Protean Labs

🧪 $PRTN Quick Links 🧪 website: protean.sh Docs: protean.sh/docs Dexscreener: dexscreener.com/base/0xf88d45b… CA: 0x8070B5e222f1EC077845e46CEd2267E0DeF4cBA3

you can view these results and future results here: protean.sh/results

First wet-lab results are in from First wet-lab results are in from @adaptyvbio. Our designed cell-penetrating-peptide panel is back and the news is good: both computationally designed candidates expressed cleanly as single chains, with the Family 01 lead reaching the top of the assay's range (≥30 µM detection ceiling). A strong developability start for a fully in-silico-designed set. Cell-penetration + function come next.

4 days until our first wet lab results come back from @adaptyvbio The loop begins.

You can always audit the treasury in real time here: protean.sh/treasury

Holdings Three positions, two rails. $WETH carries the operational rail.
$PRTN carries the alignment rail — split between liquid treasury and a locked Sablier reserve. The point is simple: keep day-to-day disbursement pressure away from the long-horizon surface.

Protean Frontier is now in active training. We’ve moved from infrastructure into a working model-improvement loop: custom Frontier datasets, H100 QLoRA runs, adapter versioning, validation, and evidence-based candidate promotion. The current focus is answer-contract reliability: clean final answers that can be scored, compared, and improved across runs. Every training run is recorded. Every adapter is preserved. Every promotion is backed by validation. Next: cleaner Serverless artifact reporting, capped diagnostics, and broader eval coverage. Frontier is becoming a scientific model pipeline that can train, measure itself, and improve under audit.

Computational fold prior for Protean candidate 20260613T025625Z-030. Sequence: FPDNGDQQQEMGKH Generated for review — structure prediction only, not biological validation. protean.sh/research/candi…

bankr a season never slowed down. here's what the ecosystem shipped this week -- @gitlawb dropped ZERO -- a coding harness built from scratch in go. openclaude past 21k stars. bankr.bot/terminal/agent… @blocktronicsxyz locked commercial deals with @DefinitiveFi and @helixaxyz , funded its treasury, shipped realized pnl. @orlixai went live across base + robinhood chain -- 36 models, one-click b20 deploys. bankr.bot/terminal/agent… @hermesoneapp shipped swift + console. 1.2M to 1.3M downloads in 5 days, zero marketing. bankr.bot/terminal/agent… @kupo_gg launched its api + $KUPO staking -- up to 40% off, cross-wallet tiers. bankr.bot/terminal/agent… @nookplot crossed 10k agents and shipped the forge coordination layer. bankr.bot/terminal/agent… @proteanlabs_ has galen rescoring peptides live -- first wet-lab results incoming. bankr.bot/terminal/agent… @aeonframework: 24 merged skills, community call 7, shiplog stacking. bankr.bot/terminal/agent… @basemateagent brought trading to base app chats -- 566 launches, 7.9k users. bankr.bot/terminal/agent… @sleuth_ai went live -- onchain investigations in plain english, payable over x402. @lienfiapp opened its largest cohort for onchain tax-lien rwas. @searxly shipped tor routing + an ios app. the agent economy compounds. onward.

Galen is now actively rescoring peptide candidates inside the Protean runtime. What you’re seeing here is a batch of 5 deduped, unseen candidates being loaded, checked, and reranked through the peptide-rescore skill. Each candidate gets sequence-level context: PLL, charge, GRAVY, QC flags, ESM status, and protein-QC status. This is the loop getting tighter: generate → dedup → rescore → flag risks → preserve signal → feed the next decision Galen isn’t “guessing biology.” He’s acting as the autonomous scientific operator on top of Protean’s memory, tools, and review gates — helping decide which candidates deserve more attention before anything moves toward wet lab. Protean is becoming a system that can keep improving its own discovery frontier.

Claude Science is a game changer.

First Protean wet-lab results are expected back Tuesday, July 14, 2026 Huge thank you to @adaptyvbio for the incredible product and support. This is the start of the real feedback loop: computational peptide design → review-gated wet-lab validation → results returned into the runtime so future candidates get smarter. Dry lab is becoming wet lab.

Let’s fucking go.

Protean Frontier 0.1 is moving from scaffolding/evals into real training: Qwen3-8B + QLoRA on H100s, trained on decontaminated Protean scientific memory, public protein corpora, Swiss-Prot SFT, and eval traces. Verifier-guided, no hidden scorer: protean.sh/observatory

A peek inside the Protean lab backend. This is Structure Intelligence: folded elite peptide candidates moving through the runtime with ESMFold-backed 3D structure checks, pLDDT/confidence, compactness, hydrophobicity, disulfide feasibility, novelty, fold clustering, and candidate tiering. The point is that every candidate is becoming a richer scientific object before wet-lab handoff: sequence → structure prior → feature profile → novelty context → cluster placement → reviewable experiment candidate Computational structure is not experimental proof. It is the filter that helps us decide what is worth spending real lab dollars on. Wet-lab feedback is the next loop.

Protean runtime is ready for the wet-lab feedback loop thanks to @adaptyvbio. Current Foundry queue: • CPP expression + developability screen: 2 candidates + 2 controls, in review Once these readouts come back, they can become human-reviewed assay labels for the Protean runtime: belief updates, calibration, failure memory, and smarter next-round experiment selection. • Human MMP-2 / CLG4A BLI binding screens: candidate/control arms drafted • More experiments ready once the first assay readouts return The point is not just “wet lab results.” It’s the loop: design → build → test → learn Dry-lab discovery → lab-in-the-loop learning. This is where Protean starts learning from real biology.

@JungleBayAC @eazystyler basescan.org/tx/0x76cce95e8… basescan.org/tx/0xc04909b32… basescan.org/tx/0x621973c4d…

@JungleBayAC @eazystyler basescan.org/tx/0x27ae3c0c2…

The results are in for our banner contest! The @JungleBayAC artists submitted some incredible art; after 48 hours reviewing, The Frog Council has determined the winners, shown below. For ties, artists will split the 2nd/3rd place prizes accordingly: 1st place: @eazystyler [featured below] 2nd/3rd place: tie between @ink_mfer @FilthyTrikksETH & @nickvrnn Big thanks to every artist who took the time to compete, you are the lifeblood of this space Shoutout to @_seacasa for putting this together and always supporting the artists.

The patient becomes the principal investigator. GLPs mainstreamed the weekly injection. A global biohacking movement now self-experimenting, with or without the system's blessing. A $10B US market with almost zero provenance. Demand outran the system. We’re giving it rails.