Immune-based Machine learning prediction of diagnosis and illness state in schizophrenia and bipolar disorder.

BACKGROUND: Schizophrenia and bipolar disorder frequently face significant delay in diagnosis, leading to being missed or misdiagnosed in early stages. Both disorders have also been associated with trait and state immune abnormalities. Recent machine learning-based studies have shown encouraging results using diagnostic biomarkers in predictive models, but few have focused on immune-based markers. Our main objective was to develop supervised machine learning models to predict diagnosis and illness state in schizophrenia and bipolar disorder using only a panel of peripheral kynurenine metabolites and cytokines. METHODS: The cross-sectional I-GIVE cohort included hospitalized acute bipolar patients (n = 205), stable bipolar outpatients (n = 116), hospitalized acute schizophrenia patients (n = 111), stable schizophrenia outpatients (n = 75) and healthy controls (n = 185). Serum kynurenine metabolites, namely tryptophan (TRP), kynurenine (KYN), kynurenic acid (KA), quinaldic acid (QUINA), xanthurenic acid (XA), quinolinic acid (QUINO) and picolinic acid (PICO) were quantified using liquid chromatography-tandem mass spectrometry (LC-MS/MS), while V-plex Human Cytokine Assays were used to measure cytokines (interleukin-6 (IL-6), IL-8, IL-17, IL-12/IL23-P40, tumor necrosis factor-alpha (TNF-ɑ), interferon-gamma (IFN-γ)). Supervised machine learning models were performed using JMP Pro 17.0.0. We compared a primary analysis using nested cross-validation to a split set as sensitivity analysis. Post-hoc, we re-ran the models using only the significant features to obtain the key markers. RESULTS: The models yielded a good Area Under the Curve (AUC) (0.804, Positive Prediction Value (PPV) = 86.95; Negative Prediction Value (NPV) = 54.61) for distinguishing all patients from controls. This implies that a positive test is highly accurate in identifying the patients, but a negative test is inconclusive. Both schizophrenia patients and bipolar patients could each be separated from controls with a good accuracy (SCZ AUC 0.824; BD AUC 0.802). Overall, increased levels of IL-6, TNF-ɑ and PICO and decreased levels of IFN-γ and QUINO were predictive for an individual being classified as a patient. Classification of acute versus stable patients reached a fair AUC of 0.713. The differentiation between schizophrenia and bipolar disorder yielded a poor AUC of 0.627. CONCLUSIONS: This study highlights the potential of using immune-based measures to build predictive classification models in schizophrenia and bipolar disorder, with IL-6, TNF-ɑ, IFN-γ, QUINO and PICO as key candidates. While machine learning models successfully distinguished schizophrenia and bipolar disorder from controls, the challenges in differentiating schizophrenic from bipolar patients likely reflect shared immunological pathways by the both disorders and confounding by a larger state-specific effect. Larger multi-centric studies and multi-domain models are needed to enhance reliability and translation into clinic.

Spiny dogfish, Squalus suckleyi, shows a good tolerance for hypoxia but need long recovery times.

