Article

Seq2KING: An unsupervised internal transformer representation of global human heritages

2025-06-23

Abstract excerpt

Determining the intricate tapestry of human genetic relationships is a central challenge in population genetics and precision medicine. We propose that the principles of lexical connectivity, which words derive meaning from their contextual interactions, can be adapted to genetic data, enabling transformer models to reveal that individuals with higher genetic similarity form stronger latent connections. We explore...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: be825af2-d01d-5d4f-a403-fca25fa4a477
DOI: 10.1101/2025.06.17.660172

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Seq2KING: An unsupervised internal transformer representation of global human heritagesDOI 10.1101/2025.06.17.660172Read

Towards a universal foundation model for biobank-scale human genome variationSemantic proximity Read

dnaSORA - A Unified Diffusion Transformer for DNA point cloudsSemantic proximity Read

Towards a universal foundation model for biobank-scale human genome variationSemantic proximity Read

Benchmarking DNA Foundation Models for Genomic and Genetic TasksSemantic proximity Read

Reading Mechanism off Biological Foundation Models: An Empirical Analysis of Genomic Neighborhood Structure in scGPT Gene EmbeddingsSemantic proximity Read

Popformer: Learning general signatures of positive selection with a self-supervised transformer.Semantic proximity Read

Popformer: Learning general signatures of positive selection with a self-supervised transformerSemantic proximity Read

Topological Deep Learning Identifies Polygenic Variant Clusters Across Familial Multimorbid DisordersSemantic proximity Read

MutBERT: Probabilistic Genome Representation Improves Genomics Foundation ModelsSemantic proximity Read

Emergent populations derived with unsupervised learning of human whole genomesSemantic proximity Read

Domain-specific embeddings uncover latent genetics knowledgeSemantic proximity Read

Clinical trajectories and genetic architecture across the neurological–psychiatric boundarySemantic proximity Read