用蛋白互作结构预测基因功能关联，比表达相似性更准。
Beyond Expression Similarity: Contrastive Learning Recovers Functional Gene Associations from Protein Interaction Structure
- 基于共现关系的对比学习，从蛋白互作中挖掘功能关联。
- 在多个数据集上跨边界预测准确率超0.9，远超表达相似性。
- 适合研究未充分探索的基因功能，尤其适用于生物物理关联场景。
预测关联记忆框架认为，有用关系往往来自共享上下文中的共现，而非嵌入空间中的相似性。在文本领域，基于共现标注训练的对比多层感知机（CAL）提升了多跳文档检索并发现语篇功能。本研究检验该原则是否适用于分子生物学：蛋白-蛋白互作提供与基因表达相似性不同的功能关联。在两个生物领域开展四项实验，涵盖基因扰动数据（Replogle K562 CRISPRi，2,285个基因），CAL模型在STRING蛋白互作上训练，跨边界AUC达0.908，而表达相似性仅0.518；另一基因数据集（DepMap，17,725基因）经负样本校正后，交叉边界AUC达0.947。两项药物敏感性实验生成有效负样本，明确边界条件。三类跨域发现：(1) 生物学中归纳迁移成功——节点不重叠划分下新基因预测AUC为0.826（+0.127），优于文本领域（±0.10），表明物理基础关联更具可迁移性；(2) CAL得分与互作度呈负相关（斯皮尔曼r = -0.590），增益集中在互作谱较聚焦的低研究基因；(3) 更高关联质量胜过更大但噪声更多数据集，逆转了文本领域的趋势。结果在不同训练种子（标准差<0.001）和阈值选择下稳定。
原文摘要 · Abstract (English)
The Predictive Associative Memory (PAM) framework posits that useful relationships often connect items that co-occur in shared contexts rather than items that appear similar in embedding space. A contrastive MLP trained on co-occurrence annotations--Contrastive Association Learning (CAL)--has improved multi-hop passage retrieval and discovered narrative function at corpus scale in text. We test whether this principle transfers to molecular biology, where protein-protein interactions provide functional associations distinct from gene expression similarity. Four experiments across two biological domains map the operating envelope. On gene perturbation data (Replogle K562 CRISPRi, 2,285 genes), CAL trained on STRING protein interactions achieves cross-boundary AUC of 0.908 where expression similarity scores 0.518. A second gene dataset (DepMap, 17,725 genes) confirms the result after negative sampling correction, reaching cross-boundary AUC of 0.947. Two drug sensitivity experiments produce informative negatives that sharpen boundary conditions. Three cross-domain findings emerge: (1) inductive transfer succeeds in biology--a node-disjoint split with unseen genes yields AUC 0.826 (Delta +0.127)--where it fails in text (+/-0.10), suggesting physically grounded associations are more transferable than contingent co-occurrences; (2) CAL scores anti-correlate with interaction degree (Spearman r = -0.590), with gains concentrating on understudied genes with focused interaction profiles; (3) tighter association quality outperforms larger but noisier training sets, reversing the text pattern. Results are stable across training seeds (SD < 0.001) and cross-boundary threshold choices.
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。