SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries

Darin Tsui (Georgia Institute of Technology) · Aryan Musharaf (Georgia Institute of Technology) · Amirali Aghazadeh (Georgia Institute of Technology) · Justin Kang (University of California, Berkeley) · Yigit Efe Erginbas (University of California, Berkeley)

computational costdna repair outcomesglobal biological insightsguide rna efficacyhigh-order feature interactionsinterpretable predictionsmarginal costmodel explanationmodel sketchingprotein fitnessshap zeroshapley valuessparse fourier transform

The growing adoption of machine learning models for biological sequences has intensified the need for interpretable predictions, with Shapley values emerging as a theoretically grounded standard for model explanation. While effective for local explanations of individual input sequences, scaling Shapley-based interpretability to extract global biological insights requires evaluating thousands of sequences—incurring exponential computational cost per query. We introduce SHAP zero, a novel algorithm that amortizes the cost of Shapley value computation across large-scale biological datasets. After a one-time model sketching step, SHAP zero enables near-zero marginal cost for future queries by uncovering an underexplored connection between Shapley values, high-order feature interactions, and the sparse Fourier transform of the model. Applied to models of guide RNA efficacy, DNA repair outcomes, and protein fitness, SHAP zero explains predictions orders of magnitude faster than existing methods, recovering rich combinatorial interactions previously inaccessible at scale. This work opens the door to principled, efficient, and scalable interpretability for black-box sequence models in biology.