SEARCH · PubMed Health

Results for “Reinforcement learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources

PubMed2026

CRISPGen: A deep generative framework for multi-objective CRISPR/Cas9 guide RNA design via Conditional Latent Diffusion and Dual-Critic Reinforcement Learning.

MOTIVATION: The CRISPR-Cas9 system offers transformative potential for precision genome editing, yet its clinical translation remains constrained by the risk of unintended off-target double-strand breaks. While current discriminative models excel at evaluating pre-specified candidate guides, resolving the fundamental antagonism between on-target cleavage efficiency and off-target specificity within a fixed sequence search space remains a major challenge. RESULTS: We present CRISPGen, a unified deep generative framework that reframes sgRNA design as a multi-objective constrained sequence synthesis problem. It integrates (i) DNABERT-2 genomic-language embeddings, (ii) a conditional latent diffusion generator conditioned on a user-specified on-target efficiency target, and (iii) a dual-critic reinforcement-learning (RL) stage that couples a frozen on-target efficiency critic with a cross-attention off-target discriminator (validation Pearson R=0.8157) trained on a unified corpus of experimental off-target events from six detection platforms. Across 1000 generated sgRNAs, CRISPGen reduces the mean off-target discriminator score by 99.7% relative to the pre-RL baseline and, under an exhaustive whole-genome screen of all 302,631,056 NGG PAM sites in GRCh38, yields zero perfect-match and only 55 one-mismatch genomic hits. We further show, transparently, that the internal on-target critic saturates under RL optimization - an instance of Goodhart's Law - and therefore assess on-target viability using an independent external CRISPRon screen (mean 47.10/100). Repeating the RL fine-tuning stage under three random seeds (with the diffusion generator, DNABERT-2 embeddings, and off-target discriminator held fixed) yields a stable operating point across seeds. Full diversity, per-mismatch, and reproducibility statistics are reported in the Results. AVAILABILITY: Source code is available at https://github.com/malekpouri/CRISPGen; the pre-trained checkpoints and the 3,000,000-sequence library are hosted on Hugging Face (https://huggingface.co/malekpouri/CRISPGen-Checkpoints) and archived on Zenodo under DOI 10.5281/zenodo.21428641.

CRISPR-Cas9↗

PubMed2025

GiantHunter: accurate detection of giant virus in metagenomic data using reinforcement-learning and Monte Carlo tree search.

MOTIVATION: Nucleocytoplasmic large DNA viruses (NCLDVs) are notable for their large genomes and extensive gene repertoires, which contribute to their widespread environmental presence and critical roles in processes such as host metabolic reprogramming and nutrient cycling. Metagenomic sequencing has emerged as a powerful tool for uncovering novel NCLDVs in environmental samples. However, identifying NCLDV sequences in metagenomic data remains challenging due to their high genomic diversity, limited reference genomes, and shared regions with other microbes. Existing alignment-based and machine learning methods struggle with achieving optimal trade-offs between sensitivity and precision. RESULTS: In this work, we present GiantHunter, a reinforcement learning-based tool for identifying NCLDVs from metagenomic data. By employing a Monte Carlo tree search strategy, GiantHunter dynamically selects representative non-NCLDV sequences as the negative training data, enabling the model to establish a robust decision boundary. Benchmarking on rigorously designed experiments shows that GiantHunter achieves high precision while maintaining competitive sensitivity, improving the F1-score by 10% and reducing computational cost by 90% compared to the second-best method. To demonstrate its real-world utility, we applied GiantHunter to 60 metagenomic datasets collected from six cities along the Yangtze River, located both upstream and downstream of the Three Gorges Dam. The results reveal significant differences in NCLDV diversity correlated with proximity to the dam, likely influenced by reduced flow velocity caused by the dam. These findings highlight GiantHunter's potential to advance our understanding of NCLDVs and their ecological roles in diverse environments. AVAILABILITY AND IMPLEMENTATION: The source code of GiantHunter is available via: https://github.com/FuchuanQu/GiantHunter.

Metagenomics↗

PubMed2026

Reinforcement learning-based dynamic ensemble for missense variant effect prediction and tiered prioritization of VUS.

