation in daily life. Compliance was high, for example, 82% of the weekly distributed NCCN distress thermometer questionnaires were answered on time, however, with interindividual variability. We observed a median distress score of 5 (range 0-10, 197 results, n = 12, weekly assessed) and a median Global health score of 58.3 according to the EORTC QLQ-C30 instrument (range 16.7-100, 77 results, n = 12, monthly assessed). Conclusions: This pilot study proved the feasibility and acceptance of the app. We will therefore expand its application during biomarker-guided therapies to enable systematic PRO assessments.

In-hospital mortality during the wild-type, alpha, delta, and omicron SARS-CoV-2 waves: a multinational cohort study in the EuCARE project.

Background: Investigating outcomes of hospitalised COVID-19 patients throughout the pandemic is crucial to understand the impact of different SARS-CoV-2 variants. We compared 28-day in-hospital mortality of Wild-type, Alpha, Delta, and Omicron variant infections. Whether the difference in risk by variant varied by age was also evaluated. Methods: We conducted a cohort study including patients ≥18 years, hospitalised between 2020 and 02-01 and 2022-10-15 with a SARS-CoV-2 positive test, from nine countries. Variant was classified based on sequenced viruses or from national public metadata. Mortality was compared using the cumulative incidence function and subdistribution hazard ratios (SHR) adjusted for age, sex, calendar time, and comorbidities. Results were shown age-stratified due to effect measure modification (P < 0.0001 for interaction between age and variant). Findings: We included 38,585 participants: 19,763 Wild-type, 6387 Alpha, 3640 Delta, and 8795 Omicron. The cumulative incidence of mortality decreased throughout the study period. Among participants ≥70 years, the adjusted SHR (95% confidence interval) for Delta vs. Omicron was 1.66 (1.29-2.13). This estimate was 1.66 (1.17-2.36) for Alpha vs. Omicron, and 1.34 (0.92-1.95) for Wild-type vs. Omicron. These were 1.21 (0.81-1.82), 1.21 (0.68-2.17), and 0.98 (0.53-1.82) among unvaccinated participants. When comparing Omicron sublineages, the aSHR for BA.1 was 1.92 (1.43-2.58) compared to BA.2 and 1.52 (1.11-2.08) compared to BA.5. Interpretation: The herein observed decrease in in-hospital mortality seems to reflect a combined effect of immunity from vaccinations and previous infections, although differences in virulence between SARS-CoV-2 variants may also have contributed. Funding: European Union's Horizon Europe Research and Innovation Programme.

SARS-CoV-2 trends in Italy, Germany and Portugal and school opening during the period of Omicron variant dominance: A quasi experimental study in the EuCARE project.

OBJECTIVES: We investigated the impact of school reopening on SARS-CoV-2 transmission in Italy, Germany, and Portugal in autumn 2022 when the Omicron variant was prevalent. METHODS: A prospective international study was conducted using the case reproduction number (Rc) calculated with the time parametrization of Omicron. For Germany and Italy, staggered difference-in-differences analysis was employed to explore the causal relationship between school reopening and Rc changes, accounting for varying reopening dates. In Portugal, interrupted time series analysis was used due to simultaneous school reopenings. Multivariable models were adopted to adjust for confounders. RESULTS: In Italy and Germany, post-reopening Rc estimates were significantly lower compared to those from regions/states that had not yet reopened at the same time points, both in the student population (overall average treatment effect for the treated subpopulation [O-ATT]: -0.80 [95% CI: -0.94;-0.66] for Italy; O-ATT-0.30 [95% CI: -0.36;-0.23] for Germany) and the adult population (O-ATT: -0.04 [95% CI: -0.07;-0.01] for Italy; O-ATT: -0.07 [95% CI: -0.11;-0.03] for Germany). In Portugal, there was a significant decreasing trend in Rc following school reopenings compared to the pre-reopening period (sustained effect: -0.03 [95% CI: -0.04; -0.03] in students; -0.02 [95% CI: -0.03; -0.02] in adults). CONCLUSIONS: We found no evidence of a causal relationship between school reopenings in autumn 2022 and Omicron SARS-CoV-2 transmission.

A dynamic time-to-event model for prediction of acute graft-versus-host disease in patients after allogeneic hematopoietic stem cell transplantation.

