{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:56Z","timestamp":1792790396089,"version":"4.5.0"},"posted":{"date-parts":[[2026,8,13]]},"group-title":"Bioinformatics","reference-count":30,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"award":["R01CA253658"],"award-info":[{"award-number":["R01CA253658"]}],"id":[{"id":"https:\/\/ror.org\/001d55x84","id-type":"ROR","asserted-by":"publisher"}]},{"award":["BC240144"],"award-info":[{"award-number":["BC240144"]}],"id":[{"id":"https:\/\/ror.org\/0447fe631","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support","award":["MED250062"],"award-info":[{"award-number":["MED250062"]}],"id":[{"id":"https:\/\/ror.org\/01v6d0b34","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Applying unconstrained generative protein models to fixed structural scaffolds can produce systematic design artifacts, including glycine enrichment, grammar violations, and discordant complex predictions. We developed DARPinMPNN, a scaffold-constrained computational framework that restricts production sequence generation to permitted DARPin Greek Grammar residue pools. A state-aware chimeric multiple sequence alignment strategy supported AlphaFold2-Multimer (AF2) screening, followed by complementary AlphaFold 3 (AF3) evaluation. Of 15,000 generated variants targeting mesothelin, VEGF-A, and HER2, 149 library designs and five separately analyzed controls had deposited 25-model AF3 results. Using the unrounded median of 25 corrected target-DARPin Ranking Scores, eight library designs passed the threshold of 0.70, all targeting mesothelin, corresponding to 0.053% of the generated library. The highest-ranked design had median corrected RS 0.794; the G3 positive control passed separately with median corrected RS 0.866. AF3 median chain-pair ipTM was lower than AF2 ipTM for 148 of 149 library designs. These results demonstrate target-dependent computational prioritization and cross-predictor discordance, not experimental binding or false-positive rates. The candidates require biophysical and cellular validation.<\/jats:p>","DOI":"10.64898\/2026.08.07.743551","type":"posted-content","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:35:16Z","timestamp":1786667716000},"source":"Crossref","is-referenced-by-count":0,"title":["Scaffold-Constrained Generative Design Overcomes Failure Modes in Computational Protein Engineering"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2648-7333","authenticated-orcid":false,"given":"Miles","family":"Pourbaghi","sequence":"first","affiliation":[{"name":"Department of Pharmacology, Weill Cornell Medicine, New York, NY 10065, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-9617","authenticated-orcid":false,"given":"Olivier","family":"Elemento","sequence":"additional","affiliation":[{"name":"Englander Institute for Precision Medicine, Weill Cornell Medicine, New York, NY, USA"},{"name":"Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY, USA"},{"name":"Institute for Computational Biomedicine, Weill Cornell Medicine, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3147-4391","authenticated-orcid":false,"given":"Michelle S.","family":"Bradbury","sequence":"additional","affiliation":[{"name":"Department of Pharmacology, Weill Cornell Medicine, New York, NY 10065, USA"},{"name":"Department of Radiation Oncology, Weill Cornell Medicine, New York, NY 10065, USA"},{"name":"Feil Family Brain & Mind Research Institute, Weill Cornell Medicine, New York, NY 10065, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026100503451442000_2026.08.07.743551v2.1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-pharmtox-010611-134654"},{"key":"2026100503451442000_2026.08.07.743551v2.2","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/S0022-2836(03)00896-9","article-title":"Designing repeat proteins: well-expressed, soluble and stable proteins from combinatorial libraries of consensus ankyrin repeat proteins","volume":"332","year":"2003","journal-title":"J Mol Biols"},{"key":"2026100503451442000_2026.08.07.743551v2.3","doi-asserted-by":"crossref","first-page":"e960","DOI":"10.1002\/cpz1.960","article-title":"Design and Construction of a Designed Ankyrin Repeat Protein (DARPin) Display Library","volume":"4","year":"2024","journal-title":"Curr Protoc"},{"key":"2026100503451442000_2026.08.07.743551v2.4","doi-asserted-by":"publisher","DOI":"10.1126\/science.add2187"},{"key":"2026100503451442000_2026.08.07.743551v2.5","first-page":"9460","article-title":"Defining and characterizing reward gaming","volume":"35","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026100503451442000_2026.08.07.743551v2.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04184-w"},{"key":"2026100503451442000_2026.08.07.743551v2.7","doi-asserted-by":"publisher","DOI":"10.1101\/2021.10.04.463034"},{"key":"2026100503451442000_2026.08.07.743551v2.8","doi-asserted-by":"crossref","first-page":"2625","DOI":"10.1038\/s41467-023-38328-5","article-title":"Improving de novo protein binder design with deep learning","volume":"14","year":"2023","journal-title":"Nature Communications"},{"key":"2026100503451442000_2026.08.07.743551v2.9","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-024-07487-W"},{"key":"2026100503451442000_2026.08.07.743551v2.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2013.08.020"},{"key":"2026100503451442000_2026.08.07.743551v2.11","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1127"},{"key":"2026100503451442000_2026.08.07.743551v2.12","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.1791"},{"key":"2026100503451442000_2026.08.07.743551v2.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-025-02626-1"},{"key":"2026100503451442000_2026.08.07.743551v2.14","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"2026100503451442000_2026.08.07.743551v2.15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu097"},{"key":"2026100503451442000_2026.08.07.743551v2.16","doi-asserted-by":"publisher","DOI":"10.1074\/jbc.M112.381756"},{"key":"2026100503451442000_2026.08.07.743551v2.17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp163"},{"key":"2026100503451442000_2026.08.07.743551v2.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2007.05.022"},{"key":"2026100503451442000_2026.08.07.743551v2.19","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(82)90515-0"},{"key":"2026100503451442000_2026.08.07.743551v2.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"2026100503451442000_2026.08.07.743551v2.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41580-023-00631-w"},{"key":"2026100503451442000_2026.08.07.743551v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/sj.onc.1210477"},{"key":"2026100503451442000_2026.08.07.743551v2.23","doi-asserted-by":"publisher","DOI":"10.1002\/pro.4379"},{"key":"2026100503451442000_2026.08.07.743551v2.24","first-page":"583","article-title":"Use of Ranks in One-Criterion Variance Analysis","volume":"7","year":"1952","journal-title":"Journal of the American Statistical Association"},{"key":"2026100503451442000_2026.08.07.743551v2.25","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"key":"2026100503451442000_2026.08.07.743551v2.26","doi-asserted-by":"publisher","DOI":"10.1038\/nature19946"},{"key":"2026100503451442000_2026.08.07.743551v2.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06415-8"},{"key":"2026100503451442000_2026.08.07.743551v2.28","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1038\/s41592-022-01488-1","article-title":"ColabFold: making protein folding accessible to all","volume":"19","year":"2022","journal-title":"Nature Methods"},{"key":"2026100503451442000_2026.08.07.743551v2.29","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.07454"},{"key":"2026100503451442000_2026.08.07.743551v2.30","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01490-7"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.07.743551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T10:45:23Z","timestamp":1791197123000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.07.743551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":30,"URL":"https:\/\/doi.org\/10.64898\/2026.08.07.743551","relation":{},"subject":[],"published":{"date-parts":[[2026,8,13]]},"subtype":"preprint"}}