BACKGROUND: Accurate classification of missense variants remains a challenging task despite major advances in genomics. Numerous computational models have been developed to assist in variant classification, but often require repeated integration and benchmarking efforts. Ensemble methods have been proposed to overcome the limitations of single predictors, but mostly rely on fixed, predefined weights that constrain their ability to capture interactions among predictive signals. METHODS: We present GenixRL, a dynamic ensemble framework that reformulates model fusion as a reinforcement learning optimization problem. GenixRL uses a Q-learning agent to learn a policy that dynamically weights the probabilistic outputs of complementary predictors, including BayesDel (addAF and noAF), ClinPred, and MetaRNN. Replacing static weighting with policy learning allows GenixRL to adaptively identify optimal weightings and substantially improve classification accuracy. RESULTS: In benchmark evaluation against 25 state-of-the-art predictors, GenixRL achieved an AUROC of 0.9644 on an independent ClinVar dataset. On saturation genome editing assays for BRCA1 and BRCA2, GenixRL achieved the best performance and ranked highest on 14 of 17 clinically significant genes in a zero-shot evaluation. Applied to uncertain and conflicting ClinVar variants, GenixRL enabled tiered, evidence-based prioritization of hundreds of thousands of variants as likely pathogenic or pathogenic with high confidence, supported by orthogonal population evidence from gnomAD. CONCLUSION: GenixRL advances pathogenicity prediction for missense variants and provides an adaptive ensemble that sorts variants of uncertain significance into tiered candidates for expert curation and functional validation.

Mutation, Missense↗

PubMed2026

A reinforcement learning-enhanced fuzzy multi-objective equilibrium optimization framework for multiple sequence alignment.

Multiple sequence alignment (MSA) is a fundamental task in bioinformatics, underpinning comparative genomics, structural analysis, and evolutionary inference. However, MSA remains a challenging multi-objective optimization problem due to the need to simultaneously maximize alignment accuracy, preserve conserved regions, and control gap proliferation, particularly in large and heterogeneous sequence collections. In this work, we propose MOFSACEO-MSA, a novel hybrid optimization framework for multiple sequence alignment that integrates a fuzzy multi-objective evaluation scheme with the Equilibrium Optimizer (EO) and a Soft Actor-Critic (SAC)-based adaptive control mechanism. The proposed framework formulates MSA as a dynamic multi-objective optimization problem, in which alignment quality is assessed using complementary residue-level and column-level criteria, including Sum-of-Pairs score, column conservation, entropy, and gap statistics. Fuzzy membership functions are employed to harmonize competing objectives into a unified optimization landscape, while EO provides robust global exploration. To further enhance adaptability, SAC dynamically regulates key EO parameters during the search process, enabling an effective balance between exploration and exploitation across datasets of varying size and heterogeneity. Extensive experiments werew conducted on diverse biological sequence datasets, with a primary focus on RNA benchmarks, including structured families from Rfam, large-scale repositories from RNAcentral and GenBank, and organism-specific tRNA datasets from GtRNAdb. Comparative evaluations against classical alignment tools (ClustalW, MAFFT, MUSCLE, PRANK, KAlign, and T-Coffee), metaheuristic methods (SAGA, Sequoya and EAFSA), and a reinforcement learning-based approach (RLALIGN) demonstrate that MOFSACEO-MSA consistently achieves competitive or superior Sum-of-Pairs scores while significantly reducing gap proportions and maintaining compact alignment lengths. Notably, the proposed framework exhibits improved robustness on large and highly heterogeneous datasets, where existing methods often suffer from excessive gap insertion or unstable convergence. Overall, MOFSACEO-MSA provides a flexible and extensible optimization paradigm that effectively bridges evolutionary search and reinforcement learning for high-quality multiple sequence alignment, with demonstrated effectiveness on challenging RNA alignment tasks.

Sequence Alignment↗

PubMed2026

Mechanistic insights into Claudin-14 dysfunction implicated in veins of Galen malformation.

