Machine learning dissection of human accelerated regions in primate neurodevelopment

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 evolu-tion, 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.

Automated summary

Using ML, the study examined the effects of human-chimpanzee genetic variants on chromatin state and neurodevelopmental enhancer activity in 2,645 human accelerated regions (HARs). The analysis revealed that 43% of HARs had variants with opposing effects on chromatin state, and 14% had effects on neurodevelopmental enhancer activity. This pattern, indicative of compensatory evolution, was confirmed through experimental assays in chimpanzee and human neural progenitor cells.