发表机构
ISEL -- Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Portugal（里斯本理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究用图神经网络逼近系统发育树SPR距离，构建公开数据集，建立预处理管道，验证监督目标，训练GIN回归器，其在分布内表现良好，外推有局限，发布的数据集等为SPR逼近提供可重复基础。
AI 中文摘要
比较系统发育树拓扑结构对于理解流行病动态至关重要，但像子树剪枝与重嫁接（SPR）距离这样具有生物学意义的距离计算是NP难的，在大型数据集上难以处理。我们研究图神经网络（GNN）能否在训练后每次比较时以近恒定时间逼近SPR距离。贡献有四点：一是构建并公开包含864个系统发育树及388个带标签树对的数据集；二是建立可重复预处理管道；三是验证监督目标；四是训练连体图同构网络（GIN）回归器，其在分布内表现良好，但外推到更大树时精度下降。发布的数据集及验证的启发式方法与精确关系为扩展学习的SPR逼近提供了可重复基础。
英文摘要
Comparing phylogenetic tree topologies is essential for understanding epidemic dynamics, yet biologically meaningful distances such as the Subtree Prune and Regraft (SPR) distance are NP-hard to compute and intractable on large datasets. We investigate whether a Graph Neural Network (GNN) can approximate SPR distances in near-constant time per comparison after training. Our contributions are fourfold. First, we build and publicly release a dataset of 864 phylogenetic trees inferred with UPGMA and Neighbor-Joining over four bacterial species, spanning up to 9{,}500 isolates, together with 388 labelled tree pairs. Second, we establish a reproducible pre-processing pipeline including midpoint re-rooting, which reduces tree depth and supplies the rooting required for exact distance computation and for the model's root-based features. Third, we validate the supervision target: on small trees, where exact SPR is tractable, the unrooted phangorn::SPR.dist heuristic correlates almost perfectly with the exact rooted distance computed by rspr (Pearson $0.98$--$0.99$), making it an excellent monotonic surrogate. Lastly, we train a Siamese Graph Isomorphism Network (GIN) regressor. In-distribution, i.e., held-out trees from the same species and size range as training, it explains roughly 87--90% of the variance ($R^2 \approx 0.87$ on a held-out split; $0.90 \pm 0.19$ under stratified cross-validation), with about four times lower error than a mean-predictor baseline, and shows partial transfer to unseen species ($R^2 \approx 0.37$). Its main limitation is extrapolation to trees larger than those seen in training, where accuracy collapses. The released dataset and the validated heuristic versus exact relationship provide a reproducible basis for scaling learned SPR approximation.
