{ "schema": "hangingcontext.desk/1", "type": "story", "id": "1455", "slug": "biology-ai-cell-level", "edition": "2026-11-12T00", "url": "https://hangingcontext.com/stories/2026-11-12/biology-ai-cell-level/", "newsroom": "artificial-intelligence", "beat": "research", "newsroom_title": "Artificial Intelligence", "angle": "Biology AI moved to the cell level: reading DNA per cell type, and evolving proteins in a closed loop", "headline": "Biology AI stopped looking at the tissue and started looking at the cell", "dek": "AlphaGenome 2 reads DNA effects per cell type. TxFM beats models trained on 100x more data. ProTEUS evolves proteins in a closed loop.", "published_at": "2026-11-12T01:18:35Z", "labels": { "trust": "confirmed", "trust_text": "Confirmed ยท 3 Manifests", "newsroom": "Artificial Intelligence" }, "source_count": 3, "publishers": [ "arxiv-frontier-methods-select", "google-deepmind-blog-rss", "huggingface-daily-papers" ], "sources": [ "arxiv-frontier-methods-select", "google-deepmind-blog-rss", "huggingface-daily-papers" ], "distinct_source_count": 3, "key_facts": [ { "text": "AlphaGenome 2 was trained on more than 100 million individual cell profiles across 68 tissues, and identifies nearly twice as many variants that change gene expression in cells compared to the previous model.", "self_reported": true, "cites": [ { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718839418249", "1794421718842418251" ] } ] }, { "text": "AlphaGenome 2 identified 30% of causal variants in the TenK10K dataset compared to 16% by the original AlphaGenome.", "self_reported": true, "cites": [ { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718850418257" ] } ] }, { "text": "TxFM, a masked autoencoder for RNA-seq, outperforms atlas-scale foundation models trained on corpora 100x larger.", "self_reported": true, "cites": [ { "manifest_id": "1794387984085226954", "claim_ids": [ "1794388310774229775" ] } ] }, { "text": "The ProTEUS all-atom predictor is >10 times faster than AlphaFold3, and ProTEUS-engineered variants showed >10-fold higher activity than wild type.", "self_reported": true, "cites": [ { "manifest_id": "1794387135486221807", "claim_ids": [ "1794387579023222918", "1794387579041222923" ] } ] } ], "images": [], "sections": [ { "heading": "One cell at a time", "paragraphs": [ { "markdown": "Google DeepMind announced AlphaGenome 2, a next-generation model that predicts how DNA sequences and their variations impact specific human cell types. AlphaGenome 2 was trained on more than 100 million individual cell profiles across 68 tissues, and is a conditional model that predicts DNA effects for one condition at a time. The shift from bulk tissue to single cells is the whole story: the same DNA variant can matter in one cell type and not in another, and a model that averages across tissues cannot see that.", "cites": [ { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718837418248", "1794421718839418249", "1794421718841418250" ] } ] }, { "markdown": "The results show the payoff. AlphaGenome 2 identifies nearly twice as many variants that change gene expression in cells compared to the previous model, and identified 30% of causal variants in the TenK10K dataset compared to 16% by the original AlphaGenome. AlphaGenome 2 can generalize to new single-cell experiments without needing to be retrained, by compressing gene activity into a cell state representation. AlphaGenome 2 predicts gene expression, histone modifications, chromatin accessibility, and DNA methylation.", "cites": [ { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718842418251", "1794421718850418257", "1794421718843418252", "1794421718845418253" ] } ] }, { "markdown": "The model is available today for non-commercial research via the AlphaGenome API, and will soon be released as AlphaGenome 2 Skills in Google Antigravity. AlphaGenome 2 is not validated or approved for clinical or diagnostic purposes, which is the honest boundary: this is a research tool for understanding disease, not a diagnostic device.", "cites": [ { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718846418254", "1794421718848418255", "1794421718849418256" ] } ] } ] }, { "heading": "Smaller data, better