Claudin-14 (CLDN14) is a key component of tight junctions (TJs) critical for maintaining paracellular barrier function. Variants of CLDN14 have been linked to Vein of Galen malformations (VOGMs), a rare cerebrovascular disorder; however, the molecular mechanisms underlying their pathogenicity remain unknown. Here, we investigate the mechanistic effects of two VOGM-associated mutations, A113P and V143M, using reinforcement-learning driven enhanced sampling molecular dynamics simulations combined with DiffNets-based deep learning and independent trajectory-wide structural analyses. Our analysis reveals that A113P induces broader structural disruption of CLDN14, perturbing paracellular sealing, pore symmetry, and inter-protomer communication, whereas V143M induces structural rearrangements centred around TM3 and the TM3-ECL2 region. In both cases, mutation-specific alterations are observed in structural stability and interfacial organization across oligomeric assemblies. Notably, these effects are qualitatively consistent across different modelled architectures, despite variability in local responses. In the absence of experimentally resolved structures, the structural perturbations reported here provide a mechanistic understanding of how VOGM-associated variants may influence CLDN14 structure and dynamics.

Aneurysm↗

PubMed2025

Asymmetric cortical projections to striatal direct and indirect pathways distinctly control actions.

The striatal direct and indirect pathways constitute the core for basal ganglia function in action control. Although both striatal D1- and D2-spiny projection neurons (SPNs) receive excitatory inputs from the cerebral cortex, whether or not they share inputs from the same cortical neurons, and how pathway-specific corticostriatal projections control behavior remain largely unknown. Here using a G-deleted rabies system in mice, we found that more than two-thirds of excitatory inputs to D2-SPNs also target D1-SPNs, while only one-third do so vice versa. Optogenetic stimulation of striatal D1- vs. D2-SPN-projecting cortical neurons differently regulate locomotion, reinforcement learning and sequence behavior, implying the functional dichotomy of pathway-specific corticostriatal subcircuits. These results reveal the partially segregated yet asymmetrically overlapping cortical projections on striatal D1- vs. D2-SPNs, and that the pathway-specific corticostriatal subcircuits distinctly control behavior. It has important implications in a wide range of neurological and psychiatric diseases affecting cortico-basal ganglia circuitry.

Journal Article↗

PubMed2026

A systematic review of human avoidance learning: Cognition, computation, and methods.

Avoidance behaviour is fundamental for survival but can become maladaptive in clinical conditions. A large body of literature has accumulated on the dynamics of human avoidance learning. However, current theories and overviews do not provide an exhaustive account of this evidence. In this systematic review, we identify N = 116 studies on human avoidance learning. We analyse these studies with the goal of distilling robust empirical phenomena as a basis for theory-building, and examine their diagnostic value in differentiating between competing theories. We find that the evidence is difficult to reconcile with foundational two-factor and classical safety-signal accounts, and most strongly supports expectancy- and inference-based views, in which avoidance responses are selected with respect to represented consequences. At the same time, no current framework provides a complete account of the evidence: several findings point to an additional role for operant valuation, Pavlovian influences, and contextual or latent-state control over the expression of avoidance. Methodologically, we observe that the problem setting in the most common experimental paradigms is radically simpler than real-world avoidance and therefore unlikely to expose the limits of inferential or reflective mechanisms. Consequently, we argue that paradigms with greater computational demands and more realistic action affordances are required to identify the mechanisms underlying avoidance learning. Collectively, these insights provide a foundation for theoretical refinement, computational modelling, and methodological innovation, with implications for advancing interventions targeting maladaptive avoidance.

Humans↗

PubMed2026

Integrative dual-track transcriptomics reveals stage-specific coordination, regulatory divergence, and HSP90AA1-associated remodeling in human folliculogenesis.

