公开(公告)号：ZA202007739B

公开(公告)日：2024-11-27

申请号：ZA202007739

申请日：2020-12-11

Applicant: IBM

Inventor： MAPIYE DARLINGTON SHINGIRIRAI ,  MASHIYANE JAMES ,  MULLER STEPHANIE JULIA ,  MOKOATLE MPHO ,  DLAMINI GCINIWE

Abstract: In an approach to automatically downsampling DNA sequence data using variational autoencoders and preserving genomic integrity of an origional file embodiments execute, by an encoder, bootstrapping on genomic sequence data to produce resamples.Furthermore, embodiments assess, by the encoder, unrepresentativeness and self-inconsistency of the resamples and selecting a representative resample according to the assessment, and build, by a modified encoder, vector representations from genotype likelihoods based on the selected representative sample. Additionally, embodiments integrate, by an analytics engine, mapping positional information and the genotype likelihoods to identified optimum vector representation of a resample, and decode, by a modified decoder, the identified optimum vector representation of the resample to obtain a down-sampled read file that resembles and maintains the genomic integrity of the original file.