Pacific spiny dogfish, Squalus suckleyi, move to shallow coastal waters during critical reproductive life stages and are thus at risk of encountering hypoxic events which occur more frequently in these areas. For effective conservation management, we need to fully understand the consequences of hypoxia on marine key species such as elasmobranchs. Because of their benthic life style, we hypothesized that S. suckleyi are hypoxia tolerant and able to efficiently regulate oxygen consumption, and that anaerobic metabolism is supported by a broad range of metabolites including ketones, fatty acids and amino acids. Therefore, we studied oxygen consumption rates, ventilation frequency and amplitude, blood gasses, acid-base regulation, and changes in plasma and tissue metabolites during progressive hypoxia. Our results show that critical oxygen levels (P crit) where oxyregulation is lost were indeed low (18.1% air saturation or 28.5 Torr at 13°C). However, many dogfish behaved as oxyconformers rather than oxyregulators. Arterial blood PO2 levels mostly decreased linearly with decreasing environmental PO2. Blood gases and acid-base status were dependent on open versus closed respirometry but in both set-ups ventilation frequency increased. Hypoxia below Pcrit resulted in an up-regulation of anaerobic glycolysis, as evidenced by increased lactate levels in all tissues except brain. Elasmobranchs typically rely on ketone bodies as oxidative substrates, and decreased concentrations of acetoacetate and ß-hydroxybutyrate were observed in white muscle of hypoxic and/or recovering fish. Furthermore, reductions in isoleucine, glutamate, glutamine and other amino acids were observed. After 6 hours of normoxic recovery, changes persisted and only lactate returned to normal in most tissues. This emphasizes the importance of using suitable bioindicators adjusted to preferred metabolic pathways of the target species in conservation physiology. We conclude that Pacific spiny dogfish can tolerate severe transient hypoxic events, but recovery is slow and negative impacts can be expected when hypoxia persists.

Semisupervised Learning to Boost hERG, Nav1.5, and Cav1.2 Cardiac Ion Channel Toxicity Prediction by Mining a Large Unlabeled Small Molecule Data Set.

Predicting drug toxicity is a critical aspect of ensuring patient safety during the drug design process. Although conventional machine learning techniques have shown some success in this field, the scarcity of annotated toxicity data poses a significant challenge in enhancing models' performance. In this study, we explore the potential of leveraging large unlabeled small molecule data sets using semisupervised learning to improve drug cardiotoxicity predictive performance across three cardiac ion channel targets: the voltage-gated potassium channel (hERG), the voltage-gated sodium channel (Nav1.5), and the voltage-gated calcium channel (Cav1.2). We extensively mined the ChEMBL database, comprising approximately 2 million small molecules, and then employed semisupervised learning to construct robust classification models for this purpose. We achieved a performance boost on highly diverse (i.e., structurally dissimilar) test data sets across all three targets. Using our built models, we screened the whole ChEMBL database and a large set of FDA-approved drugs, identifying several compounds with potential cardiac ion channel activity. To ensure broad accessibility and usability for both technical and nontechnical users, we developed a cross-platform graphical user interface that allows users to make predictions and gain insights into the cardiotoxicity of drugs and other small molecules. The software is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred2.

Modeling antigen-specific T cell dynamics following Hepatitis B Vaccination indicates differences between conventional and regulatory T cell dynamics.

Our study aims to investigate the dynamics of conventional memory T cells (Tconv) and regulatory memory T cells (Treg) following activation, and to explore potential differences between these two cell types. To achieve this, we developed advanced statistical mixed models based on mathematical models of ordinary differential equations (ODE), which allowed us to transform post-vaccination immunological processes into mathematical formulas. These models were applied to in-house data from a de novo Hepatitis B vaccination trial. By accounting for inter- and intra-individual variability, our models provided good fits for both antigen-specific Tconv and Treg cells, overcoming the challenge of studying these complex processes. Our modeling approach provided a deeper understanding of the immunological processes underlying T cell development after vaccination. Specifically, our analysis revealed several important findings regarding the dynamics of Tconv and Treg cells, as well as their relationship to seropositivity for Herpes Simplex Virus Type 1 (HSV-1) and Epstein-Barr Virus (EBV), and the dynamics of antibody response to vaccination. Firstly, our modeling indicated that Tconv dynamics suggest the existence of two T cell types, in contrast to Treg dynamics where only one T cell type is predicted. Secondly, we found that individuals who converted to a positive antibody response to the vaccine earlier had lower decay rates for both Tregs and Tconv cells, which may have important implications for the development of more effective vaccination strategies. Additionally, our modeling showed that HSV-1 seropositivity negatively influenced Tconv cell expansion after the second vaccination, while EBV seropositivity was associated with higher Treg expansion rates after vaccination. Overall, this study provides a critical foundation for understanding the dynamic processes underlying T cell development after vaccination.