BACKGROUND: Acute graft-versus-host disease (aGvHD) is a major cause of death for patients following allogeneic hematopoietic stem cell transplantation (HSCT). Effective management of moderate to severe aGvHD remains challenging despite recent advances in HSCT, emphasizing the importance of prophylaxis and risk factor identification. METHODS: In this study, we analyzed data from 1479 adults who underwent HSCT between 2005 and 2017 to investigate the effects of aGvHD prophylaxis and time-dependent risk factors on the development of grades II-IV aGvHD within 100 days post-HSCT. RESULTS: Using a dynamic longitudinal time-to-event model, we observed a non-monotonic baseline hazard overtime with a low hazard during the first few days and a maximum hazard at day 17, described by Bateman function with a mean transit time of approximately 11 days. Multivariable analysis revealed significant time-dependent effects of white blood cell counts and cyclosporine A exposure as well as static effects of female donors for male recipients, patients with matched related donors, conditioning regimen consisting of fludarabine plus total body irradiation, and patient age in recipients of grafts from related donors on the risk to develop grades II-IV aGvHD. Additionally, we found that higher cumulative hazard on day 7 after allo-HSCT are associated with an increased incidence of grades II-IV aGvHD within 100 days indicating that an individual assessment of the cumulative hazard on day 7 could potentially serve as valuable predictor for later grades II-IV aGvHD development. Using the final model, stochastic simulations were performed to explore covariate effects on the cumulative incidence over time and to estimate risk ratios. CONCLUSION: Overall, the presented model showed good descriptive and predictive performance and provides valuable insights into the interplay of multiple static and time-dependent risk factors for the prediction of aGvHD.

Insights to HIV-1 coreceptor usage by estimating HLA adaptation with Bayesian generalized linear mixed models.

The mechanisms triggering the human immunodeficiency virus type I (HIV-1) to switch the coreceptor usage from CCR5 to CXCR4 during the course of infection are not entirely understood. While low CD4+ T cell counts are associated with CXCR4 usage, a predominance of CXCR4 usage with still high CD4+ T cell counts remains puzzling. Here, we explore the hypothesis that viral adaptation to the human leukocyte antigen (HLA) complex, especially to the HLA class II alleles, contributes to the coreceptor switch. To this end, we sequence the viral gag and env protein with corresponding HLA class I and II alleles of a new cohort of 312 treatment-naive, subtype C, chronically-infected HIV-1 patients from South Africa. To estimate HLA adaptation, we develop a novel computational approach using Bayesian generalized linear mixed models (GLMMs). Our model allows to consider the entire HLA repertoire without restricting the model to pre-learned HLA-polymorphisms. In addition, we correct for phylogenetic relatedness of the viruses within the model itself to account for founder effects. Using our model, we observe that CXCR4-using variants are more adapted than CCR5-using variants (p-value = 1.34e-2). Additionally, adapted CCR5-using variants have a significantly lower predicted false positive rate (FPR) by the geno2pheno[coreceptor] tool compared to the non-adapted CCR5-using variants (p-value = 2.21e-2), where a low FPR is associated with CXCR4 usage. Consequently, estimating HLA adaptation can be an asset in predicting not only coreceptor usage, but also an approaching coreceptor switch in CCR5-using variants. We propose the usage of Bayesian GLMMs for modeling virus-host adaptation in general.

Dynamics and durability of HIV-1 neutralization are determined by viral replication.

Human immunodeficiency virus type 1 (HIV-1)-neutralizing antibodies (nAbs) that prevent infection are the main goal of HIV vaccine discovery. But as no nAb-eliciting vaccines are yet available, only data from HIV-1 neutralizers-persons with HIV-1 who naturally develop broad and potent nAbs-can inform about the dynamics and durability of nAb responses in humans, knowledge which is crucial for the design of future HIV-1 vaccine regimens. To address this, we assessed HIV-1-neutralizing immunoglobulin G (IgG) from 2,354 persons with HIV-1 on or off antiretroviral therapy (ART). Infection with non-clade B viruses, CD4+ T cell counts <200 µl-1, being off ART and a longer time off ART were independent predictors of a more potent and broad neutralization. In longitudinal analyses, we found nAb half-lives of 9.3 and 16.9 years in individuals with no- or low-level viremia, respectively, and 4.0 years in persons who newly initiated ART. Finally, in a potent HIV-1 neutralizer, we identified lower fractions of serum nAbs and of nAb-encoding memory B cells after ART initiation, suggesting that a decreasing neutralizing serum activity after antigen withdrawal is due to lower levels of nAbs. These results collectively show that HIV-1-neutralizing responses can persist for several years, even at low antigen levels, suggesting that an HIV-1 vaccine may elicit a durable nAb response.

