Author

Dylan D. Ray

University of North Carolina at Chapel HillORCID 0000-0002-2864-2107Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Evolutionary Biology· 1 Genomics· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 2 Approach:benchmark study· 1 Approach:deep learning· 1 Assay:GWAS summary statistics· 1 Approach:statistical model· 1 Assay:whole-genome sequencing· 1

Frequent Co-Authors

Aaron P. RagsdaleiD· 1 shared Adam C. SiepeliD· 1 shared Andrés Moreno‐EstradaiD· 1 shared Andrew H. VaughniD· 1 shared Austin DaigleiD· 1 shared Daniel R. SchrideriD· 1 shared Eilish S. McMasteriD· 1 shared Ekaterina NoskovaiD· 1 shared

Activity by Year

2025-2026 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 36 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

1 shared paperEvolutionary Biology

Aaron P. RagsdaleORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

Interpreting Convolutional Neural Networks in Population Genetics

Huiting Xu, Leon Zong, Dylan D. Ray, Lei Lei, Daniel R. Schrider, Franz Baumdicker, Sara Mathieson

This study investigates how convolutional neural networks in population genetics implicitly compute summary statistics and reveals their ability to efficiently approximate long-range linkage disequilibrium.

Molecular Biology and Evolution · Oct 1, 2026Peer-reviewedGenomics

GHIST 2024: The 1st Genomic History Inference Strategies Tournament

Travis J. Struck, Andrew H. Vaughn, Austin Daigle, Dylan D. Ray, Ekaterina Noskova, Jaison Jeevan Sequeira, Svetlana Antonets, Elizaveta Alekseevskaya, Elizaveta Grigoreva, Evgenii Raines, Eilish S. McMaster, Toby G. L. Kovacs, Aaron P. Ragsdale, Andrés Moreno‐Estrada, Katie E. Lotterhos, , Ryan N. Gutenkunst

GHIST 2024 evaluates population genetic inference methods through four demographic history challenges, revealing the dominance of site frequency spectrum-based methods and the potential of flexible models for complex histories.

bioRxiv · Aug 5, 2025 · PreprintEvolutionary Biology