arXiv：cs.LG（机器学习，全量分类）· Maryam Rahimimovassagh, Ivan Garibay, Niloofar Yousefi·· 14 小时前AI 评分33
ORBIT-FMIB：追踪 ESM-2 中按阶分解的 epistatic 信息
ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2
AI 导读
研究者提出 ORBIT-FMIB 诊断框架，结合 Walsh 交互分解与子集条件神经依赖估计，用于探测蛋白质基础模型 ESM-2 各层表征中不同阶 epistatic 信息的保留情况。
正文
Abstract:Protein foundation models support mutation-effect and structural prediction, but predictive performance alone does not reveal which forms of biological interaction information remain accessible through model depth. We ask whether ESM-2 retains higher-order epistatic information as strongly as first- and second-order information across its representation hierarchy, introducing ORBIT-FMIB, a diagnostic framework combining Walsh-based interaction decomposition with subset-conditioned neural dependence estimation. The method is validated on synthetic landscapes with known interaction structure before being applied to the dense four-site GB1 fitness landscape using frozen ESM-2 representations.
An initial production run suggested ESM-2 retains higher-order epistatic information less well than lower-order information ($\Delta_{\mathrm{HO-LO}}=-0.107$). An independent replication of the complete measurement grid, under matched GPU hardware and identical critic seeds, substantially reduced this contrast ($\Delta_{\mathrm{HO-LO}}=-0.017$), and its sign was unstable across otherwise-defensible evaluation-pairing choices applied to the same trained critics ($-0.011$ to $+0.015$). We therefore do not currently have robust evidence that ESM-2 selectively loses higher-order epistatic information, nor that retention is equal across orders; the directional question remains open. The measurement protocol itself, including its documented removal of a positional-subset shortcut in pooled critics, remains validated and is unaffected by this finding. ORBIT-FMIB is offered as a diagnostic framework for probing interaction structure in protein foundation models; this study's own replication result illustrates why such probing requires adequately-powered reproducibility checks before its output is treated as a biological finding.
| Subjects: | Machine Learning (cs.LG); Quantitative Methods (q-bio.QM) |
| Cite as: | arXiv:2610.00672 [cs.LG] |
| (or arXiv:2610.00672v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00672 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Maryam Rahimimovassagh [view email]
[v1]
Wed, 30 Sep 2026 20:09:32 UTC (101 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org