Human folliculogenesis depends on coordinated yet non-identical developmental remodeling in the oocyte and its surrounding granulosa cells. When these two compartments remain synchronized and when they diverge into lineage-specific regulatory states, however, remains incompletely resolved. Here we performed an integrative dual-track re-analysis of the human RNA-seq dataset GSE107746, modeling oocytes and granulosa cells as distinct but developmentally linked compartments across follicular progression. Analysis of 148 sequencing libraries showed that compartment identity was the dominant source of transcriptomic variation, supporting compartment-aware downstream interpretation. Within this framework, oocytes followed a relatively continuous developmental trajectory, with substantial transcriptional remodeling already evident across adjacent stages, whereas granulosa cells showed weaker early-stage contrasts but markedly stronger late-stage reorganization, particularly around the antral and preovulatory transitions. Functional enrichment indicated that oocyte maturation was associated with RNA-processing and broader genome-regulatory remodeling, whereas granulosa maturation was dominated by progressive mitochondrial and bioenergetic activation. Co-expression analysis showed that both compartments contained strong late-stage programmes together with inverse early-state modules, indicating a shared systems-level architecture of maturation, although the hub-gene composition and biological content of these programmes were largely compartment-specific. Machine-learning validation reinforced this asymmetry: oocyte stage classification was best recovered from a compact eigengene-based representation, whereas granulosa stage discrimination was better resolved by a broader differential-expression-derived feature set. At the gene level, HSP90AA1 emerged as a stage-associated marker with compartment-specific behavior, showing progressive attenuation across oocyte development, assignment to the selected oocyte blue module, and sharper transitional dynamics in granulosa cells. Together, these findings support a model in which human folliculogenesis proceeds through coordinated but non-equivalent transcriptomic remodeling, with shared developmental logic at the systems level but distinct molecular execution in germline and somatic compartments.

Co-expression networks↗

PubMed2026

User Engagement and Feature Preferences in an AI-Powered mHealth Intervention for Diabetes Prevention: Secondary Analysis of a Randomized Controlled Trial.

BACKGROUND: Prediabetes is highly prevalent and increasing globally, yet lifestyle interventions remain underused. AI-driven mobile health (mHealth) tools can help scale diabetes prevention efforts, but the key factors driving their success are not well understood. OBJECTIVE: This post hoc secondary analysis of a randomized controlled trial (RCT) aimed to characterize the most valued features and the role of user engagement in outcomes of a fully automated mHealth intervention for diabetes prevention. METHODS: Data from 151 participants with prediabetes and overweight or obesity who were assigned to an AI-based diabetes prevention program (Sweetch) in a parent RCT (NCT05056376) were analyzed. Engagement (defined as the total number of days the app was used) was categorized into tertiles (low, medium, and high). Baseline characteristics were compared across engagement groups using ANOVA, Kruskal-Wallis, and chi-square tests, and regression models assessed the association between engagement and achievement of diabetes risk reduction outcomes (≥5% weight loss, ≥4% weight loss with ≥150 min/week of physical activity, or ≥0.2 percentage point reduction in hemoglobin A1c [HbA1c] at 12 months). Perceived usefulness of intervention features was surveyed at 12 months. RESULTS: Median engagement was 98 (IQR 34-232) days. Older age (P<.001) and lower baseline BMI (P=.04) were significantly associated with higher engagement. Compared with low engagement, high engagement was associated with greater odds of achieving the composite diabetes risk reduction outcome (odds ratio [OR] 2.59, 95% CI 1.11-6.01; P=.03), ≥5% weight loss (OR 3.31, 95% CI 1.16-9.42; P=.03), and ≥0.2 percentage point reduction in HbA1c (OR 3.57, 95% CI 1.19-10.75; P=.02). Participants most frequently rated weight tracking, physical activity tracking, and the digital body weight scale as the features that were most helpful for achieving their health goals. CONCLUSIONS: Higher engagement with an AI-driven intervention requiring no human intervention was associated with improved diabetes risk reduction. Contrary to concerns about lower digital literacy, older adults engaged with the intervention more than younger adults. Features related to weight and physical activity tracking were most valued by patients in the program. TRIAL REGISTRATION: ClinicalTrials.gov NCT05056376; https://clinicaltrials.gov/study/NCT05056376.

Humans↗

PubMed2023

Human mutations in high-confidence Tourette disorder genes affect sensorimotor behavior, reward learning, and striatal dopamine in mice.