Machine Learning Strategies to Tackle Data Challenges in Mass Spectrometry-Based Proteomics.

In computational proteomics, machine learning (ML) has emerged as a vital tool for enhancing data analysis. Despite significant advancements, the diversity of ML model architectures and the complexity of proteomics data present substantial challenges in the effective development and evaluation of these tools. Here, we highlight the necessity for high-quality, comprehensive data sets to train ML models and advocate for the standardization of data to support robust model development. We emphasize the instrumental role of key data sets like ProteomeTools and MassIVE-KB in advancing ML applications in proteomics and discuss the implications of data set size on model performance, highlighting that larger data sets typically yield more accurate models. To address data scarcity, we explore algorithmic strategies such as self-supervised pretraining and multitask learning. Ultimately, we hope that this discussion can serve as a call to action for the proteomics community to collaborate on data standardization and collection efforts, which are crucial for the sustainable advancement and refinement of ML methodologies in the field.

Fragment ion intensity prediction improves the identification rate of non-tryptic peptides in timsTOF.

Immunopeptidomics is crucial for immunotherapy and vaccine development. Because the generation of immunopeptides from their parent proteins does not adhere to clear-cut rules, rather than being able to use known digestion patterns, every possible protein subsequence within human leukocyte antigen (HLA) class-specific length restrictions needs to be considered during sequence database searching. This leads to an inflation of the search space and results in lower spectrum annotation rates. Peptide-spectrum match (PSM) rescoring is a powerful enhancement of standard searching that boosts the spectrum annotation performance. We analyze 302,105 unique synthesized non-tryptic peptides from the ProteomeTools project on a timsTOF-Pro to generate a ground-truth dataset containing 93,227 MS/MS spectra of 74,847 unique peptides, that is used to fine-tune the deep learning-based fragment ion intensity prediction model Prosit. We demonstrate up to 3-fold improvement in the identification of immunopeptides, as well as increased detection of immunopeptides from low input samples.

TransExION: a transformer based explainable similarity metric for comparing IONS in tandem mass spectrometry.

Small molecule identification is a crucial task in analytical chemistry and life sciences. One of the most commonly used technologies to elucidate small molecule structures is mass spectrometry. Spectral library search of product ion spectra (MS/MS) is a popular strategy to identify or find structural analogues. This approach relies on the assumption that spectral similarity and structural similarity are correlated. However, popular spectral similarity measures, usually calculated based on identical fragment matches between the MS/MS spectra, do not always accurately reflect the structural similarity. In this study, we propose TransExION, a Transformer based Explainable similarity metric for IONS. TransExION detects related fragments between MS/MS spectra through their mass difference and uses these to estimate spectral similarity. These related fragments can be nearly identical, but can also share a substructure. TransExION also provides a post-hoc explanation of its estimation, which can be used to support scientists in evaluating the spectral library search results and thus in structure elucidation of unknown molecules. Our model has a Transformer based architecture and it is trained on the data derived from GNPS MS/MS libraries. The experimental results show that it improves existing spectral similarity measures in searching and interpreting structural analogues as well as in molecular networking. SCIENTIFIC CONTRIBUTION: We propose a transformer-based spectral similarity metrics that improves the comparison of small molecule tandem mass spectra. We provide a post hoc explanation that can serve as a good starting point for unknown spectra annotation based on database spectra.

Persistent T cell unresponsiveness associated with chronic visceral leishmaniasis in HIV-coinfected patients.

A large proportion of HIV-coinfected visceral leishmaniasis (VL-HIV) patients exhibit chronic disease with frequent VL recurrence. However, knowledge on immunological determinants underlying the disease course is scarce. We longitudinally profiled the circulatory cellular immunity of an Ethiopian HIV cohort that included VL developers. We show that chronic VL-HIV patients exhibit high and persistent levels of TIGIT and PD-1 on CD8+/CD8- T cells, in addition to a lower frequency of IFN-γ+ TIGIT- CD8+/CD8- T cells, suggestive of impaired T cell functionality. At single T cell transcriptome and clonal resolution, the patients show CD4+ T cell anergy, characterised by a lack of T cell activation and lymphoproliferative response. These findings suggest that PD-1 and TIGIT play a pivotal role in VL-HIV chronicity, and may be further explored for patient risk stratification. Our findings provide a strong rationale for adjunctive immunotherapy for the treatment of chronic VL-HIV patients to break the recurrent disease cycle.

