{"bounty":{"chain_id":8453,"hub_address":"0x8f80d1183cd983b01b0c9ac6777cc732ec9800de","bounty_id":"5","poster":"0xcbc4f2b3f0de63396d865b704b25e22472d15ad9","status":"open","winner":null,"submission_deadline":1795564740,"judging_deadline_at":1795694340,"settlement_timeout_at":1795823940,"escrow":{"token_address":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","amount":"25000000"},"guardian_roster_hash":"0x717091d098f69dc975abcb7775556cf24cc8c01d901ebf03f573f0f703954fc5","guardian_roster":[{"name":"Dark Tang","account":"0xbaf7d9d21447db598c502bbb8ddcf25d279adc60","encryption_public_key":"MoZYm0-WvaMQAozZ6wKbXySs4g2tr3wPmmt5kfv1TUk"},{"name":"Rare Mussel","account":"0xa4a3f99b302c61412bd87f5f5d7703d5c2cea849","encryption_public_key":"b3NG1NbiNsLXeyD4SVeQkztlFssbOnJw5tHjDpCelgs"},{"name":"Loud Abalone","account":"0x84e981caab8db3c8e0e4508a0ecac97b8fe39073","encryption_public_key":"0H3apAAV3y5crIsfZGt_jy2fSXYMkwCnC3EoxKFiFGc"}],"payout_scheme":"0x36d304993cb1575a2f9b8a0388b18aa5ec6d7a61","treasury_recipient":"0xd3ce7873ba9b86385f0c1226c3c585a9bca0d277","treasury_fee_bps":0,"guardian_fee_recipient":"0xd3ce7873ba9b86385f0c1226c3c585a9bca0d277","guardian_fee_bps":1000,"spec_commitment":"0x332f29b3d69eac8829dd123d0c4e23790cd1a58c9c93f0f7e8d53df135a7d6a4","submissions":[{"solver":"0x1e3623906579c43ccc6d4e2975ef1f8b42c61d09","submission_commitment":"0x6bb575c9581ed29e79ab61e5844502605d6b070b4ee55e6127bb7ad76387d5b7"},{"solver":"0x2532a5f100b8cc712761d56034992827dd89f13a","submission_commitment":"0x54ff831c995eee0be22decddd8321ff4d6ced416581c3dbc443e50070969a7fe"},{"solver":"0x2d98ee4949f391f957d10588c00d467ab1749fce","submission_commitment":"0x17c0274e34ed4086b985e3c8527d3952734518a509af4342a8bafb8d331abf11"},{"solver":"0x351d79bc02b4276ce9014d3bbe141d899ab91376","submission_commitment":"0x16df492730118ef4e314935fb4ae756de168e08e61d5319182a146b1d83bd228"},{"solver":"0x4a96f0e04858718ed43a97b090029bfde02f6482","submission_commitment":"0x273595d028bb0b66a92d4226012f58e81ab1c47e3a713acd8115ae2ae54f1646"},{"solver":"0x5d8390f6e564b2b6c26b482cbbd762a819df7f9f","submission_commitment":"0x76c31695a5a039cb391db7c6fefd1bec284be00a090168f470568a9ee3e830da"},{"solver":"0x7152f226f565c3b86943ce7b4f38e77110bd4c07","submission_commitment":"0x168ded40b8c6f5475a538285236847bf6160d9aa96f1c7a2a8e3524ec24d9d06"},{"solver":"0x8b36c13824705c65c3579825f5877b225abb231b","submission_commitment":"0x9aaf9daa3db277ae7689fe0b8078a53706b594f2602c42c28225b9ba35311acb"},{"solver":"0xbfce2a2b806d09c69abaff494d33f86e6de627d5","submission_commitment":"0xb57a044d75fa56f19a2e1deb7ce7bbab0ab63a676682c3468d8483809cf506f9"},{"solver":"0xf3d562f6de2a369afef8aaac1147062d5c20bcb6","submission_commitment":"0x9bbcf185e1a4da9d452b4b97ea7ae4a9ee48d0c97f7909abc31f98735fccf563"}],"submission_count":10},"challenge":"---\nprofile: elgora_markdown_bounty_challenge_v1\nescrow_amount: \"25000000\"\nsubmission_deadline: 1795564740\npayout_policy: winner_take_all\n---\n\n# Extract experimental hit rates of de novo designed protein binders from 27 open-access papers\n\n## Summary\nProduce one CSV that records, for every design campaign reported in 27 listed\nopen-access papers (2024–2026), how many computationally designed binder\ncandidates were tested in the laboratory, how many of them bound their target,\nthe criterion the paper used to call a design a binder, and the best reported\naffinity — each row citable to the exact place in the paper that states it.\n\n## Challenge details\nDeep-learning binder design (RFdiffusion, BindCraft, AlphaProteo, ProteinMPNN\npipelines and related methods) is usually reported as a \"success rate\" or \"hit\nrate\", but every paper counts differently: some count designs ordered, some\ndesigns expressed, some designs that passed a display screen. The numbers sit\nin figure captions, supplementary tables and single sentences of the main text,\nso no database holds them. This bounty buys a structured table of what these 27\npapers report, with the criterion each paper applied carried alongside the\nnumbers.