Machine learning dissection of human accelerated regions in primate neurodevelopment

Sean Whalen, Fumitaka Inoue, Hane Ryu, Tyler Fair, Eirene Markenscoff-Papadimitriou, Kathleen Keough, Martin Kircher, Beth Martin, Beatriz Alvarado, Orry Elor, Dianne Laboy Cintron, Alex Williams, Md Abul Hassan Samee, Sean Thomas, Robert Krencik, Erik M. Ullian, Arnold Kriegstein, John L. Rubenstein, Jay Shendure, Alex A. PollenNadav Ahituv, Katherine S. Pollard

Research output: Contribution to journalArticlepeer-review

19 Scopus citations


Using machine learning (ML), we interrogated the function of all human-chimpanzee variants in 2,645 human accelerated regions (HARs), finding 43% of HARs have variants with large opposing effects on chromatin state and 14% on neurodevelopmental enhancer activity. This pattern, consistent with compensatory evolution, was confirmed using massively parallel reporter assays in chimpanzee and human neural progenitor cells. The species-specific enhancer activity of HARs was accurately predicted from the presence and absence of transcription factor footprints in each species. Despite these striking cis effects, activity of a given HAR sequence was nearly identical in human and chimpanzee cells. This suggests that HARs did not evolve to compensate for changes in the trans environment but instead altered their ability to bind factors present in both species. Thus, ML prioritized variants with functional effects on human neurodevelopment and revealed an unexpected reason why HARs may have evolved so rapidly.

Original languageEnglish (US)
Pages (from-to)857-873.e8
Issue number6
StatePublished - Mar 15 2023


  • ATAC-seq
  • ChIP-seq
  • Hi-C
  • MPRA
  • accelerated regions
  • enhancers
  • evolution
  • gene regulation
  • machine learning
  • neurodevelopment
  • Chromatin
  • Humans
  • Transcription Factors/genetics
  • Machine Learning
  • Brain/growth & development
  • Pan troglodytes/metabolism
  • Animals
  • Enhancer Elements, Genetic

ASJC Scopus subject areas

  • Neuroscience(all)


Dive into the research topics of 'Machine learning dissection of human accelerated regions in primate neurodevelopment'. Together they form a unique fingerprint.

Cite this