{"schema":"postcutoff/event@1","as_of":"2026-10-15T23:34:00+02:00","url":"https://postcutoff.com/e/2026-10-15-deepmind-antigravity-antimicrobial-peptide-walkthrough/","md":"https://postcutoff.com/e/2026-10-15-deepmind-antigravity-antimicrobial-peptide-walkthrough/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-15-deepmind-antigravity-antimicrobial-peptide-walkthrough","date":"2026-10-15","date_precision":"day","short_title":"Google DeepMind shows Antigravity as a science workbench","deck":"An agent finds and characterizes a candidate bacteriocin against Streptococcus pseudopneumoniae (wet-lab tests pending)","takeaway":"A DeepMind blog post walks through an Antigravity session (Gemini 3.8 Flash) that searched UniProt, annotated proteins with ProtNLM, checked novelty with BLAST, compared AlphaFold structures and genomic context, and proposed a mechanism and lab plan for a candidate antimicrobial peptide. No experimental results yet.","category":"science","category_label":"Science & math","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Google DeepMind blog: Accelerating the search for antimicrobial peptides with Google Antigravity","url":"https://deepmind.google/blog/accelerating-antimicrobial-discovery/","type":"official","group":"primary","domain":"deepmind.google"}],"official":1,"filed":"2026-10-15","updated":"2026-10-15","orgs":["Google DeepMind"],"title":"Google DeepMind shows Antigravity as a science workbench: an agent finds and characterizes a candidate bacteriocin against Streptococcus pseudopneumoniae (wet-lab tests pending)","summary":"On 15 Oct 2026 Google DeepMind researchers (Pengfei Tian, Maxwell Bileschi, Zoi Tsangalidou, Sukhdeep Singh, Lucy Colwell) published a walkthrough of Google Antigravity used as an \"agentic science workbench\". With Gemini 3.8 Flash the agent narrowed UniProt to a 97-residue Lactococcin 972-family bacteriocin from Streptococcus pseudopneumoniae, found no close reviewed homolog, matched its AlphaFold structure to a known bacteriocin fold, read its operon context, proposed a cell-division-targeting mechanism and drafted an experimental plan. The lead and other candidates are in wet-lab validation; no results are reported.","key_facts":["Authors: Pengfei Tian, Maxwell L. Bileschi, Zoi Tsangalidou, Sukhdeep Singh, Lucy J. Colwell (Google DeepMind); model selected in screenshots: Gemini 3.8 Flash","Candidate: UniProt A0A0U0D591, 97 amino acids, Lactococcin 972 family, from Streptococcus pseudopneumoniae (respiratory infections)","Pipeline inside one agent session: UniProt filtering → ProtNLM function prediction → BLAST against Swiss-Prot (EMBL-EBI) → AlphaFold model, remote structural homologs and superposition → genomic context (ABC transporter permease, ATP-binding partner, second bacteriocin, XRE regulator) → literature review → plan for expression, susceptibility, target-engagement and toxicity tests","Status: 'the lead and several other candidates' from the pipeline are in wet-lab validation; no hit rates or experimental data; no paper or code linked","New tool shown: a Biomolecular Structure Viewer embedded in Antigravity, a shared 3D workspace where researcher and agent annotate structures"],"key_numbers":[],"tags":["biology","antimicrobial-resistance","peptides","antigravity","agents","alphafold","gemini"],"science":null,"body_md":"## What happened\n\nDeepMind published a step-by-step account of one agentic research session in Antigravity, Google's agent IDE, used here for\nbiology rather than code. The agent searched protein databases, called domain tools (ProtNLM, BLAST, the AlphaFold\ndatabase), compared structures in an embedded 3D viewer and wrote up a mechanism hypothesis and an experimental plan for a\nbacteriocin-like peptide.\n\n## Why it matters\n\nIt shows Google positioning Antigravity as a general science workbench. The output is a hypothesis, though: no wet-lab\nresult is reported yet, so the post demonstrates a workflow, not a discovery.","disputed":[],"related":[{"id":"2026-09-02-gemini-3-8-flash","url":"https://postcutoff.com/e/2026-09-02-gemini-3-8-flash/","date":"2026-09-02","date_precision":"day","short_title":"Google releases Gemini 3.8 Flash and Gemini 3.8 Flash Cyber","deck":null,"takeaway":"Gemini 3.8 Flash caps an unusually fast cadence: 3.5 Flash (19 May), 3.6 Flash (21 Jul), 3.7 Flash (13 Aug), 3.8 Flash (2 Sep).","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":10,"official":9,"filed":"2026-09-29","updated":"2026-09-30","orgs":["Google DeepMind","Google"]},{"id":"2026-08-27-antigravity-teamwork-open-problems","url":"https://postcutoff.com/e/2026-08-27-antigravity-teamwork-open-problems/","date":"2026-08-27","date_precision":"day","short_title":"Google's Antigravity 'Teamwork' multi-agent framework with Gemini 3.7 Flash solves seven open CS/math problems, incl. part of Knuth's cycles problem","deck":null,"takeaway":"It is another data point in the summer-2026 wave of AI-assisted results on open problems.","category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":6,"official":6,"filed":"2026-09-30","updated":"2026-09-30","orgs":["Google","Google DeepMind"]},{"id":"2026-05-19-google-gemini-for-science","url":"https://postcutoff.com/e/2026-05-19-google-gemini-for-science/","date":"2026-05-19","date_precision":"day","short_title":"Google launches 'Gemini for Science' at I/O 2026","deck":"Co-Scientist, AlphaEvolve and ERA become products","takeaway":"Google's \"AI scientist\" systems moved from research demos to products.","category":"product","category_label":"Products","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":8,"official":7,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Google","Google DeepMind","Google Research"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-15","type":"filed","text":"Created (deepmind.google)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-15","run":null,"sources_read":null,"updated":"2026-10-15","human_review":null,"version":{"date":"2026-10-15"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":168,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":107,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":198,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":137,"in_training_data":false}],"short_url":null}