Inherently interpretable position-aware convolutional motif kernel networks for biological sequencing data.

Artificial neural networks show promising performance in detecting correlations within data that are associated with specific outcomes. However, the black-box nature of such models can hinder the knowledge advancement in research fields by obscuring the decision process and preventing scientist to fully conceptualize predicted outcomes. Furthermore, domain experts like healthcare providers need explainable predictions to assess whether a predicted outcome can be trusted in high stakes scenarios and to help them integrating a model into their own routine. Therefore, interpretable models play a crucial role for the incorporation of machine learning into high stakes scenarios like healthcare. In this paper we introduce Convolutional Motif Kernel Networks, a neural network architecture that involves learning a feature representation within a subspace of the reproducing kernel Hilbert space of the position-aware motif kernel function. The resulting model enables to directly interpret and evaluate prediction outcomes by providing a biologically and medically meaningful explanation without the need for additional post-hoc analysis. We show that our model is able to robustly learn on small datasets and reaches state-of-the-art performance on relevant healthcare prediction tasks. Our proposed method can be utilized on DNA and protein sequences. Furthermore, we show that the proposed method learns biologically meaningful concepts directly from data using an end-to-end learning scheme.

EuCARE-hospitalised study protocol: a cohort study of patients hospitalised with COVID-19 in the EuCARE project.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS CoV-2), the virus responsible for coronavirus disease 2019 (COVID-19), can lead to hospitalisation, particularly in elderly, immunocompromised, and non-vaccinated or partially vaccinated individuals. Although vaccination provides protection, the duration of this protection wanes over time. Additional doses can restore immunity, but the influence of viral variants, specific sequences, and vaccine-induced immune responses on disease severity remains unclear. Moreover, the efficacy of therapeutic interventions during hospitalisation requires further investigation. The study aims to analyse the clinical course of COVID-19 in hospitalised patients, taking into account SARS-CoV-2 variants, viral sequences, and the impact of different vaccines. The primary outcome is all-cause in-hospital mortality, while secondary outcomes include admission to intensive care unit and length of stay, duration of hospitalisation, and the level of respiratory support required. METHODS: This ongoing multicentre study observes hospitalised adult patients with confirmed SARS-CoV-2 infection, utilising a combination of retrospective and prospective data collection. It aims to gather clinical and laboratory variables from around 35,000 patients, with potential for a larger sample size. Data analysis will involve biostatistical and machine-learning techniques. Selected patients will provide biological material. The study started on October 14, 2021 and is scheduled to end on October 13, 2026. DISCUSSION: The analysis of a large sample of retrospective and prospective data about the acute phase of SARS CoV-2 infection in hospitalised patients, viral variants and vaccination in several European and non-European countries will help us to better understand risk factors for disease severity and the interplay between SARS CoV-2 variants, immune responses and vaccine efficacy. The main strengths of this study are the large sample size, the long study duration covering different waves of COVID-19 and the collection of biological samples that allows future research. TRIAL REGISTRATION: The trial has been registered on ClinicalTrials.gov. The unique identifier assigned to this trial is NCT05463380.

EuCARE-POSTCOVID Study: a multicentre cohort study on long-term post-COVID-19 manifestations.

