ML and Genome Annotation

Self-supervised learning is a machine learning process where the model trains itself to learn one part of the input data from another part of the input data, rather than relying on human labeled data. This approach helps bioinformaticians when there is a limited amount of labeled data. In addition, this approaches costs involved in data annotation.  In the genomics field, large quantities of unlabeled genomic sequencing data is available, and functional annotation of this large data can be expensive. A team of researchers from Ludwig Maximilian University of Munich, Germany, Technical University of Braunschweig, Germany, have designed a self-supervised learning technique that is tailored for genomic data. To learn more, read- https://www.nature.com/articles/s42003-023-05310-2