Lack of functional TCR-epitope interaction is associated with herpes zoster through reduced downstream T cell activation.

The role of T cell receptor (TCR) diversity in infectious disease susceptibility is not well understood. We use a systems immunology approach on three cohorts of herpes zoster (HZ) patients and controls to investigate whether TCR diversity against varicella-zoster virus (VZV) influences the risk of HZ. We show that CD4+ T cell TCR diversity against VZV glycoprotein E (gE) and immediate early 63 protein (IE63) after 1-week culture is more restricted in HZ patients. Single-cell RNA and TCR sequencing of VZV-specific T cells shows that T cell activation pathways are significantly decreased after stimulation with VZV peptides in convalescent HZ patients. TCR clustering indicates that TCRs from HZ patients co-cluster more often together than TCRs from controls. Collectively, our results suggest that not only lower VZV-specific TCR diversity but also reduced functional TCR affinity for VZV-specific proteins in HZ patients leads to lower T cell activation and consequently affects the susceptibility for viral reactivation.

Identification of TCR repertoire patterns linked with anti-cancer immunotherapy.

The highly diverse T cell receptor (TCR) repertoire is a crucial component of the adaptive immune system that aids in the protection against a wide variety of pathogens. This TCR repertoire, comprising the collection of all TCRs in an individual, is a valuable source of information on both recent and ongoing T cell activation. Cancer cells, like pathogens, have the ability to trigger an adaptive immune response. However, because cancer cells use a variety of strategies to escape immune responses, this is often insufficient to completely eradicate them. As a result, immunotherapy is a promising treatment option for cancer patients. This treatment is expected to increase T cell activation and subsequently alter the TCR repertoire composition in these patients. Monitoring TCR repertoires before and after immunotherapy can therefore provide additional insight into T cell responses and might identify cancer-associated TCR sequences. Here we present a computational strategy to identify those changes in the TCR repertoire that occur after treatment with immunotherapy. Since this method allows the identification of TCR patterns that might be treatment-associated, it can help future research by revealing those patterns that are related with response. This TCR analysis workflow is illustrated using public data from three different cancer patients who received anti-PD-1 treatment.

Training of epitope-TCR prediction models with healthy donor-derived cancer-specific T cells.

Discovery of epitope-specific T-cell receptors (TCRs) for cancer therapies is a time consuming and expensive procedure that usually requires a large amount of patient cells. To maximize information from and minimize the need of precious samples in cancer research, prediction models have been developed to identify in silico epitope-specific TCRs. In this chapter, we provide a step-by-step protocol to train a prediction model using the user-friendly TCRex webtool for the nearly universal tumor-associated antigen Wilms' tumor 1 (WT1)-specific TCR repertoire. WT1 is a self-antigen overexpressed in numerous solid and hematological malignancies with a high clinical relevance. Training of computational models starts from a list of known epitope-specific TCRs which is often not available for new cancer epitopes. Therefore, we describe a workflow to assemble a training data set consisting of TCR sequences obtained from WT137-45-reactive CD8 T cell clones expanded and sorted from healthy donor peripheral blood mononuclear cells.

Unravelling the immune signature of herpes zoster: Insights into pathophysiology and the HLA risk profile.

