English(EN) Protein Language Models Fail To Capture Contact Predictions Under Invariant Relabeling

蛋白质语言模型在重标定下的接触预测测试中失败

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

一篇新近发表在arXiv上的研究表明，当氨基酸字母表被任意重标定时，蛋白质语言模型（pLMs）在准确预测蛋白质接触方面表现不佳。尽管Potts模型等经典方法对此类转换保持不变，但各种架构和规模的pLMs，包括ESM-2和MSA Transformer，在接触图准确性方面均出现显著下降。这表明pLMs依赖于特定的残基身份，而非纯粹的共演化统计数据，突显了这些模型计算接触方式的差异及其表示中的潜在偏差。 AI

影响强调了蛋白质语言模型中存在的潜在偏差，表明需要超越标准基准的更鲁棒的评估方法。

排序理由学术论文，详细介绍了评估蛋白质语言模型的新诊断框架。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了评估蛋白质语言模型的新诊断框架。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Paarth Batra, Aryan Keluskar · 2026-11-14 05:00

蛋白质语言模型在不变重标记下无法捕捉接触预测

arXiv:2611.16881v1 Announce Type: cross Abstract: Protein language models (pLMs) produce highly accurate contact maps from single-sequence inputs. People often take this accuracy as proof that these models implicitly learn invariant coevolutionary statistics, extracting the same …

本文如何被排名

报道来源 [1]

蛋白质语言模型在不变重标记下无法捕捉接触预测

相关实体

相关话题