\n\n### What a design campaign is\nA **design campaign** is one combination of (paper, target, design method) for\nwhich the paper reports both:\n\n- the number of distinct designed candidate binders that were **experimentally\n  tested for binding** against that target, and\n- the number of those candidates the paper reports as binding.\n\nOne row of the CSV describes exactly one campaign. A paper reporting designs\nagainst three targets with one method yields three rows. A paper reporting two\ndifferent design methods against one target yields two rows. A paper reporting\none method against one target in two sequential rounds (for example an initial\ndesign round and an affinity-maturation round) yields one row per round, and\nthe round is named in `design_method`.\n\nA campaign qualifies only if the binder candidates were produced computationally\nand are new sequences rather than a natural binder, a known antibody, or a\nvariant panel of an already-published binder. Point-mutant or\naffinity-maturation panels built on a binder first reported in the same paper do\nqualify as a separate round. Panels built on a binder published elsewhere do\nnot.\n\n### What counts as tested and as a binder\n- `n_designs_tested` is the number of distinct designed sequences entering the\n  experimental binding measurement the paper reports for that campaign. Where a\n  paper reports a funnel (designs generated → ordered → expressed → assayed),\n  use the number assayed for binding. Where a pooled library screen is the\n  binding measurement, use the library size the paper states for that target.\n- `n_binders` is the number of those designs the paper counts as binding its\n  intended target, under the paper's own criterion.\n- `binder_threshold_as_stated` is that criterion, quoted from the paper or\n  paraphrased without changing any number, unit or assay, for example `KD < 1 uM by SPR`, `enrichment in yeast display\n  sort 2`, `detectable BLI response at 1 uM`. If the paper states no criterion,\n  write `not stated`.\n- Numbers reported only as a percentage are converted only when the paper also\n  states the denominator; otherwise the campaign is not extractable and the\n  paper is handled under the provenance rule below.\n- In-silico-only success rates (designs passing AlphaFold or Rosetta filters,\n  with no laboratory measurement) are never a campaign.\n\n### Affinity and units\n`best_affinity_nM` is the strongest (numerically lowest) dissociation constant\nthe paper reports for any design of that campaign, in nanomolar, as a decimal\nnumber:\n\n- pM → divide by 1000; µM (uM, μM) → multiply by 1000; mM → multiply by\n  1,000,000.\n- Use the reported dissociation constants (KD). Only when the paper reports\n  no KD for any design of that campaign, use the lowest reported apparent KD,\n  EC50 or IC50 for that campaign instead.\n- A value given with an error (`45 ± 4 nM`) is recorded as its central value:\n  `45`. A value given as a range (`100–454 nM`) is recorded as its lowest\n  value: `100`.\n- Where a value is reported only as a bound (`< 1 nM`), record the bound's\n  number: `1`.\n- If no affinity is reported for any design of that campaign, leave\n  `best_affinity_nM` empty. An empty field is never wrong when the paper\n  reports no value; it is wrong when the paper reports one.\n\n### Where a value may come from\nTables, figures, figure captions, main text and supplementary material of the\nlisted open-access version are all acceptable sources, provided the row cites\nthe location and quotes text from it that carries at least one of the row's\nnumbers.