Coarse composition suffices: tabular in-context learning for multi-activity antimicrobial peptide profiling

📄 arXiv: 2608.30337v1 📥 PDF

作者: Raunak Kumar, Anuj Pal, Dhruvi Solanki, Parikshit Pareek, Juhi Singh, Jitin Singla

分类: cs.LG, q-bio.BM

发布日期: 2026-08-31


💡 一句话要点

提出基于表格的上下文学习方法以解决多标签抗菌肽活性预测问题

🎯 匹配领域: 支柱八:物理动画 (Physics-based Animation) 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 抗菌肽 多标签预测 表格学习 上下文学习 生物信息学 药物发现 深度学习

📋 核心要点

  1. 现有的多标签抗菌肽活性预测方法通常依赖复杂的深度学习模型,训练成本高且难以调优。
  2. 论文提出了一种基于序列的简单管道,结合可解释的序列描述符与TabPFN模型,实现高效的上下文预测。
  3. 在ESCAPE基准上,所提方法在每个标签上同时达到或超过最佳平均精度,且在远亲同源体上提升显著。

📝 摘要(中文)

抗菌肽(AMPs)通常对多种病原体类别具有活性,因此多标签活性预测比二元抗菌分类更具现实意义。ESCAPE基准正式化了这一设置,但现有方法通常依赖于多模态、结构条件的深度模型,训练和调优成本高昂。我们展示了一种简单的仅基于序列的管道,通过结合330个可解释的序列描述符与TabPFN,一个无需基于梯度的训练或超参数搜索的表格基础模型,能够匹配并超越这些方法。在ESCAPE数据集上,标签-幂集TabPFN模型实现了mAP-5 = 77.8%,超越了之前报告的72.1%。

🔬 方法详解

问题定义:本论文旨在解决抗菌肽的多标签活性预测问题,现有方法通常依赖于复杂的多模态深度学习模型,训练和调优成本高,且难以解释。

核心思路:论文提出了一种仅基于序列的简单管道,通过结合330个可解释的序列描述符与TabPFN模型,能够在单次前向传播中进行上下文预测,无需梯度训练或超参数搜索。

技术框架:整体架构包括数据预处理、特征提取、模型训练和预测四个主要模块。特征提取阶段使用可解释的序列描述符,模型训练阶段采用TabPFN进行高效的上下文学习。

关键创新:最重要的技术创新在于使用TabPFN模型进行表格数据的上下文学习,显著降低了训练成本,并且在多标签预测中表现优异,超越了现有的深度学习方法。

关键设计:在模型设计中,使用了330个可解释的序列描述符,且通过标签依赖建模来提高稀缺活性的预测效果,确保模型在推理时不依赖于预测结构。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

实验结果显示,标签-幂集TabPFN模型在ESCAPE基准上实现了77.8%的mAP-5,超越了之前的最佳结果72.1%。此外,首次实现了在每个标签上同时达到或超过最佳平均精度,特别是在远亲同源体上提升了11.2个百分点。

🎯 应用场景

该研究具有广泛的应用潜力,尤其是在药物发现和生物医学领域。通过高效的多标签活性预测,能够加速抗菌肽的筛选过程,帮助研究人员更快地识别有效的抗菌剂,进而推动新药的开发与应用。

📄 摘要(原文)

Antimicrobial peptides (AMPs) often act against multiple pathogen classes, making multi-label activity prediction a more realistic screening target than binary antimicrobial classification. The ESCAPE benchmark formalizes this setting, but leading approaches typically rely on multimodal, structure-conditioned deep models that are costly to train and tune. We show that a simple, sequence-only pipeline can match and surpass these methods by combining 330 interpretable sequence descriptors with TabPFN, a tabular foundation model that performs in-context prediction in a single forward pass without gradient-based training or hyperparameter search. On ESCAPE (82,359 peptides; five labels), a label-powerset TabPFN model achieves mAP-5 = 77.8%, improving on the previously best reported 72.1%. A probabilistic classifier chain is the first method to match or exceed the best published average precision on each of the five labels simultaneously. The gains persist under the prior state-of-the-art single-fold training protocol, indicating they are not a training-set-size artefact, and are largest for remote homologues (+11.2 points below 30% sequence identity). Ablations further show that predicted structure is unnecessary at inference and that performance is not driven by any single descriptor family: ten global physicochemical scalars recover 91% of full-feature performance. Finally, explicitly modelling label dependence yields targeted benefits for scarce activities and supports ranking which activity to assay next from partial positive evidence.