Identification of animal species images based on mito- chondrial DNA

The appearance of an animal species is a complex phenotype partially encoded in its genome. Previous work on linking genotype to visually-identifiable phenotypes has focused on univariate or low-dimensional traits such as eye color1, principal variations in skeletal structure2 and height3, as well as on the discovery of specific genes that contribute to these traits. Here, we go beyond single traits to the full genotype-phenotype analysis of photographs and illustrations of animal species. We address the problems of (1) identification and (2) synthesis of images of previously unseen animals using genetic data. We demonstrate that both these problems are feasible: in a multiple choice test, our algorithm identifies with high accuracy the correct image of previously unseen fish, birds and ants, based only on a short gene sequence; additionally, using the same sequence we are able to approximate images of unseen fish contours. Our predictions are based on correlative phenotype-genotype links rather than on specific gene targeting, and they employ the cytochrome c oxidase I mitochondrial gene which is assumed to have little causal influence on appearance. Such correlative links enable the use of high-dimensional phenotypes in genetic research, and applications may range from forensics to personalized medical treatment. There is little doubt that appearance is to a large extent influenced by heritage, yet the actual mechanisms that determine our looks may be difficult to unravel since they are likely to involve complex pathways consisting of a multitude of genes. This, however, does not eliminate the possibility of predicting appearance according to genetic data. In order to predict it is sufficient to discover statistical