Biology subjects

Jacoby, D.

Publications and source records attributed to Jacoby, D..

3 recordsLinked to original sources

bioRxiv2025

Mobius: Mixture-Of-Experts Transformer Model in Epigenetics of ME/CFS and Long COVID

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) and Long COVID are chronic debilitating post-infectious illnesses that collectively affect up to 470 million individuals. Unlike illnesses of comparable scale, there are no validated blood or imaging tests for the clinical diagnosis of these conditions. Currently, these conditions are diagnosed through clinical exclusion, resulting in approximately 90% of ME/CFS patients being incorrectly diagnosed as Long COVID patients. This misdiagnosis contributes to delayed care and millions of dollars in healthcare burdens. We present Mobius, a transformer-based model that uses autoencoder-derived features from blood DNA methylation to distinguish ME/CFS, Long COVID, and healthy controls. Using 852 samples from 14 distinct datasets, our method employs three innovations: (i) self-supervised masked pretraining to learn epigenetic patterns, (ii) a sparsely-gated mixture-of-experts architecture to handle heterogeneous data, and (iii) an adaptive computation time mechanism for dynamic inference. Mobius achieved 97.06% accuracy (macro-F1 0.95, AUROC 0.96), outperforming current symptom-based diagnostics (58%) and baseline models such as XGBoost (82%). Ablation experiments showed that pretraining added 6% accuracy and that the gating and adaptive depth contributed an additional 7%. Our open-source pipeline could enable a much-needed objective blood test for these conditions and guide targeted precision medicine therapies.

genomics↗

bioRxiv2020

Disease-specific variant pathogenicity prediction significantly improves variant interpretation in inherited cardiac conditions

BackgroundAccurate discrimination of benign and pathogenic rare variation remains a priority for clinical genome interpretation. State-of-the-art machine learning tools are useful for genome-wide variant prioritisation but remain imprecise. Since the relationship between molecular consequence and likelihood of pathogenicity varies between genes with distinct molecular mechanisms, we hypothesised that a disease-specific classifier may outperform existing genome-wide tools. MethodsWe present a novel disease-specific variant classification tool, CardioBoost, that estimates the probability of pathogenicity for rare missense variants in inherited cardiomyopathies and arrhythmias, trained with variants of known clinical effect. To benchmark against state-of-the-art genome-wide pathogenicity classification tools, we assessed classification of hold-out test variants using both overall performance metrics, and metrics of high-confidence (>90%) classifications relevant to variant interpretation. We further evaluated the prioritisation of variants associated with disease and patient clinical outcomes, providing validations that are robust to potential mis-classification in gold-standard reference datasets. ResultsCardioBoost has higher discriminating power than published genome-wide variant classification tools in distinguishing between pathogenic and benign variants based on overall classification performance measures with the highest area under the Precision-Recall Curve as 91% for cardiomyopathies and as 96% for inherited arrhythmias. When assessed at high-confidence (>90%) classification thresholds, prediction accuracy is improved by at least 120% over existing tools for both cardiomyopathies and arrhythmias, with significantly improved sensitivity and specificity. Finally, CardioBoost improves prioritisation of variants significantly associated with disease, and stratifies survival of patients with cardiomyopathies, confirming biologically relevant variant classification. ConclusionsWe demonstrate that a disease-specific variant pathogenicity prediction tool outperforms state-of-the-art genome-wide tools for the classification of rare missense variants of uncertain significance for inherited cardiac conditions. To facilitate evaluation of CardioBoost, we provide pre-computed pathogenicity scores for all possible rare missense variants in genes associated with cardiomyopathies and arrhythmias (https://www.cardiodb.org/cardioboost/). Our results also highlight the need to develop and evaluate variant classification tools focused on specific diseases and clinical application contexts. Our proposed model for assessing variants in known disease genes, and the use of application-specific evaluations, is broadly applicable to improve variant interpretation across a wide range of Mendelian diseases.

genetics↗

bioRxiv2018

Quantitative approaches to variant classification increase the yield and precision of genetic testing in Mendelian diseases: The case of hypertrophic cardiomyopathy

BackgroundInternational guidelines for variant interpretation in Mendelian disease set stringent criteria to report a variant as (likely) pathogenic, prioritising control of false positive rate over test sensitivity and diagnostic yield. Genetic testing is also more likely informative in individuals with well-characterised variants from extensively studied European-ancestry populations. Inherited cardiomyopathies are relatively common Mendelian diseases that allow empirical calibration and assessment of this framework.\n\nResultsWe compared rare variants in large hypertrophic cardiomyopathy (HCM) cohorts to reference populations to identify variant classes with high prior likelihoods of pathogenicity, as defined by etiological fraction (EF). Analysis of variant distribution identified regions in which variants are significantly enriched in cases and variant location was a better discriminator of pathogenicity than generic computational functional prediction algorithms. Non-truncating variant classes with an EF[≥]0.95, and therefore clinically actionable, were identified in 5 established HCM genes. Applying this approach leads to an estimated 14-20% increase in cases with actionable HCM variants.\n\nConclusionsWhen found in a patient confirmed to have disease, novel variants in some genes and regions are empirically shown to have a sufficiently high probability of pathogenicity to support a \"likely pathogenic\" classification, even without additional segregation or functional data. This could increase the yield of high confidence actionable variants, consistent with the framework and recommendations of current guidelines. The techniques outlined offer a consistent, unbiased and equitable approach to variant interpretation for Mendelian disease genetic testing. We propose adaptations to ACMG/AMP guidelines to incorporate such evidence in a quantitative and transparent manner.

genetics↗