BACKGROUND: Post-COVID-19 condition refers to persistent or new onset symptoms occurring three months after acute COVID-19, which are unrelated to alternative diagnoses. Symptoms include fatigue, breathlessness, palpitations, pain, concentration difficulties ("brain fog"), sleep disorders, and anxiety/depression. The prevalence of post-COVID-19 condition ranges widely across studies, affecting 10-20% of patients and reaching 50-60% in certain cohorts, while the associated risk factors remain poorly understood. METHODS: This multicentre cohort study, both retrospective and prospective, aims to assess the incidence and risk factors of post-COVID-19 condition in a cohort of recovered patients. Secondary objectives include evaluating the association between circulating SARS-CoV-2 variants and the risk of post-COVID-19 condition, as well as assessing long-term residual organ damage (lung, heart, central nervous system, peripheral nervous system) in relation to patient characteristics and virology (variant and viral load during the acute phase). Participants will include hospitalised and outpatient COVID-19 patients diagnosed between 01/03/2020 and 01/02/2025 from 8 participating centres. A control group will consist of hospitalised patients with respiratory infections other than COVID-19 during the same period. Patients will be followed up at the post-COVID-19 clinic of each centre at 2-3, 6-9, and 12-15 months after clinical recovery. Routine blood exams will be conducted, and patients will complete questionnaires to assess persisting symptoms, fatigue, dyspnoea, quality of life, disability, anxiety and depression, and post-traumatic stress disorders. DISCUSSION: This study aims to understand post-COVID-19 syndrome's incidence and predictors by comparing pandemic waves, utilising retrospective and prospective data. Gender association, especially the potential higher prevalence in females, will be investigated. Symptom tracking via questionnaires and scales will monitor duration and evolution. Questionnaires will also collect data on vaccination, reinfections, and new health issues. Biological samples will enable future studies on post-COVID-19 sequelae mechanisms, including inflammation, immune dysregulation, and viral reservoirs. TRIAL REGISTRATION: This study has been registered with ClinicalTrials.gov under the identifier NCT05531773.

PlasmoFAB: a benchmark to foster machine learning for Plasmodium falciparum protein antigen candidate prediction.

MOTIVATION: Machine learning methods can be used to support scientific discovery in healthcare-related research fields. However, these methods can only be reliably used if they can be trained on high-quality and curated datasets. Currently, no such dataset for the exploration of Plasmodium falciparum protein antigen candidates exists. The parasite P.falciparum causes the infectious disease malaria. Thus, identifying potential antigens is of utmost importance for the development of antimalarial drugs and vaccines. Since exploring antigen candidates experimentally is an expensive and time-consuming process, applying machine learning methods to support this process has the potential to accelerate the development of drugs and vaccines, which are needed for fighting and controlling malaria. RESULTS: We developed PlasmoFAB, a curated benchmark that can be used to train machine learning methods for the exploration of P.falciparum protein antigen candidates. We combined an extensive literature search with domain expertise to create high-quality labels for P.falciparum specific proteins that distinguish between antigen candidates and intracellular proteins. Additionally, we used our benchmark to compare different well-known prediction models and available protein localization prediction services on the task of identifying protein antigen candidates. We show that available general-purpose services are unable to provide sufficient performance on identifying protein antigen candidates and are outperformed by our models that were trained on this tailored data. AVAILABILITY AND IMPLEMENTATION: PlasmoFAB is publicly available on Zenodo with DOI 10.5281/zenodo.7433087. Furthermore, all scripts that were used in the creation of PlasmoFAB and the training and evaluation of machine learning models are open source and publicly available on GitHub here: https://github.com/msmdev/PlasmoFAB.

COmic: convolutional kernel networks for interpretable end-to-end learning on (multi-)omics data.

MOTIVATION: The size of available omics datasets is steadily increasing with technological advancement in recent years. While this increase in sample size can be used to improve the performance of relevant prediction tasks in healthcare, models that are optimized for large datasets usually operate as black boxes. In high-stakes scenarios, like healthcare, using a black-box model poses safety and security issues. Without an explanation about molecular factors and phenotypes that affected the prediction, healthcare providers are left with no choice but to blindly trust the models. We propose a new type of artificial neural network, named Convolutional Omics Kernel Network (COmic). By combining convolutional kernel networks with pathway-induced kernels, our method enables robust and interpretable end-to-end learning on omics datasets ranging in size from a few hundred to several hundreds of thousands of samples. Furthermore, COmic can be easily adapted to utilize multiomics data. RESULTS: We evaluated the performance capabilities of COmic on six different breast cancer cohorts. Additionally, we trained COmic models on multiomics data using the METABRIC cohort. Our models performed either better or similar to competitors on both tasks. We show how the use of pathway-induced Laplacian kernels opens the black-box nature of neural networks and results in intrinsically interpretable models that eliminate the need for post hoc explanation models. AVAILABILITY AND IMPLEMENTATION: Datasets, labels, and pathway-induced graph Laplacians used for the single-omics tasks can be downloaded at https://ibm.ent.box.com/s/ac2ilhyn7xjj27r0xiwtom4crccuobst/folder/48027287036. While datasets and graph Laplacians for the METABRIC cohort can be downloaded from the above mentioned repository, the labels have to be downloaded from cBioPortal at https://www.cbioportal.org/study/clinicalData?id=brca\_metabric. COmic source code as well as all scripts necessary to reproduce the experiments and analysis are publicly available at https://github.com/jditz/comics.

