Comprehensive review and assessment of multi-species splicing variant prediction: task-specific deep learning models...

Alternative splicing generates transcriptomic and proteomic diversity essential for eukaryotic complexity, yet genetic variants disrupting the splicing code underlie numerous human diseases. Deep learning (DL) models and genomic foundation models (GFMs) have achieved outstanding accuracy for predicting splicing variant effects in humans. However, their transferability to non-human species remains poorly understood, limiting applications in agricultural genomics, comparative biology, and non-model organism research, where experimentally validated variant datasets are limited or lacking. In this study, we comprehensively reviewed 35 computational approaches in terms of their architectural characteristics for splicing site and variant prediction and analysis. We systematically benchmarked the performance of 10 representative models for splicing variant prediction across human, rat, pig, and chicken, including four task-specific DL models and six GFMs, using our manually assembled benchmark datasets. Our benchmarking results revealed a substantial cross-species performance decrease (~21%-33% in the area under the receiver operating characteristic curve - AUROC) using task-specific models from human to non-human species datasets. We then applied a supervised adaptation to frozen GFM embeddings (DNABERT-2, Evo 2, Genos) by adding a lightweight classifier (i.e. a multi-layer perceptron) and reduced the cross-species performance decrease for rat and pig (8.56%-23.84% in AUROC), while performance on chicken was very close to human (decline within 1%, even exceeding by 0.52% when using the Evo 2 embedding). We proposed several directions to improve the prediction performance of splicing variants, including feature representation transfer and multi-modal fusion integrating global context, universal embeddings, and species-aware conditioning. We hope our comprehensive review and performance benchmarking can provide useful computational insights for further advancement of splicing variant prediction.