{
  "id": 5006077,
  "title": "Using sequence-to-function models to interpret archaic hominin introgression",
  "url": "https://urgent.news/2026/09/01/using-sequence-to-function-models-to-interpret-archaic-hominin",
  "topic": "science",
  "section": "Science",
  "published": "2026-09-01T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.08.31.748430v1?rss=1"
  },
  "original_language": "en",
  "account": "The study explores the use of sequence-to-function models, such as AlphaGenome, to interpret the functional consequences of archaic hominin introgression in modern human genomes. Due to limited representation of global introgression in existing genomics resources, these models can help address this challenge. The research employed AlphaGenome to predict the effects of 144,139 introgressed SNPs in Papuan individuals.\n\nThe chromatin accessibility predictions generated by AlphaGenome align with experimentally observed effects, while gene expression predictions do not perform significantly better than chance. However, the predictions do correlate more strongly with a separate reporter assay of single-variant activity compared to the same variants' effects in live cells. This suggests that AlphaGenome captures the regulatory potential of individual variants more effectively.\n\nFurthermore, the study identifies genes such as JAK1 and TAB2 that are associated with haplotypes containing an excess of variants predicted by AlphaGenome to have significant impacts on chromatin accessibility. The researchers acknowledge that tissue specificity of the predictions allows for the identification of specific tissues potentially impacted by introgressed haplotypes.\n\nThe study also highlights the challenges and limitations associated with utilizing sequence-to-function models for predicting the effects of introgressed variants. While AlphaGenome's chromatin accessibility predictions can aid in prioritizing candidate functional regions, expression predictions and the assignment of variants to target genes remain open challenges.",
  "summary": "Understanding the functional impact of archaic hominin introgression remains challenging due to the poor representation of global introgression in publicly available genomics resources. Sequence-to-function models can predict the effects of any possible variant in the human genome and may fill this gap. Here, we used AlphaGenome to predict the effects of 144,139 introgressed SNPs segregating in…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}