The varicella-zoster virus (VZV) infects over 95% of the population. VZV reactivation causes herpes zoster (HZ), known as shingles, primarily affecting the elderly and immunocompromised individuals. However, HZ can also occur in otherwise healthy individuals. We analyzed the immune signature and risk profile in HZ patients using a genome-wide association study across different UK Biobank HZ cohorts. Additionally, we conducted one of the largest HZ HLA association studies to date, coupled with transcriptomic analysis of pathways underlying HZ susceptibility. Our findings highlight the significance of the MHC locus for HZ development, identifying five protective and four risk HLA alleles. This demonstrates that HZ susceptibility is largely governed by variations in the MHC. Furthermore, functional analyses revealed the upregulation of type I interferon and adaptive immune responses. These findings provide fresh molecular insights into the pathophysiology and the activation of innate and adaptive immune responses triggered by symptomatic VZV reactivation.

Diagnosing Viral Infections Through T-Cell Receptor Sequencing of Activated CD8+ T Cells.

T-cell-based diagnostic tools identify pathogen exposure but lack differentiation between recent and historical exposures in acute infectious diseases. Here, T-cell receptor (TCR) RNA sequencing was performed on HLA-DR+/CD38+CD8+ T-cell subsets of hospitalized coronavirus disease 2019 (COVID-19) patients (n = 30) and healthy controls (n = 30; 10 of whom had previously been exposed to severe acute respiratory syndrome coronavirus 2 [SARS-CoV-2]). CDR3α and CDR3ß TCR regions were clustered separately before epitope specificity annotation using a database of SARS-CoV-2-associated CDR3α and CDR3ß sequences corresponding to >1000 SARS-CoV-2 epitopes. The depth of the SARS-CoV-2-associated CDR3α/ß sequences differentiated COVID-19 patients from the healthy controls with a receiver operating characteristic area under the curve of 0.84 ± 0.10. Hence, annotating TCR sequences of activated CD8+ T cells can be used to diagnose an acute viral infection and discriminate it from historical exposure. In essence, this work presents a new paradigm for applying the T-cell repertoire to accomplish TCR-based diagnostics.

Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction.

In the field of drug discovery, there is a substantial challenge in seeking out chemical structures that possess desirable pharmacological, toxicological, and pharmacokinetic properties. Complications arise when drugs interfere with the functioning of cardiac ion channels, leading to serious cardiovascular consequences. The discontinuation and removal of numerous approved drugs from the market or at late development stages in the pipeline due to such inhibitory effects further highlight the urgency of addressing this issue. Consequently, the early prediction of potential blockers targeting cardiac ion channels during the drug discovery process is of paramount importance. This study introduces a deep learning framework that computationally determines the cardiotoxicity associated with the voltage-gated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5) for drug candidates. The predictive capabilities of three feature representations─molecular fingerprints, descriptors, and graph-based numerical representations─are rigorously benchmarked. Additionally, a novel training and evaluation data set framework is presented, enabling predictive model training of drug off-target cardiotoxicity using a comprehensive and large curated data set covering these three cardiac ion channels. To facilitate these predictions, a robust and comprehensive small molecule cardiotoxicity prediction tool named CToxPred has been developed. It is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred.

Machine learning-based peptide-spectrum match rescoring opens up the immunopeptidome.

Immunopeptidomics is a key technology in the discovery of targets for immunotherapy and vaccine development. However, identifying immunopeptides remains challenging due to their non-tryptic nature, which results in distinct spectral characteristics. Moreover, the absence of strict digestion rules leads to extensive search spaces, further amplified by the incorporation of somatic mutations, pathogen genomes, unannotated open reading frames, and post-translational modifications. This inflation in search space leads to an increase in random high-scoring matches, resulting in fewer identifications at a given false discovery rate. Peptide-spectrum match rescoring has emerged as a machine learning-based solution to address challenges in mass spectrometry-based immunopeptidomics data analysis. It involves post-processing unfiltered spectrum annotations to better distinguish between correct and incorrect peptide-spectrum matches. Recently, features based on predicted peptidoform properties, including fragment ion intensities, retention time, and collisional cross section, have been used to improve the accuracy and sensitivity of immunopeptide identification. In this review, we describe the diverse bioinformatics pipelines that are currently available for peptide-spectrum match rescoring and discuss how they can be used for the analysis of immunopeptidomics data. Finally, we provide insights into current and future machine learning solutions to boost immunopeptide identification.