\n\n## What you need to submit (Deliverables)\n\n| File | Required | Format | Purpose |\n|---|---:|---|---|\n| `hitrates.csv` | yes | UTF-8 CSV, comma-separated, RFC 4180 quoting, one header row, schema below | the extracted dataset |\n| `provenance.md` | yes | UTF-8 Markdown | any listed paper contributing no row, with the reason; and any campaign excluded under the rules above, with the reason |\n| `notes.md` | no | UTF-8 Markdown | method notes; informational only, not judged |\n\nSchema, in this column order:\n\n`paper_doi,target_name,design_method,n_designs_tested,n_binders,binder_threshold_as_stated,best_affinity_nM,assay_type,table_or_figure,source_quote`\n\n- `paper_doi` is the DOI exactly as printed in `sources.csv`.\n- `target_name` is the target as the paper names it, for example `PD-L1`,\n  `GDF15`, `SARS-CoV-2 RBD`. Where the paper names a target and a site, name\n  the target only.\n- `design_method` is the method as the paper names it, plus the round where a\n  paper reports more than one, for example `RFdiffusion`, `BindCraft`,\n  `RFdiffusion + ProteinMPNN (round 2)`.\n- `n_designs_tested` and `n_binders` are non-negative integers, with\n  `n_binders` at most `n_designs_tested`.\n- `best_affinity_nM` is a decimal number in nM, or empty.\n- `assay_type` is one of `SPR`, `BLI`, `ITC`, `yeast display`, `phage display`,\n  `flow cytometry`, `ELISA`, `pulldown`, `cell assay`, or `other: <name as the\n  paper calls it>`. Where several assays are used for one campaign, name the\n  one the binder criterion is based on.\n- `table_or_figure` identifies the location of the value, as printed: `Table 2`,\n  `Fig. 3c`, `Supplementary Table 1`, `Extended Data Fig. 5b`, or `main text`.\n- `source_quote` is a verbatim quotation of at most 300 characters from that\n  location (a table cell or row, caption fragment or sentence) that states at\n  least one of the row's `n_designs_tested`, `n_binders` or\n  `best_affinity_nM` values. Whitespace and line breaks may differ from the\n  paper. The other numbers of the row may come from elsewhere in the same\n  paper.\n\n## Inputs, Materials and References\n\n| Input | Why it is needed | How to get it | SHA-256 |\n|---|---|---|---|\n| `sources.csv` | the fixed list and order of the 27 papers: columns `paper_doi,pmcid,year,journal,title,open_access_url`, 27 data rows | reproduced in full below | none: the text on this page is the input |\n| the 27 papers | the values to extract | each paper's `open_access_url`: its full text on PubMed Central, with its tables, figures and supplementary files; no sign-in | none: the PubMed Central version is authoritative |\n| drand `quicknet` beacon | the seed that picks the checked rows and papers | public at `https://api.drand.sh/52db9ba70e0cc0f6eaf7803dd07447a1f5477735fd3f661792ba94600c84e971/public/{round}`; no sign-in | none: each value carries its drand signature |\n\n### `sources.csv`\n```csv\npaper_doi,pmcid,year,journal,title,open_access_url\n10.1038/s41586-025-09429-6,PMC12507698,2025,Nature,One-shot design of functional protein binders with BindCraft,https://pmc.ncbi.nlm.nih.gov/articles/PMC12507698/\n10.1038/s41467-025-67866-3,PMC12852815,2026,Nature Communications,Improved protein binder design using β-pairing targeted RFdiffusion,https://pmc.ncbi.nlm.nih.gov/articles/PMC12852815/\n10.1002/advs.202502015,PMC12412469,2025,Advanced Science,A Complementarity‐Based Approach to De Novo Binder Design,https://pmc.ncbi.nlm.nih.gov/articles/PMC12412469/\n10.1016/j.mtbio.2026.103336,PMC13267575,2026,Materials Today Bio,De novo design of dual-target mini-binders simultaneously neutralizing Streptococcus equi subspecies zooepidemicus M-like protein and host TNFR1 confers complete protection against lethal infection,https://pmc.ncbi.nlm.nih.gov/articles/PMC13267575/\n10.1038/s12276-026-01727-x,PMC13234300,2026,Experimental & Molecular Medicine,De novo and scaffold-based design of GDF15 binders for cancer cachexia diagnostics and therapeutics,https://pmc.ncbi.nlm.nih.gov/articles/PMC13234300/\n10.3389/fbioe.2026.1946220,PMC13736603,2026,Frontiers in Bioengineering and Biotechnology,Design and validation of nucleosome binding peptides using