Predicting functional effects of ion channel variants using new phenotypic machine learning methods.

Missense variants in genes encoding ion channels are associated with a spectrum of severe diseases. Variant effects on biophysical function correlate with clinical features and can be categorized as gain- or loss-of-function. This information enables a timely diagnosis, facilitates precision therapy, and guides prognosis. Functional characterization presents a bottleneck in translational medicine. Machine learning models may be able to rapidly generate supporting evidence by predicting variant functional effects. Here, we describe a multi-task multi-kernel learning framework capable of harmonizing functional results and structural information with clinical phenotypes. This novel approach extends the human phenotype ontology towards kernel-based supervised machine learning. Our gain- or loss-of-function classifier achieves high performance (mean accuracy 0.853 SD 0.016, mean AU-ROC 0.912 SD 0.025), outperforming both conventional baseline and state-of-the-art methods. Performance is robust across different phenotypic similarity measures and largely insensitive to phenotypic noise or sparsity. Localized multi-kernel learning offered biological insight and interpretability by highlighting channels with implicit genotype-phenotype correlations or latent task similarity for downstream analysis.

Deep Learning in the Detection of Rare Fractures - Development of a "Deep Learning Convolutional Network" Model for Detecting Acetabular Fractures. / Deep Learning in der Erkennung seltener Frakturen ­ Entwicklung eines "Deep Convolutional Neural Network" (DCNN) am Beispiel der Azetabulumfraktur.

BACKGROUND: Fracture detection by artificial intelligence and especially Deep Convolutional Neural Networks (DCNN) is a topic of growing interest in current orthopaedic and radiological research. As learning a DCNN usually needs a large amount of training data, mostly frequent fractures as well as conventional X-ray are used. Therefore, less common fractures like acetabular fractures (AF) are underrepresented in the literature. The aim of this pilot study was to establish a DCNN for detection of AF using computer tomography (CT) scans. METHODS: Patients with an acetabular fracture were identified from the monocentric consecutive pelvic injury registry at the BG Trauma Center XXX from 01/2003 - 12/2019. All patients with unilateral AF and CT scans available in DICOM-format were included for further processing. All datasets were automatically anonymised and digitally post-processed. Extraction of the relevant region of interests was performed and the technique of data augmentation (DA) was implemented to artificially increase the number of training samples. A DCNN based on Med3D was used for autonomous fracture detection, using global average pooling (GAP) to reduce overfitting. RESULTS: From a total of 2,340 patients with a pelvic fracture, 654 patients suffered from an AF. After screening and post-processing of the datasets, a total of 159 datasets were enrolled for training of the algorithm. A random assignment into training datasets (80%) and test datasets (20%) was performed. The technique of bone area extraction, DA and GAP increased the accuracy of fracture detection from 58.8% (native DCNN) up to an accuracy of 82.8% despite the low number of datasets. CONCLUSION: The accuracy of fracture detection of our trained DCNN is comparable to published values despite the low number of training datasets. The techniques of bone extraction, DA and GAP are useful for increasing the detection rates of rare fractures by a DCNN. Based on the used DCNN in combination with the described techniques from this pilot study, the possibility of an automatic fracture classification of AF is under investigation in a multicentre study.

Attentive Variational Information Bottleneck for TCR-peptide interaction prediction.