UNLABELLED: Tourette disorder (TD) is poorly understood, despite affecting 1/160 children. A lack of animal models possessing construct, face, and predictive validity hinders progress in the field. We used CRISPR/Cas9 genome editing to generate mice with mutations orthologous to human de novo variants in two high-confidence Tourette genes, CELSR3 and WWC1 . Mice with human mutations in Celsr3 and Wwc1 exhibit cognitive and/or sensorimotor behavioral phenotypes consistent with TD. Sensorimotor gating deficits, as measured by acoustic prepulse inhibition, occur in both male and female Celsr3 TD models. Wwc1 mice show reduced prepulse inhibition only in females. Repetitive motor behaviors, common to Celsr3 mice and more pronounced in females, include vertical rearing and grooming. Sensorimotor gating deficits and rearing are attenuated by aripiprazole, a partial agonist at dopamine type II receptors. Unsupervised machine learning reveals numerous changes to spontaneous motor behavior and less predictable patterns of movement. Continuous fixed-ratio reinforcement shows Celsr3 TD mice have enhanced motor responding and reward learning. Electrically evoked striatal dopamine release, tested in one model, is greater. Brain development is otherwise grossly normal without signs of striatal interneuron loss. Altogether, mice expressing human mutations in high-confidence TD genes exhibit face and predictive validity. Reduced prepulse inhibition and repetitive motor behaviors are core behavioral phenotypes and are responsive to aripiprazole. Enhanced reward learning and motor responding occurs alongside greater evoked dopamine release. Phenotypes can also vary by sex and show stronger affection in females, an unexpected finding considering males are more frequently affected in TD. SIGNIFICANCE STATEMENT: We generated mouse models that express mutations in high-confidence genes linked to Tourette disorder (TD). These models show sensorimotor and cognitive behavioral phenotypes resembling TD-like behaviors. Sensorimotor gating deficits and repetitive motor behaviors are attenuated by drugs that act on dopamine. Reward learning and striatal dopamine is enhanced. Brain development is grossly normal, including cortical layering and patterning of major axon tracts. Further, no signs of striatal interneuron loss are detected. Interestingly, behavioral phenotypes in affected females can be more pronounced than in males, despite male sex bias in the diagnosis of TD. These novel mouse models with construct, face, and predictive validity provide a new resource to study neural substrates that cause tics and related behavioral phenotypes in TD.

Preprint↗

PubMed2024

Human mutations in high-confidence Tourette disorder genes affect sensorimotor behavior, reward learning, and striatal dopamine in mice.

Tourette disorder (TD) is poorly understood, despite affecting 1/160 children. A lack of animal models possessing construct, face, and predictive validity hinders progress in the field. We used CRISPR/Cas9 genome editing to generate mice with mutations orthologous to human de novo variants in two high-confidence Tourette genes, CELSR3 and WWC1. Mice with human mutations in Celsr3 and Wwc1 exhibit cognitive and/or sensorimotor behavioral phenotypes consistent with TD. Sensorimotor gating deficits, as measured by acoustic prepulse inhibition, occur in both male and female Celsr3 TD models. Wwc1 mice show reduced prepulse inhibition only in females. Repetitive motor behaviors, common to Celsr3 mice and more pronounced in females, include vertical rearing and grooming. Sensorimotor gating deficits and rearing are attenuated by aripiprazole, a partial agonist at dopamine type II receptors. Unsupervised machine learning reveals numerous changes to spontaneous motor behavior and less predictable patterns of movement. Continuous fixed-ratio reinforcement shows that Celsr3 TD mice have enhanced motor responding and reward learning. Electrically evoked striatal dopamine release, tested in one model, is greater. Brain development is otherwise grossly normal without signs of striatal interneuron loss. Altogether, mice expressing human mutations in high-confidence TD genes exhibit face and predictive validity. Reduced prepulse inhibition and repetitive motor behaviors are core behavioral phenotypes and are responsive to aripiprazole. Enhanced reward learning and motor responding occur alongside greater evoked dopamine release. Phenotypes can also vary by sex and show stronger affection in females, an unexpected finding considering males are more frequently affected in TD.

Animals↗

PubMed2026

School-based sexual violence prevention: A systematic review.