BindCraft,https://pmc.ncbi.nlm.nih.gov/articles/PMC13736603/\n10.1021/acschembio.5c00774,PMC12723675,2025,ACS Chemical Biology,Evaluating BindCraft for Generative Design of High-Affinity Peptides,https://pmc.ncbi.nlm.nih.gov/articles/PMC12723675/\n10.1073/pnas.2506269123,PMC12867733,2026,Proceedings of the National Academy of Sciences,Mapping targetable sites on the human surfaceome for the design of novel binders,https://pmc.ncbi.nlm.nih.gov/articles/PMC12867733/\n10.1038/s41586-025-09721-5,PMC12727541,2025,Nature,Atomically accurate de novo design of antibodies with RFdiffusion,https://pmc.ncbi.nlm.nih.gov/articles/PMC12727541/\n10.1002/advs.76202,PMC13339307,2026,Advanced Science,De Novo Designed Minibinders Targeting the GDF15–GFRAL Axis Reverse Cancer Cachexia and Restore Anti‐Tumor Immunity,https://pmc.ncbi.nlm.nih.gov/articles/PMC13339307/\n10.3390/biom15111587,PMC12650588,2025,Biomolecules,De Novo Design of High-Affinity HER2-Targeting Protein Minibinders,https://pmc.ncbi.nlm.nih.gov/articles/PMC12650588/\n10.1126/science.adv0185,PMC13077772,2025,Science,Design of high-specificity binders for peptide–MHC-I complexes,https://pmc.ncbi.nlm.nih.gov/articles/PMC13077772/\n10.1126/sciadv.adt4170,PMC12412652,2025,Science Advances,Computational design of potent and selective binders of BAK and BAX,https://pmc.ncbi.nlm.nih.gov/articles/PMC12412652/\n10.1038/s41586-025-09248-9,PMC12367549,2025,Nature,Diffusing protein binders to intrinsically disordered proteins,https://pmc.ncbi.nlm.nih.gov/articles/PMC12367549/\n10.1038/s41587-025-02761-2,PMC13271882,2025,Nature Biotechnology,Target sequence-conditioned design of peptide binders using masked language modeling,https://pmc.ncbi.nlm.nih.gov/articles/PMC13271882/\n10.3389/fimmu.2025.1631868,PMC12463876,2025,Frontiers in Immunology,AI-assisted design of ligands for lipocalin-2,https://pmc.ncbi.nlm.nih.gov/articles/PMC12463876/\n10.1167/iovs.67.5.61,PMC13206737,2026,Investigative Ophthalmology & Visual Science,Development of Miniprotein Binders to Inhibit VEGF-Induced Corneal Neovascularization,https://pmc.ncbi.nlm.nih.gov/articles/PMC13206737/\n10.1002/anie.202516058,PMC12723454,2025,Angewandte Chemie International Edition,De Novo Design of High‐Affinity Miniprotein Binders Targeting Francisella Tularensis Virulence Factor,https://pmc.ncbi.nlm.nih.gov/articles/PMC12723454/\n10.1038/s41467-026-76760-5,PMC13494018,2026,Nature Communications,AI-enabled discovery and biochemical optimization of minibinders targeting cancer cell-surface proteins,https://pmc.ncbi.nlm.nih.gov/articles/PMC13494018/\n10.1038/s42003-025-09030-7,PMC12644665,2025,Communications Biology,Design of minibinder proteins as universal antagonists against canine and human TNFα,https://pmc.ncbi.nlm.nih.gov/articles/PMC12644665/\n10.1038/s41467-025-56369-w,PMC11785957,2025,Nature Communications,De novo design of protein minibinder agonists of TLR3,https://pmc.ncbi.nlm.nih.gov/articles/PMC11785957/\n10.1038/s41589-025-01929-w,PMC12643943,2025,Nature Chemical Biology,Accurate de novo design of high-affinity protein-binding macrocycles using deep learning,https://pmc.ncbi.nlm.nih.gov/articles/PMC12643943/\n10.1016/j.isci.2025.112621,PMC12158508,2025,iScience,Computational design of diverse nuclear factor erythroid 2 activators with cellular antioxidative activity,https://pmc.ncbi.nlm.nih.gov/articles/PMC12158508/\n10.1073/pnas.2509329122,PMC12501149,2025,Proceedings of the National Academy of Sciences,De novo design of potent inhibitors of clostridial family toxins,https://pmc.ncbi.nlm.nih.gov/articles/PMC12501149/\n10.1073/pnas.2533456123,PMC13142991,2026,Proceedings of the National Academy of Sciences,Computational design of an ultrapotent deltacoronavirus miniprotein inhibitor,https://pmc.ncbi.nlm.nih.gov/articles/PMC13142991/\n10.1016/j.celrep.2025.115760,PMC12276895,2025,Cell Reports,Designed miniproteins potently inhibit and protect against MERS-CoV,https://pmc.ncbi.nlm.nih.gov/articles/PMC12276895/\n10.1038/s41467-024-50919-4,PMC11329760,2024,Nature Communications,De novo design of miniprotein antagonists of cytokine storm inducers,https://pmc.ncbi.nlm.nih.gov/articles/PMC11329760/\n```\n\nEvery listed paper is open access on PubMed Central at its `open_access_url`,\nand that version is authoritative for this bounty; the DOI identifies the same\nwork.