Image-based DNA sequencing encoding for detecting low-mosaicism somatic mobile element insertions

Active mobile elements in the human genome can create novel mobile element insertions (MEIs) in somatic tissues. Detection of somatic MEIs, particularly those with low mosaicism, remains a significant challenge due to sequencing artifacts and alignment errors. Existing methods lack sensitivity or require biased manual inspection. Here we present RetroNet, a deep learning algorithm that encodes sequencing reads into images to identify somatic MEIs with as few as two reads. Trained on diverse datasets, RetroNet outperforms previous methods and eliminates the need for manual examinations. RetroNet achieves high precision (0.885) and recall (0.579) on a cancer cell line, detecting insertions in just 1.79% of cells. RetroNet is also effective for degraded DNA, like circulating tumor DNA. This tool is applicable to the rapidly generated short-read sequencing data and has the potential to provide further insights into the functional and pathological implications of somatic retrotranspositions. Detection of somatic mobile element insertions (MEIs), particularly those with low mosaicism, remains a significant challenge. This study presents RetroNet, a deep learning method that transforms sequencing reads into images to detect somatic MEIs, enabling accurate discovery of rare insertions with very low read support.