MOTIVATION: We present a multi-sequence generalization of Variational Information Bottleneck and call the resulting model Attentive Variational Information Bottleneck (AVIB). Our AVIB model leverages multi-head self-attention to implicitly approximate a posterior distribution over latent encodings conditioned on multiple input sequences. We apply AVIB to a fundamental immuno-oncology problem: predicting the interactions between T-cell receptors (TCRs) and peptides. RESULTS: Experimental results on various datasets show that AVIB significantly outperforms state-of-the-art methods for TCR-peptide interaction prediction. Additionally, we show that the latent posterior distribution learned by AVIB is particularly effective for the unsupervised detection of out-of-distribution amino acid sequences. AVAILABILITY AND IMPLEMENTATION: The code and the data used for this study are publicly available at: https://github.com/nec-research/vibtcr. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Molecular Epidemiology of HIV-1 in Eastern Europe and Russia.

The HIV epidemic in Eastern Europe and Russia is large and not well-controlled. To describe the more recent molecular epidemiology of HIV-1, transmitted drug resistance, and the relationship between the epidemics in this region, we sequenced the protease and reverse transcriptase genes of HIV-1 from 812 people living with HIV from Ukraine (n = 191), Georgia (n = 201), and Russia (n = 420) before the initiation of antiretroviral therapy. In 190 Ukrainian patients, the integrase gene sequence was also determined. The most reported route of transmission was heterosexual contact, followed by intravenous drug use, and men having sex with men (MSM). Several pre-existing drug resistance mutations were found against non-nucleoside reverse transcriptase inhibitors (RTIs) (n = 103), protease inhibitors (n = 11), and nucleoside analogue RTIs (n = 12), mostly polymorphic mutations or revertants. In the integrase gene, four strains with accessory integrase strand transfer inhibitor mutations were identified. Sub-subtype A6 caused most of the infections (713/812; 87.8%) in all three countries, including in MSM. In contrast to earlier studies, no clear clusters related to the route of transmission were identified, indicating that, within the region, the exchange of viruses among the different risk groups may occur more often than earlier reported.

Time-dependent prediction of mortality and cytomegalovirus reactivation after allogeneic hematopoietic cell transplantation using machine learning.

Allogeneic hematopoietic cell transplantation (HCT) effectively treats high-risk hematologic diseases but can entail HCT-specific complications, which may be minimized by appropriate patient management, supported by accurate, individual risk estimation. However, almost all HCT risk scores are limited to a single risk assessment before HCT without incorporation of additional data. We developed machine learning models that integrate both baseline patient data and time-dependent laboratory measurements to individually predict mortality and cytomegalovirus (CMV) reactivation after HCT at multiple time points per patient. These gradient boosting machine models provide well-calibrated, time-dependent risk predictions and achieved areas under the receiver-operating characteristic of 0.92 and 0.83 and areas under the precision-recall curve of 0.58 and 0.62 for prediction of mortality and CMV reactivation, respectively, in a 21-day time window. Both models were successfully validated in a prospective, non-interventional study and performed on par with expert hematologists in a pilot comparison.

Respiratory viruses dynamics and interactions: ten years of surveillance in central Europe.

BACKGROUND: Lower respiratory tract infections are among the main causes of death. Although there are many respiratory viruses, diagnostic efforts are focused mainly on influenza. The Respiratory Viruses Network (RespVir) collects infection data, primarily from German university hospitals, for a high diversity of infections by respiratory pathogens. In this study, we computationally analysed a subset of the RespVir database, covering 217,150 samples tested for 17 different viral pathogens in the time span from 2010 to 2019. METHODS: We calculated the prevalence of 17 respiratory viruses, analysed their seasonality patterns using information-theoretic measures and agglomerative clustering, and analysed their propensity for dual infection using a new metric dubbed average coinfection exclusion score (ACES). RESULTS: After initial data pre-processing, we retained 206,814 samples, corresponding to 1,408,657 performed tests. We found that Influenza viruses were reported for almost the half of all infections and that they exhibited the highest degree of seasonality. Coinfections of viruses are frequent; the most prevalent coinfection was rhinovirus/bocavirus and most of the virus pairs had a positive ACES indicating a tendency to exclude each other regarding infection. CONCLUSIONS: The analysis of respiratory viruses dynamics in monoinfection and coinfection contributes to the prevention, diagnostic, treatment, and development of new therapeutics. Data obtained from multiplex testing is fundamental for this analysis and should be prioritized over single pathogen testing.