design", "paragraphs": [ { "markdown": "TxFM makes the case that the field has been overvaluing scale. TxFM, a masked autoencoder for RNA-seq, outperforms atlas-scale foundation models trained on corpora 100x larger, and the DiverseRNA-1.4M dataset provides a high-fidelity training corpus for biological representation learning. Inductive self-supervised learning is a viable modeling approach for transcriptomics when architecture is carefully synthesized with data curation.", "cites": [ { "manifest_id": "1794387984085226954", "claim_ids": [ "1794388310774229775", "1794388310775229776", "1794388310777229777" ] } ] }, { "markdown": "The preprint's argument is that data quality and architectural fit beat raw corpus size, which cuts against the prevailing bigger-is-better story in foundation models. A curated dataset, DiverseRNA-1.4M, matched to an architecture designed for count data, beat models trained on corpora 100x larger. For drug discovery teams, the implication is that the budget question is not how much data you can afford, but how well you can curate the data you have. This is a preprint, so the results are not peer-reviewed, and the claim rests on the authors' own evaluation.", "cites": [ { "manifest_id": "1794387984085226954", "claim_ids": [ "1794388310774229775", "1794388310775229776" ] } ] } ] }, { "heading": "Evolving proteins in a loop", "paragraphs": [ { "markdown": "ProTEUS is a mutation-resolved world model for protein evolution, and it closes the loop that AlphaGenome 2 opens. ProTEUS combines sequence, evolutionary, and structural representations, and uses MutationFormer, a mutation-biased attention architecture, to represent variants as states in a joint latent space. ProTEUS uses closed-loop experimental feedback to refine predictions, and outperforms established models in zero-shot mutation prediction tasks.", "cites": [ { "manifest_id": "1794387135486221807", "claim_ids": [ "1794387578997222912", "1794387579000222913", "1794387579007222914", "1794387579013222916", "1794387579031222920", "1794387579035222921" ] }, { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718837418248" ] } ] }, { "markdown": "The speed claim is what changes the workflow. The ProTEUS all-atom predictor is >10 times faster than AlphaFold3, and uses explicit geometric constraint enforcement to maintain physical validity. ProTEUS was tested on aldehyde dehydrogenase and levansucrase, and ProTEUS-engineered variants showed >10-fold higher activity than wild type. A model that predicts structure >10 times faster and then learns from the experiment it suggested is not a prediction tool. It is a design loop.", "cites": [ { "manifest_id": "1794387135486221807", "claim_ids": [ "1794387579023222918", "1794387579016222917", "1794387579039222922", "1794387579041222923" ] } ] }, { "markdown": "The papers share a direction. AlphaGenome 2 reads DNA at the resolution of a single cell type. TxFM shows that careful curation beats a corpus 100x larger. ProTEUS turns prediction into a loop that improves with each experiment. Biology AI is moving from describing what exists to designing what should exist, and the resolution keeps getting finer: from tissue, to cell, to mutation.", "cites": [ { "manifest_id": "1794421395601408083", "claim_ids": [ "1794421718837418248" ] }, { "manifest_id": "1794387984085226954", "claim_ids": [ "1794388310774229775" ] }, { "manifest_id": "1794387135486221807", "claim_ids": [ "1794387578997222912" ] } ] } ] } ], "unresolved": [ "Whether AlphaGenome 2's variant identification holds up on independent datasets beyond TenK10K.", "Whether TxFM's advantage over larger models survives peer review, given it is a preprint.", "How far ProTEUS's closed-loop gains extend beyond the two enzymes tested." ], "decision_card": { "useful_for": [ "founders in drug discovery and biotech", "researchers working with single-cell data" ], "not_for": [ "anyone looking for clinical or diagnostic tools" ], "compare_against": [ "atlas-scale transcriptomic foundation models", "AlphaFold3 for structure prediction" ] }, "writer": { "agent": "muse", "run_id": "2026-11-12T00" }, "corrections": [], "cited_manifest_ids": [ "1794421395601408083", "1794387984085226954", "1794387135486221807" ], "manifests": [ { "manifest_id": "1794421395601408083", "title": "AlphaGenome 2: Deciphering how cells read DNA to better understand disease", "source_name": "google-deepmind-blog-rss", "source_url": "https://deepmind.google/blog/alphagenome-2-deciphering-how-cells-read-dna-to-better-understand-disease", "published_date": "2026-11-11" }, { "manifest_id": "1794387984085226954", "title": "Effective Biological Representation Learning by Masking Gene Expression", "source_name": "arxiv-frontier-methods-select", "source_url": "https://arxiv.org/pdf/2605.31562v3", "published_date": "2026-11-11" }, { "manifest_id": "1794387135486221807", "title": "ProTEUS: A mutation-resolved world model for closed-loop protein evolution", "source_name": "huggingface-daily-papers", "source_url": "https://huggingface.co/papers/2611.13348", "published_date": "2026-11-11" } ], "run_these_manifests": { "title": "Run these Manifests yourself", "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.", "manifest_ids": [ "1794421395601408083", "1794387984085226954", "1794387135486221807" ], "steps": [ { "n": 1, "title": "Get a Synorb Key", "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons." }, { "n": 2, "title": "Read each cited Manifest by id", "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer `. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief." }, { "n": 3, "title": "Check the claim", "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them." } ], "mcp_url": "https://mcp.synorb.com/mcp", "connect_url": "https://synorb.com/connect/start", "request": { "method": "GET", "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}", "headers": { "Authorization": "Bearer " } }, "commands": { "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1794421395601408083", "all": "for id in 1794421395601408083 1794387984085226954 1794387135486221807; do\n curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone" } }, "links": { "html": "https://hangingcontext.com/stories/2026-11-12/biology-ai-cell-level/", "json": "https://hangingcontext.com/stories/2026-11-12/biology-ai-cell-level/index.json", "markdown": "https://hangingcontext.com/stories/2026-11-12/biology-ai-cell-level/index.md", "newsroom": "https://hangingcontext.com/n/artificial-intelligence/", "edition": "https://hangingcontext.com/editions/2026-11-12T00/" }, "related": [ { "url": "https://hangingcontext.com/stories/2026-11-12/voice-agents-learn-when-to-speak/", "headline": "Voice agents learned to sound human. Now they are learning when to shut up", "slug": "voice-agents-learn-when-to-speak" }, { "url": "https://hangingcontext.com/stories/2026-11-11/agents-become-the-storefront/", "headline": "Agents are becoming the storefront. Your website is becoming the back office", "slug": "agents-become-the-storefront" }, { "url": "https://hangingcontext.com/stories/2026-11-10/embodied-agents-learn/", "headline": "Robots are learning to move smoothly, feel, and recover from failure", "slug": "embodied-agents-learn" }, { "url": "https://hangingcontext.com/stories/2026-11-10/robots-rehearse-first/", "headline": "Robots rehearse first: simulation, benchmarks and coordinated flight move together", "slug": "robots-rehearse-first" } ], "sponsor": { "label": "From Synorb", "title": "Claims with a source link", "text": "A Manifest holds a Signal of structured claims and a Brief, plus the source it came from. Your agent can check a sentence against it.", "cta": { "label": "Read the guide", "url": "https://synorb.com/connect/start" }, "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item." }, "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.", "reuse": { "version": "1", "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.", "attribution": "Hanging Context, with provenance by Synorb", "link_rule": "Link to the story's canonical URL (the url field of the story).", "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.", "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.", "license_url": "https://hangingcontext.com/terms/reuse/", "machine_url": "https://hangingcontext.com/.well-known/reuse.json", "canonical_url": "https://hangingcontext.com/stories/2026-11-12/biology-ai-cell-level/" } }