arXiv：cs.LG（机器学习，全量分类）· Jason X. Liu, Sebastian Ibarraran, Frank Hu, Soojung Yang, Xinyu A. Feng, Abigail Park, Anagha Aneesh, Lacramioara Bintu, Alexander R. Dunn, Grant M. Rotskoff·· 14 小时前AI 评分42
IDiom：用稀疏自编码器特征强化生成内在无序蛋白区域
Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features
AI 导读
研究团队提出 IDiom，一个在 5400 万条 AlphaFold Database 预测 IDR 数据集 IDiom-DB 上训练的自回归蛋白质语言模型，并配套 RL-SAE 后训练方法，通过奖励激活指定特征集的序列来控制功能相关序列模式。
正文
Abstract:Intrinsically disordered protein regions (IDRs) play central roles in cellular processes such as transcriptional regulation, signal transduction, and subcellular localization, yet their functional design remains challenging. Structure-based design methods do not readily apply to IDRs, and existing protein language models are trained on full-length protein sequences, thus learning a prior that is biased towards folded domains. Here, we present IDiom, an autoregressive protein language model trained on IDiom-DB, a dataset of 54 million predicted IDRs curated from the AlphaFold Database. IDiom generates diverse sequences that recapitulate the composition, patterning, motifs, and predicted disorder of natural IDRs. To control function-associated sequence patterns, we also introduce reinforcement learning with sparse autoencoder features (RL-SAE), a post-training method that rewards the generation of sequences that activate specified feature sets. Across eight IDR design tasks, RL-SAE sequences activate, on average, 90% of 30 targeted features, compared to 24% for activation steering. We demonstrate that RL-SAE improves the predicted subcellular localization and transcriptional activity of generated IDRs compared to steering and supervised fine-tuning, and enables features associated with distinct biological functions to be combined within individual sequences. Thus, IDiom and RL-SAE enable interpretable and composable IDR design through explicit control of function-associated sequence features. More broadly, RL-SAE could extend to other protein design settings where interpretable features provide useful design targets. Code is available at this https URL.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02189 [cs.LG] |
| (or arXiv:2610.02189v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02189 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jason Liu [view email]
[v1]
Thu, 1 Oct 2026 17:59:20 UTC (5,830 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org