Prediction of deleterious mutations in coding regions of mammals with transfer learning.

ABSTRACT: The genomes of mammals contain thousands of deleterious mutations. It is important to be able to recognize them with high precision. In conservation biology, the small size of fragmented populations results in accumulation of damaging variants. Preserving animals with less damaged genomes could optimize conservation efforts. In breeding of farm animals, trade-offs between farm performance versus general fitness might be better avoided if deleterious mutations are well classified. In humans, the problem of such a precise classification has been successfully solved, in large part due to large databases of disease-causing mutations. However, this kind of information is very limited for other mammals. Here, we propose to better use information available on human mutations to enable classificat

SUBMITTER: Plekhanova E 

PROVIDER: S-EPMC6304693 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature