Generalizing deep variant callers via domain adaptation and semi-supervised learning

Deep learning-based variant callers (DVCs) offer state-of-the-art perfor-mance in small variant detection from DNA sequencing data. However, their reliance on supervised learning and the subsequent need for exten-sive labeled data pose a potential hurdle to their generalizability across diverse sequencing methods with varying error profiles. Indeed, even minor discrepancies in error profiles can compromise the robustness of DVCs and impair the variant calling accuracy in the target sequencing method. To mitigate these challenges, we propose RUN-DVC, the first semi-supervised training approach for DVCs that presents two complemen-tary training techniques to the conventional supervised training approach. RUN-DVC leverages semi-supervised learning techniques to learn error profiles from unlabeled datasets of the target sequencing method as well as a domain adaptation technique to aid semi-supervised learning by reducing the domain discrepancy due to different error profiles. We ana-lyze and contrast RUN-DVC against the supervised training approach under various generalization scenarios using nine sequencing methods from Illumina, BGI, PacBio, and Oxford Nanopore sequencing platforms. Remarkably, RUN-DVC significantly improves the variant calling accu-racy of DVC in the target sequencing method even with purely unlabeled datasets in the target domain and enables label-efficient generalization when partially labeled datasets are available. Our results suggest RUN-DVC is a promising semi-supervised training method for DVCs with the potential to broaden the use of DVC across diverse sequencing methods.