TY - RPRT TI - Detecting and avoiding homology-based data leakage in genome-trained sequence models AU - Rafi, A. M. AU - Kiyota, B. AU - Yachie, N. AU - de Boer, C. G. PY - 2025 DO - 10.1101/2025.01.22.634321 UR - https://www.biorxiv.org/content/10.1101/2025.01.22.634321v1 ID - 10.1101/2025.01.22.634321 ER -