Biology subjects

Meyer, A. G.

Publications and source records attributed to Meyer, A. G..

3 recordsLinked to original sources

bioRxiv2026

Interpretable sequence-based machine learning consolidates candidate H3N2 hemagglutinin antigenic sites

Vaccine strain selection for seasonal influenza A(H3N2) depends on knowing which hemagglutinin (HA) substitutions are most likely to erode neutralizing antibody recognition, yet published antigenic site sets disagree substantially on which positions matter most. We applied interpretable gradient-boosted tree models with SHAP-based site attribution to two complementary hemagglutination inhibition (HI) datasets to produce a more consolidated ranking of candidate antigenic positions. Models trained on a Neher/Bedford benchmark dataset recover the canonical cluster-transition sites established by prior analyses. Moreover, after filtering the WIC dataset for confounding factors, our models recover the majority of positions from four major prior reference sets (Koel, Neher/Bedford, Harvey, and Shah) and improve concordance between rankings derived from the Neher/Bedford and WIC datasets. Rankings from our models also agree more strongly with models trained to predict sampling time or passage identity than with standard evolutionary metrics used to detect diversifying selection. Our results show that interpretable sequence-based models can provide a more integrative ranking of candidate antigenic positions across different data sources and modeling approaches. This work should aid efforts to prioritize H3N2 substitutions for epidemic surveillance. Significance StatementEvery year, health authorities must update the seasonal flu vaccine to account for mutations in influenza A(H3N2) that allow the virus to escape existing immunity. Knowing which specific positions in the hemagglutinin protein drive this immune escape is essential for evaluating newly emerging variants, but published studies disagree substantially on which positions matter most. We show that interpretable machine learning models applied to two hemagglutination inhibition datasets, the Neher/Bedford benchmark dataset and the larger WHO Collaborating Centre dataset, can help to resolve the disagreements. The models recover canonical cluster-transition sites from the Neher/Bedford benchmark data, and show that our analysis approach with the WIC data improves concordance across several prior rankings produced from distinct datasets and modeling approaches. The resulting rankings provide a practical, consolidated reference for prioritizing hemagglutinin mutations most likely to affect vaccine effectiveness.

bioinformatics↗

bioRxiv2025

Explainable machine learning reveals evolutionary signals in Influenza hemagglutinin

Identifying amino acid changes that lead to phenotypic change is a central problem that is critical to viral surveillance. Common metrics used to measure protein evolution like site-wise evolutionary rates and entropy are truly measures of variability rather than phenotypic importance. Here I show that supervised, explainable machine learning models provide a complementary approach that could serve to date and classify sequences, identify important mutations for host adaptation, and control directly for confounding covariates like sampling date and geography of origin. I curated 39,121 hemagglutinin (H3) protein sequences from GISAID with passage annotations and associated sample metadata to create models of sequence change. Gradient boosted decision trees were trained with encoded amino acids plus latitude, longitude, and date; SHAP values quantified site importance. The passage classifier achieved 81% overall accuracy (balanced accuracy = 0.77), distinguishing egg grown from unpassaged isolates with nearly 90% recall, and recovering known and novel adaptive substitutions. A separate regressor, trained solely on unpassaged sequences, predicted sample collection date with R2 = 0.98 and a mean absolute error of 74.5 days. Crucially, the sites identified as most important by the models showed a strong enrichment for experimentally validated antigenic sites, with the passage model ranking these functionally critical residues far more effectively than traditional evolutionary metrics. Across both tasks, correlations between SHAP values and standard evolutionary metrics were strong (0.63[≤] {rho} [≤] 0.9), indicating a strong connection between importance and variability depending on model specification. These results demonstrate that explainable machine learning can reveal important substitutions, deliver tree free molecular dating, and may transform passage metadata from a nuisance into an experimental probe.

evolutionary biology↗

bioRxiv2018

Dynamic Control of Ca2+ Binding in the C2 Domains of Synaptotagmin 1

Synaptotagmin senses fluctuations in the Ca2+ environment of neurons near active zones and transduces a signal to the SNARE complex to initiate exocytosis at the presynaptic terminus. The 3D structures of the two tandem C2 domains of synaptotagmin have been determined to high resolution; however, it is currently unclear how each domain dynamically interacts with Ca2+ at the atomic level. To study the mechanistic consequences of the lethal mutations at the AD3 locus, we introduced tyrosine to asparagine point mutations in both the C2A and C2B domains of synaptotagmin 1, and we have constructed a model that describes the relationship between Ca2+ -binding and the structural changes within each C2 domain. We show that the mobility of loop 3 in the Ca2+ binding pocket increases markedly in C2A, while the mobility of loop 1 changes in C2B with the AD3 mutation. This increase in loop mobility results in an increase in the average volume and variance of the Ca2+ -binding pockets of C2A and C2B. The volume of the unbound Ca2+ -binding pocket in C2A is usually restrained by intra-domain interactions between the tyrosine residue at the AD3 locus and residues on loop 3; however, the AD3 mutation decouples the restraint and results in a larger, more variable Ca2+ -binding pocket in C2A. C2B maintains a more compact Ca2+ -binding pocket; however, its volume also fluctuates significantly with the AD3 mutation. Changes in binding pocket volume that involve more variable Ca2+ binding loops would likely affect Ca2+ affinity in the neurons of the affected organism. Using molecular-dynamics simulations, we show that mutations at the AD3 locus alter the mobility of the Ca2+ -binding loops by removing a key stabilization mechanism that is normally present in C2 domains. The lack of loop stabilization results in a net increase in the volume of the Ca2+ -binding pocket and provides an explanation for the observed lethal phenotype.

bioinformatics↗