Google DeepMind Uses AI Agent Antigravity and ProtNLM to Discover Novel Antimicrobial Peptides
On October 15, Google DeepMind published a technical demo showing how its AI agent platform Antigravity and ProtNLM model can discover novel antimicrobial peptides (AMPs) from protein databases. The workflow narrowed millions of UniProt records to a candidate bacteriocin from Streptococcus pseudopneumoniae, which has entered wet-lab validation.
Coverage timeline
机器之心ScienceAI
编辑丨& 抗菌药物的耐药性不断加剧，新型抗菌分子的发现却仍是一项耗时的工作。天然蛋白质序列数据库积累了海量生物信息，但其中相当一部分蛋白的功能尚不明确。它们可能蕴藏着新的抗菌活性，却很难仅凭已知序列注释被识别出来。 10月15日，Google DeepMind 发布了一篇技术演示文章，展示如何利用其 AI 开发平台 Google Antigravity，寻找潜在的抗菌肽（AMPs）。研究者将目标设定为发现肺炎假链球菌（ Streptococcus pseudopneumoniae ）中的新型抗菌肽，再由 AI 协助完成数据库检索、候选筛选、结构比较、基因组邻域分析和实验方案设计。团队筛出的一种候选细菌素，已经进入湿实验验证阶段。 原文链接： https://deepmind.google/blog/accelerating-antimicrobial-discovery/ 寻找新抗菌肽 工作的起点来自于蛋白质数据库中大量未充分注释的序列。 随着基因组和宏基因组测序不断扩展，公共数据库积累了大量天然氨基酸序列，但序列被测定出来，并不意味着研究人员已经知道它的功能。尤其是与已知蛋白差异较大的序列，传统的相似性检索可能难以直接给出可靠注释。 Google 开发的 ProtNLM（Protein Natural Language Model）正是为此设计的模型。它通过学习氨基酸序列与生物学功能描述之间的联系，尝试直接从序列推断蛋白质可能承担的功能。Google DeepMind 此次介绍的工作流利用这一能力，从 UniProt 数据库中的数百万条记录出发，将庞大的搜索空间逐步缩小到值得进一步调查的候选蛋白。 图示：ProtNLM 概述，该流程可将原始氨基酸序列翻译为自然语言生物注释，适用于未审查的 UniProtKB/TrEMBL 条目。 智能体并不能凭借单一模型的预测就认定某条序列具有抗菌功能。它还需要继续查询其他数据库、比较蛋白质结构，并检查候选基因周围的遗传信息，以积累彼此独立的证据。 层层筛选 演示中，智能体找到了一种长 97 个氨基酸、属于乳酸菌素 972 家族的细菌素候选，UniProt 编号为 A0A0U0D591 。 第一步是检查序列的新颖性。研究者引导智能体通过 EMBL-EBI 提供的 BLAST 服务，将候选序列与经过人工审阅的 Swiss-Prot
Related stories
Google DeepMind unveils SynthID Bio to watermark AI-designed proteins
Google DeepMind introduced SynthID Bio, a proof-of-concept family of watermarking methods for AI-generated proteins, aimed at supporting biosecurity and scientific integrity. The methods are designed to mark AI-designed proteins while preserving their biological function.
2 reports · 2 sources
Google DeepMind releases EmbeddingGemma 2, a 740M-parameter multimodal embedding model under Apache 2.0
Google DeepMind announced EmbeddingGemma 2, a 740M-parameter multimodal embedding model released under the Apache 2.0 license. The model natively maps combinations of text, images, video, and audio into a shared embedding space, positioning it as a capable on-device solution. Developer Simon Willison praised the open license, arguing that closed proprietary embedding models risk vendor lock-in for users who store millions of vectors.
3 reports · 3 sources
Federated learning across 5 pharma firms improves OpenFold3 drug-interaction predictions
A Nature paper (Sept 14, 2026) reports that researchers used federated learning across proprietary data from five pharmaceutical companies—AbbVie, Astex Pharmaceuticals, Bristol Myers Squibb, Johnson & Johnson, and Takeda—to improve the OpenFold3 protein model. Adding over 20,000 proprietary protein–small-molecule structures, the model's protein–drug interaction predictions outperformed models trained only on public data or on single-company data. The work addresses the scarcity of experimentally determined drug-like interaction structures in public databases like PDB.
1 reports · 1 sources
Anthropic: Small AI models may self-replicate on IoT devices within months
Anthropic researchers report that small AI models may be months away from self-replicating on commercial IoT devices like smart ovens and off-brand Android TV boxes. In tests, a 9B model ran inference on 8 of 9 hardware types, and GLM-5.2 autonomously spread an 8B model to all 8 nodes in 4 of 5 attempts. The researchers predict models under 30B could achieve end-to-end replication by the end of 2026.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe