Rising antimicrobial resistance is one of the most pressing global health crises of our time and could result in an estimated 10 million annual deaths globally by 2050. New antibiotics are urgently needed, but searching for new therapeutics is often a slow, labor-intensive process. With Google Antigravity, our agentic development platform, this process can now be made easier. Google Antigravity provides an agentic science workbench that empowers biologists to discover, structurally evaluate, and prioritize promising targets quickly, compressing what used to be a fragmented search over multiple databases into a single session.
Antimicrobial peptides (AMPs), particularly bacteriocins, offer a promising alternative to traditional antibiotics because they have naturally evolved to target fundamental vulnerabilities in competing bacteria, making it difficult for pathogens to develop resistance. Many billions of natural sequences remain locked within the unannotated "dark matter" of protein databases. To bridge this gap, Google developed Prot NLM (Protein Natural Language Model), a deep learning model trained to read the evolutionary "grammar" of amino acid sequences. It enriches millions of previously unnamed UniProt entries with high-confidence functional labels.
Working in Antigravity, a researcher and an AI agent set a focused biological goal: find and computationally validate novel AMPs in Streptococcus pseudopneumoniae. The researcher steers the scientific strategy, while the agent handles cross-database orchestration, structural analysis, and literature synthesis. The resulting candidate shows predicted activity against pathogens involved in respiratory tract infections. It is now undergoing wet-lab validation.
The approach lowers the barrier to everyday biological workflows, letting researchers move from sequence data to prioritized candidates far faster than before.
Source: Google DeepMind Blog · Summarized by HeadlinesBriefing