PURPOSE: Sexual violence profoundly affects the health and development of children, adolescents, and young adults, representing a persistent challenge to public policy. This systematic review examined the effectiveness of school-based interventions aimed at prevention. METHODS: Eighteen randomized controlled trials published between 2012 and 2024 were retrieved from four major databases. The programs were implemented in primary, secondary, and higher education settings and targeted children, adolescents, and young adults. RESULTS: The results revealed improvements in knowledge and attitude, particularly regarding consent and awareness, whereas evidence supporting behavioral changes was less frequent and often limited. Methodological limitations, such as short follow-up periods and participant attrition, restricted the assessment of long-term outcomes. CONCLUSIONS: This review highlights the importance of multicomponent, participatory, and culturally sensitive approaches, along with the integration of digital tools and continuous evaluation systems, to strengthen the role of schools as safe and transformative spaces in the prevention of sexual violence. IMPLICATIONS AND CONTRIBUTIONS: This systematic review suggests that school-based interventions hold significant potential for the prevention of sexual violence. It identifies promising strategies and reinforces the importance of culturally sensitive, sustained, evidence-based approaches to ensure learning environments that are safe, protective, and promotive of gender equity.

Humans↗

PubMed2026

How AI-supported intelligent systems support infection prevention and control training in healthcare: A systematic review of educational functions and outcomes.

AIMS: Artificial intelligence (AI)-supported intelligent systems have been increasingly incorporated into infection prevention and control (IPC) education and training, primarily to support the monitoring of observable behaviors and the provision of feedback. However, existing evidence has focused largely on short-term compliance outcomes, with limited synthesis of the educational role of AI-supported intelligent systems in supporting sustained IPC competence. This systematic review examined how AI-supported intelligent systems have been designed and used to support IPC education and training, with a focus on system characteristics, educational functions, and reported outcomes. DESIGN: A systematic literature search was conducted across the PubMed/MEDLINE, Embase, Cochrane, and CINAHL databases. DATA SOURCES: A total of 18 studies met the inclusion criteria. Findings were qualitatively synthesized according to system design characteristics, educational functions, and outcome domains. REVIEW METHODS: Methodological quality was appraised using the Mixed Methods Appraisal Tool. RESULTS: Most AI-supported intelligent systems focused on hand hygiene and relied on fully automated monitoring systems to capture behaviors and provide performance feedback. Educational functions were predominantly limited to performance assessment, automated feedback, and reminders. Outcomes were mainly measured using compliance or performance metrics, whereas sustained behavioral change and decision quality were rarely assessed. CONCLUSIONS: AI-supported intelligent systems have been used primarily to reinforce short-term IPC performance and compliance. However, their current applications for supporting sustained competence over time remain limited. The findings of this review suggest that AI-supported intelligent systems may serve as maintenance-oriented educational support by extending learning beyond initial instruction through repeated practice and feedback. Future research should prioritize outcome measures that capture the durability of performance and decision-making processes to better align AI-supported intelligent systems used in IPC education and training with the educational demands of clinical practice.

Humans↗

PubMed2026

Machine learning approaches for cancer prognosis and diagnosis via non-coding RNA: a comprehensive review.

Non-coding RNAs (ncRNAs), once considered genomic dark matter, are now established as key regulators of gene expression with widespread roles in cellular homeostasis and disease. In cancer, ncRNA expression is frequently and systematically dysregulated, and many of these molecules circulate in stable, protected form within biofluids, offering a compelling basis for non-invasive or minimally invasive diagnostic strategies. However, their clinical translation remains substantially hindered to date due to biological complexity, technical noise, and high dimensionality inherent to ncRNA expression datasets. In this context, machine learning (ML) has emerged as a powerful analytical tool to address these challenges, enabling the identification of subtle, reproducible ncRNA signatures predictive of diverse malignancies. This review critically evaluates ML-driven frameworks for cancer diagnosis and prognosis across four ncRNA subclasses, namely miRNAs, lncRNAs, circRNAs, and piRNAs, while also acknowledging the biophysical and thermodynamic models that reinforce ncRNA bioinformatics. Despite substantial methodological progress in ML-based cancer diagnosis and prognosis, key challenges persist, including tumor biological heterogeneity, limited multicenter validation, and the lack of widely adopted standardized protocols for preprocessing, normalization, and reporting workflows. Furthermore, many current ML models lack interpretability in biological or clinical context, constraining their translational utility. By synthesizing recent advances and identifying unresolved barriers, this review charts a roadmap for developing a robust, clinically actionable ncRNA biomarker platform for cancer detection. With global cancer incidence projected to exceed 35 million annual cases by 2050, validated ncRNA-ML-driven frameworks hold potential to revolutionize early-stage detection and personalized therapeutic strategies, thereby reducing the escalating socio-economic burden of cancer worldwide.

