Input and output data for the publication "Detection of alternative splicing: deep sequencing or deep learning?"

This dataset contains the junction data extracted by the aligners STAR and HISAT2 from 50M and 500M reads DCM data which was used as input for the tools and the prediction scores returned by the evaluated tools for the publication "Detection of alternative splicing: deep sequencing or deep learning?". The input data is necessary for reproducing the pipeline, whereas the output data contains results from our run of the evaluation pipeline. The code for tool evaluation and plots can be found here: https://github.com/lenamariahackl/deep-sequencing-vs-DL. The study addresses the question: Can we utilize the vast repository of publicly available RNA-seq data for AS detection, despite often lacking the sequencing depth typically required? We show that sequence-based tools such as DeepSplice and SpliceAI show promising performance in retrieving novel and unannotated splice junctions, even when RNA-seq data are limited, but are not suitable for de novo splice junction detection. Our results demonstrate the potential of sequence-based tools for initial hypothesis development and as additional filters in standard RNA-seq pipelines, especially when sequencing depth is limited. Nonetheless, validation with higher sequencing depths remains essential for confirmation of splice events.