engleski

Read classification using semi-supervised deep learning

n this paper, we propose a semi-supervised deep learning method for detecting the specific types of reads that impede the de novo genome assembly process. Instead of dealing directly with sequenced reads, we analyze their cov- erage graphs converted to 1D-signals. We noticed that specific signal patterns occur in each relevant class of reads. Semi-supervised approach is chosen be-cause manually labelling the data is a very slow and tedious process, so our goal was to facilitate the assembly process with as little labeled data as possible. We tested two models to learn patterns in the coverage graphs: M1+M2 and semi-GAN. We evaluated the performance of each model based on a manually labeled dataset that comprises various reads from multiple reference genomes with re-spect to the number of labeled examples that were used during the training pro-cess. In addition, we embedded our detection in the assembly process which im-proved the quality of assemblies.

deep learning, Semi-supervised learning, De novo assembly, chimeric read, repeat read

nije evidentirano