Humans↗

PubMed2025

Machine learning detection of heteroresistance in Escherichia coli.

BACKGROUND: Heteroresistance (HR) is a significant type of antibiotic resistance observed for several bacterial species and antibiotic classes where a susceptible main population contains small subpopulations of resistant cells. Mathematical models, animal experiments and clinical studies associate HR with treatment failure. Currently used susceptibility tests do not detect heteroresistance reliably, which can result in misclassification of heteroresistant isolates as susceptible which might lead to treatment failure. Here we examined if whole genome sequence (WGS) data and machine learning (ML) can be used to detect bacterial HR. METHODS: We classified 467 Escherichia coli clinical isolates as HR or non-HR to the often used β-lactam/inhibitor combination piperacillin-tazobactam using pre-screening and Population Analysis Profiling tests. We sequenced the isolates, assembled the whole genomes and created a set of predictors based on current knowledge of HR mechanisms. Then we trained several machine learning models on 80% of this data set aiming to detect HR isolates. We compared performance of the best ML models on the remaining 20% of the data set with a baseline model based solely on the presence of β-lactamase genes. Furthermore, we sequenced the resistant sub-populations in order to analyse the genetic mechanisms underlying HR. FINDINGS: The best ML model achieved 100% sensitivity and 84.6% specificity, outperforming the baseline model. The strongest predictors of HR were the total number of β-lactamase genes, β-lactamase gene variants and presence of IS elements flanking them. Genetic analysis of HR strains confirmed that HR is caused by an increased copy number of resistance genes via gene amplification or plasmid copy number increase. This aligns with the ML model's findings, reinforcing the hypothesis that this mechanism underlies HR in Gram-negative bacteria. INTERPRETATION: We demonstrate that a combination of WGS and ML can identify HR in bacteria with perfect sensitivity and high specificity. This improved detection would allow for better-informed treatment decisions and potentially reduce the occurrence of treatment failures associated with HR. FUNDING: Funding provided to DIA from the Swedish Research Council (2021-02091) and NIH (1U19AI158080-01).

Machine Learning↗

PubMed2026

PHACE syndrome: a systematic literature review and illustrative case report of a patient with severe cerebrovascular and neurodevelopmental sequelae.

BACKGROUND: PHACE syndrome is a rare neurocutaneous disorder defined by the association of large segmental infantile hemangiomas of the head and neck with malformations of the posterior fossa, cerebral and cervical arteries, heart, eyes, and ventral midline structures. Although facial hemangiomas are often the presenting feature, the cerebrovascular, neurodevelopmental, and airway manifestations are responsible for the greatest long-term morbidity. METHODS: A systematic literature review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, searching PubMed, Web of Science, EMBASE, and PsycINFO. After removal of duplicates and screening of 308 records, five studies meeting the inclusion criteria were retained for qualitative synthesis. We additionally present the case of a now 12-year-old girl with PHACE syndrome characterized by a left V1-distribution facial hemangioma, ocular abnormalities, multiple cerebrovascular venous and arterial malformations, neonatal intraventricular hemorrhage with hydrocephalus, and a subsequently diagnosed dural arteriovenous fistula requiring repeated embolization. RESULTS: The five included studies collectively describe epidemiology and early supportive care needs, long-term health outcomes and quality of life into adulthood, airway hemangioma prevalence and management, and the clinical spectrum of infantile hemangiomas with minimal or arrested growth (IH-MAG) as a cutaneous marker of PHACE syndrome. Across studies, cerebrovascular arteriopathy (72-91%) and facial hemangioma residua (> 90%) were the most consistent findings, while progressive arteriopathy, headaches, learning differences, and airway involvement emerged as the principal sources of long-term morbidity. The reported case illustrates an unusually severe cerebrovascular phenotype, including neonatal hemorrhagic hydrocephalus, dural venous sinus thrombosis, and a late dural arteriovenous fistula, culminating in ataxic cerebral palsy and mild intellectual disability. CONCLUSIONS: PHACE syndrome requires a multidisciplinary, lifelong follow-up strategy. The presented case underscores that cerebrovascular complications may evolve over years to decades after the initial diagnosis, reinforcing the need for long-term neuroradiological surveillance even after apparent clinical stability.