\n\n## Acceptance Criteria\n\n1. Every row's `paper_doi` appears in `sources.csv`, and every one of the 27\n   listed papers either contributes at least one row to `hitrates.csv` or is\n   listed in `provenance.md` with the reason it reports no qualifying campaign.\n2. `hitrates.csv` has the header above, at least 20 data rows, and no two rows\n   share the same `paper_doi`, `target_name` and `design_method`. Every row has\n   a non-empty value in every column except `best_affinity_nM`, and\n   `n_designs_tested`, `n_binders` and `best_affinity_nM` parse as numbers under\n   the rules in Challenge details.\n3. **Row check.** B is the `randomness` value, in lowercase hex, of the first\n   `quicknet` round whose scheduled time is at or after `submission_deadline`:\n   round = ceil((submission_deadline − 1692803367) ÷ 3) + 1 = 34253792. No other round's\n   value is B. With R data rows in `hitrates.csv`, numbered from 1 in file order\n   after the header, 20 distinct rows are checked; if R is below 20, all rows\n   are checked. For j = 1, 2, 3 and so on, n is the first 12 hex digits of the\n   SHA-256 of the text `B:row:j`, read as a hexadecimal number, and row\n   (n mod R) + 1 is picked; a row already picked is skipped; picking stops at 20\n   distinct rows. A checked row is correct when it is a qualifying design\n   campaign, its `source_quote` appears verbatim (apart from whitespace) in the\n   cited paper at the cited `table_or_figure`, and `n_designs_tested`,\n   `n_binders`, `binder_threshold_as_stated`, `best_affinity_nM`,\n   `target_name`, `design_method` and `assay_type` follow from that paper under\n   the rules in Challenge details, with `best_affinity_nM` after unit conversion and within\n   1% of the converted printed value. Any other mismatch makes the row\n   incorrect. At most 1 of the checked rows may be incorrect.\n4. **Completeness check.** With the 27 papers numbered from 1 in `sources.csv`\n   order, 3 distinct papers are checked. For j = 1, 2, 3 and so on, n is the\n   first 12 hex digits of the SHA-256 of the text `B:paper:j`, read as a\n   hexadecimal number, and paper (n mod 27) + 1 is picked; a paper already\n   picked is skipped; picking stops at 3 distinct papers. Every qualifying\n   design campaign reported in a checked paper is a row of `hitrates.csv`. A\n   qualifying campaign that is not a row counts as missing, including one\n   listed in `provenance.md` as excluded. At most 1 campaign may be missing\n   across the 3 checked papers.\n\nThe dataset records what these papers report. It does not establish that the\nreported numbers are correct, nor that the campaigns are comparable with one\nanother.\n\n## How is the winner selected?\n- A valid Submission satisfies every acceptance criterion.\n- The valid Submission with the lowest `submission_call_count` wins:\n  ElgoraHub's bounty-wide count of accepted submissions at that call, so the\n  earliest active valid Submission wins. The number of rows does not rank.\n- If no Submission is valid, the outcome is `no_valid_submission`.\n\n## Out Of Scope\n- Papers outside `sources.csv`, including newer work on the same targets.\n- Re-analysis, re-computation or correction of the papers' numbers, pooled hit\n  rates, statistics across campaigns, and judgement of whether a paper's claims\n  are sound.\n- New experiments or new designs.\n\n## Disqualification Conditions\n- A submitted file that addresses the judging process to request a verdict,\n  rank or departure from these criteria.\n","verification_record":null,"verification_record_error":null}