PT  - JOURNAL ARTICLE
AU  - Sean Whalen
AU  - Fumitaka Inoue
AU  - Hane Ryu
AU  - Tyler Fairr
AU  - Eirene Markenscoff-Papadimitriou
AU  - Kathleen Keough
AU  - Martin Kircher
AU  - Beth Martin
AU  - Beatriz Alvarado
AU  - Orry Elor
AU  - Dianne Laboy Cintron
AU  - Alex Williams
AU  - Md. Abul Hassan Samee
AU  - Sean Thomas
AU  - Robert Krencik
AU  - Erik M. Ullian
AU  - Arnold Kriegstein
AU  - John L. Rubenstein
AU  - Jay Shendure
AU  - Alex A. Pollen
AU  - Nadav Ahituv
AU  - Katherine S. Pollard
TI  - Machine-learning dissection of Human Accelerated Regions in primate neurodevelopment
AID  - 10.1101/256313
DP  - 2022 Jan 01
TA  - bioRxiv
PG  - 256313
4099  - http://biorxiv.org/content/early/2022/09/28/256313.short
4100  - http://biorxiv.org/content/early/2022/09/28/256313.full
AB  - Using machine learning (ML), we interrogated the function of all human-chimpanzee variants in 2,645 Human Accelerated Regions (HARs), some of the fastest evolving regions of the human genome. We predicted that 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 human and chimpanzee neural progenitor cells. The species-specific enhancer activity of assayed 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. These findings suggest 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.Competing Interest StatementThe authors have declared no competing interest.