2024/10/25 by Darin Tsui, Aryan Musharaf, Tsui, Darin +7 · 1 voice · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Cancer Genomics and Diagnostics #Computation (stat.CO) #Computational Engineering #Evolution and Genetic Dynamics #FOS: Biological sciences #FOS: Computer and information sciences #Finance #Gene expression and cancer classification #Genomics (q-bio.GN) #Machine Learning (cs.LG) #and Science (cs.CE) #cs.CE #cs.LG #q-bio.GN #stat.CO
paper · pdf · doi:10.48550/arxiv.2410.19236
openalex publication_date 2024/10/25 · arxiv published 2024/10/25 · openalex created_date 2024/11/14 · arxiv updated 2025/05/22 · openalex updated_date 2026/07/28
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.