提出molFTP框架，实现快速无泄漏的分子片段特征构建。
Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction
- 用片段-靶点流行度向量表示分子，结合虚拟掩码防信息泄露。
- 关键留一法（key-LOO）误差低于8%，接近真实留一法性能。
- 适合需要高效训练与可靠评估的药物发现场景。
我们提出molFTP（分子片段-靶点流行度），一种紧凑的表示方法，具有优异的预测性能。为防止交叉验证中特征泄露，采用虚拟掩码机制，移除保留分子中出现的片段信息。进一步表明，关键留一法（key-LOO）在我们的数据集上与真实分子级留一法（LOO）的偏差低于8%，可实现接近全量数据训练的同时，保持无偏的模型性能估计。整体而言，molFTP提供了一种快速、抗泄漏的片段-靶点流行度向量化方案，通过虚拟掩码或key-LOO等实用防护措施，在远低于真实留一法成本的情况下近似实现留一法效果。
原文摘要 · Abstract (English)
We introduce molFTP (molecular fragment-target prevalence), a compact representation that delivers strong predictive performance. To prevent feature leakage across cross-validation folds, we implement a dummy-masking procedure that removes information about fragments present in the held-out molecules. We further show that key leave-one-out (key-loo) closely approximates true molecule-level leave-one-out (LOO), with deviation below 8% on our datasets. This enables near full data training while preserving unbiased cross-validation estimates of model performance. Overall, molFTP provides a fast, leakage-resistant fragment-target prevalence vectorization with practical safeguards (dummy masking or key-LOO) that approximate LOO at a fraction of its cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。