Humans↗

PubMed2025

Ophthalmic imaging as a measure of cardiovascular and neurological health: a multi-omic analysis of deep-learning derived phenotypes.

The eye is a recognised source of biomarkers for cardiovascular and neurodegenerative disease risk. Here, we characterise the breadth of these associations and identify biological axes that may mediate them. Using UK Biobank data, we developed a multi-omic analysis pipeline integrating physiological, radiomic, metabolomic, and genomic information. We trained adversarial autoencoders (Ret-AAE) to represent optical coherence tomography (OCT) images and colour fundus photographs as 256-dimensional embeddings. Ret-AAE derived embeddings were associated with a range of cardiovascular and neurodegenerative diseases, including ischaemic heart disease, cerebrovascular disease, Parkinson's disease, and dementia. Examining associations across diverse omics datasets, we provide evidence linking ophthalmic imaging features to neurological and cardiovascular anatomy and function, lipid metabolism, and gene sets associated with neurodegenerative pathology. Collectively, our findings demonstrate that ophthalmic features reflect complex, multisystem biological processes, and reinforce the role of the eye as a composite indicator of systemic health.

Journal Article↗

PubMed2024

Blood-based DNA methylation and exposure risk scores predict PTSD with high accuracy in military and civilian cohorts.

BACKGROUND: Incorporating genomic data into risk prediction has become an increasingly useful approach for rapid identification of individuals most at risk for complex disorders such as PTSD. Our goal was to develop and validate Methylation Risk Scores (MRS) using machine learning to distinguish individuals who have PTSD from those who do not. METHODS: Elastic Net was used to develop three risk score models using a discovery dataset (n = 1226; 314 cases, 912 controls) comprised of 5 diverse cohorts with available blood-derived DNA methylation (DNAm) measured on the Illumina Epic BeadChip. The first risk score, exposure and methylation risk score (eMRS) used cumulative and childhood trauma exposure and DNAm variables; the second, methylation-only risk score (MoRS) was based solely on DNAm data; the third, methylation-only risk scores with adjusted exposure variables (MoRSAE) utilized DNAm data adjusted for the two exposure variables. The potential of these risk scores to predict future PTSD based on pre-deployment data was also assessed. External validation of risk scores was conducted in four independent cohorts. RESULTS: The eMRS model showed the highest accuracy (92%), precision (91%), recall (87%), and f1-score (89%) in classifying PTSD using 3730 features. While still highly accurate, the MoRS (accuracy = 89%) using 3728 features and MoRSAE (accuracy = 84%) using 4150 features showed a decline in classification power. eMRS significantly predicted PTSD in one of the four independent cohorts, the BEAR cohort (beta = 0.6839, p-0.003), but not in the remaining three cohorts. Pre-deployment risk scores from all models (eMRS, beta = 1.92; MoRS, beta = 1.99 and MoRSAE, beta = 1.77) displayed a significant (p < 0.001) predictive power for post-deployment PTSD. CONCLUSION: Results, especially those from the eMRS, reinforce earlier findings that methylation and trauma are interconnected and can be leveraged to increase the correct classification of those with vs. without PTSD. Moreover, our models can potentially be a valuable tool in predicting the future risk of developing PTSD. As more data become available, including additional molecular, environmental, and psychosocial factors in these scores may enhance their accuracy in predicting the condition and, relatedly, improve their performance in independent cohorts.

DNA methylation↗