Fig. 4. Impact of training data-set size on classification accuracy.

(A) Improved performance of PrimateAI-3D with increasing number of common human and primate variants in the training dataset (x-axis). Performance of each dataset (y-axis) was divided by the maximum performance observed _; across all training dataset sizes. (B) Cumulative fractions of all possible human synonymous (gray) and missense (green) variants observed as common variants in 234 primate species, including humans (allele frequency > 0.1%). Each point shows the average of 10 permutations, calculated with a different random ordering of the list of primate species each time.