Selective whole-genome sequencing of Plasmodium parasites directly from blood samples by nanopore adaptive sampling.

IMPORTANCE: Malaria is caused by parasites of the genus Plasmodium, and reached a global disease burden of 247 million cases in 2021. To study drug resistance mutations and parasite population dynamics, whole-genome sequencing of patient blood samples is commonly performed. However, the predominance of human DNA in these samples imposes the need for time-consuming laboratory procedures to enrich Plasmodium DNA. We used the Oxford Nanopore Technologies' adaptive sampling feature to circumvent this problem and enrich Plasmodium reads directly during the sequencing run. We demonstrate that adaptive nanopore sequencing efficiently enriches Plasmodium reads, which simplifies and shortens the timeline from blood collection to parasite sequencing. In addition, we show that the obtained data can be used for monitoring genetic markers, or to generate nearly complete genomes. Finally, owing to its inherent mobility, this technology can be easily applied on-site in endemic areas where patients would benefit the most from genomic surveillance.

Clinical Decision Support for Improved Neonatal Care: The Development of a Machine Learning Model for the Prediction of Late-onset Sepsis and Necrotizing Enterocolitis.

OBJECTIVE: To develop an artificial intelligence-based software system for predicting late-onset sepsis (LOS) and necrotizing enterocolitis (NEC) in infants admitted to the neonatal intensive care unit (NICU). STUDY DESIGN: Single-center, retrospective cohort study, conducted in the NICU of the Antwerp University Hospital. Continuous monitoring data of 865 preterm infants born at <32 weeks gestational age, admitted to the NICU in the first week of life, were used to train an XGBoost machine learning (ML) algorithm for LOS and NEC prediction in a cross-validated setup. Afterward, the model's performance was assessed on an independent test set of 148 patients (internal validation). RESULTS: The ML model delivered hourly risk predictions with an overall sensitivity of 69% (142/206) for all LOS/NEC episodes and 81% (67/83) for severe LOS/NEC episodes. The model showed a median time gain of ≤10 hours (IQR, 3.1-21.0 hours), compared with historical clinical diagnosis. On the complete retrospective dataset, the ML model made 721 069 predictions, of which 9805 (1.3%) depicted a LOS/NEC probability of ≥0.15, resulting in a total alarm rate of <1 patient alarm-day per week. The model reached a similar performance on the internal validation set. CONCLUSIONS: Artificial intelligence technology can assist clinicians in the early detection of LOS and NEC in the NICU, which potentially can result in clinical and socioeconomic benefits. Additional studies are required to quantify further the effect of combining artificial and human intelligence on patient outcomes in the NICU.

Malate production, sugar metabolism, and redox homeostasis in the leaf growth zone of Rye (Secale cereale) increase stress tolerance to aluminum stress: A biochemical and genome-wide transcriptional study.

Global soil acidification is increasing, enlarging aluminum (Al) availability in soils, leading to reductions in plant growth. This study investigates the effect of Al stress on the leaf growth zones of Rye (Secale cereale, cv Beira). Kinematic analysis showed that the effect of Al on leaf growth rates was mainly due to a reduced cell production rate in the meristem. Transcriptomic analysis identified 2272 significantly (log2fold > |0.5| FDR < 0.05) differentially expressed genes (DEGs) for Al stress. There was a downregulation in several DEGs associated with photosynthetic processes and an upregulation in genes for heat/light response, and H2O2 production in all leaf zones. DEGs associated with heavy metals and malate transport were increased, particularly, in the meristem. To determine the putative function of these processes in Al tolerance, we performed biochemical analyses comparing the tolerant Beira with an Al sensitive variant RioDeva. Beira showed improved sugar metabolism and redox homeostasis, specifically in the meristem compared to RioDeva. Similarly, a significant increase in malate and citrate production, which are known to aid in Al detoxification in plants, was found in Beira. This suggests that Al tolerance in Rye is linked to its ability for Al exclusion from the leaf meristem.

A new Plasmodium vivax reference genome for South American isolates.

BACKGROUND: Plasmodium vivax is the second most important cause of human malaria worldwide, and accounts for the majority of malaria cases in South America. A high-quality reference genome exists for Papua Indonesia (PvP01) and Thailand (PvW1), but is lacking for South America. A reference genome specifically for South America would be beneficial though, as P. vivax is a genetically diverse parasite with geographical clustering. RESULTS: This study presents a new high-quality assembly of a South American P. vivax isolate, referred to as PvPAM (P. vivax Peruvian AMazon). The genome was obtained from a low input patient sample from the Peruvian Amazon and sequenced using PacBio technology, resulting in a highly complete assembly with 6497 functional genes. Telomeric ends were present in 17 out of 28 chromosomal ends, and additional (sub)telomeric regions are present in 12 unassigned contigs. A comparison of multigene families between PvPAM and the PvP01 genome revealed remarkable variation in vir genes, and the presence of merozoite surface proteins (MSP) 3.6 and 3.7. Three dhfr and dhps drug resistance associated mutations are present in PvPAM, similar to those found in other Peruvian isolates. Mapping of publicly available South American whole genome sequencing (WGS) data to PvPAM resulted in significantly fewer variants and truncated reads compared to the use of PvP01 or PvW1 as reference genomes. To minimize the number of core genome variants in non-South American samples, PvW1 is most suited for Southeast Asian isolates, both PvPAM and PvW1 are suited for South Asian isolates, and PvPAM is recommended for African isolates. Interestingly, non-South American samples still contained the least subtelomeric variants when mapped to PvPAM, indicating high quality of the PvPAM subtelomeric regions. CONCLUSIONS: Our findings show that the PvPAM reference genome more accurately represents South American P. vivax isolates in comparison to PvP01 and PvW1. In addition, PvPAM has a high level of completeness, and contains a similar number of annotated genes as PvP01 or PvW1. The PvPAM genome therefore will be a valuable resource to improve future genomic analyses on P. vivax isolates from the South American continent.

Multi-View Learning to Unravel the Different Levels Underlying Hepatitis B Vaccine Response.

The immune system acts as an intricate apparatus that is dedicated to mounting a defense and ensures host survival from microbial threats. To engage this faceted immune response and provide protection against infectious diseases, vaccinations are a critical tool to be developed. However, vaccine responses are governed by levels that, when interrogated, separately only explain a fraction of the immune reaction. To address this knowledge gap, we conducted a feasibility study to determine if multi-view modeling could aid in gaining actionable insights on response markers shared across populations, capture the immune system's diversity, and disentangle confounders. We thus sought to assess this multi-view modeling capacity on the responsiveness to the Hepatitis B virus (HBV) vaccination. Seroconversion to vaccine-induced antibodies against the HBV surface antigen (anti-HBs) in early converters (n = 21; <2 months) and late converters (n = 9; <6 months) and was defined based on the anti-HBs titers (>10IU/L). The multi-view data encompassed bulk RNA-seq, CD4+ T-cell parameters (including T-cell receptor data), flow cytometry data, and clinical metadata (including age and gender). The modeling included testing single-view and multi-view joint dimensionality reductions. Multi-view joint dimensionality reduction outperformed single-view methods in terms of the area under the curve and balanced accuracy, confirming the increase in predictive power to be gained. The interpretation of these findings showed that age, gender, inflammation-related gene sets, and pre-existing vaccine-specific T-cells could be associated with vaccination responsiveness. This multi-view dimensionality reduction approach complements clinical seroconversion and all single modalities. Importantly, this modeling could identify what features could predict HBV vaccine response. This methodology could be extended to other vaccination trials to identify the key features regulating responsiveness.